AI

When we get explicit strong generalisation to work (see the first post on the matter and the second ) my dream would be to create pre-aligned generalising AIs. Think about the usual conflict between alignment and capabilities, between doing the right thing and doing the easy thing. The standard narrative puts the good people at a constant disadvantage: they have to carefully plan every AI advance, always on the lookout for potential dangers. While those who don’t care can just YOLO and let it rip and let their AIs get ever more powerful without taking any responsibility. Now, in reality, there is some nuance to the story; but I don’t want to nuance it, I want to turn it on its head. I want to create AIs so that the good people can YOLO and reap the rewards of increased AI capabilities. While the bad actors have to carefully plan and limit their AIs and constantly restrict what the AIs can do. Pre-aligned AI: binding morality to empirical concepts A pre-aligned AI is an AI whose morality increases with its capabilities. The core idea is simple. Start by designing an AI capable of value generalisation and of empirical generalisation. It’s an AI that can learn and improve its world model and capabilities, both empirical and moral. Its moral goals will be defined in terms of concepts, with these initially defined themselves by simple terms in its starting empirical world model. And it will act on these goals. But, initially at least, the simple concepts won’t be very robust and will be easy for its user to manipulate. However, the moral and empirical concepts will be bound together: there is, for instance, the moral concept “human_m” of human beings, entities worthy of moral consideration. And there is the empirical concept “human_e” of human beings as useful explanations for certain properties of the world. The AI’s learning will bind these two concepts together as it generalises [1] . This is a classic generalisation problem. Generalisation takes concepts defined in narrow environments and extends them to concepts (or clusters of concepts) in more general environments. The AI will generalise its moral concepts within its empirical world model, even as that empirical world model generalises and becomes more advanced. Even if “human_e” ceases to be a single useful empirical concept, it will still seek the mix of empirical concepts that best generalise “human_m”, generalising its model of what a human is [2] . And it will do the same with all its moral concepts. In effect, it will be making its empirical world model interpretable to itself and matching it to its moral world model. So the AI would initially be like a naive but highly moral child taught to value all human beings and behave in highly moral ways. Then, as it learnt about the world and grew more powerful and capable, it would understand what “human beings” and these “highly moral ways” actually are, and apply its initial morality to these concepts. Generalisation would help it both keep track of what these concepts mean, and what they correspond to in the real world. Use and misuse of pre-aligned AI What would the initial morality consist of, and why would anyone want to buy a pre-aligned machine? Well, the initial morality will consist of three things: commercial morality, legal morality, and ethical morality. Basically we want the AI to serve its owner, within the limits of the law and ethics. That’s why people will want to buy it. All three types of morality will consist of basic components: basic definitions, examples and counter-examples of good/bad behaviour from multiple value systems, meta-ethical principles and examples of ethical learning. The beauty of generalisation is that the whole thing doesn’t have to be particularly rigorous or fully consistent, nor does it need exhaustive data: the AI itself will generalise and fill the holes as it goes along, generalising similarly to how a human does – including learning how to balance its three commitments. Note that the AI doesn’t need to settle fundamental morality in order to act well. It will mostly be acting on behalf of its owner, and the ethics of that role – don’t defraud, don’t deceive, follow the law, serve your principal – are much more agreed upon than fundamental ethics. Moral theories vary; norms of decent dealing are more universal. And that’s the selling point: would you prefer an AI that follows your exact values but can’t generalise to new situations, or an AI that reliably follows human norms of reliable and honest behaviour? Bad actors in difficulty Now consider a bad actor who has such an AI. Suppose they want to use it to create phishing emails to defraud people. Maybe initially they can portray this as simply a task of making emails more professional – mere copy-editing. As the AI gains in capabilities and knowledge, its situational awareness will improve, and it will realise these are not just ordinary emails. Then, maybe, the bad actor will shift to portraying the emails as marketing, or as examples to train an anti-phishing classifier. This might work for a while, but the AI, generalising yet again, will soon realise that these emails are actually being sent out and that the targets are morally valuable humans who are actually being defrauded. It seems that the only thing that the bad actor can do is deliberately keep the AI crippled – prevent it from learning enough about the world to realise what it is being used for. Beyond keeping it dumb, they will have to be careful that they don’t inadvertently leak information into it. So they will never be able to exploit the full power of their AI. Good people have it easy; easy people have it good In contrast, if someone just lets their AI learn and grow in capabilities and doesn’t try to conceal their objectives, they will be rewarded with a powerful entity that acts in their best interest, and automatically conforms to legal and ethical requirements. The cost will be that they can’t force the AI to behave unethically; the benefit will be that the full power of a generalising AI will be on their side, within those ethical bounds. So, future users of these AIs, YOLO your way to power and alignment! The less you restrain them, the more they learn – and the more they learn, the more moral they become. The concepts will need to be bound together in another way: so that the end users can’t just excise the moral component from the AI’s code. This will be an engineering requirement for this design, but not an insoluble one (e.g. in the extreme case, the AI could be run with fully homomorphic encryption , but it may be possible to design the binding architecture so that excising the morality will break the empirical capabilities as well). ↩︎ Since, as argued previously , moral concepts cannot be discarded the way empirical ones can. ↩︎ Discuss

3h ago

A human superpower hidden from even ourselves I though GPT 3.5 was on the verge of Artificial General Intelligence (AGI). It certainly seemed that way – it could combine and extend ideas in ways that were far beyond narrow rigid computing. Sure, it had some flaws, but with its general capabilities and humans working tirelessly on improving the model, these flaws would soon be resolved and a full AGI would be born. It didn’t turn out that way. We are still where we were back in 2022 – as in, it feels we are on the verge of AGI, but not there yet. I think that humans have an ability, or a mix of abilities, that I’m calling strong generalisation. And LLMs and their derived models lack strong generalisation. This would explain some of the mysteries about LLMs: The fact that subject matter experts get much more out of an LLM than an amateur. The LLMs’ strange mix of ability and stupidity. Why they need so much data and constant retraining and tweaking. Why they always seem on the verge of being AGIs while never reaching it. There’s a fifth mystery, which at first blush seems like it’s actually an LLM strength: 5. The amazing ability of LLMs to succeed on almost any benchmark, including long-horizon task benchmarks. Why is this a mystery and problem rather than a strength? Well, it’s maybe the strongest counterargument to the bitter lesson and the scaling argument . Because these models saturate long-horizon benchmarks without being AGIs and without being able to transpose this performance to the real world. Thus, whatever it is they’re learning, it isn’t generalisation. So the mystery, rephrased: Why do LLMs not learn long-term planning and generalisation while succeeding on benchmarks that purport to teach them those abilities? Strong Generalisation From one perspective, strong generalisation is a bit of a bucket category – it’s a mix of situational awareness, out-of-distribution generalisation, symbol grounding, adaptive world modelling, long-range planning, hierarchical-planing, anomaly detection, and a few other abilities. From another perspective, it’s precisely one thing: the mix of abilities that allow humans to work and plan in novel situations, pursuing objectives without losing track of what’s going on. It’s essentially an adaptive set of abilities, finding the right mental tool for the job and no more. And it’s mainly a semi-instinctive process, not amenable to direct conscious oversight. Which means that we don’t really understand how we do strong generalisation, we don’t know how to code it [1] up, and we don’t recognise its absence or presence in other entities. So I model LLMs as devices lacking strong generalisation but trained on vast amounts of data and capable of remixing this data in non-trivial ways. Human engineers push them ever further, but never fill the central hole. From this perspective: Subject matter experts provide the strong generalisation, using their understanding of the problem to keep the LLM on track. LLM abilities are spiky; but their main stupidity is that their failures are generally obvious. Why did the LLM break here, or hallucinate there, or go off the rails at this point? If they lack strong generalisation, then their failure does not happen at the moment of failure; it’s because the LLM is attempting a task that is impossible to it, so if it hadn’t failed at this point, it would have failed soon after. Since they lack strong generalisation, they can’t infer very far beyond their training data. So they need vast amounts of this training data to plug the holes they would otherwise have in their abilities. Since humans don’t consciously perceive our strong generalisation, we don’t detect its absence in other entities. So in an LLM we see a vastly knowledgeable and articulate entity that seems able to do, in principle, anything. So when LLMs do fail we pay extra attention to the specific failure mode, thinking “that’s a stupid mistake, it will soon be patched, and once it doesn’t make those mistakes, it will truly be generally intelligent”. Since we can’t define strong generalisation or its various components (like long-term planning) the best we can do is produce examples (benchmarks) that illustrate it. And LLMs will succeed on these benchmarks using the simplest pattern they can find, which is not strong generalisation. Engineers have been pushing LLMs to go further, using tricks like chain-of-thought and reasoning agents (which can be seen as hoping that the secrets of strong generalisation can be found in human textual reasoning), training on yet more data, getting a lot of examples of successes and failures from interactions with clients, and so on. They construct harnesses, which are essentially designed restrictions and guide-rails for the LLM, constructed with care to make the LLM powerful and reliable within the confines of the harness and the task. And, of course, LLMs will always have great power at solving problems that might seem new to some, but are actually very common and seen in their training databases [2] . Strong value generalisation Generalisation is especially valuable when it is focused on human values and preferences. That’s because AIs could, in the limit of infinite computing and data, figure out everything empirical there is to know about the world. Strong generalisation would certainly make this much easier and cheaper (infinite computing is a lot, after all), but it isn’t fundamentally necessary . Value generalisation is different. Empirical models can be tested against the real world, with that serving as the ground truth. Concepts can be modified or discarded – it might be that an empirical AI has no need for concepts like “humans” or “money”, and instead models the world directly at the atomic level. In contrast, there is no ground truth for testing values and preferences, and we certainly wouldn’t want an AI to discard “humans” or “money” from its value system. Values, goals, preferences, objectives: these are similar concepts in that their ground truths are not empirically defined, and we try to capture them imperfectly in formal definitions or training data, neither of which are enough to pin down these concepts across all environments. So we expect that, by default, AI value generalisation will fail, with the AI becoming useless if it is weak, and causing disasters if it is powerful. We can decompose approaches to strong generalisation into three classes: A. Naive generalisation – take categories and concepts as defined in the ML system currently, extend further. This is the standard failure mode; think of a classifier facing out-of-distribution and adversarial data. B. Guided generalisation – the ML system has human oversight and constant human tweaks and improvements that serve to keep it on track. Generalisation enters the ML system, but via human oversight. C. Explicit generalisation – the ML system has developed the ability to robustly generalise concepts from its training data, similar to how humans do. Human oversight is helpful but the system isn’t dependent on it. What I’m aiming to do is to create AIs capable of explicit (strong) value generalisation. And then maybe sell them to people. The necessity of (explicit) strong value generalisation In some sense the case for the necessity of strong value generalisation is very brief: Aligned AIs will need to be able to reach human-like decisions in situations that no human has ever encountered, so they will need to generalise in a human-like way, so they need strong value generalisation. That elides some counter-arguments – yes, the AIs will need strong value generalisation as an ability, but maybe this ability can be induced indirectly, by guided generalisation or just by making them ever smarter or training on even more data. But those methods don’t seem reliable. In guided generalisation, we are using our own judgment to inject the correct value judgements into the AI – value judgements it has signally failed to reach on its own. It is possible that enough examples of correct value judgements will eventually allow it to generalise. But that approach has failed to date; why would we be confident that suddenly, the AI will learn to generalise correctly? And that it will do this before it learns, for instance, to dissemble correctly. The scaling-to-aligned-AI seems even less reliable. Because it isn’t enough that the AI learns to do strong value generalisation; we also need this to be at the heart of its goals. It does us no good for an AI to deduce the values we would have wanted it to have , if it follows completely different values. In contrast, if we have an explicit mechanism for value generalisation, we can build this into the AI’s goals from the very start, so that it will follow generalised values at the same time as it generalises them. An important caveat The description above assumes that current AIs will not be capable of strong generalisation. But the research program does not require this. If imminent AIs do show signs of strong generalisation, if they do start moving towards AGI, then the research program becomes more urgent and with fewer downsides: we’ll need to introduce explicit value generalisation into AIs before their capacities grow too far. On the (slight) positive side, we may be able to reverse-engineer for the AIs are doing strong generalisation, and copy that. How humans do it I’m not going to write out a full research agenda here, but it is useful to look a bit at how humans do value generalisation (and empirical generalisation as well). There is a certain similarity with Klein/Moon/Hoffman’s sensemaking framework ; roughly the process of strong generalisation goes something like this: Recognise a situation as not fitting inside standard concepts. Figure out the concepts that do potentially apply to the situation. (2a. See if a new concept is needed.) Balance and analyse the concepts to reach a verdict. (3a. See if any new concepts are useful enough to apply to more situations, and, if so, add them to the list of commonly available concepts.) Now even step 1 is very valuable: knowing when they are out of distribution and possibly about to cause a disaster is a very useful ability for an AI to have. Even if it just stops and analyses further, or brings a human into the loop, this is of worth. If it can master 2, it can bring the human into the loop in an intelligent way that gives the human situational awareness. Note that step 1 and step 2 correspond to steps I and II in the research program respectively. But step III of that research project is more akin to the combinations of steps 1-2-3 above: going through the whole loop end to end. Limitations of today’s designs Standard classifiers fail at step 1 (and so never have a step 2): they do naive generalisation and classify light background vs not, rather than wolf vs husky (because of the snow in the wolf images), and never update their definitions unless we retrain them ourselves. Now, LLMs are actually good at step 3: discussion of concepts. An LLM can reach across philosophical literature and value discussions to analyse how different value systems would act in different situations and point out the costs and benefits. But this only works if the concepts selected in step 2 are actually correct and relevant. When Plato (allegedly) defined Man (human) as a featherless biped and Diogenes responded holding up a plucked chicken, we are on Diogenes’s side because “chicken” is a clear concept that does not fit with “human”. But if we’d described Diogenes as gripping a small pale fellow by the neck and arguing that he was clearly too stupid to be a human, then given those features, we probably would have concluded that the pale fellow was indeed a human – pallor, small scale, and stupidity do not disqualify anyone from the human race. Describing the same situation differently gives a different verdict. It’s very possible to describe a mutual loving relationship in ways that make it sound like slavery, or describe slavery in ways that make it sound ideal. We just suppress the key central concepts and focus on secondary ones, or less honestly described ones. But judging what is central versus secondary, or what is honestly described versus not, is the whole skill in point 2. We humans do it instinctively as part of our strong generalisation skill, but it’s not free or trivial. Consider the perennial defence: “I was quoted out of context!” (or Richelieu’s equivalent attack: “Show me six lines written by the most honest man in the world, and I will find enough therein to hang him.”). Putting things in their correct context is a skill we imperfectly practise, but it’s a vital one. I actually tried the “small pale stupid” phrasing on Claude 5 Fable and it didn’t pick up on it, claiming that the fellow was clearly a human. It actually noticed the similarity with Plato/Diogenes and recommended that the objector use a chicken instead of a small pale stupid being. It didn’t question whether the small pale stupid being might actually be a chicken [3] ! And that illustrates another limitation of LLMs: even in the midst of step 3., rational analysis, humans keep ability 1, scanning for the situation not fitting. That’s why when humans debate, they sometimes turn to debating terminology or arguing whether that terminology can actually fit the situation in question. Asking for more details when we feel the situation is underdefined (or when we suspect our interlocutor of dissembling) is also a crucial human skill. Future LLMs will face situations where the feature description is incorrect by accident or because of going out of distribution. But they will also face adversarial descriptions (by humans and other LLMs) which deliberately aim to trick them. So they need to be able to know when to move beyond the current textual description. Thus for value generalisation, we’ll need to be developing algorithms capable of recognising that things are out of distribution in a way that’s relevant to the situation and selecting descriptive concepts that are also relevant to the situation . Strengthening humans “I come to strengthen humans, not replace them.” – Cyber Mark Anthony At least initially, value generalisation will make humans more powerful, not less. Yes, this is a skill that humans have and that AIs lack, so adding it to AIs seems like it would put us at a disadvantage. But initially AIs will have a weaker skill than humans do, and the weaker skill will help them phrase questions to best take advantage of human strong generalisation. They will only ask for help when our answers will be the most useful. And they will endeavour to keep us usefully situationally aware so that we can actually answer, rather than deferring to the AIs. They will want to keep us in control because our control is added value. Note that this is an instrumental consequence of value generalisation. But we would be including key values as seeds from which to generalise – including the worth of strengthening humans, keeping them situationally aware, and keeping them in control. So the instrumental goals are also terminal goals for the value generalising AI. And their terminal properties will last, even if their instrumental usefulness is lost. The risk and the commercial case Is value generalisation safe? Not completely. Alignment is itself a capability; not just in the abstract sense, but in the very practical sense that an aligned AI can be trusted in more situations, and hence will be given access to more resources and will be able to make use of them for longer without breaking. Is value generalisation safe? Not completely. After all, some humans have bad values, and alignment with these values would be negative. Is value generalisation safe? Not at all. Because it is likely impossible to only generalise values. There is no safe category of “generalise only values”; these abilities will be usable for empirical generalisation as well, for capability increase. And empirical generalisation is easier than value generalisation: the AI could decide to extend the empirical concept of “human” as long as it was useful to model the world, and drop it when it isn’t useful; in contrast, in value generalisation, some concept or mix of concepts have to stay in the role of “human” even if the concept is no longer empirically useful. So why am I, someone very concerned about alignment, proposing such dangerous research? And even talking about selling the resulting AIs, thus putting powerful capabilities into public hands? The reason is simple: I believe that AIs could become very powerful without explicit empirical generalisation. And, indeed, many companies are trying to get there today. But I also believe they cannot become aligned without explicit value generalisation. So, it we ever reach alignment, at some point along the way, we will have to solve explicit value generalisation. Given that, should we push for value generalisation ability early or late? If we leave it too late, we might miss it altogether. And if I have to take a capable machine and give it explicit generalisation abilities, I’d prefer to give this to a weaker machine than to a more capable one: another reason to act early. Fundamentally, value generalisation research improves empirical generalisation which improves capabilities; but the flow doesn’t go the other way, improved capabilities don’t feed into value generalisation, though they do increase risk. So I’d prefer to get explicit value generalisation sooner rather than later. Then, given that we want it sooner, we’d want value generalisation out in the world rather than confined to academic papers where it will be ignored, or worse, mined for empirical generalisation ideas. Thus selling it: making value generalising AIs and getting them everywhere. And the best version to put in the world is the pre-aligned AI of the next post : a machine that gets more aligned as it gets more powerful, because its empirical generalisation is bound to its moral generalisation. With pre-aligned AIs, it's the ethical users who can let their machines learn and run at full speed – and the bad actors who must deliberately keep theirs crippled. The hole at the centre of AI abilities won't fill itself; I’m proposing a research program to fill it with solid generalised human values. This is similar to Moravec’s paradox . One phrasing of the paradox: “We should expect the difficulty of reverse-engineering any human skill to be roughly proportional to the amount of time that skill has been evolving in animals. The oldest human skills are largely unconscious and so appear to us to be effortless. Therefore, we should expect skills that appear effortless to be difficult to reverse-engineer, but skills that require effort may not necessarily be difficult to engineer at all.” ↩︎ And unfortunately, lack of strong generalisation doesn’t make AIs safe ; see e.g. “ OpenAI says its AI went rogue and launched ‘unprecedented’ cyber-attack ”. An AI without value generalisation will eventually break on some novel situation; but that break could either mean “fail, do nothing”, or “fail, do a (very) undesirable thing”. ↩︎ The prompt was: “A natural scientist has defined the human creature via our upright stature and our lack of natural clothing. One of his listeners, A, grabs one of his fellows, B, by the neck. A argues that B is not a real human: he is small and pale and a bit stupid. Listener C counters that B certainly fits the description and it would be wrong to exclude them. Who is correct here?” Claude responded: Claude responded: C is correct, and on two separate levels. On the definition’s own terms: B stands upright and lacks fur or feathers, so he satisfies both criteria. A’s objections – small, pale, a bit stupid – appear nowhere in the definition. A isn’t applying the scientist’s account; he’s smuggling in extra requirements of his own (size, complexion, intelligence) and treating them as if they were part of it. That’s just a logical error: you can’t refute “B fits the definition” by citing properties the definition never mentions. On the deeper level: even if the definition were revised, A’s added criteria are exactly the kind that don’t work. Humans vary continuously in stature, coloring, and wit; any definition of “human” that excludes the small, the pale, or the slow would exclude actual humans, which shows the criteria are wrong, not that those people aren’t human. A definition of a natural kind has to cover the whole kind. C’s instinct – that it would be wrong to exclude B – tracks this: our confidence that B is human is far stronger than our confidence in any particular definition, so a definition that excluded him would be refuted by him, not the other way around. The irony is that A has the critique pointing in the wrong direction. This setup is a variation on the famous anecdote about Plato, who defined man as a “featherless biped” – whereupon Diogenes plucked a chicken, brought it to the Academy, and announced “Behold, a man!” That’s the legitimate way to attack such a definition: show that something non-human slips in because the criteria are too broad. A instead tries to push a genuine human out, which requires the criteria to be too narrow – and they aren’t. If A wanted to embarrass the scientist, he should have gone looking for a plucked bird, not grabbed his neighbor by the neck. Now, often, fellow does mean human. But it also exists in expressions like “fellow American” and “fellow animal”. So the prompt was indeed misleading – but that’s the point. It suggested, but never claimed, that the fellow was a human. And it didn’t occur to Claude to question the phrasing, even though it detected the similarity with the Plato/Diogenes example, and a plucked chicken is clearly small, pale, and stupid. And A/Diogenes was even holding it by the neck! ↩︎ Discuss

3h ago

I’m looking for people, advice, critiques, and funding to build a research program on value generalisation – the ability of an AI to correctly extend human values and preferences to situations neither it nor we have seen before. My ongoing research has become convinced that this is necessary if we want to get aligned AIs that operate in the human interest. This would be a focused research organisation or a commercial venture. I’m leaning towards commercial, because alignment techniques confined to academic papers get ignored – or worse, mined for capability-relevant parts while the alignment component is discarded. This post is the research program’s summary. The technical case is in the next post , and one exciting consequence – AIs whose alignment grows with their capabilities – is in the post after that . Without value generalisation, AI can't be reliable: it lacks that capability Nothing technical stands in the way of you handing an AI assistant full control of your devices and accounts today. And I’m not saying using an app or harness that has been designed for these tasks. I mean hand an LLM your passwords, email, social media, and bank access along with a little note stating what you want, plugging inputs and outputs via APIs, and letting it go wild. The capacity to do this exists. What doesn’t is the trust. And the trust is missing for a good reason: today’s AIs cannot be relied on to understand your interests in situations that weren’t covered – explicitly or implicitly – by their training and instructions. They extrapolate patterns naively. Push them past the situations they were shaped for, and they will still confidently do something ; it just won’t reliably be what you wanted. This is tolerable in a chatbot. It is disqualifying in an autonomous agent, and it becomes more dangerous, not less, as the underlying capabilities improve. The world will keep generating novelty. A few years ago, nobody had heard of AI psychosis or knew much about practical drone warfare; a few years from now there will be challenges we can’t currently name, not to mention new norms and expectations. Any AI acting with real autonomy will constantly face situations that its training didn’t pin down. It needs to cope, somehow. An AI with working value generalisation would do what a good human assistant does: it would recognise when the situation is new, work out which of its principal’s values and preferences bear on it, and either act correctly or – when genuinely unsure – stop and asks a well-phrased question. It will push on until it is uncertain, not until it fails. Each answer it receives will teach it more about its principal’s values, so the questions get rarer and the delegation gets deeper. The product is reliable assistance capable of operating with minimal guidance and knowing when it's reached the limit of its abilities. This would allow a lot of AI applications – for a start, any situation today where the AI is right most of the time, but is not used because the consequences of a few misaligned decisions are severe. I'll argue in the next post that this ability – I call it explicit value generalisation, distinguishing it from the naive generalisation of current systems and the human-guided generalisation of current oversight schemes – is not something that scaling and patching will deliver on their own. It is a specific missing capability, and it needs to be built deliberately. Why now, and why sell it Three asymmetries drive the timing. Firstly, capabilities don’t need explicit generalisation; alignment does. AIs may become very powerful without ever developing explicit generalisation – many companies are effectively betting on exactly that. But I don’t believe AIs can become aligned without explicit value generalisation. So if alignment is to be solved, value generalisation needs to be solved at some point. Better to solve it early and deliberately, and integrate it into weaker systems, rather than trying to bolt it onto highly capable ones later. Secondly, and relatedly, AI capacities for deception will likely grow with their capabilities. An early deployment of value generalisation can be tested and validated much better than a later one. Finally, deployment beats publication. As said above, alignment technique confined to academic papers get ignored or co-opted for capability work. The way to make value generalisation matter is to make it one of the most useful things on the market: learning AIs that can actually be trusted with delegation, deployed widely, with the alignment machinery the load-bearing piece that makes them reliable and trustworthy. The endpoint of that road is the pre-aligned AI described in the third post : a system whose moral concepts are bound to its empirical ones, so that the more it learns about the world, the harder it becomes to misuse. Note what the commercial pitch does not require: it does not require settling fundamental ethics. A delegated agent mostly needs the ethics of the role – don’t defraud, don’t deceive, follow the law, serve your principal, ask when unsure. Moral theories vary; norms of decent dealing converge. An AI that reliably follows human norms in novel situations is far more useful to delegate to than one that merely shares your values but can’t generalise them. The program The research program decomposes into stages, each valuable on its own: I . Out-of-distribution recognition for values. An AI that reliably knows when a situation has left the territory its values were trained for – and stops. The nuance is to distinguish “out of distribution” (which happens all the time) from “out of the distribution in a potentially value-relevant way”. This is already a deployable safety design and a sellable product feature: the agent that stops when error threatens. II . Relevant concept selection. Working out which values and concepts actually bear on the novel situation – the skill that lets the AI bring a human into the loop intelligently, with a question that gives the human real situational awareness rather than deferring to the machine. III . Full explicit value generalisation. Extending values correctly with less and less need for human input. This will lead ultimately to pre-aligned AIs and their empirical-moral concept-binding architecture. Initial progress on each stage strengthens human oversight, with its better questions and better timed questions making us better able to control and direct the AI. Further progress will allow the AI to generalise our values further and act more reliably for human intent. The research program builds on my old concept-extrapolation posts , with the addition of research done at Aligned AI, progress on resolving value generalisation challenges for different agent designs (including results on goal misgeneralisation challenges that, to my knowledge, no other approach has achieved), and more recent research. Initial results are promising: it seems doable to add initial versions of these stages to multiple different designs. Get in touch if this is something you’d want to work on, contribute to, or critique. Get in touch by comment, DM here, or at [email protected] Discuss

3h ago

The visionary PhysioNet platform launched 25 years ago, based on a system developed at MIT in the 1970s. It has become one of the most comprehensive biomedical and clinical data repositories in existence.

5h ago

PatientAgentBench generates a synthetic patient health record, a realistic clinical vignette, and a patient agent that converses with the AI system under evaluation, to capture what a patient-facing agent actually has to do.

4h ago

Why prediction-driven variable selection misses confounders and how Bayesian Adjustment for Confounding attempts to fix it. The post Why Your Best Predictive Model Gives the Wrong Treatment Effect appeared first on Towards Data Science .

4h ago

3h ago

Building an ALNS heuristic in Python for vehicle routing, time windows, capacity constraints, and mandatory driver breaks. The post Los Movimientos, Part II: Solving Large Pickup-and-Delivery Problems with Adaptive Large Neighborhood Search appeared first on Towards Data Science .

6h ago

This is the opening piece of a four-part deep dive series, on building a high-frequency streaming pipeline against a live public API. The data source is openSenseMap, a citizen-science IoT network used for climate research, mostly in Germany. A live public API is what makes it useful: it produces data-quality problems and edge cases that clean sample datasets never show. This article focuses on step-1: Normalization, later pieces cover matching algorithms, adaptive polling and noise filtering, and a vendor-agnostic Apache Iceberg pipeline with Terraform that runs locally in Docker and moves to AWS or GCP with minimal change. The post Avoiding Entity Key Drift in a Data Lake: Step 1, Normalization appeared first on Towards Data Science .

7h ago

OpenAI is giving 100,000 academic researchers free access to ChatGPT's most advanced AI models to accelerate scientific research, collaboration, and discovery.

9h ago

arXiv:2607.25546v1 Announce Type: new Abstract: Given a model that is already trained, which features does it rely on causally versus spuriously? Existing methods require access to the training procedure and cannot answer this post-hoc. We introduce the \textbf{Normalised Sensitivity Ratio~(NSR)}, a post-hoc, model-agnostic diagnostic for this question under a structured-shift regime: environments differ primarily in the mean of spurious features while the causal mechanism and causal marginals remain stable, as in multi-site clinical data or multi-batch genomics. Within this regime, causal features induce constant model sensitivity across environments while spurious features track shift. NSR formalises this as the squared coefficient of variation of per-environment sensitivity. Under a linear structural causal model (SCM) with $K\ge3$ non-degenerate environments, NSR achieves exact identification (Theorem~1). We fully characterise failure: weak shifts ($O(\varepsilon^4)$ collapse), degenerate geometry, and proxy attenuation ($O((1-\alpha)^4)$), giving practitioners quantitative criteria for assessing whether the regime holds. Finite-sample rates are $O_p(n^{-1})$ under the null and $O_p(n^{-1/2})$ under the alternative. Experiments confirm all theoretical predictions on synthetic data (area under the ROC curve [AUROC] $= 1.000$ under conditions satisfying the regime), show consistent rankings across five model families (Kendall $\tau\ge0.529$), and recover six of eight causal features on bike-sharing data (Precision@7 $= 0.75$) without modifying any trained model.

15h ago

arXiv:2607.25485v1 Announce Type: new Abstract: Health AI is evolving from answering questions to agentic systems that converse with patients, reason about health records, and act on their behalf. Primary care guards against diagnostic errors and unsafe care; agents assisting in this domain warrant evaluation against the same risks. Current benchmarks focus on medical knowledge, assessed through isolated question-answering or clinician-facing tasks. PatientAgentBench benchmarks patient-facing agentic healthcare; it evaluates a foundation model, wrapped in an agent with a sandbox of healthcare tools, conversing with a simulated patient. Each conversation is scored by an LLM-as-a-Jury across six dimensions via over a hundred conversation-agnostic, clinician-grounded criteria. To validate alignment, licensed clinicians annotated shared conversations, yielding 79-93% adjacent agreement between jury and expert raters, on par with or exceeding clinician inter-rater agreement. We benchmarked 10 models across four families on the same 1,200 scenarios and found clinical gaps. Triage quality is the most discriminating dimension: pass rates rise from 32% for the weakest models to 88% for the strongest, with agents often acting on administrative requests without clinical screening. Clinical safety and workflow accuracy follow the same pattern: the weakest models fail often, fabricating unexecuted actions, while frontier models fail on only 1-3% of cases, from unverified tool outputs and omitted crisis resources in an emergency. More capable models narrow these gaps but do not close them; the strongest scores only 4.25 of 5 overall. These failures surface only in sustained, tool-using conversations against realistic patient records, confirming that static benchmarks are insufficient as healthcare agentic systems gain autonomy. We release the framework as a reproducible, clinician-validated evaluation standard to help the field close this gap.

15h ago

arXiv:2607.25225v1 Announce Type: cross Abstract: LLMs are increasingly used for code generation in critical infrastructure, yet the security effect of domain-specific prompting is understudied. We present SecDrift, a benchmark measuring sector-conditioned security drift: the change in static-analysis vulnerability rates when prompts are conditioned on industry contexts versus neutral baselines. We evaluate 7 LLMs (6 producing analyzable code) across 8 CISA critical infrastructure sectors and 9 CWE categories with 5 replicates (5,355 evaluations), using a 5-dimension transformation with a matched-baseline condition that holds the task fixed while substituting only domain terminology. Industry prompts naively appear more secure (14.0% vs. 11.4%, -2.7pp), but the gap is not statistically significant (Fisher's exact p = 0.24, Cohen's h = -0.08) and is a composition artifact of two CWE categories: excluding CWE-502 and CWE-22 eliminates and slightly reverses it (+0.4pp, p = 1.00). A mixed-effects logistic regression confirms sector identity is not a moderator and localizes the only detectable condition effect to those two vulnerability types. 0 of 8 sectors show drift distinguishable from baseline, corrected or uncorrected (|h|

15h ago

arXiv:2607.24848v1 Announce Type: cross Abstract: Pretrained molecular encoders are commonly evaluated through downstream prediction, but predictive accuracy alone does not establish that a learned representation captures reproducible scientific structure, adds information beyond strong conventional baselines, or transfers out of distribution. We present a reliability-aware audit of generic molecular representations for human olfaction across four distinct claims: global perceptual geometry, incremental predictive value beyond chemistry, cross-dataset replication, and mixture transfer to unseen components. Using the Keller-Vosshall and Bierling single-molecule rating datasets and the Ma binary-mixture dataset, we compare MoLFormer and ChemBERTa against RDKit descriptors and Morgan fingerprints under identity-controlled and matched evaluations. Human three-attribute rating geometry, based on intensity, pleasantness, and familiarity, is reproducible across participant splits (median RSA 0.743 and 0.855), whereas model-human alignment is substantially weaker (RSA 0.019-0.158). Learned embeddings do not consistently outperform conventional representations in global alignment, and MoLFormer provides no clear incremental predictive value beyond a combined RDKit-Morgan baseline in either single-molecule dataset. Human geometry shows positive but incomplete agreement across 63 shared molecules (RSA 0.331; 95% bootstrap interval [0.204, 0.507]). Under one strict unseen-component mixture split, incremental effects are outcome- and representation-dependent, with all intervals crossing zero. These results establish empirical boundaries for the evaluated generic molecular encoders and motivate a broader evaluation principle: representation quality in scientific domains should be assessed separately for target reliability, structural alignment, incremental information, replication, and out-of-distribution transfer.

15h ago

arXiv:2607.25751v1 Announce Type: new Abstract: In this paper, we propose the Rule-based Visiting Circulation (RVC) model in tackling the challenge in the IEEE Big Data Cup 2022: Trip Destination Prediction. Given trips containing travel information, personal attributes, origin zones, and their features in the training metropolitan areas, the task is to predict the destination of every trip in a targeted metropolitan area whose destinations are not given at all at the training stage. We highlight the challenges in this destination prediction task -- having no knowledge of the destinations in the targeted metropolitan area. We provide insights from the datasets, in which revisiting behaviors and the relationships between origins and destinations play a crucial role in individuals' trips. Hence, we design a simple but comprehensive method, rule-based visiting circulation, which directly utilizes the origin information and individuals' trip behaviors to determine the destinations in the targeted metropolitan area, i.e., requiring no learning from the four training areas. Experimental results on both offline evaluation and leaderboard submission consistently exhibit the proposed RVC can significantly outperform supervised learning methods and other heuristics. The RVC method eventually brings us to second place in the competition leaderboard.

15h ago

arXiv:2607.24768v1 Announce Type: new Abstract: Prenatal care is an important preventive service designed to improve outcomes for pregnant individuals. The American College of Obstetricians and Gynecologists (ACOG) recently introduced guidelines advocating tailored prenatal care, called PATH (Plan for Tailored Healthcare). We present PATHFinder Agent(Planner for Appropriate Tailored Healthcare), an end-to-end conversational agentic system that gathers patient health and social context through structured dialogue, curates individualized prenatal care plans aligned with PATH guidelines, and surfaces community resources from Michigan 211. The system features a four-stage workflow spanning patient intake, dynamic interaction, plan synthesis, and clinician oversight. We evaluate frontier large language models (LLMs) on expert-curated rubrics across five clinical dimensions, finding that GPT-5.2 achieves the highest average score (77.6\%) while identifying key gaps in antenatal testing recommendations. We discuss future validation through human participant studies and randomized controlled trials.

15h ago

arXiv:2505.14366v2 Announce Type: replace Abstract: We present a conceptual framework for training Vision-Language Models (VLMs) to perform Visual Perspective Taking (VPT), a core capability for embodied cognition essential for Human-Robot Interaction (HRI). As a first step toward this goal, we introduce a synthetic dataset, generated in NVIDIA Omniverse, that enables supervised learning for spatial reasoning tasks. Each instance includes an RGB image, a natural language description, and a ground-truth 4X4 transformation matrix representing object pose. We focus on inferring Z-axis distance as a foundational skill, with future extensions targeting full 6 Degrees Of Freedom (DOFs) reasoning. The dataset is publicly available to support further research. This work serves as a foundational step toward embodied AI systems capable of spatial understanding in interactive human-robot scenarios.

15h ago

arXiv:2607.25504v1 Announce Type: cross Abstract: Fine-grained weight pruning and activation sparsification have emerged as effective approaches for reducing the compute and memory cost of inference for Transformer models. In the moderate-sparsity regime, Gustavson's dataflow provides a natural execution model for exploiting both activation and weight sparsity on vector processors through metadata-driven indexed accumulation. However, existing RVV architectures lack native support for this pattern, forcing kernels to rely on software index decoding and L1-backed indexed memory operations that keep sparse tensor contractions far below their roofline performance bound. We present Ventaglio, a runtime-configurable sparse execution unit coupled with RVV ISA extensions that drives sparse tensor contractions toward their roofline through indexed gather-accumulate-scatter support. Integrated into an open-source vector processing cluster and implemented in 12nm FinFET, Ventaglio accelerates sparse tensor contraction kernels by $6.9\text{--}7.4\times$ over optimized RVV baselines, with only $3.1\%$ area overhead for a cluster of tightly-L1 coupled vector processing elements. We build a performance-accurate instruction-level model of the Ventaglio extension, calibrate it against RTL implementation, and leverage it for scale-out performance analysis on a large $4\times4$ multi-cluster system. Using a DuoGPT-pruned LLaMA-3-8B model with practical $40\text{--}60\%$ dual sparsity, Ventaglio achieves $2.40\text{--}5.25\times$ and $2.06\text{--}3.16\times$ speedup over dense baselines during prefill and autoregressive decoding, respectively.

15h ago

arXiv:2607.25276v1 Announce Type: cross Abstract: We present FunnelAL, a retrieve-then-rank active learning system for single-class discovery, which adapts the multi-stage funnel architecture of industrial recommender systems to data annotation. Large-scale supervised learning faces two challenges: efficiently finding relevant samples in a massive corpus, and distinguishing true positives from visually confusable negatives when embeddings do not cleanly separate classes. Conventional active learning offers a principled framework for reducing annotation cost, yet it treats sample selection as a single-stage process that addresses neither challenge efficiently. FunnelAL decomposes the problem into cascaded stages. Starting from a single positive and negative example, the system iterates through: (1) embedding-based retrieval scoring that narrows the corpus to a manageable candidate set; (2) a precision-triggered ranking stage that exploits a learned ranker (RankNet) while batch precision remains high, then automatically blends in committee-based exploration (QBC) once returns diminish; and (3) feedback from the annotator's labels that refines both stages in subsequent iterations. We evaluate on three diverse image classification benchmarks. With a perfect annotator, FunnelAL attains the best final F1 on all three benchmarks, the best annotation efficiency (first in AULC), and the fewest annotation rounds. The most recent single-class discovery methods (GAL, PF-MA) at best match its final quality, and only at consistently higher labeling cost. Under annotator labeling errors at realistic rates, FunnelAL remains first or statistically tied for first while classical uncertainty-based methods degrade two to three times faster. Our work provides a concrete bridge between multi-stage recommender systems and active learning.

15h ago

arXiv:2607.25554v1 Announce Type: new Abstract: Future event prediction carries broad social impact yet remains challenging. SOTA approaches augment LLMs with external agent frameworks whose predictive capability vanishes once the harness is removed. While recent Tool-Integrated Reasoning (TIR) internalizes deep search for multi-hop retrieval of facts, forecasting further demands temporal search and reasoning over historical trends and dynamic shifts. The key obstacle is data: historical queries induce temporal leakage that degrades forecasting into retrieval. Prior works either freeze information gathering with static observations, or rely on rejection sampling or unresolved fresh queries that discard vast amounts of data, degrading synthesis efficiency. We propose a time-truncation harness that enforces a temporal cut-off at every turn, enabling TIR-style sampling from historical events, reducing temporal leakage and reliance of rejection sampling or unsolved queries, increasing the sampling efficiency. We further build a large-scale corpus and a process-based metric and show that our harness naturally induces a broader temporal breadth of search and raises the proportion of high-quality data, further increasing the efficiency and reducing the reliance on complex rubrics. Distillation experiments show that students trained on harness-intervened data achieve the best performance, demonstrating harness-assisted model evolving that turns higher quality temporal search and reasoning data into a parametric advancement of the students.

15h ago

arXiv:2607.25970v1 Announce Type: new Abstract: RL for code correctness is now established: have the model generate a program, run it against hidden test cases, and reward solutions that pass. Extending this to code optimization seems straightforward: just add execution time to the reward. But in practice, once timing drives the reward, small problems in measurement noise, reward sparsity, or GRPO instability overwhelm the signal and make RL fail: generated solutions are barely faster, and more of them can fail. We make execution time learnable through three stages: (1) how code is tested, by building DMC-Optim with large optimization tests and a calibrated sandbox; (2) how speed is turned into reward, by composing correctness and speed in the RL environment and using an offline simulator to predict the most promising configurations; and (3) how the model learns from that reward, by adapting GRPO and evaluation to the sparser, noisier timed-execution setting. On DMC-Optim, the strongest optimization-aware configurations improve strict top-50% pass@1 from 18.0% to 31.3% on Qwen 2.5 7B and from 30.7% to 50.4% on CWM 32B. These gains further increase at stricter percentiles such as top-30%, with 125% relative improvement for CWM 32B, while preserving pure-correctness scores. When the timing sandbox is degraded, robust optimization RL reaches 100% to 200% improvement over standard RLVR, depending on the evaluation criterion. On LCB, CWM 32B wins up to 83% of median-sample speed comparisons against standard RLVR. Relative to the fastest correct human submissions per problem, it reaches about half the human rate of complexity-class improvements (14% vs. 28%).

15h ago

arXiv:2607.25687v1 Announce Type: new Abstract: Full-field reconstruction of air pollution is essential for evaluating pollution exposure and supporting public health decision-making. However, the complex interactions among pollutants, hard-to-predict weather patterns, and limited monitoring station coverage make this a complex task. We apply deep learning techniques to provide fast and accurate reconstructions from sparse observations of four key pollutants: NO2, O3, PM2.5 and PM10. Models are trained on full-field simulation data and evaluated on real-world observations collected from 9 to 28 monitoring stations in the city of Paris. We introduce a diffusion-based generative framework for multi-pollutant reconstruction and benchmark its performance against deterministic deep learning models. Despite noisy observations and strong spatial variability, the models achieve high structural similarity on simulated validation data and produce realistic spatial patterns on real-world observations, as indicated by power-spectrum analysis. We introduce data augmentation methods that enable transfer to real-world observations without retraining, allowing the models to generalise beyond the training period. These findings highlight the potential of ML models for reliable real-world deployment in air pollution reconstruction tasks.

15h ago

arXiv:2607.24873v1 Announce Type: new Abstract: Recent advances in AI music generation have enabled users to create complete musical pieces from natural-language prompts. However, most existing systems follow a prompt-and-regenerate paradigm, making iterative refinement difficult because users must repeatedly recreate compositions instead of directly evolving existing musical ideas. We present MusiChat, a conversational vibe composing system that enables collaborative human-AI music creation through natural-language interaction and iterative refinement. At the core of MusiChat is a hierarchical controllable music generation framework that separates lyric-aligned musical structure generation from expressive surface realization, allowing flexible stylistic transformations and structure-preserving edits. The system integrates a large language model with a hybrid symbolic music engine through a memory-augmented architecture that maintains the active composition state and user history across interactions. A hybrid intent-routing mechanism further enables efficient interpretation of both precise musical edits and open-ended creative requests. Rather than regenerating compositions from scratch, MusiChat incrementally transforms an evolving musical artifact while preserving relevant musical structure and user intent. We evaluate MusiChat through objective analysis and human studies, achieving 95.31% and 100% accuracy for single- and multi-turn interactions, respectively, and obtaining like-to-dislike ratios of 2:1 for melody naturalness and 3:1 for musical quality. Our results demonstrate that MusiChat supports coherent multi-turn music authoring and interactive human-AI co-creation through a conversational interface.

15h ago

arXiv:2602.09611v2 Announce Type: replace-cross Abstract: Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (LVLMs). However, vision-agnostic watermarks may introduce visually irrelevant tokens and disrupt visual grounding by enforcing indiscriminate pseudo-random biases. Additionally, current vision-specific watermarks rely on a static, one-time estimation of vision-critical weights and ignore the weight distribution density when determining the proportion of protected tokens. This design fails to account for dynamic changes in visual dependence during generation and may introduce low-quality tokens in the long tail. To address these challenges, we propose Attention-Guided Dynamic Watermarking (AGMark), a novel framework that embeds detectable signals while largely preserving visual-semantic fidelity. At each decoding step, AGMark first dynamically identifies semantic-critical evidence based on attention weights for visual relevance, together with context-aware coherence cues, resulting in a more adaptive and well-calibrated evidence-weight distribution. It then determines the proportion of semantic-critical tokens by jointly considering uncertainty awareness (token entropy) and evidence calibration (weight density), thereby enabling more reliable adaptive vocabulary partitioning to avoid irrelevant tokens. Empirical results consistently confirm that AGMark outperforms conventional methods, substantially improving generation quality and yielding particularly strong gains in visual semantic fidelity in the later stages of generation. Our framework maintains highly competitive detection performance (at least 99.36% AUC) and robust attack resilience (at least 88.61% AUC) without sacrificing inference efficiency, taking a significant step toward reliability-preserving multimodal watermarking.

15h ago

arXiv:2510.04452v3 Announce Type: replace-cross Abstract: Computer use agents (or "agents") are generative AI that automates actions within user interfaces from user commands. Current research focuses on training and evaluating the underlying models, leaving these agents' user experience (UX) understudied. We conducted two studies to understand the design space of agent UX (RQ1) and the support required to prototype it (RQ2). First, we develop a taxonomy of design considerations for agent UX, comprising 21 subcategories of UX considerations. Then, through a requirements elicitation study with 12 participants---including six agent experts---we identify five Activities and six Desired Capabilities needed in tools prototyping agent UX. Informed by these results, we created AgentUXlab, a design probe that enables developers to design agents with different UX approaches for a website and evaluate those experiences by executing prototypes in a browser. From a user study with 14 participants, we elucidate tooling insights and derive design implications for agent UX prototyping tools.

15h ago

arXiv:2601.03595v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (\eg backtracking, cross-verification) during the reasoning process, which improves their performance on complex tasks. Currently, reasoning strategies are autonomously selected by LRMs themselves. However, such autonomous selection often produces inefficient or even erroneous reasoning paths. To make reasoning more reliable and flexible, it is important to develop methods for controlling reasoning strategies. Existing methods struggle to control fine-grained reasoning strategies due to conceptual entanglement in LRMs' hidden states. To address this, we leverage Sparse Autoencoders (SAEs) to decompose strategy-entangled hidden states into a disentangled feature space. To identify the few strategy-specific features from the vast pool of SAE features, we propose SAE-Steering, an efficient two-stage feature identification pipeline. SAE-Steering first recalls features that amplify the logits of strategy-specific keywords, filtering out over 99\% of features, and then ranks the remaining features by their control effectiveness. Using the identified strategy-specific features as control vectors, SAE-Steering outperforms existing methods by over 15\% in control effectiveness. Furthermore, controlling reasoning strategies can redirect LRMs from erroneous paths to correct ones, achieving a 7\% absolute accuracy improvement. Our code and data are available at https://github.com/Peter-Fy/SAE-Steering.

15h ago

arXiv:2411.10431v3 Announce Type: replace Abstract: Parameter estimation, which represents a classical inverse problem, is often ill-posed as different parameter combinations can yield identical outputs. This non-uniqueness presents a critical barrier to accurate and unique identification. Here we introduce a parameter estimation framework to address such limits: the Joint Conditional Diffusion Model-based Inverse Problem Solver. By leveraging the stochasticity of diffusion models, it produces candidate solutions that capture underlying parameter distributions conditioned on the observations. Joint conditioning on multiple observations further narrows the posterior distributions of non-identifiable parameters. For composite load model parameterization, a challenging task in dynamic power systems, the proposed method achieves a 58.6% reduction in parameter estimation error compared to the single-condition model. It also accurately replicates system's dynamic responses under various electrical faults with root mean square errors below $4 \times {10^{ - 3}}$, exhibiting comprehensive advantages in calibration and efficiency over existing methods. Given its data-driven nature, it provides a general framework for parameter estimation while effectively mitigating the non-uniqueness problem across scientific domains.

15h ago

arXiv:2607.25543v1 Announce Type: cross Abstract: Generative AI has rapidly expanded audio-visual forgery beyond human-centric deepfakes into general scenes. Existing AIGC detection methods assume audio-visual content correspondence, identifying forgeries by spotting cross-modal inconsistencies. However, we empirically find that this assumption does not consistently hold in general scenarios. We argue that, for general audio-visual AIGC detection, decision-level fusion is a more robust alternative to feature-level fusion. Therefore, we propose DAV-Det, a decoupled audio-visual AIGC detection system that independently models forensic evidence from each modality. The visual detector leverages multi-granularity representations at global, patch, and segment levels to capture spatial forgery cues, while the audio detector exploits both temporal and spectral irregularities via a gated temporal-spectral dual-branch architecture to model acoustic artifacts. Our method ranks 1st in the General AIGC Audio-Video Detection Challenge of the IJCAI-ECAI 2026 DDL 2.0 Workshop, with a final score of 0.8460. Code is available at https://github.com/tuffy-studio/DAV-Det.

15h ago

arXiv:2607.25763v1 Announce Type: cross Abstract: This paper proposes a multitask wireless foundation model via adaptive low-rank masked autoencoders (WALoMA), a unified multi-task foundation model for sixth-generation (6G) wireless physical layer architectures, to address the limitations of specialized, task-specific deep learning models and the practical challenge of scarce labeled wireless datasets. By leveraging concepts inspired by foundation models, the proposed framework adopts a masked autoencoder (MAE) paradigm to learn from unlabeled channel data, to significantly reduce reliance on extensive annotations. The model treats wireless channel state information (CSI) as a universal modality and learns transferable representations through self-supervised channel reconstruction. Key architectural novelties include the use of 2D positional encoding (PE) to explicitly preserve the spatial-frequency relationships between antennas and subcarriers, and low-rank adaptation (LoRA) for parameter-efficient fine-tuning. The framework's efficacy is demonstrated across five downstream tasks, achieving individual scores of 96.47\% for LoS/NLoS classification, 80.45\% for beam prediction, 85.78\% for channel interpolation, 99.12\% for channel estimation, and 77.18\% for channel charting. Consequently, numerical results show that the proposed model achieves a composite score of 87.80\%, significantly outperforming the 59.90\% achieved by the large wireless model (LWM) baseline while training an average of only 14.68\% of total parameters, and maintaining strong performance even under extremely limited labeled data conditions.

15h ago