All entries

arXiv:2609.19149v1 Announce Type: new Abstract: Subliminal learning shows that language models can transmit a hidden trait through outputs that appear unrelated to it. One proposed explanation, token

arXiv:2505.03953v3 Announce Type: replace Abstract: When solving optimization problems under uncertainty with contextual data, utilizing machine learning to predict the uncertain parameters' values is

arXiv:2609.20712v1 Announce Type: new Abstract: This paper introduces and operationalizes summarization bias: a proposed systematic tendency of large language models (LLMs) to represent narrative mean

Super interesting work from Zoom and colleagues. If you maintain a hand-built coding harness, there are some great insights here. (bookmark it) They held the execution loop of a coding harness fixed a

super pumped for this convo w/ @huntlovell and @allietheicon on all things langchain 🤝 jev Hot topic livestream: Learn about Jev A buzzy new model Jev, by @typesafeai, reports up to 200x faster infere

arXiv:2609.20171v1 Announce Type: new Abstract: The support threshold of the Apriori algorithm involves a trade-off in conducting market basket analysis: the associations that occur frequently are not

arXiv:2609.19613v1 Announce Type: cross Abstract: Dexterous food manipulation requires control under deformation, occlusion, and uncertain contact. We present TacSushi, a tactile-grounded, Cosmos3-bas

arXiv:2609.19824v1 Announce Type: new Abstract: Language-guided navigation for terrestrial-aerial bimodal robots requires selecting routes and locomotion modes that match scene context and task intent

arXiv:2609.20077v1 Announce Type: new Abstract: Interest in developing personalised language models is rapidly growing. While personalisation is often viewed as a mechanism to better serve diverse use

arXiv:2609.20577v1 Announce Type: cross Abstract: We study the Bayes-optimal spherical linear model as the ambient dimension and sample size grow proportionally, under a quantitative Marchenko--Pastur

arXiv:2609.19378v1 Announce Type: new Abstract: Online residual learning can reduce model mismatch in predictive control, but passive data collection may fail to adequately cover states that become im

arXiv:2609.20150v1 Announce Type: new Abstract: Conventional satellite remote sensing transmission follows a reconstruct-then-infer paradigm that optimizes pixel-level fidelity, creating an objective

arXiv:2609.19577v1 Announce Type: new Abstract: Teleoperation, a human-in-the-loop control scheme, allows a human operator to remotely command and guide a mobile robot to navigate in off-road environm

Ternary Bonsai 2 27B Tried it out and was excited. Gave it a prompt 'create a 3d little planet globe where I (player can walk around) and it has all these biomes to explore, the globe doesn't have to

Tried the same detailed face prompt on a pile of models and in my Opinion KREA beats paid models Wanted something more real than the usual AI “pretty girl.” Same fictional character, same prompt, grid

arXiv:2609.20693v1 Announce Type: cross Abstract: Detecting phases of matter in general relies on identifying the correct order parameter - a task that remains notoriously difficult for unknown transi

arXiv:2609.19234v1 Announce Type: cross Abstract: This paper presents the AR fairness metamodel, a framework designed to represent, analyze, and compare different fairness scenarios. The metamodel con

arXiv:2609.20409v1 Announce Type: new Abstract: Two-timescale stochastic approximation (TTSA) is a fundamental tool for analyzing coupled iterative algorithms in reinforcement learning, optimization,

arXiv:2609.19616v1 Announce Type: new Abstract: Complexity measured from generated code is failure-dependent: a difficult prompt can yield a short failing program and be assigned low output complexity

This week we kicked off the DevFest season in North America at Google Hudson Square in New York City with 80 engineers packed into the room. Typical technical workshops hand you a finished repo, tell

arXiv:2510.09022v2 Announce Type: replace Abstract: Recent Machine Learning (ML) approaches have shown increased performance on benchmarks at the cost of escalating compute demands. Hardware, algorith

arXiv:2609.20687v1 Announce Type: cross Abstract: We study first-order black-box convex optimization over an ell_p-ball for objectives Lipschitz in the ell_q-norm, solving in the affirmative the nonsm

arXiv:2609.19924v1 Announce Type: cross Abstract: Large Language Models (LLMs) transform vast collections of unstructured text into semantic patterns used for language generation and reasoning tasks.

arXiv:2609.20050v1 Announce Type: cross Abstract: A coding agent halfway through an issue has already read much of what a retriever ranks highest. Relevance is scored per passage, but sufficiency belo

arXiv:2606.09735v2 Announce Type: replace Abstract: The ambition behind alignment training is to make large language models safe and useful. The primary mechanisms, reinforcement learning from human f

Today we are announcing the new AgentCore runtime, a capability of Amazon Bedrock AgentCore built for the speed, flexibility, and cost efficiency that production agents demand. It reclaims memory as s

arXiv:2609.20449v1 Announce Type: new Abstract: The economic value of inference depends on how capacity and task information are distributed across stages of AI production. We study these organization

arXiv:2609.19611v1 Announce Type: cross Abstract: Tensor programs, as used in deep learning models, are a prime target for optimization, as small performance improvements can have a large impact acros

arXiv:2609.20232v1 Announce Type: new Abstract: We introduce the extbf{Public Discourse Corpus (PDC)}, the first dataset of public-figure interview speech jointly annotated for affective valence and e

arXiv:2609.19366v1 Announce Type: new Abstract: Prior work has shown that internal harmfulness representations in large language models vary across risk categories, while sharing a common general harm

arXiv:2609.19730v1 Announce Type: cross Abstract: Accurate estimation of left ventricular ejection fraction (EF) from echocardiography is central to cardiovascular care, and deep learning enables auto

The simple truth: not even Anthropic has a plan for how to make AI safe in advance. There is no theory. I've asked! Outside evaluators don't change the situation. No one at these companies has workabl

In recent weeks, leaders of some of the biggest AI companies have warned that the very tech they are developing is dangerous. Last weekend, Anthropic CEO Dario Amodei argued that AI carries serious ri

arXiv:2609.19448v1 Announce Type: new Abstract: In both cognitive science and computer science, goals are conceptualized as cognitive states that flexibly combine with world knowledge to organize and

These are precisely the scenarios that I spend a significant time actually being concerned with. The adoption of unreliable, brittle, and inaccurate LLMs within safety-critical fields (e.g., defense a

arXiv:2609.20131v1 Announce Type: cross Abstract: Reasoning-based reranking with Large Language Models (LLMs) has shown promising improvements in text ranking. However, current methods predominantly r

This is absolutely the right way to think about this moment in human history - and it should be relatively easy to prevent this kind of damage from large-scale agent swarms. The problem is that it's s

This is crazy. In late July, 'three guys with Claude and Codex subscriptions' were able to use Opus 5 to access OAI auth tokens and gain write access to OpenAI's monorepo openai/openai over the course

This new Claude Code mods system looks pretty interesting - more example mods here: https://github.com/anthropics/claude-code/tree/main/mods AGENTS.md support is built off of Claude Code mods, our upc

this this this The focus on AI causing extinction is going to get people killed. AI lab employees talk about how hard security is, not to point to some new solution, but to say security won’t work. On

This was a super fun podcast, went far further afield than most of them do. Give it a listen! Episode 432 w/ Connor Leahy (@NPCollapse) is available now. Connor is an AI researcher & co-founder of Ele

Through the VOICE trial, Terry is using his Neuralink implant to help fine-tune a brain-to-voice interface for himself and others who can’t speak. He trained the algorithm first by miming speech as be

arXiv:2609.20435v1 Announce Type: new Abstract: Autonomous mobile robots require timeefficient planning and safety-critical dynamic obstacle avoidance under constrained onboard computation. While Iter

arXiv:2609.20290v1 Announce Type: new Abstract: Detecting crop disease early is central to sustainable agriculture and food security under United Nations Sustainable Development Goal 2 (Zero Hunger),

arXiv:2609.20186v1 Announce Type: new Abstract: Speculative Decoding (SD) has significantly accelerated Large Language Model (LLM) inference, yet existing approaches face a fundamental tradeoff betwee

arXiv:2609.19167v1 Announce Type: new Abstract: As AI systems evolve into personalized digital companions, a central capability is reasoning over a user's long-term personal history: not merely storin