Knowledge catalogue
arXiv:2609.09907v1 Announce Type: new Abstract: Meta-learning has emerged as an effective paradigm for transferring knowledge across sequential bandit tasks. While substantial progress has been made f
arXiv:2609.07998v1 Announce Type: new Abstract: We study the control of Markov decision processes in which the quality of a policy is evaluated by a dynamic, time-consistent Markov risk measure rather
arXiv:2609.10433v1 Announce Type: cross Abstract: This study develops a deep reinforcement learning framework for training Unmanned Aerial Vehicle (UAV) agents to navigate and monitor simulated wildfi
arXiv:2512.10237v2 Announce Type: replace Abstract: Reinforcement Learning from Human Feedback has emerged as a standard for aligning diffusion models. However, we identify a fundamental limitation in
arXiv:2609.09384v1 Announce Type: cross Abstract: This paper addresses safety-critical coordination for scalar agents whose distributed commands are implemented through constrained physical-input dyna
arXiv:2609.09250v1 Announce Type: cross Abstract: A verifier for robot policies reads a candidate behavior and returns a score for how well it did, used both to evaluate vision-language-action policie
arXiv:2609.07663v1 Announce Type: cross Abstract: A wrong number is worse than no answer. Across factuality-critical domains -- audience metrics, scheduling and rights in media; dosages and lab values
not counting Sam himself who is frequently in DC OpenAI employs FIVE lobbying firms and has over 100 staffers in their Washington, DC office. They must push for AI legislation to justify their existen
arXiv:2609.10336v1 Announce Type: new Abstract: Despite significant progress in odometry estimation, long-term drift remains a fundamental limitation of incremental pose integration, especially in lar
arXiv:2609.10321v1 Announce Type: new Abstract: Knowledge distillation offers an efficient route to transfer a task-adapted vision-language teacher to a compact student. The training target in current
Paul Christiano / @paulfchristiano: OpenAI Foundation board member Paul Christiano says the AI industry is currently not on track to reduce the acute loss-of-control risk to an “acceptable” level — I
OpenAI hid the details of the wiki incident from the investigators of the later HuggingFace hack. When caught, they responded only with corporate BS. This cover-up of unprecedentedly misaligned behavi
arXiv:2609.09981v1 Announce Type: cross Abstract: We study offline inference for the optimal value in reinforcement learning. Two new nuisances are derived as fixed points of a self-induced Bellman eq
arXiv:2203.06158v3 Announce Type: replace Abstract: Scheduled batch jobs are widely used on asynchronous computing platforms to execute enterprise applications such as promotional notifications and ca
arXiv:2609.10198v1 Announce Type: new Abstract: Emotions are a pervasive feature of political communication, yet existing research has focused primarily on describing patterns of emotional expression
arXiv:2603.22714v2 Announce Type: replace-cross Abstract: We present PopResume, a population-representative resume dataset for causal fairness auditing of LLM- and VLM-based resume screening systems.
arXiv:2609.07910v1 Announce Type: new Abstract: Multi-agent federations need governance that answers three questions under adversarial conditions: who participated (identity), did they conform (enforc
Maxwell Zeff / Wired: Q&A with AI researcher Jacob Coxon, who quit Anthropic, on the need for industry-wide, international coordination to limit recursive self-improvement, and more — Jacob Coxon talk
arXiv:2609.07901v1 Announce Type: new Abstract: Weight quantization largely determines the economics of serving open-weight LLMs. Its costs are usually assessed with capability benchmarks, on which 4-
arXiv:2609.08258v1 Announce Type: new Abstract: Long-running language-model agents depend on persistent memory. Many agent-memory systems preserve history through soft revocation: a contradicted fact
arXiv:2609.10021v1 Announce Type: new Abstract: Vision--language--action (VLA) models acquire broad generalization through large-scale pretraining, yet adapting them to a new task and robot embodiment
arXiv:2609.08515v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly integrated into human society, aligning them with pluralistic social values has become a critical pri
arXiv:2609.08789v1 Announce Type: cross Abstract: Frontier AI developers publish safety frameworks that commit them to evidencing whether their models are dangerous. The European Union and California
arXiv:2609.07255v1 Announce Type: new Abstract: Language-model agents increasingly rely on skills: reusable procedural knowledge for reasoning, tool use, and interaction. Existing work studies how ski
Maxwell Zeff / Wired: Sources: OpenAI asked members of Congress for guidance on whether orchestrating an industry-wide slowdown in AI development would be legal under antitrust law — Substantive coord
arXiv:2609.05800v1 Announce Type: new Abstract: Activation steering controls LLM behavior at inference time by adding learned directions to hidden states, but existing methods handle one concept at a
arXiv:2609.08452v1 Announce Type: new Abstract: Multi-agent large language models solve complex tasks by coordinating several policies in a shared environment. However, existing reinforcement learning
arXiv:2609.09899v1 Announce Type: cross Abstract: Language models can fluently describe how they would behave: whether they would cave to pushback, misuse a tool, or lie under pressure. Is that descri
arXiv:2609.09719v1 Announce Type: new Abstract: Text-aligned speech tokenization methods have emerged to better align speech tokens with LLM token spaces, enabling more effective utilization of pretra
arXiv:2609.09890v1 Announce Type: new Abstract: Multi-view diffusion models have shown strong performance in scenes with strong geometric priors and sparse semantics, such as indoor rooms or simple ou
arXiv:2609.09840v1 Announce Type: new Abstract: Accurate long-term trajectory prediction for maritime vessels is essential for safety and logistical efficiency. While deep learning models, particularl
arXiv:2509.24877v3 Announce Type: replace Abstract: The social science of large language models (LLMs) examines how these systems evoke mind attributions, interact with one another, and transform huma
arXiv:2609.07713v1 Announce Type: new Abstract: Generative and agentic AI are reshaping both the production and evaluation of scientific research. These developments are often studied separately, as q
arXiv:2609.05749v1 Announce Type: new Abstract: Work on the risks of artificial intelligence has focused predominantly on capability risk: the danger that systems become too powerful, too autonomous,
arXiv:2609.07731v1 Announce Type: new Abstract: We show that ordinary business language --- 'maximize profitability' --- induces profit-oriented ambiguity resolution: LLMs systematically dismiss ambig
arXiv:2609.10296v1 Announce Type: new Abstract: Non-invasive speech decoding remains constrained by the low signal-to-noise ratio of neural recordings, which makes fine-grained reconstruction of phone
this was wild amounts of disinformation / fear mongering / the stupidest interview ive ever seen: 1) ai did NOT hack huggingface on its own 'independent volition'. it wasnt sitting there thinking hmm
arXiv:2609.09925v1 Announce Type: cross Abstract: Modern vision-language-action (VLA) policies predict a whole chunk of actions: one to two seconds of coordinated motion emitted in a single forward pa
Tomorrow I will rip Jacob Coxon’s CNN appearance. But let’s cut with the six weeks/entry level bullshit and the character assassination. My best source (and one I have a lot of faith) in is that he st
Two big updates 1. I published an @FT op-ed on the OpenAI/HF incident & follow-ups 2. We’re starting an Open Alignment team at @huggingface to work on safety & alignment for open models, incl cybersec
arXiv:2603.15576v2 Announce Type: replace Abstract: This paper develops new variance-reduction techniques for the forward-reflected-backward splitting (FRBS) method to solve a class of possibly nonmon
arXiv:2609.06816v1 Announce Type: new Abstract: Decision-time search in perfect and imperfect information games with enumerable belief states are effective methods for game AI. Collectible card games
arXiv:2609.10224v1 Announce Type: new Abstract: Vision-language models such as CLIP embed images and text in a shared space, where modality-specific distributions often remain separated. Existing acco
arXiv:2609.09300v1 Announce Type: new Abstract: Video understanding demands a convergence of complementary capabilities across perception, temporal understanding, and complex reasoning, which are diff
arXiv:2603.25021v3 Announce Type: replace Abstract: Existing Multimodal Large Language Models (MLLMs) often suffer from hallucinations in long video understanding (LVU), primarily due to the imbalance
arXiv:2609.06840v1 Announce Type: cross Abstract: Web Application Firewalls (WAFs) mainly rely on signatures to detect known attacks, which can leave gaps against modified or previously unseen payload
arXiv:2609.10261v1 Announce Type: new Abstract: Multi-modal medical image segmentation leverages complementary diagnostic information, yet fusion can underperform single-modality baselines when spatia
arXiv:2609.05871v1 Announce Type: cross Abstract: Audio-conditioned language models often underuse acoustic cues such as prosody, emotion, and non-speech sounds, raising the question of whether ASR-su
arXiv:2510.15047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call explorat
Why the public needs to step up. I talk with @CBCNews about why a (temporary) boycott of generative AI, as unlikely as it is, ought to be on the table. https://youtu.be/3BBp-tCvsOM?si=88KxNluVZnuzRw3L
arXiv:2609.05591v1 Announce Type: cross Abstract: Safety evaluations typically focus on individual agents, but interacting agents can spread harmful information and influence the environment in which
arXiv:2609.09677v1 Announce Type: new Abstract: Incremental-text streaming text-to-speech (TTS) needs online text progress tracking for synchronized highlighting, interruption handling, and dialogue-h
arXiv:2609.08672v1 Announce Type: cross Abstract: Streaming automatic speech recognition (ASR) for real-time voice agents and full-duplex dialogue must provide accurate partial transcripts with low co
arXiv:2609.09388v1 Announce Type: new Abstract: Brain-age prediction models are commonly evaluated by predictive accuracy, yet accurate predictions alone do not establish that a model relies on reprod
arXiv:2609.08247v1 Announce Type: new Abstract: Wallet reputation scores decide who receives an airdrop, who can borrow, and who enters an allowlist across decentralised finance. They almost always be
arXiv:2609.08211v1 Announce Type: cross Abstract: Real-world Multi-Objective Reinforcement Learning (MORL) often suffers from sparse rewards, reward conflicts, and late-stage reward tug-of-war, causin
arXiv:2609.08826v1 Announce Type: cross Abstract: When an external reference set (an anchor) is used to decompose an LLM-judge panel's error into a quality signal and a shared common-mode error, stand
arXiv:2609.05895v1 Announce Type: new Abstract: We study a finite-horizon online resource allocation problem with initial resource capacities proportional to the horizon. In each period, a request typ
arXiv:2609.08338v1 Announce Type: new Abstract: Object detection and tracking are fundamental components of perception systems for autonomous driving. Achieving robust performance under adverse condit
arXiv:2506.12809v2 Announce Type: replace Abstract: The long horizon forecasting (LHF) problem has come up in the time series literature for over the last 35 years or so. This review covers aspects of