Knowledge catalogue
arXiv:2610.20035v1 Announce Type: cross Abstract: We introduce Weighted Adjoint Matching, a method to finetune a pretrained diffusion or flow matching model given a differentiable reward. We derive it
arXiv:2610.19202v1 Announce Type: new Abstract: Rare but severe failures of large language models can become practically significant at deployment scale. Estimating their probabilities with direct Mon
We're expanding access to GPT-Rosalind for academic research. The new Rosalind Academic Plan helps scientific labs bring AI into the work of understanding biology, exploring ideas, and deciding what t
£299.99 Lenovo IdeaCentre Mini (Snapdragon X1-26-100, 32GB, CPU only): - Qwen3.6 35B A3B coder: reads ~118 tok/s, writes 24.5, ~30 with MTP - Qwen3-Next 80B A3B: 17-18 tok/s writes with MTP How I got
arXiv:2610.19611v1 Announce Type: new Abstract: Modern vision-language models can accept multi-image contexts, but aggregate accuracy rarely reveals where a multi-image reasoning pipeline fails. We st
What can large-scale AI models bring to the growing complexity of particle physics? @CERN and Mistral join forces to explore this question. The ambition: a single Large Physics Model, trained on billi
arXiv:2610.14477v1 Announce Type: cross Abstract: Robustness tests for tool-using agents often change the agent's environment, for example by hiding a hostile note in an invoice, and then judge the ag
arXiv:2610.20104v1 Announce Type: new Abstract: Autoregressive transformers trained on limit order book (LOB) message streams are increasingly proposed as foundation models for market microstructure.
arXiv:2610.20450v1 Announce Type: cross Abstract: Pairwise comparison data are a standard supervision signal in preference learning, but disagreement in such data can reflect stable latent heterogenei
arXiv:2610.19476v1 Announce Type: cross Abstract: Post-training often improves the performance of large audio-language models on audio understanding and reasoning benchmarks. However, these improvemen
arXiv:2610.19731v1 Announce Type: new Abstract: Goal misgeneralization is a common failure mode in which an agent behaves competently out of distribution but does not pursue the intended goal. However
arXiv:2610.19046v1 Announce Type: new Abstract: Information-theoretic exploration is of primary interest in methodological studies of reinforcement learning (RL) and computational cognitive neuroscien
arXiv:2610.20052v1 Announce Type: new Abstract: Ambiguous inputs can admit multiple interpretations, each potentially yielding a different answer. Existing work largely treats this ambiguity as a prop
arXiv:2610.20195v1 Announce Type: new Abstract: Effective social interaction requires more than fluent responses: agents must reach plans that fit the participants' needs and circumstances. Existing e
What makes NVIDIA Nemotron 3.5 Super VL different? → Text, image, document, and video understanding in one model → Reasoning and tool use with visual context preserved across steps → 120B hybrid MoE (
arXiv:2610.19825v1 Announce Type: cross Abstract: Integrating world models into Vision-Language-Action models (VLAs) has emerged as a promising direction, enabling policies to anticipate future dynami
Small teams, short runway, and constant pressure to ship faster — it’s the reality we see every day among the founders we work with at Google for Startups. When you are building a company from the gro
arXiv:2610.17090v1 Announce Type: cross Abstract: On 6 October 2026 OpenAI published an initial 722 AI-written mathematical manuscripts, organized into 372 problem families, in the public repository g
arXiv:2610.15883v1 Announce Type: cross Abstract: Text wrapped in a trigger can be made behaviorally invisible to a language model: omitted from summaries and quotations, ignored in question answering
arXiv:2607.11197v2 Announce Type: replace Abstract: When LLMs exhibit uneven performance across planning tasks, these gaps are often attributed to task difficulty. We argue that this explanation is in
arXiv:2610.19498v1 Announce Type: cross Abstract: Model signing authenticates the full-precision weights W an LLM is released with, yet users run a quantized artifact Q whose producing transformation
arXiv:2610.16615v1 Announce Type: new Abstract: Visual token compression has emerged as a critical technique for reducing the inference cost of Vision-Language Models. Existing methods select tokens b
arXiv:2610.16325v1 Announce Type: new Abstract: When a steering intervention changes a language model's behavior, which part of the intervention deserves the credit? We test this question for a target
arXiv:2610.16067v1 Announce Type: cross Abstract: Agent evaluation harnesses are software systems that run test suites, generate inputs, and decide outcomes with test oracles. This paper audits such s
arXiv:2606.22936v2 Announce Type: replace Abstract: Tool-using LLM agents make early choices about what to search for, which evidence to trust, and what to do next. A wrong early choice can steer ever
arXiv:2610.16039v1 Announce Type: cross Abstract: Multi-agent LLM systems (MALS) introduce a privacy-leakage problem that conventional sensitivity-based defenses miss, since information disclosed to o
arXiv:2610.18158v1 Announce Type: new Abstract: Learning dealer agents can settle on persistently wide quotes, raising what customers pay to trade. A venue can route more orders to tighter quotes, but
arXiv:2610.20429v1 Announce Type: new Abstract: Though modern AI models like LLMs predict discrete tokens, today's robotic foundation models represent actions as continuous vectors. In this paper, we
arXiv:2610.19814v1 Announce Type: new Abstract: Transformer-based tabular foundation models (TFMs) achieve state-of-the-art performance on small to medium-sized tabular prediction tasks while processi
arXiv:2610.20413v1 Announce Type: new Abstract: Momentum is a classical tool for accelerating convex optimization and a standard component of modern large language model training. Yet recent empirical
arXiv:2610.20342v1 Announce Type: new Abstract: Missing data is a pervasive challenge in machine learning, often degrading predictive performance and complicating model deployment. Most existing appro
arXiv:2610.19769v1 Announce Type: cross Abstract: Architectural technical debt arises when a system's implementation drifts from its inten ded modular decomposition, while the mapping between source f
arXiv:2610.17365v1 Announce Type: new Abstract: As LLM agents take on more autonomous roles, they may interact with multiple clients and counterparties whose goals and incentives conflict. If an agent
arXiv:2602.07549v3 Announce Type: replace-cross Abstract: In agentic search, an LLM agent searches the web, reads the pages it finds, and decides what to look for next before returning an answer. But
arXiv:2610.15459v1 Announce Type: cross Abstract: LLM-based multi-agent systems (LLM-MAS) use specialized agents that exchange messages to accomplish complex tasks. Their reliance on networked protoco
arXiv:2610.19910v1 Announce Type: new Abstract: Large language model agents increasingly improve by distilling experience into reusable skills, but errors in that experience can persist in learned rul
arXiv:2610.20186v1 Announce Type: new Abstract: Skills are widely assumed to play a central role in career transitions, motivating their use in career path prediction (CPP) systems. In this work, we c
arXiv:2610.20089v1 Announce Type: new Abstract: Pairwise preference feedback has become a widely adopted supervision signal for reinforcement learning in video generation models, as pairwise compariso
arXiv:2610.14360v1 Announce Type: new Abstract: Large language model (LLM) alignment often assumes that the user interacting with a model is also the primary beneficiary of its behavior. Yet in many c
arXiv:2610.17643v1 Announce Type: new Abstract: An enterprise agent that answers under a written policy must choose an action before it says anything: answer, ask for a missing fact, ask for confirmat
arXiv:2610.15492v1 Announce Type: new Abstract: Skill internalization aims to convert externally specified procedural skills into persistent model capabilities, allowing language-model agents to execu
arXiv:2610.18786v1 Announce Type: cross Abstract: LLM ensemble gains are often measured against a single baseline, but the value attributed to additional candidates can change with the comparison used
arXiv:2610.16102v1 Announce Type: cross Abstract: We argue that tacit knowing is better modelled as an operating regime of one memory substrate than as a kind of content. The substrate is VaCoAl, an a
arXiv:2610.20397v1 Announce Type: new Abstract: Anatomical labels help 3D Gaussian splatting preserve vessels in cinematic renderings of CT, but the representation is still found by optimising each pa
arXiv:2610.19349v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) provides no reward-relative learning signal when all rollouts receive identical rewards. In long-horizon tas
arXiv:2610.20067v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently encounter conflicts between internal parametric knowledge and external contextual knowledge, yet the mechanisms
arXiv:2610.14334v1 Announce Type: new Abstract: In Model Context Protocol (MCP) systems, LLMs select tools from metadata rather than from their implementations. Names and descriptions summarize what a
arXiv:2610.17126v1 Announce Type: cross Abstract: The rapid proliferation of autonomous AI agents in decentralized ecosystems challenges existing identity paradigms. While human identity is traditiona
arXiv:2610.19035v1 Announce Type: cross Abstract: Pluralistic alignment needs to accommodate diverse preferences under limited human feedback. Using AI simulators to label preference comparisons reduc
arXiv:2610.19583v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly used to generate text, their misuse has become a growing societal problem, with implications for acad
arXiv:2610.19268v1 Announce Type: new Abstract: Benchmarks shape how model capabilities are measured and interpreted, yet their scores can obscure whose conventions, contexts, and judgments define suc
arXiv:2610.19993v1 Announce Type: new Abstract: Reconstruction of 3D structures using under-ice AUV video footage has been inaccurate, although it is not certain whether this is due to shortcomings in
arXiv:2610.17418v1 Announce Type: cross Abstract: Agentic workflows combine large language models with planning, memory, tools, execution environments, and iterative feedback. Their failures are diffi
arXiv:2610.19052v1 Announce Type: new Abstract: Video-based remote physiological measurement (RPM) has broad applications, while Vision-Language Models (VLMs) provide a promising opportunity to enable
arXiv:2610.19324v1 Announce Type: new Abstract: In large language models (LLMs), attention concentrates heavily on the first token. This 'attention sink' is believed to protect deep models against ove
arXiv:2610.20107v1 Announce Type: new Abstract: Web agents built on vision language models decide every action by generating text such as click(12), although most of that text encodes a choice among a
arXiv:2610.10226v2 Announce Type: replace-cross Abstract: Can AI make Software Engineering (SE) -- the discipline -- obsolete? And can it make software engineers -- the professionals -- redundant? Thi
arXiv:2610.19419v1 Announce Type: new Abstract: MLLM-based detectors formulate vision-language grounding as autoregressive coordinate generation, yet in dense scenes, they often collapse into a box re
arXiv:2610.18939v1 Announce Type: cross Abstract: This paper studies Wong--Zakai convergence and Fourier neural operator learning for stochastic Volterra integral equations (SVIEs) describing random s
arXiv:2610.15228v1 Announce Type: new Abstract: Words are increasingly becoming an interface for action: large language models (LLMs) can now invoke tools, operate devices, and make decisions that aff