Knowledge catalogue
arXiv:2510.22170v2 Announce Type: replace Abstract: Persona conditioning is widely used to steer large language model (LLM) behavior, but it is unclear whether it induces stable behavioral structure o
arXiv:2605.08445v1 Announce Type: new Abstract: AI models are increasingly deployed in live clinical environments where they must perform reliably across complex, high-stakes workflows that standard t
arXiv:2507.23511v3 Announce Type: replace-cross Abstract: While large audio-language models have advanced open-ended audio understanding, they still fall short of nuanced human-level comprehension. Th
arXiv:2605.10002v1 Announce Type: new Abstract: Large vision-language models (VLMs) demonstrate strong performance in medical image understanding, but frequently generate clinically plausible yet inco
arXiv:2605.10025v1 Announce Type: cross Abstract: In high-stakes domains such as healthcare, the reliability of Large Language Models (LLMs) is critical, particularly when generating clinical insights
arXiv:2605.09661v1 Announce Type: cross Abstract: Large language models (LLMs) have saturated standard medical benchmarks that test factual recall, yet their ability to perform higher-order reasoning,
Meet physics-intern🧑🎓, our agentic framework for theoretical physics. It takes Gemini 3.1 Pro from 17.7% to 31.4% on CritPt, a new SOTA on one of the hardest benchmarks for LLMs. Theoretical physics
arXiv:2605.09530v1 Announce Type: cross Abstract: As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and u
arXiv:2605.08374v1 Announce Type: new Abstract: Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval
arXiv:2605.09152v1 Announce Type: new Abstract: Deciphering animal intent is a fundamental challenge in computational ethology, largely because of semantic aliasing, the phenomenon where identical ext
arXiv:2603.13452v2 Announce Type: replace Abstract: Fairness in machine learning is predominantly evaluated through outcome-oriented metrics, such as Demographic parity, which measure whether predicti
arXiv:2605.09708v1 Announce Type: cross Abstract: We present Metal-Sci, a 10-task benchmark of scientific Apple Silicon Metal compute kernels spanning six optimization regimes (stencils, all-pairs in
arXiv:2605.10067v1 Announce Type: cross Abstract: Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). While automated methods have improved scalability, existing ap
arXiv:2605.08815v1 Announce Type: new Abstract: Predicting microbial operon co-membership requires integrating two complementary biological signals: protein-scale molecular identity and genome-context
arXiv:2605.10120v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) show remarkable potential for scientific reasoning, yet their performance in specialized domains such as micr
arXiv:2512.13751v2 Announce Type: replace-cross Abstract: Expanding pre-trained language models offers a practical way to increase capacity without training larger models from scratch. Depth Up-Scalin
arXiv:2510.09592v2 Announce Type: replace Abstract: Real-time Spoken Language Models (SLMs) struggle to leverage Chain-of-Thought (CoT) reasoning due to the prohibitive latency of generating the entir
arXiv:2605.09633v1 Announce Type: new Abstract: We study multi-robot persistent monitoring on weighted graphs, where node weights encode monitoring priorities and edge weights encode travel distances.
arXiv:2605.08816v1 Announce Type: new Abstract: In the animal kingdom, mirror self-recognition is a canonical probe of higher-order cognition, emerging only in some species. We ask whether an analogou
arXiv:2605.08678v1 Announce Type: new Abstract: Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonst
arXiv:2605.10833v1 Announce Type: cross Abstract: Industrial anomaly detection is critical for manufacturing quality control, yet existing datasets mainly focus on static images or sparse views, which
arXiv:2605.09724v1 Announce Type: new Abstract: Existing accounts of grokking explain the phenomena in terms of mechanistic frameworks such as circuit efficiency or lazy-to-rich transitions. However,
arXiv:2601.21266v3 Announce Type: replace Abstract: Neural network models are increasingly used for state estimation in control and decision-making, yet it remains unclear to what extent they behave a
A year ago, frontier models started losing track of instructions somewhere around 200–300 simultaneous constraints. With 2026 models, that ceiling is closer to 2,000 — an order-of-magnitude jump. We r
arXiv:2603.18256v2 Announce Type: replace-cross Abstract: Recent reasoning-based large language models have shown strong performance on tasks with verifiable outcomes, but their use in de novo molecul
arXiv:2605.10157v1 Announce Type: cross Abstract: Every molecule ever synthesised can be drawn as a 2D skeletal diagram, yet in modern property prediction this universally available representation has
arXiv:2605.09684v1 Announce Type: cross Abstract: We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-eli
Boris Cherny announced upcoming releases of code related to 'cardputer,' likely a computing or card-based project, and expressed gratitude to Claude (presumably the AI assistant). The post suggests ne
arXiv:2605.09703v1 Announce Type: new Abstract: Understanding human mental states from natural behavior is crucial for intelligent systems in the real world. However, most current research focuses on
arXiv:2605.10769v1 Announce Type: cross Abstract: The multimodal fusion of images and scene captions has been extensively explored and applied in various fields. However, when dealing with complex rem
arXiv:2605.10616v1 Announce Type: cross Abstract: Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generaliza
arXiv:2605.10550v1 Announce Type: new Abstract: Document classification forms the backbone of modern enterprise content management, yet existing benchmarks remain trapped in oversimplified paradigms -
arXiv:2605.09790v1 Announce Type: cross Abstract: Detecting orbital anomalies, such as maneuvers, atmospheric decay, and attitude upsets, across the rapidly growing population of low-Earth-orbit (LEO)
arXiv:2605.08163v1 Announce Type: cross Abstract: Text-in-image editing has become a key capability for visual content creation, yet existing benchmarks remain overwhelmingly English-centric and often
arXiv:2605.08949v1 Announce Type: new Abstract: A central challenge in continual learning for large language models (LLMs) is catastrophic forgetting, where adapting to new tasks can substantially deg
arXiv:2605.10813v1 Announce Type: new Abstract: LLM-powered multi-agent systems can now automate the full research pipeline from ideation to paper writing, but a fundamental question remains: automati
arXiv:2605.08503v1 Announce Type: new Abstract: Interactive narrative tasks require LLMs to sustain a coherent, evolving story while adapting to a user over multiple turns. However, suitable benchmark
arXiv:2605.09863v1 Announce Type: cross Abstract: Production LLM coding agents drift over long sessions: they forget user-specified constraints, slip into mistakes the user already flagged, and confab
arXiv:2605.10639v1 Announce Type: new Abstract: The rapid adoption of LLMs in both research and industry highlights the challenges of deploying them safely and reveals a gap in the systematic evaluati
$NBIS announced a partnership with LangChain to integrate Nebius Token Factory with LangChain’s Deep Agents. The goal is to make it easier for teams building AI agents on LangChain to run those worklo
Need document parsing that stays fully local and private? 👀 Meet liteparse-server, a self-hostable, open-source HTTP server for parsing documents and generating screenshots from PDFs, Office files, an
arXiv:2601.23252v2 Announce Type: replace-cross Abstract: Model comparison and calibrated uncertainty quantification often require integrating over parameters, but scalable inference can be challengin
arXiv:2605.09301v1 Announce Type: cross Abstract: The Capacitated Vehicle Routing Problem (CVRP) underpins modern last-mile logistics. Current Neural Combinatorial Optimization (NCO) methods construct
arXiv:2605.09316v1 Announce Type: cross Abstract: Query-separated computation forces a representation to play an operational role: data are encoded before a query is known, and a later decoder can ans
arXiv:2605.08179v1 Announce Type: cross Abstract: Radar sounders are electromagnetic instruments that can probe deep into the subsurface of Earth and other planetary bodies by processing the echo of t
arXiv:2605.10878v1 Announce Type: new Abstract: Why does weight decay work? We prove that, in any fixed-precision regime, the smallest weight norm of a looped neural network outputting a binary string
arXiv:2605.08495v1 Announce Type: new Abstract: Deep learning and large public datasets have recently catalyzed the proliferation of AI models for processing brain recordings. However, systematically
arXiv:2605.08192v1 Announce Type: cross Abstract: Frontier AI safety claims - published assertions that a highly capable general-purpose model is below a threshold of concern, adequately mitigated, or
Microservices testing company Signadot Inc. today launched /signadot-validate, a new skill that lets coding agents such as Anthropic PBC’s Claude Code, OpenAI Group PBC’s Codex and Cursor validate the
arXiv:2605.08193v1 Announce Type: cross Abstract: Normalization Equivariance (NE), equivariance to global contrast and brightness transforms, improves robustness to distribution shift in image-to-imag
arXiv:2605.10379v1 Announce Type: new Abstract: Large language models (LLMs) have become capable mathematical problem-solvers, often producing correct proofs for challenging problems. However, correct
arXiv:2605.08762v1 Announce Type: cross Abstract: Current omni-modal benchmarks mainly evaluate models under settings where multiple modalities are provided simultaneously, while the ability to start
arXiv:2605.09996v1 Announce Type: new Abstract: While multimodal large language models have advanced across text, image, and audio, personalization research has remained primarily vision-language, wit
arXiv:2605.09727v1 Announce Type: cross Abstract: A central challenge in reinforcement learning (RL) is to learn models that generalize beyond the tasks on which they are trained, a goal traditionally
OpenAI contacted me to say “Study Mode is still live and accessible via /study and /learn shortcuts” so that’s good, although the official study mode page doesn’t mention that. (I don’t think slash co
arXiv:2605.10484v1 Announce Type: new Abstract: Scene graph alignment establishes object correspondences between two 3D scene graphs constructed from partially overlapping observations. This enables e
arXiv:2605.08904v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and tool use. However, the fundamental cognitive faculties essential
arXiv:2605.08332v1 Announce Type: cross Abstract: Feedback-based adaptive quantum optimization (FALQON) is a promising approach for solving combinatorial problems on noisy intermediate-scale quantum (
arXiv:2605.09075v1 Announce Type: cross Abstract: Although the Laplace approximation offers a simple route to uncertainty quantification in deep neural networks, its reliance on inverting large Hessia
arXiv:2605.08660v1 Announce Type: new Abstract: In the recent literature, Support Vector Regression (SVR) has been cited as one of the weakest performers on the California Housing benchmark dataset, w