Knowledge catalogue
arXiv:2605.10019v1 Announce Type: cross Abstract: Generative models trained on finite data face a fundamental tension: their score-matching or next-token objective converges to the empirical training
Connie Loizos / TechCrunch: The US' Centers for Medicare & Medicaid Services is testing ACCESS, an outcome-based payment model for AI-driven medical care, with 150 tech companies — Neil Batlivala has
Reuters: The US DOD says it is deploying Mythos to find and patch software vulnerabilities across the US government, even as it works on a transition away from Anthropic — WASHINGTON, May 12 (Reuters)
Christian Martinez / Reuters: The US FCC approves EchoStar's sale of approximately 65MHz of spectrum to SpaceX and 50MHz to AT&T — The U.S. Federal Communications Commission's Wireless Telecommunicati
Wall Street Journal: The US House Oversight Committee launches a probe into potential conflicts in Sam Altman's personal investments; letter: several GOP AGs call for an SEC review — Republican-led Ho
arXiv:2605.10018v1 Announce Type: new Abstract: Hybrid mechanistic models, physical priors with learned residuals, promise to reduce the data required for good decisions, but have no computable criter
arXiv:2605.09352v1 Announce Type: new Abstract: Understanding why independently trained neural networks from different modalities converge toward shared representations, and where this convergence lea
arXiv:2601.02954v3 Announce Type: replace-cross Abstract: Large audio-language models have made rapid progress in recognizing what is present in an audio clip, but spatial audio-language understanding
arXiv:2605.08749v1 Announce Type: new Abstract: We present the Wristband Gaussian Loss, a deterministic batch loss for Gaussianizing point embeddings without sampling, KL terms, or iterative transport
There will be no AI jobpocalypse. The story that AI will lead to massive unemployment is stoking unnecessary fear. AI — like any other technology — does affect jobs, but telling overblown stories of l
arXiv:2605.10130v1 Announce Type: new Abstract: Existing open-vocabulary detectors focus on RGB images and fail to generalize to thermal imagery, where low texture and emissivity variations challenge
arXiv:2605.10117v1 Announce Type: cross Abstract: Autonomous driving scenes range from empty highways to dense intersections with dozens of interacting road users, yet current 3D detection models appl
Thinking Machines Lab Inc., the artificial intelligence research startup founded by former OpenAI Group PBC Chief Technology Officer Mira Murati, wants to move beyond the era of “turn-based” AI intera
arXiv:2605.10588v1 Announce Type: new Abstract: Current Large Multimodal Models (LMMs) struggle with spatial reasoning tasks requiring viewpoint-dependent understanding, largely because they are confi
This NVIDIA remains the strongest platform for large-model inference at scale. Prefill/decode disaggregation, Blackwell-native quantization, custom kernels, and rack-scale NVLink turn GB200 into faste
This was posted exactly 3 years ago. What 3 years of progress look like is wild. Can't wait for the next 3 years. guess who has access to runway #gen2 now? 👀 first quick trial for animated #aicinema,
Ethan Mollick discusses a tradeoff in OpenAI's newer realtime voice model, where improved capabilities require developers to revise prompts that were written for the previous version. The post highlig
thoughts after doing a bunch of synthetic data gen for eval + environment building - LLMs are incredible projections of the world bundled into a set of weights - but doing targeted extraction of certa
Aisha Malik / TechCrunch: Threads is testing a Meta AI integration similar to X's Grok, letting users mention Meta AI in a post or a reply to get more context, in five countries — Threads is testing a
arXiv:2605.10808v1 Announce Type: cross Abstract: Large Language Models(LLMs) are increasingly explored for cybersecurity applications such as vulnerability detection. In the domain of threat modellin
arXiv:2605.10563v1 Announce Type: cross Abstract: Threat detection in Natural Language Processing lacks consistent definitions and standardized benchmarks, and is often conflated with broader phenomen
arXiv:2605.09443v1 Announce Type: cross Abstract: The advancement of Multimodal Large Language Models (MLLMs) has expanded Role-Playing Agents (RPAs) into visually grounded environments. However, huma
arXiv:2605.09544v1 Announce Type: new Abstract: Tool-integrated reasoning has emerged as a promising paradigm for enhancing large language models with external computation, retrieval, and execution ca
arXiv:2605.09742v1 Announce Type: cross Abstract: Selective state space models (SSMs), such as Mamba, achieve strong per-token expressivity by making the time discretization step Tilde{Delta} a learne
arXiv:2605.10543v1 Announce Type: new Abstract: Director-style prompting, robotic action prediction, and interactive video agents demand temporal grounding over concurrent events -- a regime in which
arXiv:2605.08866v1 Announce Type: cross Abstract: Inverse optimization (IO) seeks to infer the parameters of a decision-maker's objective from observed context--action data. We study noiseless IO, whe
arXiv:2602.07999v3 Announce Type: replace-cross Abstract: Change of measure inequalities translate divergences between probability measures into explicit bounds on event probabilities, and play an imp
arXiv:2603.01960v2 Announce Type: replace-cross Abstract: TiledAttention is a scaled dot-product attention (SDPA) forward operator for SDPA research on NVIDIA GPUs. Implemented in cuTile Python (TileI
arXiv:2605.09281v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models achieve remarkable performance by sparsely activating specialized experts, yet their massive parameters in experts pose
arXiv:2604.02474v2 Announce Type: replace Abstract: Dynamical systems describe how a physical system evolves over time. Physical processes can evolve faster or slower in different environmental condit
arXiv:2605.10038v1 Announce Type: new Abstract: Time series analysis underpins forecasting, monitoring, and decision making in domains such as finance and weather, where solving a task often requires
arXiv:2605.10756v1 Announce Type: new Abstract: Vision-language models enable OOD detection by comparing image alignment with ID labels and negative semantics. Existing negative-label-based methods ma
arXiv:2605.08241v1 Announce Type: cross Abstract: Self-supervised learning (SSL) has transformed representation learning for large models, yet remains unexplored for microcontroller (MCU)-class models
arXiv:2507.09788v2 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLM) have led to a new class of autonomous agents, renewing and expanding interest in the area. LLM-
tl;dr - let's not just remove negative behavior from models, but also add positive ones 👍 If anyone builds it, everyone thrives. Over the past decade, a lot of important work on AI alignment has focus
arXiv:2605.10344v1 Announce Type: new Abstract: Test-time scaling has become an effective paradigm for improving the reasoning ability of large language models by allocating additional computation dur
Elon Musk advocated for open-sourcing X's recommendation algorithm to provide transparency and build public confidence that the platform is not secretly manipulating content recommendations. This stat
arXiv:2605.10211v1 Announce Type: cross Abstract: Government transparency laws, like the Freedom of Information (FOIA) acts in the United States and United Kingdom, and the Woo (Open Government Act) i
arXiv:2605.09904v1 Announce Type: new Abstract: Video large language models (Video-LLMs) have achieved remarkable progress in general video understanding, yet their ability to maintain temporal object
🚨 Today: OpenMed Agent ships in preview. Built on @huggingface: → HF endpoints power clinical extraction + terminology → MCP for your own services → Every tool call, every plan, fully visible 1,000+ O
Today's Hermes Agent Jam starts in 90 minutes! Join the Nous team in our Discord to share what you're working on @ http://discord.gg/nousresearch Join the Nous Research team for another Hermes Agent J
arXiv:2602.03688v2 Announce Type: replace Abstract: Multi-round LLM-based multi-agent systems rely on effective communication structures to support collaboration across rounds. However, most existing
arXiv:2508.20697v3 Announce Type: replace-cross Abstract: As large language models (LLMs) continue to grow in capability, so do the risks of harmful misuse through fine-tuning. While most prior studie
arXiv:2605.09104v1 Announce Type: new Abstract: As LLM agents evolve, tokens have emerged as the core economic primitives of Agentic AI. However, their exponential consumption introduces severe comput
arXiv:2605.08541v1 Announce Type: new Abstract: Neural scaling laws approximate a language model's loss as a power-law function of parameter count N and token count D. Following Chinchilla-style compu
Tomorrow @JulienAIArt and I are going to dive into Hermes Agent with the ComfyUI Skill and see what it can do! Bring your questions and tips! Join us for a live build session exploring Hermes Agent in
arXiv:2510.20036v2 Announce Type: replace Abstract: Large language model (LLM) agents rely on external tools to solve complex tasks, but real-world toolsets often contain redundant tools with overlapp
arXiv:2509.02510v2 Announce Type: replace-cross Abstract: Large language models (LLMs), despite their impressive performance across a wide range of tasks, often struggle to balance two competing objec
arXiv:2605.08870v1 Announce Type: new Abstract: Out-of-distribution (OOD) robustness is difficult to diagnose when target-domain labels are unavailable. We consider a more restrictive source-only vari
arXiv:2411.10298v5 Announce Type: replace Abstract: The surge of data available on the Internet has driven the adoption of a wide range of computational methods for analyzing and extracting insights f
arXiv:2605.10091v1 Announce Type: new Abstract: Many modern datasets mix points, edges, regions, groups, objects, events, hyperedges, and relations. Yet neural architectures often force such data into
arXiv:2605.09960v1 Announce Type: cross Abstract: Travel-time tomography forces a trade-off between mesh resolution and stability in which the regularizer choice dominates what can be recovered. We in
arXiv:2605.10425v1 Announce Type: cross Abstract: AI systems can now cheaply generate plausible scientific artifacts such as papers, reviews, and surveys. This creates a risk of epistemic pollution in
arXiv:2504.02343v2 Announce Type: replace Abstract: Recent advancements in Large Language Models (LLMs) and the proliferation of Text-Attributed Graphs (TAGs) across various domains have positioned LL
arXiv:2605.10373v1 Announce Type: cross Abstract: Large language models have significantly improved natural language interfaces to databases by translating user questions into executable queries. In p
arXiv:2605.08290v1 Announce Type: cross Abstract: We design the first regret guarantees for robust dynamic pricing that decouple the dependence on the corruption C and the time horizon T. In dynamic p
arXiv:2602.00678v4 Announce Type: replace Abstract: Reinforcement learning has shown strong promise for quadrupedal agile locomotion, even with proprioception-only sensing. In practice, however, sim-t
arXiv:2509.25080v3 Announce Type: replace Abstract: Data-driven models are increasingly adopted in critical scientific fields like weather forecasting and fluid dynamics. These methods can fail on out
arXiv:2605.10772v1 Announce Type: cross Abstract: Large language-vision models (LLVM), such as OpenAI's ChatGPT and GPT-4, have gained prominence as powerful tools for analyzing text and imagery. The
arXiv:2605.09366v1 Announce Type: new Abstract: Transforming neuroimaging data into clinically actionable biomarkers is a knowledge-intensive and labor-intensive process. Standardized workflows such a