Knowledge catalogue
A startup wants to pull magnesium from seawater without torching the environment. Another wants to take small language models to the podium for enterprise customers. Today @jason and @alex sat down wi
arXiv:2605.10365v1 Announce Type: new Abstract: Autonomous agents have rapidly matured as task executors and seen widespread deployment via harnesses such as OpenClaw. Safety concerns have rightly dra
arXiv:2605.10528v1 Announce Type: cross Abstract: We investigate the emergent collective dynamics of LLM-based multi-agent systems on a 2D square lattice and present a model-agnostic statistical-physi
arXiv:2604.01151v2 Announce Type: replace Abstract: As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human o
arXiv:2605.09159v1 Announce Type: new Abstract: Recent work shows that large language models (LLMs) encode behavioural traits ('personas') as linear directions in activation space, often called 'perso
arXiv:2605.08888v1 Announce Type: new Abstract: Evaluating whether Multimodal Large Language Models can produce trustworthy, verifiable reasoning over long, visually rich documents requires evaluation
arXiv:2605.08498v1 Announce Type: cross Abstract: We introduce MathConstraint, a hard, adaptive benchmark for evaluating the combinatorial reasoning capabilities of LLMs. We combine constraint satisfa
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:2604.01532v2 Announce Type: replace Abstract: LLM agents are beginning to invoke industrial asset-management tools through the Model Context Protocol (MCP), yet whether they can act reliably on
arXiv:2605.09228v1 Announce Type: cross Abstract: Most LLM benchmarks score how well a model responds to explicit requests. They leave unmeasured a different conversational ability: noticing and actin
arXiv:2605.08315v1 Announce Type: new Abstract: Existing LLM-based policy optimizers see only scalar rewards: that a policy scored 0.45, but not whether the agent got stuck in a loop, fell into a hole
arXiv:2605.09063v1 Announce Type: new Abstract: Following the recent achievement of gold-medal performance on the IMO by frontier LLMs, the community is searching for the next meaningful and challengi
arXiv:2605.08837v1 Announce Type: cross Abstract: Abstract concepts - justice, theory, availability - have no single perceivable referent; in the human brain, their meaning emerges from a web of exper
arXiv:2605.10843v1 Announce Type: cross Abstract: Large language models increasingly mediate decisions that turn on moral judgement, yet a growing body of evidence shows that their implicit preference
arXiv:2605.09692v1 Announce Type: new Abstract: Unpredictable behavior is often taken as evidence of control, yet stochastic dispersion and structured action control need not coincide. This paper test
arXiv:2605.10850v1 Announce Type: new Abstract: Self-verification, re-invoking the same vision language model (VLM) in a fresh context to check its own generated answer, is increasingly used as a defa
arXiv:2605.09860v1 Announce Type: new Abstract: Long-horizon reasoning requires deciding not only what actions to take, but how deeply to commit before the next observation. We formalize this as commi
arXiv:2605.08200v1 Announce Type: new Abstract: A pervasive intuition holds that vision-language models (VLMs) are most trustworthy when their attention maps look sharp: concentrated attention on the
arXiv:2512.05439v2 Announce Type: replace Abstract: As large language models (LLMs) transition from research prototypes to production systems, practitioners often need reliable methods to verify model
arXiv:2605.07251v1 Announce Type: new Abstract: Large Language Models (LLMs) have become increasingly capable as tool-using agents, with benchmarks spanning diverse general agentic tasks. Yet rigorous
arXiv:2510.07926v2 Announce Type: replace Abstract: Despite demonstrating remarkable performance across a wide range of tasks, large language models (LLMs) have also been found to frequently produce o
arXiv:2605.07024v1 Announce Type: new Abstract: Large Language Models for code generation frequently produce hallucinations in Fill-in-the-Middle (FIM) tasks -- plausible but incorrect completions suc
arXiv:2602.20338v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting significantly improves reasoning in Large Language Models, yet the temporal dynamics of the underlying representati
HiDream-Studio v.01 was open-sourced on May 8, 2026, releasing the HiDream-O1-Image model (8B parameters) with both undistilled and distilled variants. HiDream-O1-Image is a unified image generative f
arXiv:2605.07342v1 Announce Type: cross Abstract: Compile-pass rate is the dominant evaluation signal for LLM code generation, yet for multi-component domain-specific artifacts it can be actively misl
arXiv:2605.06672v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning and reasoning-tuned models such as DeepSeek-R1 are commonly assumed to reduce shallow heuristic biases by thinking care
arXiv:2605.07447v1 Announce Type: cross Abstract: Vision-language models (VLMs) have advanced rapidly and are increasingly deployed in real-world applications, especially with the rise of agent-based
arXiv:2605.06761v1 Announce Type: new Abstract: The web is complex, open-ended, and constantly changing, making it challenging to scale training data for visual web agents. Existing data collection at
Local AI is having its moment! Below is the number of new GGUF models created each month over the past 8 months & insights from our HF internal agent (May is partial): - 176,000 total public GGUF mode
arXiv:2605.03952v1 Announce Type: cross Abstract: Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The chal
arXiv:2605.04221v1 Announce Type: new Abstract: Clinical named entity recognition from dental progress notes is challenging because documentation is highly unstructured, domain-specific, and often pri
arXiv:2605.01986v1 Announce Type: new Abstract: What if the twelve jurors of Sidney Lumet's 12 Angry Men (1957) were not men, but large language models? Would the one juror who disagrees still be able
arXiv:2605.00932v1 Announce Type: cross Abstract: This report documents the preparedness assessment of Code World Model (CWM), a model for code generation and reasoning about code from Meta. We conduc
arXiv:2603.26845v2 Announce Type: replace-cross Abstract: Most LLM-driven GIS assistants solve narrow single-step tasks tightly coupled to proprietary platforms such as ArcGIS or QGIS, limiting their
arXiv:2605.03799v1 Announce Type: new Abstract: This preprint presents a systematic, research-oriented practicum that guides the reader through the entire modern NLP pipeline: from tokenisation and ve
arXiv:2605.03450v1 Announce Type: new Abstract: In studies of media coverage of extreme climate events, NLP methods have become indispensable for identifying relevant texts in large news databases. St
arXiv:2605.03301v1 Announce Type: new Abstract: De-identification of clinical text remains essential for secondary use of electronic health records (EHRs), yet public benchmarks such as i2b2 2006/2014
arXiv:2605.02170v1 Announce Type: new Abstract: In this paper, we present our system for SemEval-2026 Task 6 (CLARITY) on response clarity and evasion detection in question-answer pairs from U.S. pres
arXiv:2605.02348v1 Announce Type: new Abstract: Large language models pick up social biases from the data they are trained on and carry those biases into downstream applications, often reinforcing ste
arXiv:2605.02443v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, yet they remain susceptible to
arXiv:2605.01870v1 Announce Type: new Abstract: Large Language Models (LLMs) have substantially advanced the field of Natural Language Processing (NLP), achieving state-of-the-art performance across a
arXiv:2605.01417v1 Announce Type: new Abstract: Evaluating large language models (LLMs) for medical applications remains challenging due to benchmark saturation, limited data accessibility, and insuff
arXiv:2605.02834v1 Announce Type: new Abstract: Videos are unique in their ability to capture actions which transcend multiple frames. Accordingly, for many years action recognition was the quintessen
arXiv:2605.02038v1 Announce Type: new Abstract: Single-prompt accuracy is the dominant way to benchmark language models, but it can miss reliability failures that matter. We evaluate a 15-model open-w
arXiv:2605.00238v1 Announce Type: new Abstract: Automated short answer grading (ASAG) with large language models (LLMs) is commonly evaluated with aggregate metrics such as macro-F1 and Cohen's kappa.
arXiv:2605.00226v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly tasked with strategic decision-making under incomplete information, such as in negotiation and policymakin
NIST: An evaluation by NIST's CAISI says DeepSeek V4 Pro lags behind leading US AI models by about eight months and is the most capable Chinese AI model to date — In April 2026, the Center for AI Stan
arXiv:2604.28031v1 Announce Type: new Abstract: When researchers iteratively refine ideas with large language models, do the models preserve fidelity to the original objective? We introduce DriftBench
arXiv:2506.08332v3 Announce Type: replace Abstract: Machine learning has been widely used to optimize complex engineering workflows across numerous domains. In integrated circuit design, modern flows
You don't have to choose between either. It's best to use a combination of them. My advice is to learn how to use a few of these models in different harnesses. Learn to combine their strengths. Open-w
arXiv:2604.26607v1 Announce Type: new Abstract: As Competency-Based Education (CBE) is gaining traction around the world, the shift from marks-based assessment to qualitative competency mapping is a m
arXiv:2603.06198v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) is a framework in which a Generator, such as a Large Language Model (LLM), produces answers by retrieving docum
arXiv:2510.20956v2 Announce Type: replace-cross Abstract: We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaki
arXiv:2604.25359v1 Announce Type: new Abstract: Large Language Models are increasingly being deployed to extract structured data from unstructured and semi-structured sources: parsing invoices, medica
arXiv:2604.23072v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly tasked with complex real-world analysis (e.g., in financial forecasting, scientific discovery), yet t
arXiv:2604.23135v1 Announce Type: new Abstract: Natural-language variation poses a key challenge in Lean autoformalization: semantically equivalent paraphrases of the same theorem statements can induc
This post likely discusses how to prompt or configure an AI coding agent to incorporate unexpected or whimsical elements like goblins into its outputs, possibly as part of a broader discussion about A
New work with @AlecRad and @DavidDuvenaud: Have you ever dreamed of talking to someone from the past? Introducing talkie, a 13B model trained only on pre-1931 text. Vintage models should help us to un
arXiv:2510.11586v2 Announce Type: replace Abstract: Many in-silico simulations of human survey responses with large language models (LLMs) focus on generating closed-ended survey responses, whereas LL
This post discusses the need for built-in speech-to-text (STT) and text-to-speech (TTS) capabilities in a product or platform (likely referring to Hugging Face's platform based on the mention of Clem