Knowledge catalogue
arXiv:2610.12361v1 Announce Type: new Abstract: Large language models increasingly justify legal decisions by naming the statute or precedent behind a verdict, treated as evidence that the decision fo
We are expanding the Clef decision model family with Clef-omni, natively processing audio, video, images, and text in a single pipeline. We’ve also lowered Clef-flash pricing and boosted Clef inferenc
arXiv:2610.12085v1 Announce Type: new Abstract: Large language models (LLMs) can expose memorized training sequences under prefix-based extraction: given a prefix from a training example, the model ma
arXiv:2610.11328v1 Announce Type: new Abstract: Advances in foundation models are driving efforts to introduce agents to assist people in the physical world. Such agents require agentic spatial intell
arXiv:2610.11233v1 Announce Type: cross Abstract: A core challenge in short-video fact-checking is identifying which evidence is sufficient to support a verification conclusion. Existing approaches ei
arXiv:2610.11605v1 Announce Type: cross Abstract: We introduce NanoProof, to our knowledge the first factorized execution-guided theorem prover in Lean 4 whose training data, extraction tooling, train
arXiv:2610.11768v1 Announce Type: cross Abstract: Large language model (LLM) agents are beginning to operate industrial energy equipment, and what they get right depends on what they are told about th
arXiv:2610.11030v1 Announce Type: cross Abstract: Tool-using LLM agents violate the policies they are deployed to enforce, often silently. Prior defenses hand-write rules, query an LLM verifier per ac
arXiv:2601.14994v2 Announce Type: replace-cross Abstract: Data contamination can invalidate benchmark evaluation when a model benefits from memorized evaluation content rather than genuine generalizat
arXiv:2610.12292v1 Announce Type: new Abstract: A typed decision model reads a piece of text and returns a probability over caller-defined options, each with a short written definition, generating no
arXiv:2610.11922v1 Announce Type: cross Abstract: Project Greenhouse represents our exploration of a simple thesis: We believe that it is possible to build fully open and sovereign models for agentic
(Don't judge by the screenshot, the cache is cold. It hits 24+ tok/s with a warm cache!) About two months ago, I made a post here asking whether predicting which MoE experts would be used on the next
arXiv:2610.11451v1 Announce Type: new Abstract: We introduce SAIL, an open model with 35B total and 3B active parameters for literature research, scientific coding, and multi-step research workflows.
Youtu-Parsing-Omni is a compact (5B) omni-modal parsing model. Given a single input — a document page, a natural image, a chart / flowchart, a geometry figure, an audio clip or an audio-visual video —
arXiv:2602.02639v2 Announce Type: replace-cross Abstract: LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process i
arXiv:2610.10145v1 Announce Type: new Abstract: We present InterView-C, a German multimodal corpus of 27 survey interviews conducted entirely in virtual reality, with both interlocutors represented by
The other week I posted about Jev vs. Kev compared and since then, OpenAI released the decisions endpoint, Cloudflare released Clef and many here asked about Laya as well. This time we compared six po
LightOn OCR-3 is now available on OpenDocRouter, priced at 0.28 / 1m input and 1.40 / 1m output (it is ~$3.19 / 1k pages on ParseBench). We benchmarked it on ParseBench. It is on the pareto frontier f
OpenDocRouter is basically OpenRouter for document OCR You can compare and use all your favorite OCR models under a single API / billing interface. They range from some of the lightweight/OSS models (
recently saw a bunch of open decision models pop out of nowhere in the last two weeks (laya, liquid's d1, cloudflare's clef-flash, interfaze's lev), so I wanted to see how far apart they actually are
Editor’s note: This article is adapted from Thomas Kurian’s keynote address at Gemini at Work 2026. It includes a number of announcements: Gemini, a single, universal agent for work that answers your
arXiv:2610.07904v1 Announce Type: new Abstract: We introduce ApexQuant, a calibration-free quantization method that recursively re-quantizes the residual error, serving as a refinement layer on top of
Claude Haiku 5.5 is now available on OpenDocRouter as one of the cheapest models for document parsing. It is roughly $1.2 / 1k pages and does quite well on tables and text reading order compared to ot
arXiv:2610.06903v1 Announce Type: cross Abstract: Activation steering manipulates large language model behavior by intervening on internal activations, but the mechanistic basis of these interventions
arXiv:2610.07132v1 Announce Type: cross Abstract: Croissant has emerged as a standard for machine-readable dataset metadata, yet populating its fields remains labor-intensive and requires careful read
arXiv:2610.07403v1 Announce Type: new Abstract: Long-term memory allows Large Language Models (LLMs) to maintain personalized context across interactions, but retrieved user history can induce memory-
arXiv:2610.08102v1 Announce Type: new Abstract: Conversational MLLM agents are increasingly expected to assist in professional workflows, from AI research and engineering design to product management
arXiv:2607.10162v2 Announce Type: replace-cross Abstract: Sound symbolism, the human tendency to map speech sounds to perceptual qualities such as roundness or sharpness, arises primarily from the aco
arXiv:2610.08585v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly relied upon to support ambient documentation and clinical reasoning. Here we examine the impact of a failu
arXiv:2610.07506v1 Announce Type: cross Abstract: Speech agents are reactive and dyadic: they speak when spoken to, and to one person at a time. We ask what it takes for a speech agent to instead take
arXiv:2610.06625v2 Announce Type: replace Abstract: Large language models (LLMs) annotate and scale political text or constructs by generating text tokens. A new class of models, which TypeSafe market
arXiv:2610.08413v1 Announce Type: cross Abstract: Large language models routinely answer questions that cannot be answered from the information given, and in dialogue they answer before enough has bee
arXiv:2610.08055v1 Announce Type: new Abstract: Automatic assessment of communication quality in dyadic counseling conversations is bottlenecked by data: expert-rated corpora are small and expensive t
Looks like you copied Chandra OCR 2 into your repo, renamed it, changed the license, and made the output worse (your olmocr score is 83.8 vs our 85.8). Introducing interfaze-1-lite, the first general
arXiv:2610.08095v1 Announce Type: new Abstract: Natural-language access to RDF knowledge graphs is a core Semantic Web ambition. Large language models (LLMs) have advanced Text-to-SPARQL, yet on unfam
arXiv:2610.07817v1 Announce Type: cross Abstract: Organizations automating operational processes need more than a correct outcome: they need to predict how a process will run, know which one actually
arXiv:2610.07766v1 Announce Type: new Abstract: We present Open Telco (OTel), an open telecom AI resource that releases derived telecom datasets for retrieval, reranking, instruction tuning, and safet
arXiv:2610.08018v1 Announce Type: new Abstract: Reliable tool use requires more than triggering a mechanism or matching a query to an API description. Before selecting a specific tool, an agent must f
MistralAI announced that its model **Mistral Large 4** ranked as the #1 open‑source (OSS) model on **Harvey’s Legal Agent Benchmark (LAB)**, an evaluation benchmark for legal AI agents. The tweet post
arXiv:2610.08162v1 Announce Type: cross Abstract: Fine-grained emotion recognition supports therapy tools and social robots, but it needs facial data, which raises privacy and data-protection concerns
Today we're announcing OpenDocRouter: every model for document parsing under one API. There are ~4,000 OCR models on Hugging Face, and the frontier labs ship a new one nearly every month. Whatever's b
arXiv:2610.06902v1 Announce Type: new Abstract: Retrieval-augmented generation grounds language models in external context, but for long documents flat top-k retrieval can cluster on a single region a
arXiv:2610.07334v1 Announce Type: new Abstract: Interpretability methods for neural networks are predominantly reactive: they analyse activations produced during specific forward passes, requiring kno
Artificial Analysis: Artificial Analysis says Mistral Large 4 is the most intelligent model from outside the US and China, achieving results comparable to DeepSeek V4.1 Flash (max) — Mistral has relea
arXiv:2610.05590v1 Announce Type: new Abstract: Cold-start drug-drug interaction (DDI) prediction tests whether models can identify clinically significant interactions for drugs without training-time
Nathan Lambert / Interconnects AI: GLM-5.3's open release has yet to produce major attacks despite Anthropic's warnings about its Mythos-level cyber risk, undercutting calls to ban open models — Open-
arXiv:2610.05139v1 Announce Type: new Abstract: Code large language model (Code LLM) assistants generate code from heterogeneous development contexts, including open files, imported modules, pasted sn
arXiv:2610.05135v1 Announce Type: new Abstract: Under a fixed physical law, the visible geometry of a scene determines how motion must change. We ask how video generators realize this relationship. We
arXiv:2610.05775v1 Announce Type: new Abstract: A video assistant must speak when its instruction warrants a response and stay silent otherwise. We introduce a benchmark that evaluates this decision f
Introducing Mistral Large 4: Le chonk Mistral are back in the game. Today they're releasing a preview of Mistral Large 4, a 1 trillion parameter, 49 billion active parameter model trained on their own
Carl Franzen / VentureBeat: Mistral launches a preview of Mistral Large 4, or Le Chonk, a 1T model it claims tops any open model developed in the US or Europe; weights are due October 27 — Mistral is
Mistral Blog: Mistral says it trained ML4 “from scratch” using 3,800 Nvidia Grace Blackwell GPUs in its data centers in Europe and much of its training data was multilingual — Le Chonk — Today, we're
pplx-decider-v1.1-27b, our updated open weights multimodal decision model, is now available. It scores the highest on the new @huggingface Decision Index 0.3 benchmark. pplx-decider-v1.1-27b costs hal
arXiv:2610.03894v1 Announce Type: cross Abstract: A deployed LLM agent emits tool calls, queries, and code that can be silently wrong -- by the time the error surfaces, the action has run. Frontier ch
arXiv:2610.04125v1 Announce Type: cross Abstract: Self-report is an appealing low-cost probe of an LLM's dispositions, but recent work finds only selective agreement between what models report and how
arXiv:2603.02348v2 Announce Type: replace Abstract: An agent meets a model as served: through an endpoint with a price card, a shared cache and other tenants, or on whatever hardware a self-hosted mod
That one took some groundwork. Trained and served on our own compute, and RL shows no sign of saturation Meet Mistral Large 4, aka Le Chonk. • 1T parameters, natively multimodal. 49B active. It is the
We’re so back. Meet Mistral Large 4, aka Le Chonk. • 1T parameters, natively multimodal. 49B active. It is the best open weights model from US or Europe on aggregated benchmarks. • State-of-the-art on
A while ago, I posted here getting OSS-120B and GLM-4.6 playing full games of Civilization V. Since then, models have moved pretty far, and we wanted a better understanding about models' capabilities
Hi r/LocalLLaMA. I'm on the team at Blockway, a small team in Hong Kong (disclosure: this is our model). Today we released Agens Volundr 32B Preview, the first model built on our own hybrid architectu