#LLM
Curated coverage on «LLM»: releases, research, benchmarks, open-source.
Cola2 beats Llama-3-8B on HellaSwag with 43 times fewer tokens
Hierarchical model Cola2 compresses text into continuous latents and scores 60.10 across eight tasks after training on 346B tokens, over 43x less than Llama-3's…
Verus-Insight Teaches an AI Video Detector to Find Artifacts and Prove Its Verdicts
Researchers split artifact hunting in generated video into three skills — planning, verification and aggregation — and released the Verus-Insight model and the…
AnyGameRenderer Dresses Gray AI Prototypes in Real Graphics and Keeps 62.9% of Units Intact
A generative renderer built on the 33B MiniMax-H3 model turns blockouts from AI-agent games into polished video; temporal entity match rose from 50.9% to 62.9%.
Cognition releases agent plugin to fix PHP and Node.js holes, including a CVSS 9.2 flaw
DirCast directs and commentates esports on its own, beating GPT-5
UserArena: A 64 729-Session Benchmark Tests Whether Shoppers Can Be Simulated
Echo Teaches VLA Robots to Recognize Success and Failure Inside Their Own Actions
HiSTEVE 1.0 Plays Minecraft With a Mouse and Keyboard: 85.0% on MineStudio Bench
VLA agent HiSTEVE 1.0 completes long Minecraft tasks with no API and no hidden game state: 85.0% on MineStudio Bench, 37.4% on OpenHA, and an iron pickaxe from…
Dual Exam: GPT 6 Astra Scores 31.3 Among Multimodal Agents
Over 80 authors built Dual Exam, which tests agents and world models separately. GPT 6 Astra leads with 31.3; a 150-case combined pilot had zero successes.
Survey by Shengqiong Wu and Hao Fei: 600+ Papers on Video Models as World Models
LeWorldModel Tested for Action Sensitivity: Axes Diverge by 36–42°
UCLA Team Pushes the Speed–Quality Frontier in Speculative Diffusion With Two Knobs
PaperFormalizer Turns LaTeX Papers into Verified Lean Code, with the Author in the Loop
Nestor: nested sparsity in attention beats MoE at equal compute
Tianzhe Chu, Druv Pai, and Yi Ma propose the Nestor transformer: attention sparsity nests inside MoE, delivering gains at equal compute and in continual pretraining.
A 17-million-parameter encoder picks the right tool in 14ms on CPU
Tardelli Stekel has released six open encoders ranging from 17M to 1B parameters for closed-set selection. The 68M and 150M models beat the 435M DeBERTa-v3 by 4.9…