Hugging Face
Hugging Face is the GitHub of machine learning — the platform hosting millions of open models, datasets and demos. Its Transformers library and open leaderboards made it the center of gravity for open-source AI. All our Hugging Face coverage lives on this page.
T2Quant Reallocates Precision Across Diffusion LLM Steps: Up to +6.7 pp
Researchers propose T2Quant, which quantizes diffusion language models by varying activation bit-width per denoising step, adding up to 6.7 pp accuracy at the same…
UserArena: A 64 729-Session Benchmark Tests Whether Shoppers Can Be Simulated
Researchers collected 64 729 real shopping sessions from 11 010 users and proposed OPTD, a method that reproduces the effect from a live A/B test more closely than…
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…
Nestor: nested sparsity in attention beats MoE at equal compute
A 17-million-parameter encoder picks the right tool in 14ms on CPU
RiseHarness Teaches Terminal Agents to Fix Their Own Harness Without Fine-Tuning
Survey: Robots Are Learning to Improve Their Own Learning, but Evidence Is Still Missing
Quant-Arena: None of 9 LLMs Beat the A-Share Market in 2024
A new benchmark tested nine frontier models on the full quant research cycle. GPT-6 Astra ranked first, but no strategy beat the equal-weighted market on the sealed…
Researchers Propose PAPAV Framework: Only 3 of 64 Benchmarks Test Verification
A new paper compares computer-use agents and robots through five PAPAV functions. Of 64 benchmarks, 5 assess outcome prediction and only 3 assess result…
WorldStream Builds an Endless 3D World and Remembers Every Player Edit
Agent4Sci: Claude Opus Beats Records on 20 Scientific Benchmarks by 10.4%
Stateful Harness Lifts World Model Accuracy on Hidden State from 32% to 92%
ActionRoPE Turns Player Actions into Coordinates and Cuts Scene Drift by 66%
Researchers Explain How JEPA Selects Features: Relationships Matter, Not Lone Features
Mosh Levy, Aly Lidayan and Yoav Goldberg introduce "predictive closure": JEPA retains not individually predictable features, but sets of features that predict each…
Fine-Tuning Gemma 4 with GPUs on Cloud Run: From 89% to 94% in Animal Classification
A complete breakdown of fine-tuning Gemma 4 on custom data in Google Cloud. An architecture with native support for video and audio, QLoRA quantization, and…