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.
LEGO-SCD learns to detect changes in 3D scenes at 17.2 FPS without manual labeling
LEGO-SCD trains on automatic edits to 3D Gaussian Splatting scenes and posts top results: 67.64% mIoU on PASLCD, 75.82% on CCS3D, and 17.2 FPS.
WorldStream Builds an Endless 3D World and Remembers Every Player Edit
WorldStream extends a playable 3D world beyond the map, executes language commands, and restores visited places with their edits. It plans on two levels…
Agent4Sci: Claude Opus Beats Records on 20 Scientific Benchmarks by 10.4%
The Agent4Sci testbed shows frontier agents beat published records on all 20 scientific ML benchmarks, but they win through engineering tricks, not scientific ideas.
Researchers Explain How JEPA Selects Features: Relationships Matter, Not Lone Features
Fine-Tuning Gemma 4 with GPUs on Cloud Run: From 89% to 94% in Animal Classification
LLM as Decoder in ASR: Adapting Nvidia's SALM Architecture for Russian-Language Telephony
Moonshot releases open Kimi K2 Thinking: 300 tool calls in a row
MTEdit: 500 thousand editing trajectories teach models not to lose quality over 8 steps
Researchers built MTEdit, a dataset of 500 thousand multi-step image edits, and fine-tuned Qwen-Image-Edit to the best result among open models.
Conditional Program shrinks DeepSeek's n-gram memory from 203 to 51 GB at 2 bits
Researchers propose Conditional Program: 2-bit compression of n-gram memory tables cuts KL error by 41–63% versus round-to-nearest and shrinks DeepSeek's table…
New Survey Maps AI in Humanitarian Work: Six Tasks, From Weather to Refugees
A Frozen 16 MB Vocabulary Matches a Trained One in Small LLMs
Cohere pitches utilities on running North AI agents inside their own perimeter
Data Rewriting Beats DP-SGD on the Privacy-Quality Trade-Off
Researchers Find a 0.4–1.1% Window in Pythia Pretraining Where the Readout Reorganizes
A model's hidden states encode a task before its output shows it. The gap traces back to the unembedding matrix, which reorganizes during 0.4–1.1% of Pythia's…
SAE on Gemma-2-2B: Share of Matched Features Rises from 2% to 29% With 50M Tokens
Experiments on four SAE architectures and three models: reconstruction plateaus at small budgets, while feature reproducibility keeps growing with data, from 2% at…