Latest stories
Hugging Face Paper: OneSearch-VL Unifies Image and Video Deep Research
A new research paper introduces OneSearch-VL, a unified multimodal agent built around a Visually Grounded Evidence Graph, reportin...
SparseDecoding Targets the Real Bottleneck in LLM Inference: The Decode Stage
A new Hugging Face paper introduces SparseDecoding, a decoding-aware pruning framework that calibrates pruning on self-generated t...
Hugging Face Paper Combines Preference and Rubric Rewards to Post-Train Text-to-Image Models
A new post-training recipe composes human-preference rewards with rubric-based rewards to improve frontier text-to-image models, b...
Memento 3 Lets Frozen LLMs Self-Improve via Reflective Rulebooks
Hugging Face paper introduces Memento 3, a model-based approach to recursive self-improvement in which a frozen LLM agent builds a...
TestPrism Challenges Single-Reference Test Evaluation for LLM Coding Agents
A new benchmark, TestPrism, shows that judging AI-generated tests against a single reference solution inflates quality scores, wit...
MC-Sparse Closes the Dense-Sparse Attention Gap in Diffusion Transformers
A new training-free sparse-attention framework from Hugging Face researchers traces quality loss in diffusion transformers to thre...
VibeEdit Lets You Edit Images by Drawing on Them
Hugging Face researchers introduce VibeEdit, a canvas-instruction interface that lets users mark regions and add short notes direc...
Hugging Face Paper Introduces Pumpire, a Unified Benchmark for Metric Point-Pair Distance Estimation
Pumpire evaluates how well image- and video-level 3D foundation models estimate point-to-point distances directly from reconstruct...
Hugging Face Paper Proposes Code-Only Policies for Robot Self-Improvement
A new paper introduces Code-Only-as-Policy (COAP), which replaces vision-language-action models and agent harnesses with stateful...
Hugging Face Paper Unveils RISEBench++ and RISE-Agent for Reasoning-Informed Visual Editing
A new Hugging Face paper introduces RISEBench++, a 1000-case benchmark spanning six reasoning dimensions for visual editing, plus...
LEGO: Hugging Face Paper Ditches Depth Lifting for Exo-to-Ego Video
A new paper proposes a lifting-free method for generating egocentric video from a single exocentric recording, replacing explicit...
Hugging Face Highlights 'Foundations of Large Language Models' Book
A new book on Hugging Face's papers page offers an introductory look at the core concepts behind large language models, spanning p...