Latest stories
Motion-Omni: End-to-End Framework Unifies Speech and Full-Body Motion for Spoken Dialogue
Hugging Face researchers introduce Motion-Omni, an end-to-end framework that jointly generates spoken dialogue and full-body co-sp...
WorldSculpt: Turning Cluttered Videos into Compositional 3D Worlds
Hugging Face researchers introduce WorldSculpt, a method that adapts a single-object 3D generative prior to multi-view video obser...
Hugging Face Unveils Iris: Open-Source Search Agents Climb to Frontier Performance
Hugging Face presents Iris-mini and Iris-pro, two open-source search agents trained via a novel SFT-RL climbing pipeline, achievin...
OpenAI's Chief Scientist Calls for Stronger AI Safeguards and Global Coordination
In a personal reflection, OpenAI's Chief Scientist Jakub Pachocki warns of the challenges posed by increasingly capable AI and urg...
OpenAI Reveals How Coding Agents Accelerate Its AI Research
OpenAI shares early data on how coding agents are transforming its internal research, boosting experiment velocity and tackling mo...
RLVR Narrows Reasoning Diversity at the First Step, Not During Execution
A new study shows that reinforcement learning with verifiable rewards (RLVR) reduces reasoning diversity primarily at the initial...
New Metric OVMI Offers Common Scale for Comparing Speech Brain-Computer Interfaces
Researchers introduce open-vocabulary mutual information (OVMI), an information-theoretic metric that enables fair comparison of s...
VeriPhy: Auditable Physical Reasoning System for World Model Evaluation
Hugging Face researchers introduce VeriPhy, an auditable physical-verification system that compiles prompts into typed physical ob...
QCell: New Query-Based Model Tackles Overlapping Cell Segmentation
Researchers introduce QCell, a query-based model that improves instance segmentation of overlapping microscopy cells via latent-sp...
AI Training as Percolation: New Theory Links SGD Collapse to Phase Transitions
Researchers model stochastic gradient descent as a percolation process, showing that neural networks collapse into simpler subnetw...
New CORD Adapter Preserves Top-1 Predictions in Post-Hoc Calibration
Researchers introduce CORD, a post-fit adapter that repairs calibrated probability vectors to exactly preserve original top-1 pred...
Frame Selection Beats Compression in Long-Video AI Models, Study Finds
A new controlled study from Hugging Face shows that which frames a long-video model selects matters far more than how much it comp...