Latest stories
ActionSplice Lets Interactive World Models Swap Actions Mid-Generation
A new inference framework, ActionSplice, splices revised actions into chunk-autoregressive video world models without replaying co...
Hugging Face Paper: Agents Can Study New Environments Without a Syllabus
A new Hugging Face paper formalizes task-agnostic environment preprocessing, showing that a meta-agent can explore an unfamiliar e...
New Framework Routes Prompts to LLM Experts as a Bandit Problem
A Hugging Face paper formulates adaptive prompt routing to LLM experts as a contextual bandit problem with limited feedback, propo...
Pelican-Sim 1.0: A General World Model Simulator for Embodied Intelligence
Hugging Face paper introduces Pelican-Sim 1.0, a world model simulator that predicts future observations from visual context and r...
Hugging Face Paper Proposes Diversity-Aware Skill Routing for LLM Agents
A new paper introduces Diverse Skill Routing (DSR), a reranking framework that uses a Determinantal Point Process to balance relev...
Hugging Face Releases Occamy-1.0, a 35B Co-work Agent Model Built for Cost Efficiency
Occamy-1.0 is a cost-efficient co-work agent model derived from the post-trained Qwen3.6-35B-A3B checkpoint, positioned at the low...
StepAudio 3 Gen Unifies Speech, Sound Effects and Music in One Autoregressive Model
A new technical report presents StepAudio 3 Gen, a discrete autoregressive audio generator built on residual vector quantization t...
ReactHuman Benchmark Exposes Reactive Safety Gaps in Embodied Multimodal LLMs
Hugging Face researchers introduce ReactHuman, a physics-grounded benchmark that tests multimodal LLMs as decision cores for simul...
Feyospace-v1: Seven-Person Team Trains Open-Weight Cyber Agents to Top-Tier Results
A data-centric framework with five specialized systems lets a small independent team post-train open-weight cyber agents that impr...
DataFlex-RL Finds Uniform Sampling Hard to Beat in RLVR Data Policies
A new Hugging Face evaluation platform, DataFlex-RL, benchmarks rollout selection, reweighting, and domain mixing for reinforcemen...
SNAP3D Brings Physics to Single-Image 3D Part Assembly
A new physics-guided framework from Hugging Face researchers resolves inter-part penetration, recovers contact graphs, and refines...
SAS Ranks Context End-to-End to Make Sparse Attention Count
A new Hugging Face paper proposes Simple Attention Sparsification (SAS), which injects a selector's continuous scores into attenti...