AgentKernel: The Trust-Native Agentic Operating System Paper ⢠2609.29647 ⢠Published 29 days ago ⢠6
PUBG Ally: A Conversational Embodied Agent as an AI Teammate Paper ⢠2609.29837 ⢠Published 3 days ago ⢠5
World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal Paper ⢠2609.29964 ⢠Published 3 days ago ⢠6
WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation Paper ⢠2609.30221 ⢠Published 3 days ago ⢠33
ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds Paper ⢠2609.30199 ⢠Published 3 days ago ⢠9
Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms Paper ⢠2609.27321 ⢠Published 4 days ago ⢠12
InternW0: A Foundational Physical World Model for Efficient Real-World Interactions Paper ⢠2609.27656 ⢠Published 4 days ago ⢠6
Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings Paper ⢠2609.25165 ⢠Published 6 days ago ⢠64
Recursive self-improvement of AI research agents Paper ⢠2609.26457 ⢠Published 5 days ago ⢠20
view post Post 130 I put together a Space to showcase tokenization-in-the-browser libs we maintain at HFLet me know what you think! sbrandeis/tokenizers-wasm-demo See translation š„ 1 1 + Reply
GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay Paper ⢠2609.25001 ⢠Published 6 days ago ⢠130
VideoGen-Agent: Reinforcing Video Generation Agents Paper ⢠2609.24997 ⢠Published 6 days ago ⢠70
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents Paper ⢠2609.22000 ⢠Published 9 days ago ⢠77
OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation Paper ⢠2609.22069 ⢠Published 9 days ago ⢠35
MintAct: A Unified Visual Agent for Digital Environments Paper ⢠2609.22083 ⢠Published 9 days ago ⢠34
When AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation Paper ⢠2609.20942 ⢠Published 10 days ago ⢠9
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper ⢠2609.19969 ⢠Published 10 days ago ⢠182
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation Paper ⢠2609.20744 ⢠Published 10 days ago ⢠52
JEPA-Anything: Learning Predictive Models across Different Worlds Paper ⢠2609.20800 ⢠Published 10 days ago ⢠72