Collections
Discover the best community collections!
Collections including paper arxiv:2605.02881
-
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 348 -
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
Paper • 2605.27365 • Published • 135 -
Continuous Latent Diffusion Language Model
Paper • 2605.06548 • Published • 80
-
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 348 -
allenai/eval_molmoact_candy_sorting_in-distribution
Viewer • Updated • 59.6k • 422 -
allenai/eval_molmoact_cup_stacking_in-distribution
Viewer • Updated • 32k • 413 -
allenai/eval_molmoact_cup_storing_in-distribution
Viewer • Updated • 45.4k • 433
-
Refusal in Language Models Is Mediated by a Single Direction
Paper • 2406.11717 • Published • 13 -
Self-Distilled Agentic Reinforcement Learning
Paper • 2605.15155 • Published • 111 -
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
Paper • 2605.14906 • Published • 76 -
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
Paper • 2605.15128 • Published • 62
-
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
Paper • 2604.28196 • Published • 72 -
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 348 -
Recursive Multi-Agent Systems
Paper • 2604.25917 • Published • 274 -
jina-embeddings-v5-omni: Text-Geometry-Preserving Multimodal Embeddings via Frozen-Tower Composition
Paper • 2605.08384 • Published • 11
-
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 348 -
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
Paper • 2605.27365 • Published • 135 -
Continuous Latent Diffusion Language Model
Paper • 2605.06548 • Published • 80
-
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 348 -
allenai/eval_molmoact_candy_sorting_in-distribution
Viewer • Updated • 59.6k • 422 -
allenai/eval_molmoact_cup_stacking_in-distribution
Viewer • Updated • 32k • 413 -
allenai/eval_molmoact_cup_storing_in-distribution
Viewer • Updated • 45.4k • 433
-
Refusal in Language Models Is Mediated by a Single Direction
Paper • 2406.11717 • Published • 13 -
Self-Distilled Agentic Reinforcement Learning
Paper • 2605.15155 • Published • 111 -
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
Paper • 2605.14906 • Published • 76 -
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
Paper • 2605.15128 • Published • 62
-
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
Paper • 2604.28196 • Published • 72 -
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 348 -
Recursive Multi-Agent Systems
Paper • 2604.25917 • Published • 274 -
jina-embeddings-v5-omni: Text-Geometry-Preserving Multimodal Embeddings via Frozen-Tower Composition
Paper • 2605.08384 • Published • 11