Behavior Spatial Benchmark: Evaluating Spatial Understanding for Robotics
Paper • 2610.34051 • Published
LongVideoHaystack
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
ManlingLi
authored 20
papers 1 day ago
SteerAct: Unlocking Action Models through Few-Shot Temporal Steering
Paper • 2610.25632 • Published • 13
Realtime-Bench: Can Frontier Models Solve Real-time Interactive Problems?
Paper • 2610.22155 • Published • 2
WOVEN: Weaving Visual World Modeling into Multimodal LLMs
Paper • 2610.12417 • Published • 21
TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning
Paper • 2610.10288 • Published • 19
SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
Paper • 2502.06994 • Published
MindTopo: Can Foundation Models Reason in Topological Space?
Paper • 2609.11900 • Published
WorldAgen: Unified State-Action Prediction with Test-Time World Model Training
Paper • 2609.08162 • Published
MANIGUARD: A Benchmark and Data Suite for Specification-Grounded Safety Evaluation and Improvement of Robotic Manipulation
Paper • 2608.17386 • Published • 2
CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded Reasoning
Paper • 2608.02833 • Published • 5
HumanCLAW: Can Vision-Language Models Act Through a Body?
Paper • 2607.27180 • Published • 76
MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding
Paper • 2112.10728 • Published
SENTINEL: Failure-Driven Reinforcement Learning for Training Tool-Using Language Model Agents
Paper • 2606.12908 • Published
Using large language models for embodied planning introduces systematic safety risks
Paper • 2604.18463 • Published
Brick-Composer: Using MLLMs for Assembly with Diverse Bricks
Paper • 2606.05445 • Published • 8
EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks
Paper • 2604.09535 • Published • 2
BAGEN: Are LLM Agents Budget-Aware?
Paper • 2606.00198 • Published
Planning with the Views
Paper • 2605.29563 • Published
VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
Paper • 2510.16907 • Published
ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
Paper • 2605.18746 • Published • 7