Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Paper • 2607.21072 • Published 3 days ago • 35
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning Paper • 2607.14777 • Published 10 days ago • 100
SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models Paper • 2510.08531 • Published Oct 9, 2025 • 14
ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models Paper • 2505.21500 • Published May 27, 2025 • 15
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning Paper • 2607.04425 • Published 21 days ago • 72
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon Paper • 2607.01804 • Published 24 days ago • 31
PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception Paper • 2606.28322 • Published about 1 month ago • 42
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning Paper • 2607.01191 • Published 25 days ago • 19
Pause or Fabricate? Training Language Models for Grounded Reasoning Paper • 2604.19656 • Published Apr 21 • 10
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments Paper • 2604.14144 • Published Apr 15 • 63
UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding Paper • 2604.14113 • Published Apr 15 • 10
UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization Paper • 2604.13822 • Published Apr 15 • 7