VisionReasoner
[ICLR 2026] VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
- 353
- Python
- Apache-2.0
- 10 mo ago
[ICLR 2026] VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
ROS 2 integration of Meta’s DINOv3 backbone with lightweight heads for vision tasks.
Unified reproductions, benchmarking & evaluation for perception-aware RLVR and OPD in VLMs, plus multi-turn agentic RL with HTTP, OpenEnv and OpenReward environments. 19 methods · 30+ benchmarks · Official code of CGPO (ACM MM 2026 Oral).
A curated list of resources, libraries, tools, frameworks for Multimodal sensor fusion.
Threshold visual detection task for neurophysiological research
Research synthesis on visual completion, explaining how the brain constructs missing visual information from partial input using perception, neuroscience, Gestalt principles, and predictive coding.