SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
Paper • 2604.14144 • Published • 61
Yuseung "Phillip" Lee
phillipinseoul
AI & ML interests
Computer Vision
Recent Activity
liked a model 1 day ago
lidingm/SpatialEvo-3B upvoted a paper 4 days ago
You Only Judge Once: Multi-response Reward Modeling in a Single Forward PassOrganizations
upvoted a paper 3 days ago
upvoted 3
papers 4 days ago
You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass
Paper • 2604.10966 • Published • 10
Lyra 2.0: Explorable Generative 3D Worlds
Paper • 2604.13036 • Published • 33
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
Paper • 2604.10098 • Published • 74
upvoted 3
papers 6 days ago
upvoted 3
papers 9 days ago
OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence
Paper • 2604.07296 • Published • 39
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 316
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
Paper • 2604.07430 • Published • 182
upvoted 4
papers 10 days ago
RAGEN-2: Reasoning Collapse in Agentic RL
Paper • 2604.06268 • Published • 64
Action Images: End-to-End Policy Learning via Multiview Video Generation
Paper • 2604.06168 • Published • 14
How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
Paper • 2604.04323 • Published • 40
Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
Paper • 2604.04934 • Published • 43
upvoted 3
papers 13 days ago
upvoted 2
papers 17 days ago
upvoted a paper 18 days ago