Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation Paper • 2603.12247 • Published about 13 hours ago • 12
GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing Paper • 2603.12264 • Published about 13 hours ago • 11
Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports Paper • 2603.09896 • Published 3 days ago • 24
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence Paper • 2603.07660 • Published 5 days ago • 76
DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing Paper • 2602.12205 • Published 29 days ago • 79
RISE-Video: Can Video Generators Decode Implicit World Rules? Paper • 2602.05986 • Published Feb 5 • 26
SGI-Bench Collection Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows • 8 items • Updated 3 days ago • 33
Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform Paper • 2512.08478 • Published Dec 9, 2025 • 77
UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation Paper • 2510.18701 • Published Oct 21, 2025 • 67
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization Paper • 2510.08540 • Published Oct 9, 2025 • 109