4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding
Paper • 2605.05997 • Published • 18
AI & ML interests
Feeling and building the multimodal intelligence.
Recent Activity
View all activity
Papers
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
xiangan
authored 2
papers 5 days ago
THUdyh
authored a
paper 5 days ago
Paranioar
authored a
paper 5 days ago
yl-1993
authored a
paper 5 days ago
Paranioar
submitted a
paper to Daily Papers 6 days ago
xiangan
updated a
collection 7 days ago
xiangan
submitted a
paper to Daily Papers 7 days ago
kcz358
authored a
paper 7 days ago
mwxely
submitted a
paper to Daily Papers 8 days ago
mwxely
authored 2
papers 12 days ago
Yuwei-Niu
authored 7
papers 19 days ago
WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation
Paper • 2503.07265 • Published • 4
UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
Paper • 2506.03147 • Published • 58
Look-Back: Implicit Visual Re-focusing in MLLM Reasoning
Paper • 2507.03019 • Published • 1
GIR-Bench: Versatile Benchmark for Generating Images with Reasoning
Paper • 2510.11026 • Published • 18
SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
Paper • 2510.12784 • Published • 20
Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback
Paper • 2510.16888 • Published • 22
OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination
Paper • 2509.00723 • Published • 1