Song Wang

songw-zju's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 5 days ago

Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion

Paper • 2512.04926 • Published 6 days ago • 40

authored a paper 2 months ago

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

Paper • 2510.02240 • Published Oct 2 • 17

upvoted a collection 2 months ago

ReasonMap

Collection

A fine-grained visual reasoning benchmark (We show more question types in the extension dataset.) • 3 items • Updated Oct 1 • 8

upvoted a paper 2 months ago

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

Paper • 2510.02240 • Published Oct 2 • 17

commented a paper 2 months ago

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

Paper • 2510.02240 • Published Oct 2 • 17 •

2

authored a paper 3 months ago

3D and 4D World Modeling: A Survey

Paper • 2509.07996 • Published Sep 4 • 58

upvoted a paper 3 months ago

3D and 4D World Modeling: A Survey

Paper • 2509.07996 • Published Sep 4 • 58

authored a paper 4 months ago

A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding

Paper • 2508.01197 • Published Aug 2 • 5

upvoted a paper 4 months ago

A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding

Paper • 2508.01197 • Published Aug 2 • 5

commented a paper 4 months ago

A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding

Paper • 2508.01197 • Published Aug 2 • 5 •

2

upvoted 2 papers 6 months ago

Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport

Paper • 2308.01779 • Published Aug 3, 2023 • 1

Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning

Paper • 2503.00513 • Published Mar 1 • 1

authored 4 papers 6 months ago

Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport

Paper • 2308.01779 • Published Aug 3, 2023 • 1

Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning

Paper • 2503.00513 • Published Mar 1 • 1

Uncertainty-Instructed Structure Injection for Generalizable HD Map Construction

Paper • 2503.23109 • Published Mar 29

SAM4D: Segment Anything in Camera and LiDAR Streams

Paper • 2506.21547 • Published Jun 26 • 17

upvoted 2 papers 6 months ago

PixelThink: Towards Efficient Chain-of-Pixel Reasoning

Paper • 2505.23727 • Published May 29 • 5

SAM4D: Segment Anything in Camera and LiDAR Streams

Paper • 2506.21547 • Published Jun 26 • 17

commented a paper 6 months ago

SAM4D: Segment Anything in Camera and LiDAR Streams

Paper • 2506.21547 • Published Jun 26 • 17 •

1

upvoted a paper 6 months ago

PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance

Paper • 2406.09326 • Published Jun 13, 2024 • 1