JPShi

JPShi's activity

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

upvoted a paper 4 days ago

Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports

Paper • 2610.31158 • Published 5 days ago • 32

upvoted a paper 6 days ago

Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding

Paper • 2605.07141 • Published May 8 • 1

authored a paper 11 days ago

EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric Alignment

Paper • 2610.22186 • Published 12 days ago • 4

updated a collection 11 days ago

EVA-Cap

Collection

4 items • Updated 11 days ago

upvoted a paper 11 days ago

EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric Alignment

Paper • 2610.22186 • Published 12 days ago • 4

submitted a paper to Daily Papers 11 days ago

EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric Alignment

Paper • 2610.22186 • Published 12 days ago • 4

updated a collection 19 days ago

EVA-Cap

Collection

4 items • Updated 11 days ago

published a model 19 days ago

JPShi/EVA-Cap-SFT-GRPO

Updated 19 days ago

updated a collection 19 days ago

EVA-Cap

Collection

4 items • Updated 11 days ago

published a model 19 days ago

JPShi/EVA-Cap-7B

Updated 19 days ago

published a dataset 19 days ago

JPShi/EVA-Data

Updated 19 days ago • 32

updated a collection 4 months ago

LoomData & LoomBench

Collection

Data and Benchmark for VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding • 1 item • Updated Jul 2

updated a dataset 4 months ago

JPShi/LoomData_spatial

Updated Jul 2 • 29

published a dataset 4 months ago

JPShi/LoomData_spatial

Updated Jul 2 • 29

upvoted a paper 4 months ago

Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification

Paper • 2606.18249 • Published Jun 16 • 16

liked a dataset 5 months ago

mjuicem/StreamingBench

Viewer • Updated May 16, 2025 • 4.55k • 22.2k • 14

upvoted 3 papers 7 months ago

DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain

Paper • 2604.10425 • Published Apr 12 • 3

FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance

Paper • 2603.12146 • Published Mar 12 • 5

Can Vision-Language Models Solve the Shell Game?

Paper • 2603.08436 • Published Mar 9 • 39