jasmineWang

Jessamine's activity

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

commented a paper about 22 hours ago

Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories

Paper • 2606.02060 • Published 5 days ago • 49 •

7

updated a dataset 1 day ago

NJU-LINK/TELBench

Updated 1 day ago • 79 • 1

updated a collection 1 day ago

Agent Papers

Collection

4 items • Updated 1 day ago • 1

upvoted a collection 1 day ago

Agent Papers

Collection

4 items • Updated 1 day ago • 1

updated a collection 1 day ago

Agent Papers

Collection

4 items • Updated 1 day ago • 1

upvoted 3 papers 1 day ago

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published 5 days ago • 80

MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?

Paper • 2606.01993 • Published 4 days ago • 13

Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories

Paper • 2606.02060 • Published 5 days ago • 49

upvoted 2 papers 3 days ago

TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation

Paper • 2606.02320 • Published 5 days ago • 13

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding

Paper • 2605.29707 • Published 9 days ago • 137

authored a paper 3 days ago

Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories

Paper • 2606.02060 • Published 5 days ago • 49

upvoted a paper 3 days ago

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion

Paper • 2605.30351 • Published 9 days ago • 26

published a dataset 8 days ago

NJU-LINK/TELBench

Updated 1 day ago • 79 • 1

upvoted a paper 9 days ago

LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV

Paper • 2605.26244 • Published 12 days ago • 38

updated a model 18 days ago

Jessamine/portraitcraft-track2

Updated 18 days ago

published a model 18 days ago

Jessamine/portraitcraft-track2

Updated 18 days ago

upvoted a paper 25 days ago

HumanNet: Scaling Human-centric Video Learning to One Million Hours

Paper • 2605.06747 • Published 30 days ago • 52