sherry

rain305's activity

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

upvoted a paper 4 days ago

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

Paper • 2605.30621 • Published May 28 • 24

liked a model 17 days ago

Qwen/Qwen3.5-27B

Image-Text-to-Text • 28B • Updated Apr 24 • 2.67M • • 1.03k

upvoted a paper 20 days ago

Tracing Agentic Failure from the Flow of Success

Paper • 2607.12747 • Published 22 days ago • 20

liked a dataset 21 days ago

lioooox/T2I-CoReBench-Images

Viewer • Updated Mar 9 • 13.4k • 2.82k • 5

upvoted a paper 22 days ago

Multi-Agent LLMs Fail to Explore Each Other

Paper • 2607.11250 • Published 23 days ago • 17

liked a dataset 22 days ago

ma-xu/fine-t2i

Viewer • Updated Feb 20 • 727k • 22.4k • 117

upvoted a paper 23 days ago

Qwen-Image-2.0 Technical Report

Paper • 2605.10730 • Published May 11 • 118

liked 3 datasets 23 days ago

VisionXLab/DisciplineGen-1M

Viewer • Updated Jul 3 • 1.1M • 883 • 5

bitmind/nano-banana

Viewer • Updated Aug 30, 2025 • 9.46k • 526 • 21

PicoTrex/Mind-Brush

Viewer • Updated Jun 1 • 525 • 127 • 3

upvoted a paper 27 days ago

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Paper • 2607.07675 • Published 28 days ago • 64

liked a dataset 27 days ago

GenSearcher/Train-Data

Viewer • Updated May 1 • 3.32k • 217 • 6

upvoted 3 papers 28 days ago

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

Paper • 2607.05804 • Published 29 days ago • 19

SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe

Paper • 2607.03451 • Published Jul 3 • 34

RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation

Paper • 2607.06558 • Published 29 days ago • 79

upvoted 4 papers about 1 month ago

Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring

Paper • 2605.30834 • Published May 29 • 11

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

Paper • 2606.26080 • Published Jun 24 • 12

Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation

Paper • 2606.26907 • Published Jun 25 • 50

DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis

Paper • 2604.13416 • Published Jun 18 • 33

upvoted a paper about 2 months ago

Kwai Keye-VL-2.0 Technical Report

Paper • 2606.10651 • Published Jun 9 • 194