Sun Yat-Sen University

university

Verified

https://www.sysu.edu.cn/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

linggm submitted a paper 10 days ago

Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models

LuHanwen submitted a paper 12 days ago

CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation

Necolizer authored a paper 26 days ago

De-biasing Skeleton-based Action Recognition with Convex Hull Adaptive Shift

View all activity

Papers

Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models

CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation

View all Papers

submitted a paper to Daily Papers 2 days ago

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

Paper • 2610.31329 • Published 3 days ago • 240

authored 2 papers 4 days ago

SolarRenderer: Few-Step Generative Reference Rendering

Paper • 2610.28630 • Published 5 days ago • 53

Orbia: Do Generated Videos Form a Consistent 3D World?

Paper • 2610.20693 • Published 11 days ago • 46

submitted a paper to Daily Papers 4 days ago

SolarRenderer: Few-Step Generative Reference Rendering

Paper • 2610.28630 • Published 5 days ago • 53

submitted a paper to Daily Papers 10 days ago

Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models

Paper • 2610.18248 • Published 12 days ago • 19

submitted a paper to Daily Papers 12 days ago

CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation

Paper • 2609.36616 • Published 26 days ago • 33

authored 2 papers about 2 months ago

Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout

Paper • 2609.09123 • Published Sep 8 • 54

SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models

Paper • 2609.02886 • Published Sep 2 • 115

authored 2 papers 5 months ago

Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification

Paper • 2605.17531 • Published May 24 • 2

Kwai Keye-VL-2.0 Technical Report

Paper • 2606.10651 • Published Jun 9 • 193

submitted a paper to Daily Papers 5 months ago

Kwai Keye-VL-2.0 Technical Report

Paper • 2606.10651 • Published Jun 9 • 193

submitted a paper to Daily Papers 5 months ago

Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems

Paper • 2605.27492 • Published May 26 • 26

submitted a paper to Daily Papers 5 months ago

Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification

Paper • 2605.17531 • Published May 24 • 2

authored a paper 5 months ago

Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification

Paper • 2605.17531 • Published May 24 • 2

authored 2 papers 5 months ago

FramePrompt: In-context Controllable Animation with Zero Structural Changes

Paper • 2506.17301 • Published Jun 17, 2025

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

Paper • 2605.13724 • Published May 13 • 104

submitted a paper to Daily Papers 6 months ago

SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents

Paper • 2605.03353 • Published May 5 • 6

submitted a paper to Daily Papers 9 months ago

Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search

Paper • 2602.04454 • Published Feb 4 • 4

authored 2 papers 9 months ago

ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations

Paper • 2501.14607 • Published Jan 24, 2025

PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild

Paper • 2504.11326 • Published Apr 15, 2025 • 5