Shanghai Jiao Tong University

university

Verified

https://www.sjtu.edu.cn/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

quantumfr submitted a paper about 22 hours ago

Imprint Reader: From Weight-Update Readout to Behavioral Intervention

Silin-Chen submitted a paper 6 days ago

Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?

Cicici1109 submitted a paper 8 days ago

Streaming Video Editing with Easy Adaptation

View all activity

Papers

GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction

View all Papers

submitted a paper to Daily Papers 6 days ago

Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?

Paper • 2609.27891 • Published Aug 21 • 31

submitted a paper to Daily Papers 8 days ago

Streaming Video Editing with Easy Adaptation

Paper • 2609.24788 • Published 9 days ago • 15

submitted a paper to Daily Papers 19 days ago

HyQuant: Hybrid-Precision Quantization for LLM Attention

Paper • 2608.27875 • Published Aug 28 • 30

submitted a paper to Daily Papers 27 days ago

EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction

Paper • 2609.02783 • Published 28 days ago • 62

submitted a paper to Daily Papers 29 days ago

Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching

Paper • 2608.28695 • Published Aug 27 • 7

authored 12 papers about 1 month ago

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

Paper • 2606.06087 • Published Jun 4 • 68

Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering

Paper • 2605.15721 • Published May 15

SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System

Paper • 2605.09341 • Published May 16

Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents

Paper • 2605.16986 • Published May 16

SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle

Paper • 2605.13139 • Published May 13

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

Paper • 2607.26784 • Published Jul 29 • 29

VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation

Paper • 2607.28590 • Published Jul 30 • 46

Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steering

Paper • 2510.27206 • Published Oct 31, 2025

Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories

Paper • 2608.02276 • Published Aug 3 • 4

EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning

Paper • 2608.06197 • Published Aug 6 • 48

SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents

Paper • 2608.18852 • Published Aug 19 • 9

What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents

Paper • 2608.27260 • Published Aug 27 • 74

submitted a paper to Daily Papers about 1 month ago

UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City

Paper • 2608.27456 • Published Aug 27 • 88

authored 2 papers about 1 month ago

ExFold: Unified Expert Folding for Training-Free MoE Prefill-Decode Acceleration

Paper • 2608.24938 • Published Aug 24 • 3

SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning

Paper • 2603.08000 • Published May 31 • 2