Chinese Academic of Science Institute of Automation

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Trae1ounG submitted a paper 10 days ago

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

MarkWang authored a paper 11 days ago

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

MarkWang submitted a paper 12 days ago

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

View all activity

Papers

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

View all Papers

submitted a paper to Daily Papers 10 days ago

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

Paper • 2609.09113 • Published 13 days ago • 19

authored a paper 11 days ago

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

Paper • 2609.07108 • Published 14 days ago • 35

submitted a paper to Daily Papers 12 days ago

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

Paper • 2609.07108 • Published 14 days ago • 35

authored 2 papers 13 days ago

Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions

Paper • 2602.09483 • Published Feb 10 • 1

Taming Modality Entanglement in Continual Audio-Visual Segmentation

Paper • 2510.17234 • Published Oct 20, 2025 • 5

hongyuyang23casia

submitted a paper to Daily Papers 19 days ago

DICS: Exploring Data Intrinsic Consistency for Visual Instruction Selection

Paper • 2608.30209 • Published 21 days ago • 6

submitted 2 papers to Daily Papers about 1 month ago

Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning

Paper • 2608.03571 • Published Aug 6 • 47

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

Paper • 2608.03573 • Published Aug 6 • 61

zd21

submitted a paper to Daily Papers about 1 month ago

Continual Learning in Transition

Paper • 2608.06216 • Published Aug 6 • 27

submitted a paper to Daily Papers about 2 months ago

SWE-Touch: Benchmarking Coding Agents When Users Touch the Code

Paper • 2608.02499 • Published Aug 3 • 25

submitted a paper to Daily Papers about 2 months ago

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

Paper • 2607.24720 • Published Jul 27 • 27

authored a paper 2 months ago

Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories

Paper • 2607.15330 • Published Jul 16 • 72

submitted 2 papers to Daily Papers 3 months ago

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

Paper • 2606.26027 • Published Jun 24 • 19

Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do

Paper • 2606.22565 • Published Jun 21 • 9

authored a paper 4 months ago

Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration

Paper • 2605.28184 • Published May 27 • 5

submitted a paper to Daily Papers 4 months ago

Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration

Paper • 2605.28184 • Published May 27 • 5

submitted a paper to Daily Papers 4 months ago

Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution

Paper • 2605.23264 • Published May 22 • 5

submitted a paper to Daily Papers 4 months ago

Uncovering Entity Identity Confusion in Multimodal Knowledge Editing

Paper • 2605.06096 • Published May 7 • 1

submitted a paper to Daily Papers 5 months ago

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning

Paper • 2605.00380 • Published May 1 • 7

submitted a paper to Daily Papers 5 months ago

From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space

Paper • 2604.14142 • Published Apr 15 • 30