Chinese Academic of Science Institute of Automation

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

wanglucs submitted a paper 2 days ago

AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding

PSRben authored a paper about 1 month ago

DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization

PSRben authored a paper about 1 month ago

Self-Supervised Skill Optimization

View all activity

Papers

AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding

CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models

View all Papers

submitted a paper to Daily Papers 2 days ago

AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding

Paper • 2610.38678 • Published 4 days ago • 10

authored 2 papers about 1 month ago

DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization

Paper • 2508.01873 • Published Nov 27, 2025 • 1

Self-Supervised Skill Optimization

Paper • 2607.28777 • Published Jul 30 • 1

authored 5 papers about 1 month ago

Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild

Paper • 2605.22064 • Published May 21 • 5

MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning

Paper • 2602.03320 • Published Feb 3 • 2

CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering

Paper • 2602.23952 • Published Feb 27 • 6

How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining

Paper • 2609.35457 • Published Sep 28 • 68

Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding

Paper • 2603.10863 • Published Jun 26

submitted a paper to Daily Papers about 1 month ago

VisionHOPE: Visual Backbones as Self-Modifying Learning Systems

Paper • 2609.33325 • Published Sep 27 • 337

authored a paper about 1 month ago

VisionHOPE: Visual Backbones as Self-Modifying Learning Systems

Paper • 2609.33325 • Published Sep 27 • 337

authored 3 papers about 1 month ago

Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding

Paper • 2603.10863 • Published Jun 26

How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining

Paper • 2609.35457 • Published Sep 28 • 68

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

Paper • 2602.09483 • Published Feb 10 • 1

submitted a paper to Daily Papers about 1 month ago

How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining

Paper • 2609.35457 • Published Sep 28 • 68

submitted a paper to Daily Papers about 2 months ago

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

Paper • 2609.09113 • Published Sep 8 • 21

authored a paper about 2 months ago

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

Paper • 2609.07108 • Published Sep 7 • 20

submitted a paper to Daily Papers about 2 months ago

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

Paper • 2609.07108 • Published Sep 7 • 20

authored 2 papers about 2 months 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 2 months ago

DICS: Exploring Data Intrinsic Consistency for Visual Instruction Selection

Paper • 2608.30209 • Published Aug 31 • 5