Chinese Academic of Science Institute of Automation

CASIA's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

yxzhang2024 

submitted a paper to Daily Papers 1 day ago

World Models for Policy Refinement in StarCraft II

Paper • 2602.14857 • Published 5 days ago • 2

hongyuyang23casia 

authored a paper 4 days ago

Enhanced Graph Transformer with Serialized Graph Tokens

Paper • 2602.09065 • Published 13 days ago • 1

KunChen 

submitted a paper to Daily Papers 11 days ago

Flexible Entropy Control in RLVR with Gradient-Preserving Perspective

Paper • 2602.09782 • Published 11 days ago • 3

hongyuyang23casia 

submitted a paper to Daily Papers 2 months ago

IF-Bench: Benchmarking and Enhancing MLLMs for Infrared Images with Generative Visual Prompting

Paper • 2512.09663 • Published Dec 10, 2025 • 4

hongyuyang23casia 

authored a paper 2 months ago

IF-Bench: Benchmarking and Enhancing MLLMs for Infrared Images with Generative Visual Prompting

Paper • 2512.09663 • Published Dec 10, 2025 • 4

YannQi 

authored 3 papers 3 months ago

Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering

Paper • 2510.14605 • Published Oct 16, 2025 • 5

Taming Modality Entanglement in Continual Audio-Visual Segmentation

Paper • 2510.17234 • Published Oct 20, 2025 • 5

HunyuanOCR Technical Report

Paper • 2511.19575 • Published Nov 24, 2025 • 22

yzy666 

authored a paper 3 months ago

LiveStar: Live Streaming Assistant for Real-World Online Video Understanding

Paper • 2511.05299 • Published Nov 7, 2025 • 2

Banjiuyufen 

authored a paper 4 months ago

MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models

Paper • 2510.24794 • Published Oct 27, 2025 • 32

hongyuyang23casia 

authored 2 papers 4 months ago

Taming Modality Entanglement in Continual Audio-Visual Segmentation

Paper • 2510.17234 • Published Oct 20, 2025 • 5

Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering

Paper • 2510.14605 • Published Oct 16, 2025 • 5

YannQi 

authored a paper 6 months ago

R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

Paper • 2508.21113 • Published Aug 28, 2025 • 110

yzy666 

authored a paper 8 months ago

SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding

Paper • 2502.10810 • Published Feb 15, 2025 • 1

YannQi 

authored 3 papers 9 months ago

Continuous Speculative Decoding for Autoregressive Image Generation

Paper • 2411.11925 • Published Nov 18, 2024 • 16

Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought

Paper • 2505.15431 • Published May 21, 2025 • 1

Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger

Paper • 2506.07785 • Published Jun 9, 2025 • 1

MarkWang 

authored a paper 9 months ago

Faster and Better LLMs via Latency-Aware Test-Time Scaling

Paper • 2505.19634 • Published May 26, 2025

MarkWang 

authored a paper over 1 year ago

Continuous Speculative Decoding for Autoregressive Image Generation

Paper • 2411.11925 • Published Nov 18, 2024 • 16

YannQi 

authored a paper over 1 year ago

Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis

Paper • 2409.06135 • Published Sep 10, 2024 • 16