Chinese Academic of Science Institute of Automation

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

jinzhuoran submitted a paper 6 days ago

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

jinzhuoran submitted a paper 8 days ago

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

MarkWang authored a paper about 1 month ago

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

View all activity

Papers

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

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

View all Papers

submitted a paper to Daily Papers 6 days ago

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

Paper • 2606.26027 • Published 9 days ago • 18

submitted a paper to Daily Papers 8 days ago

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

Paper • 2606.22565 • Published 12 days ago • 9

authored a paper about 1 month ago

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

Paper • 2605.28184 • Published May 27 • 6

submitted a paper to Daily Papers about 1 month ago

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

Paper • 2605.28184 • Published May 27 • 6

submitted a paper to Daily Papers about 1 month ago

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

Paper • 2605.23264 • Published May 22 • 7

submitted a paper to Daily Papers about 2 months ago

Uncovering Entity Identity Confusion in Multimodal Knowledge Editing

Paper • 2605.06096 • Published May 7 • 1

submitted a paper to Daily Papers about 2 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 3 months ago

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

Paper • 2604.14142 • Published Apr 15 • 30

CUDAOUTOFMEMORY

submitted a paper to Daily Papers 3 months ago

PLUME: Latent Reasoning Based Universal Multimodal Embedding

Paper • 2604.02073 • Published Apr 2 • 15

authored a paper 3 months ago

CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR

Paper • 2603.10101 • Published Mar 10 • 6

hongyuyang23casia

authored a paper 4 months ago

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

Paper • 2602.23952 • Published Feb 27 • 3

hongyuyang23casia

submitted a paper to Daily Papers 4 months ago

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

Paper • 2602.23952 • Published Feb 27 • 3

submitted a paper to Daily Papers 4 months ago

World Models for Policy Refinement in StarCraft II

Paper • 2602.14857 • Published Feb 16 • 9

hongyuyang23casia

authored a paper 4 months ago

Enhanced Graph Transformer with Serialized Graph Tokens

Paper • 2602.09065 • Published Feb 9 • 1

submitted a paper to Daily Papers 5 months ago

Flexible Entropy Control in RLVR with Gradient-Preserving Perspective

Paper • 2602.09782 • Published Feb 10 • 3

hongyuyang23casia

submitted a paper to Daily Papers 7 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 7 months ago

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

Paper • 2512.09663 • Published Dec 10, 2025 • 4

authored 3 papers 7 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 • 23