Voozh

AI & ML interests

None defined yet.

Recent Activity

👁 Image

jinzhuoran submitted a paper 3 days ago

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

👁 Image

jinzhuoran submitted a paper 4 days ago

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

👁 Image

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

👁 Image

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

👁 Image

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

View all Papers

👁 Image

Submitted by

👁 Image

Zhuoran Jin

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

👁 CASIA
Chinese Academic of Science Institute of Automation

3 2

👁 Image

Submitted by

👁 Image

Zhuoran Jin

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

👁 CASIA
Chinese Academic of Science Institute of Automation

👁 Image

Submitted by

👁 Image

Hongbo Wang

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

👁 CASIA
Chinese Academic of Science Institute of Automation

158 3

👁 Image

Submitted by

👁 Image

Xiaotian Ye

Uncovering Entity Identity Confusion in Multimodal Knowledge Editing

👁 CASIA
Chinese Academic of Science Institute of Automation

👁 Image

Submitted by

👁 Image

zihan

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

👁 CASIA
Chinese Academic of Science Institute of Automation

14 3

👁 Image

Submitted by

👁 Image

TanYuQiao

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

👁 CASIA
Chinese Academic of Science Institute of Automation

17 2

👁 Image

Submitted by

👁 Image

hxz

PLUME: Latent Reasoning Based Universal Multimodal Embedding

👁 CASIA
Chinese Academic of Science Institute of Automation

23 2

👁 Image

Submitted by

👁 Image

Yixin Zhang

World Models for Policy Refinement in StarCraft II

👁 CASIA
Chinese Academic of Science Institute of Automation

10 4

👁 Image

Enhanced Graph Transformer with Serialized Graph Tokens

👁 CASIA
Chinese Academic of Science Institute of Automation

👁 Image

Submitted by

👁 Image

mz.w

Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

👁 CASIA
Chinese Academic of Science Institute of Automation

60 5

👁 Image

Submitted by

👁 Image

Hongbo Zhao

VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?

👁 CASIA
Chinese Academic of Science Institute of Automation

27 3

👁 Image

Submitted by

👁 Image

hongyuyang

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

👁 CASIA
Chinese Academic of Science Institute of Automation

20 2

👁 Image

Submitted by

👁 Image

Zhuoran Jin

Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences

👁 CASIA
Chinese Academic of Science Institute of Automation

47 1

👁 Image

Submitted by

👁 Image

hongyuyang

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

👁 CASIA
Chinese Academic of Science Institute of Automation

19 2

👁 Image

Submitted by

👁 Image

WenYang

Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective

👁 CASIA
Chinese Academic of Science Institute of Automation

URL: https://huggingface.co/CASIA/papers

⇱ CASIA (Chinese Academic of Science Institute of Automation)

AI & ML interests

Recent 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

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

Uncovering Entity Identity Confusion in Multimodal Knowledge Editing

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

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

PLUME: Latent Reasoning Based Universal Multimodal Embedding

World Models for Policy Refinement in StarCraft II

Enhanced Graph Transformer with Serialized Graph Tokens

Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?

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

Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences

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

Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective