works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.CV2026

SD-MAR: Multi-image Analytical Reasoning via Synthetic Data and Reinforcement Learning

Shiyu Yuan, Sourav Sanjukta Bhabesh, Zhe Wang +3

The paper introduces SD-MAR, a synthetic-data framework and reinforcement‑learning fine‑tuning method to improve vision‑language models' ability to reason analytically across multi…

cs.LG2026

Reinforcing the Generation Order of Multimodal Masked Diffusion Models

Yidong Ouyang, Zhe Wang, Sourav Bhabesh +1

Diffusion Language Models (DLMs) have recently achieved substantial progress in natural language generation tasks. Recent research demonstrates that adaptive token generation order…

stat.ML2026

Training-Free Self-Correction for Multimodal Masked Diffusion Models

Yidong Ouyang, Panwen Hu, Zhengyan Wan +7

Masked diffusion models have emerged as a powerful framework for text and multimodal generation. However, their sampling procedure updates multiple tokens simultaneously and treats…

cs.CR2025

Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation

Daniel Schwartz, Dmitriy Bespalov, Zhe Wang +2

As large language models (LLMs) become increasingly prevalent, ensuring their robustness against adversarial misuse is crucial. This paper introduces the GAP (Graph of Attacks with…

cs.CL2025

LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning

Zifan Xu, Haozhu Wang, Dmitriy Bespalov +3

Chain-of-thought (CoT) prompting is a popular in-context learning (ICL) approach for large language models (LLMs), especially when tackling complex reasoning tasks. Traditional ICL…

cs.CR2025

TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice

Aman Goel, Xian Carrie Wu, Zhe Wang +2

Jailbreaking large-language models (LLMs) involves testing their robustness against adversarial prompts and evaluating their ability to withstand prompt attacks that could elicit u…