12 papers
SD-MAR: Multi-image Analytical Reasoning via Synthetic Data and Reinforcement Learning
Shiyu Yuan, Sourav Sanjukta Bhabesh, Zhe Wang +3
Vision Language Models (VLMs) demonstrate strong perceptual abilities but remain limited in tasks requiring analytical reasoning across multiple visual states, such as multi-image…
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…
SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation
Long Li, Zhijian Zhou, Jiangxuan Long +5
Agentic Reinforcement Learning (RL) shows promise for complex tasks, but Text-to-SQL remains mostly restricted to single-turn paradigms. A primary bottleneck is the credit assignme…
DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay
Long Li, Zhijian Zhou, Tianyi Wang +7
While Reinforcement Learning (RL) enhances Large Language Model reasoning, on-policy algorithms like GRPO are sample-inefficient as they discard past rollouts. Existing experience…
ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation
Songlin Yang, Zhe Wang, Xuyi Yang +7
Text-driven video generation has democratized film creation, but camera control in cinematic multi-shot scenarios remains a significant block. Implicit textual prompts lack precisi…
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…
The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
Long Li, Zhijian Zhou, Jiaran Hao +9
A central paradox in fine-tuning Large Language Models (LLMs) with Reinforcement Learning with Verifiable Reward (RLVR) is the frequent degradation of multi-attempt performance (Pa…
A Closer Look at Adversarial Suffix Learning for Jailbreaking LLMs: Augmented Adversarial Trigger Learning
Zhe Wang, Yanjun Qi
Gradient optimization-based adversarial attack methods automate the learning of adversarial triggers to generate jailbreak prompts or leak system prompts. In this work, we take a c…
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…
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…
Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidance
Zhe Wang, Haozhu Wang, Yanjun Qi
Decision transformers recast reinforcement learning as a conditional sequence generation problem, offering a simple but effective alternative to traditional value or policy-based m…
Bayesian Calibration of Win Rate Estimation with LLM Evaluators
Yicheng Gao, Gonghan Xu, Zhe Wang +1
Recent advances in large language models (LLMs) show the potential of using LLMs as evaluators for assessing the quality of text generations from LLMs. However, applying LLM evalua…