collaborators

13 papers

cs.LG2026

CANDI: Hybrid Discrete-Continuous Diffusion Models

Patrick Pynadath, Jiaxin Shi, Ruqi Zhang

While continuous diffusion has shown remarkable success in continuous domains such as image generation, its direct application to discrete data has underperformed pure discrete for…

cs.CV2026

Learning Self-Correction in Vision-Language Models via Rollout Augmentation

Yi Ding, Ziliang Qiu, Bolian Li +1

Self-correction is essential for solving complex reasoning problems in vision-language models (VLMs). However, existing reinforcement learning (RL) methods struggle to learn it, as…

cs.AI2026

SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology

Yifan Wang, Bolian Li, David Cho +3

Reinforcement learning is critical to improving large reasoning models, but its success relies heavily on verifiable rewards (RLVR), making it hard to use in open-ended domains whe…

cs.CL2026

DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning

Yifan Wang, Bolian Li, Junlin Wu +5

Real-world large language model deployments (e.g., conversational AI systems, code generation assistants) naturally generate abundant implicit user dissatisfaction (DSAT) signals,…

cs.CV2025

Sherlock: Self-Correcting Reasoning in Vision-Language Models

Yi Ding, Ruqi Zhang

Reasoning Vision-Language Models (VLMs) have shown promising performance on complex multimodal tasks. However, they still face significant challenges: they are highly sensitive to…

cs.LG2025

Bayesian Computation in Deep Learning

Wenlong Chen, Bolian Li, Ruqi Zhang +1

Bayesian methods have shown success in deep learning applications. For example, in predictive tasks, Bayesian neural networks leverage Bayesian reasoning of model uncertainty to im…