Chao Du

Variational Reasoning for Language Models

Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning

Muon Outperforms Adam in Tail-End Associative Memory Learning

Reinforcing Query-Level Meta-Agents

Fostering Video Reasoning via Next-Event Prediction

Language Models Can Learn from Verbal Feedback Without Scalar Rewards

Verl-Tool: Towards Holistic Agentic Reinforcement Learning with Tool Use

Nonparametric Data Attribution for Diffusion Models

Sample-Efficient Alignment for LLMs

Reinforcing General Reasoning Without Verifiers

Anatomy of a Hybrid Mind: Deconstructing Hybrid Reasoning in Large Language Models

Imperceptible Jailbreaking against Large Language Models

FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models

Orient Anything V2: Unifying Orientation and Rotation Understanding

Understanding R1-Zero-Like Training: A Critical Perspective

Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates

When Attention Sink Emerges in Language Models: An Empirical View

NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation

Continual Reinforcement Learning by Planning with Online World Models

Improving Your Model Ranking on Chatbot Arena by Vote Rigging

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

Scaling up Masked Diffusion Models on Text

Optimizing Anytime Reasoning via Budget Relative Policy Optimization

Lifelong Safety Alignment for Language Models

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Weak-to-Strong Jailbreaking on Large Language Models

Bootstrapping Language Models with DPO Implicit Rewards

A Closer Look at Machine Unlearning for Large Language Models

LLM-based Multi-Agents System Attack via Continuous Optimization with Discrete Efficient Search

Sample-Efficient Alignment for LLMs

Improving Long-Text Alignment for Text-to-Image Diffusion Models

Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models

Weak-to-Strong Jailbreaking on Large Language Models

SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction

Sample Efficient Alignment for LLMs

BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms

Test-Time Backdoor Attacks on Multimodal Large Language Models

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts

Denial-of-Service Poisoning Attacks against Large Language Models