Jiangchao Yao

Decoupling the Class Label and the Target Concept in Machine Unlearning

Improving Diffusion Models for Class-imbalanced Training Data via Capacity Manipulation

Towards Understanding Valuable Preference Data for Large Language Model Alignment

Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models

Long-tailed Learning with Muon Optimizer

Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs

Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning

TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification

Bilateral Information-aware Test-time Adaptation for Vision-Language Models

Sequence Length Matters in Data Scheduling for Accelerating Language Model Pretraining

Parameter-wise Weighted Model Editing for Efficient and Retentive LLM Unlearning

RewardFlow: Propagating Reward in the State Graphs of Agentic Learning with LLMs

Conformal Risk-Controlled Routing for Large Language Model

Learning to Instruct for Visual Instruction Tuning

Fast and Accurate Blind Flexible Docking

RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis

4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming

SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation

Long-tailed Recognition with Model Rebalancing

MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition

CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration

Decoupling the Class Label and the Target Concept in Machine Unlearning

Breaking the Detection-Generalization Paradox on Out-Of-Distribution Data

G4Seg: Generation for Online Segmentation Refinement with Diffusion Models

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?

Protecting Minorities in Diffusion Models via Capacity Allocation

Nested Gloss Makes Large Language Models Lost