Ze Li

13

Papers

169

Total Citations

Papers (13)

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning

FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities

NeurIPS 2025arXiv

Implicit Concept Removal of Diffusion Models

Is Artificial Intelligence Generated Image Detection a Solved Problem?

NeurIPS 2025arXiv

Jailbreaking as a Reward Misspecification Problem

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning

Fast Training of Diffusion Transformer with Extreme Masking for 3D Point Clouds Generation

Dynamic Risk Assessments for Offensive Cybersecurity Agents

NeurIPS 2025arXiv

Distilling Knowledge from Large-Scale Image Models for Object Detection

Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM

NeurIPS 2025arXiv

Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens

NeurIPS 2025arXiv

Robust Low-light Scene Restoration via Illumination Transition