Kaifu Zhang

Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images

A State-Transition Framework for Efficient LLM Reasoning

ORION: Decoupling and Alignment for Unified Autoregressive Understanding and Generation

iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance

Getting Your LLMs Ready for Reinforcement Learning with Lightweight SFT

Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models

HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents in Hierarchical Rule Application

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models

MirrorCAPTCHA: Wild CAPTCHA, Wild Distribution, Wild Web-based Platform Meet Multimodal LLM Agents

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models

Multimodal Tabular Reasoning with Privileged Structured Information

Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs

SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models

Alleviating Hallucinations in Large Language Models through Multi-Model Contrastive Decoding and Dynamic Hallucination Detection

Towards Visualization-of-Thought Jailbreak Attack against Large Visual Language Models

Parrot: Multilingual Visual Instruction Tuning

Parrot: Multilingual Visual Instruction Tuning

FTP: Efficient Prefilling for Long-Context LLM Inference via FFN Token Pruning

CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation

MOSLIM:Align with diverse preferences in prompts through reward classification