Weihua Luo

Researcher@Alibaba International Digital Commerce Group·中国·OpenReview

研究方向

Multimodal Large Language Model · Multimodal large language model · large language model · language modeling · Machine Translation · machine translation · natural language processing

Weihua Luo

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

A State-Transition Framework for Efficient LLM Reasoning

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

MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoning

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

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

Multimodal Tabular Reasoning with Privileged Structured Information

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

Parrot: Multilingual Visual Instruction Tuning

Let the LLM Stick to Its Strengths: Learning to Route Economical LLM

Parrot: Multilingual Visual Instruction Tuning

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

M3GIA: A Cognition Inspired Multilingual and Multimodal General Intelligence Ability Benchmark

MOSLIM:Align with diverse preferences in prompts through reward classification