6 citations · 14 across the 31 of their papers we have counts for
31 papers
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Team HY-World, Chenjie Cao, Xuhui Zuo +42
We introduce HY-World 2.0, a multi-modal world model framework that advances our prior project HY-World 1.0. HY-World 2.0 accommodates diverse input modalities, including text prom…
BiasIG: Benchmarking Multi-dimensional Social Biases in Text-to-Image Models
Hanjun Luo, Zhimu Huang, Haoyu Huang +5
Text-to-Image (T2I) generative models have revolutionized content creation, yet they inherently risk amplifying societal biases. While sociological research provides systematic cla…
Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation
Zhiting Fan, Ruizhe Chen, Tianxiang Hu +7
Large language models (LLMs) achieve strong downstream performance largely due to abundant supervised fine-tuning (SFT) data. However, high-quality SFT data in knowledge-intensive…
Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos
Songtao Jiang, Sibo Song, Chenyi Zhou +12
The transition from image to video understanding requires vision-language models (VLMs) to shift from recognizing static patterns to reasoning over temporal dynamics such as motion…
From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
Ruilin Luo, Chufan Shi, Yizhen Zhang +10
The cold-start initialization stage plays a pivotal role in training Multimodal Large Reasoning Models (MLRMs), yet its mechanisms remain insufficiently understood. To analyze this…
Towards Proactive Personalization through Profile Customization for Individual Users in Dialogues
Xiaotian Zhang, Yuan Wang, Ruizhe Chen +3
The deployment of Large Language Models (LLMs) in interactive systems necessitates a deep alignment with the nuanced and dynamic preferences of individual users. Current alignment…
GRIT: Graph-Regularized Logit Refinement for Zero-shot Cell Type Annotation
Tianxiang Hu, Chenyi Zhou, Jiaxiang Liu +6
Cell type annotation is a fundamental step in the analysis of single-cell RNA sequencing (scRNA-seq) data. In practice, human experts often rely on the structure revealed by princi…
Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning
Ruizhe Chen, Zhiting Fan, Tianze Luo +7
Video Temporal Grounding (VTG) aims to localize relevant temporal segments in videos given natural language queries. Despite recent progress with large vision-language models (LVLM…
Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learning
Xiaotian Zhang, Yuan Wang, Zhaopeng Feng +6
Medical Question-Answering (QA) encompasses a broad spectrum of tasks, including multiple choice questions (MCQ), open-ended text generation, and complex computational reasoning. D…
CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making
Songtao Jiang, Yuan Wang, Ruizhe Chen +8
In medical visual question answering (Med-VQA), achieving accurate responses relies on three critical steps: precise perception of medical imaging data, logical reasoning grounded…
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
Zhaopeng Feng, Shaosheng Cao, Jiahan Ren +7
Large-scale reinforcement learning (RL) methods have proven highly effective in enhancing the reasoning abilities of large language models (LLMs), particularly for tasks with verif…
BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models
Zhiting Fan, Ruizhe Chen, Zuozhu Liu
Identifying bias in LLM-generated content is a crucial prerequisite for ensuring fairness in LLMs. Existing methods, such as fairness classifiers and LLM-based judges, face limitat…
FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering
Yichen Li, Zhiting Fan, Ruizhe Chen +4
Large language models (LLMs) are prone to capturing biases from training corpus, leading to potential negative social impacts. Existing prompt-based debiasing methods exhibit insta…
Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment
Xiaotian Zhang, Ruizhe Chen, Yang Feng +1
Aligning language models with human preferences presents significant challenges, particularly in achieving personalization without incurring excessive computational costs. Existing…
DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models
Ruizhe Chen, Wenhao Chai, Zhifei Yang +5
Inference-time alignment provides an efficient alternative for aligning LLMs with humans. However, these approaches still face challenges, such as limited scalability due to policy…
Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level Alignment
Chengting Yu, Fengzhao Zhang, Ruizhe Chen +4
Knowledge Distillation (KD), a learning manner with a larger teacher network guiding a smaller student network, transfers dark knowledge from the teacher to the student via logits…
FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs
Zhiting Fan, Ruizhe Chen, Tianxiang Hu +1
The growing use of large language model (LLM)-based chatbots has raised concerns about fairness. Fairness issues in LLMs can lead to severe consequences, such as bias amplification…
Modality-Fair Preference Optimization for Trustworthy MLLM Alignment
Songtao Jiang, Yan Zhang, Ruizhe Chen +6
Multimodal large language models (MLLMs) have achieved remarkable success across various tasks. However, separate training of visual and textual encoders often results in a misalig…
PAD: Personalized Alignment of LLMs at Decoding-Time
Ruizhe Chen, Xiaotian Zhang, Meng Luo +2
Aligning with personalized preferences, which vary significantly across cultural, educational, and political differences, poses a significant challenge due to the computational cos…
DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition
Hanjun Luo, Yingbin Jin, Xinfeng Li +6
The advancements of Large Language Models (LLMs) have spurred a growing interest in their application to Named Entity Recognition (NER) methods. However, existing datasets are prim…
VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversary
Hanjun Luo, Ziye Deng, Haoyu Huang +3
With the rapid development of Text-to-Image (T2I) models, biases in human image generation against demographic social groups become a significant concern, impacting fairness and et…
Identifying and Mitigating Social Bias Knowledge in Language Models
Ruizhe Chen, Yichen Li, Jianfei Yang +3
Generating fair and accurate predictions plays a pivotal role in deploying large language models (LLMs) in the real world. However, existing debiasing methods inevitably generate u…
BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs
Zhiting Fan, Ruizhe Chen, Ruiling Xu +1
Evaluating the bias in Large Language Models (LLMs) becomes increasingly crucial with their rapid development. However, existing evaluation methods rely on fixed-form outputs and c…
BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Models
Hanjun Luo, Haoyu Huang, Ziye Deng +6
Text-to-Image (T2I) generative models are becoming increasingly crucial due to their ability to generate high-quality images, but also raise concerns about social biases, particula…