3 citations · 11 across the 32 of their papers we have counts for
37 papers
LadderEdit: Edit-Level Residual Compression for Memory-Efficient Lifelong Editing of LLMs
Xiaobing Yu, Peijie Qiu, Jin Yang +5
Lifelong editing of LLMs requires storing thousands of edits after acquisition. A widely used family of approaches attaches one LoRA adapter per edit, which preserves behavior but…
ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis
Weiwei Ma, Xiaobing Yu, Peijie Qiu +5
Clinical diagnosis is inherently sequential: clinicians escalate from cheap to costly tests only when additional evidence is expected to resolve diagnostic uncertainty. We present…
TEFM: Token-Efficient Faithful Modeling for Structured Data
Zhichao Hou, Lingdao Sha, Xueyu Mao +3
In this paper, we solve two fundamental obstacles in applying LLMs to critical domains: token efficiency and faithfulness. To address both constraints jointly, we present TEFM (Tok…
S-SPPO: Semantic-Calibrated Self-Play Preference Optimization
Xiwen Chen, Wenhui Zhu, Jingjing Wang +13
Aligning Large Language Models (LLMs) with human preferences is often formulated via Direct Preference Optimization (DPO). However, the standard Bradley-Terry instantiation of DPO…
Mags-RL: Wearing Multimodal LLMs a Magnifying Glass via Agentic Reinforcement Learning For Complex Scene Reasoning
Xuanzhao Dong, Wenhui Zhu, Peijie Qiu +11
Despite their popularity and success, Multimodal Large Language Models (MLLMs) often struggle to interpret images accurately, which limits their reasoning capability in complex sce…
Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs
Wenhui Zhu, Xuanzhao Dong, Xiwen Chen +7
The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled pri…
SODA: Semi On-Policy Black-Box Distillation for Large Language Models
Xiwen Chen, Jingjing Wang, Wenhui Zhu +7
Black-box knowledge distillation for large language models presents a strict trade-off. Simple off-policy methods (e.g., sequence-level knowledge distillation) struggle to correct…
OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport
Xiwen Chen, Wenhui Zhu, Gen Li +9
Multi-modal large language models (MLLMs) achieve strong visual-language reasoning but suffer from high inference cost due to redundant visual tokens. Recent work explores visual t…
ImageRAGTurbo: Towards One-step Text-to-Image Generation with Retrieval-Augmented Diffusion Models
Peijie Qiu, Hariharan Ramshankar, Arnau Ramisa +4
Diffusion models have emerged as the leading approach for text-to-image generation. However, their iterative sampling process, which gradually morphs random noise into coherent ima…
AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents
Wenhui Zhu, Xiwen Chen, Zhipeng Wang +11
Long-horizon LLM agents require memory systems that remain accurate under fixed context budgets. However, existing systems struggle with two persistent challenges in long-term dial…
AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives
Yanxi Chen, Wenhui Zhu, Xiwen Chen +9
Although Large Audio-Language Models (LALMs) deliver state-of-the-art (SOTA) performance, they frequently suffer from hallucinations, e.g. generating text not grounded in the audio…
LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding
Xuanzhao Dong, Wenhui Zhu, Xiwen Chen +5
Autoregressive models (ARMs) have long dominated the landscape of biomedical vision-language models (VLMs). Recently, masked diffusion models such as LLaDA have emerged as promisin…
Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysis
Xiwen Chen, Peijie Qiu, Wenhui Zhu +8
While multiple instance learning (MIL) has shown to be a promising approach for histopathological whole slide image (WSI) analysis, its reliance on permutation invariance significa…
Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
Wenhui Zhu, Xuanzhao Dong, Xin Li +6
Recently, reinforcement learning (RL)-based tuning has shifted the trajectory of Multimodal Large Language Models (MLLMs), particularly following the introduction of Group Relative…
How Effective Can Dropout Be in Multiple Instance Learning ?
Wenhui Zhu, Peijie Qiu, Xiwen Chen +4
Multiple Instance Learning (MIL) is a popular weakly-supervised method for various applications, with a particular interest in histological whole slide image (WSI) classification.…
FIC-TSC: Learning Time Series Classification with Fisher Information Constraint
Xiwen Chen, Wenhui Zhu, Peijie Qiu +6
Analyzing time series data is crucial to a wide spectrum of applications, including economics, online marketplaces, and human healthcare. In particular, time series classification…
DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning
Xiwen Chen, Wenhui Zhu, Peijie Qiu +7
Post-training LLMs with Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), has emerged as a paradigm for enhancing mathematical reasoning. However, sta…
Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA
Xuanzhao Dong, Wenhui Zhu, Hao Wang +5
Medical question answering (QA) is a reasoning-intensive task that remains challenging for large language models (LLMs) due to hallucinations and outdated domain knowledge. Retriev…
A BERT-Style Self-Supervised Learning CNN for Disease Identification from Retinal Images
Xin Li, Wenhui Zhu, Peijie Qiu +3
In the field of medical imaging, the advent of deep learning, especially the application of convolutional neural networks (CNNs) has revolutionized the analysis and interpretation…
RetinalGPT: A Retinal Clinical Preference Conversational Assistant Powered by Large Vision-Language Models
Wenhui Zhu, Xin Li, Xiwen Chen +8
Recently, Multimodal Large Language Models (MLLMs) have gained significant attention for their remarkable ability to process and analyze non-textual data, such as images, videos, a…
Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation
Xiwen Chen, Wenhui Zhu, Peijie Qiu +6
Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks. Prompt learning has emerged as an efficient and effective s…
EyeBench: A Call for More Rigorous Evaluation of Retinal Image Enhancement
Wenhui Zhu, Xuanzhao Dong, Xin Li +8
Over the past decade, generative models have achieved significant success in enhancement fundus images.However, the evaluation of these models still presents a considerable challen…
Sequence Complementor: Complementing Transformers For Time Series Forecasting with Learnable Sequences
Xiwen Chen, Peijie Qiu, Wenhui Zhu +5
Since its introduction, the transformer has shifted the development trajectory away from traditional models (e.g., RNN, MLP) in time series forecasting, which is attributed to its…
Many-MobileNet: Multi-Model Augmentation for Robust Retinal Disease Classification
Hao Wang, Wenhui Zhu, Xuanzhao Dong +9
In this work, we propose Many-MobileNet, an efficient model fusion strategy for retinal disease classification using lightweight CNN architecture. Our method addresses key challeng…