72 citations · 103 across the 53 of their papers we have counts for
61 papers
Budgeted KV-Cache Repair for Evolving Contexts
Han Yu, Wenhui Zhu, Jincheng Cao +15
Language-model agents revise their working context as information becomes obsolete, but deleting text does not erase its influence on cached computation. Later key-value (KV) state…
AvoKV-E: Payload-Aware KV Cache Eviction for Long Reasoning
Han Yu, Wenhui Zhu, Xiwen Chen +9
Long-output reasoning shifts the KV-cache bottleneck from the fixed prompt to the generated trace. Existing reasoning-cache eviction methods largely treat cached entries as routing…
Smaller Models, Better Rejects: Preference Distillation Scaling
Rui Cai, Wenhui Zhu, Xiwen Chen +15
Preference distillation typically treats a teacher response as preferred and the student's own response as rejected. This assumes that self-generated failures are the most informat…
Adaptive Safety Filtering for Frozen ACC Policies via Conformal Residual Calibration
Zhiruo Zhou, Rigaudiere Z. Li, Chen Xiwen +3
Frozen adaptive cruise control (ACC) policies can violate constraints when deployment dynamics differ from their training conditions. We propose residual-aware conformal action fil…
Think Only When Needed: Prompt-Authority Control for Selective Slow-Path Intervention in Vision-Language-Action Manipulation
Zhiruo Zhou, Zelin Li, Xiwen Chen +4
Retrieval can efficiently and effectively augment a frozen vision--language--action (VLA) policy without retraining, yet retrieved text becomes a control intervention once it enter…
Pointing-VLA: Typed Spatial Grounding Interfaces for Vision-Language-Action Manipulation
Xiwen Chen, Zelin Li, Zhiruo Zhou +3
Vision-language-action (VLA) models often expose spatial grounding through autoregressive text coordinates or opaque action tokens, creating brittle interfaces between multimodal r…
Does Your ViT Still Need U-Net for Segmentation?
Xin Li, Wenhui Zhu, Xuanzhao Dong +6
Medical image segmentation is dominated by U-Net-style encoder-decoder architectures. Vision Transformers (ViTs) overcome the limited receptive field of convolutional networks thro…
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…
OphIn-500K: Curating Web-Scale Visual Instructions for Scaling Ophthalmic Multimodal Large Language Models
Xuanzhao Dong, Wenhui Zhu, Xiwen Chen +13
The advancement of general medical Multimodal Large Language Models (MLLMs) has shown great potential for building conversational assistants to support clinical diagnosis. However,…
Closed-Loop Bidirectional Prompting for Adversarial Robustness of Vision Language Models
Xiao Liu, Jiaxiang Liu, Boci Peng +6
Vision Language Models adapt well to downstream tasks but are highly vulnerable to adversarial perturbations that disrupt cross-modal semantic alignment. Existing defenses are larg…
Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning
Jingjing Wang, Xiwen Chen, Wenhui Zhu +6
LLM-powered coding agents spend the majority of their token budget reading repository files, yet much of the retrieved code is irrelevant to the task at hand. Existing learned prun…
ModelLens: Finding the Best for Your Task from Myriads of Models
Rui Cai, Weijie Jacky Mo, Xiaofei Wen +5
The open-source model ecosystem now contains hundreds of thousands of pretrained models, yet picking the best model for a new dataset is increasingly infeasible: new models and unb…
SHARP: A Self-Evolving Human-Auditable Rubric Policy for Financial Trading Agents
Xiwen Chen, Wenhui Zhu, Songzhu Zheng +3
Large language models (LLMs) are increasingly deployed for autonomous financial trading, a domain requiring continuous adaptation to noisy, non-stationary markets. Existing self-im…
MedMamba: Recasting Mamba for Medical Time Series Classification
ZhengXiao He, Huayu Li, Xiwen Chen +4
Medical time series, such as electrocardiograms (ECG) and electroencephalograms (EEG), exhibit complex temporal dynamics and structured cross-channel dependencies, posing fundament…
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…
Bridging Restoration and Diagnosis: A Comprehensive Benchmark for Retinal Fundus Enhancement
Xuanzhao Dong, Wenhui Zhu, Xiwen Chen +8
Over the past decade, generative models have demonstrated success in enhancing fundus images. However, the evaluation of these models remains a challenge. A benchmark for fundus im…
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…
AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs
Brendan R. Hogan, Xiwen Chen, James T. Wilson +5
We present AlphaLab, an autonomous research harness that leverages frontier LLM agentic capabilities to automate the full experimental cycle in quantitative, computation-intensive…
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…
EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent
Hao Wang, Wenhui Zhu, Shao Tang +8
As a cornerstone of the modern digital economy, 3D modeling and rendering demand substantial resources and manual effort when scene editing is performed in the traditional manner.…
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…
VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement
Xuanzhao Dong, Wenhui Zhu, Yujian Xiong +8
Color fundus photography (CFP) is central to diagnosing and monitoring retinal disease, yet its acquisition variability (e.g., illumination changes) often degrades image quality, w…