2 citations · 2 across the 13 of their papers we have counts for
16 papers
VERA: Scaling Verifiable Environments for Agentic co-Evolution
Junqi Liu, Yongyang Pan, Zhuosong Jiang +14
Competent agents need precise and verifiable environments, such as sandboxes that are resumable at any stage and evolve from observable evidence. However, most long-horizon work ex…
Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models
Yahong Wang, Zhangkai Ni, Juncheng Wu +3
Multimodal large language models (MLLMs) incur substantial computational overhead due to the reliance on hundreds of visual tokens to represent images. While token pruning has emer…
BaT: Towards Self-Evolving Medical Research Agent with Stage Rubrics
Junqi Liu, Yufan He, Yexiao He +9
Long-horizon agents are beginning to automate complete workflows that produce code, reports, and research artifacts. Medical imaging workflows are multi-stage and data-sensitive, w…
VisualClaw: A Real-Time, Personalized Agent for the Physical World
Haoqin Tu, Jianwen Chen, Zijun Wang +14
Vision language models are serving as general-purpose interfaces for complex multimodal tasks. However, deployment still faces three gaps: VLMs typically incur high latency and cos…
AutoMedBench: Towards Medical AutoResearch with Agentic AI Models
Junqi Liu, Selena Song, Yuhan Wang +12
Autonomous agents are increasingly expected to support end-to-end medical-AI research workflows, moving beyond isolated prediction tasks or short-form clinical question answering.…
Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation
Ziyue Lin, Jiahe Hou, Hongyu Xia +6
We propose Decoupled Residual Denoising Diffusion models (DRDD) for unified and data-efficient image-to-image (I2I) translation. While diffusion models have advanced I2I translatio…
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
Minhua Lin, Juncheng Wu, Zijun Wang +14
LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing…
Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows
Hardy Chen, Nancy Lau, Haoqin Tu +8
Frontier coding agents are increasingly used in workflows where users supervise progress primarily through repeated improvement of a public score, namely the reported score on a pu…
EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models
Yahong Wang, Juncheng Wu, Zhangkai Ni +6
Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although token pruning has proven effective…
SCING:Towards More Efficient and Robust Person Re-Identification through Selective Cross-modal Prompt Tuning
Yunfei Xie, Yuxuan Cheng, Juncheng Wu +3
Recent advancements in adapting vision-language pre-training models like CLIP for person re-identification (ReID) tasks often rely on complex adapter design or modality-specific tu…
More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
Chengzhi Liu, Zhongxing Xu, Qingyue Wei +5
Test-time compute has empowered multimodal large language models to generate extended reasoning chains, yielding strong performance on tasks such as multimodal math reasoning. Howe…
MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning
Suhao Yu, Haojin Wang, Juncheng Wu +9
Real-world clinical practice demands multi-image comparative reasoning, yet current medical benchmarks remain limited to single-frame interpretation. We present MedFrameQA, the fir…
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
Juncheng Wu, Wenlong Deng, Xingxuan Li +12
Medical tasks such as diagnosis and treatment planning require precise and complex reasoning, particularly in life-critical domains. Unlike mathematical reasoning, medical reasonin…
Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization
Jiawei Mao, Xiaoke Huang, Yunfei Xie +7
This paper introduces Story-Iter, a new training-free iterative paradigm to enhance long-story generation. Unlike existing methods that rely on fixed reference images to construct…
Restorer: Removing Multi-Degradation with All-Axis Attention and Prompt Guidance
Jiawei Mao, Juncheng Wu, Yuyin Zhou +2
There are many excellent solutions in image restoration.However, most methods require on training separate models to restore images with different types of degradation.Although exi…
DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor
Juncheng Wu, Zhangkai Ni, Hanli Wang +3
Image deep features extracted by pre-trained networks are known to contain rich and informative representations. In this paper, we present Deep Degradation Response (DDR), a method…