55 citations · 264 across the 40 of their papers we have counts for
42 papers
VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness
Zihao Lin, Haoyu Dong, Haobo Xu +10
LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reasoning, and memory. Recursive h…
Knowing When to Trust Images: Reliability-Aware Multi-modal Entity Alignment
Chenxiao Li, Yunhe Feng, Dongfang Liu +3
The visual modality, i.e., images, plays a key role in multi-modal entity alignment (MMEA). Existing approaches often directly fuse the image with other modalities to align differe…
VLA-Scope: Shift-Aware Failure Prediction for Vision-Language-Action Models
Kaiwen Zhu, Dongfang Liu, Liangkai Liu
Vision-language-action (VLA) models map visual observations and natural-language instructions to robotic actions, but distribution shifts can compromise their reliability. Because…
Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion Prediction
Xiang Zhang, Varchas Gopalaswamy, Rahman Ejaz +2
Inertial confinement fusion (ICF) is a leading pathway toward clean energy, but each shot at the National Ignition Facility costs on the order of one million dollars, making accura…
HIVE: Understanding Post-Hallucination Reasoning in Vision Language Models
Feng He, Zhenting Wang, Qifan Wang +4
Hallucinations in vision language models (VLMs) are commonly treated as semantic errors, yet they often arise from partial or ambiguous visual evidence. Prior work mainly focuses o…
AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
Boxuan Zhang, Jianing Zhu, Zeru Shi +2
LLM-based multi-agent systems are increasingly deployed on long-horizon tasks, but a single decisive error is often accepted by downstream agents and cascades into trajectory-level…
Personalize Your Large Vision-language Models With In-context Prompt Tuning
Yanshu Li, Jiaqian Li, Kuai Yu +4
Large vision-language models (LVLMs) have demonstrated strong general multimodal capability and are increasingly deployed in downstream systems. This trend has driven growing inter…
Radiance Field Learners As UAV First-Person Viewers
Liqi Yan, Qifan Wang, Junhan Zhao +4
First-Person-View (FPV) holds immense potential for revolutionizing the trajectory of Unmanned Aerial Vehicles (UAVs), offering an exhilarating avenue for navigating complex buildi…
Visual Agents as Fast and Slow Thinkers
Guangyan Sun, Mingyu Jin, Zhenting Wang +7
Achieving human-level intelligence requires refining cognitive distinctions between System 1 and System 2 thinking. While contemporary AI, driven by large language models, demonstr…
Diff-PIC: Revolutionizing Particle-In-Cell Nuclear Fusion Simulation with Diffusion Models
Chuan Liu, Chunshu Wu, Shihui Cao +8
The rapid development of AI highlights the pressing need for sustainable energy, a critical global challenge for decades. Nuclear fusion, generally seen as an ultimate solution, ha…
AMD: Automatic Multi-step Distillation of Large-scale Vision Models
Cheng Han, Qifan Wang, Sohail A. Dianat +6
Transformer-based architectures have become the de-facto standard models for diverse vision tasks owing to their superior performance. As the size of the models continues to scale…
Inertial Confinement Fusion Forecasting via Large Language Models
Mingkai Chen, Taowen Wang, Shihui Cao +10
Controlled fusion energy is deemed pivotal for the advancement of human civilization. In this study, we introduce , a novel integration of Large Language Models (…
EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction
Li Yang, Qifan Wang, Jianfeng Chi +7
Product attribute value extraction involves identifying the specific values associated with various attributes from a product profile. While existing methods often prioritize the d…
Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks
Zhiyuan Cheng, Cheng Han, James Liang +3
Monocular Depth Estimation (MDE) plays a vital role in applications such as autonomous driving. However, various attacks target MDE models, with physical attacks posing significant…
ProMotion: Prototypes As Motion Learners
Yawen Lu, Dongfang Liu, Qifan Wang +6
In this work, we introduce ProMotion, a unified prototypical framework engineered to model fundamental motion tasks. ProMotion offers a range of compelling attributes that set it a…
Prototypical Transformer as Unified Motion Learners
Cheng Han, Yawen Lu, Guohao Sun +9
In this work, we introduce the Prototypical Transformer (ProtoFormer), a general and unified framework that approaches various motion tasks from a prototype perspective. ProtoForme…
SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Driving
Yiming Cui, Cheng Han, Dongfang Liu
Visual-based perception is the key module for autonomous driving. Among those visual perception tasks, video object detection is a primary yet challenging one because of feature de…
BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
Zhiyuan Cheng, Zhaoyi Liu, Tengda Guo +4
Pixel-wise regression tasks (e.g., monocular depth estimation (MDE) and optical flow estimation (OFE)) have been widely involved in our daily life in applications like autonomous d…
Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval
Jiamian Wang, Guohao Sun, Pichao Wang +5
The increasing prevalence of video clips has sparked growing interest in text-video retrieval. Recent advances focus on establishing a joint embedding space for text and video, rel…
Image Translation as Diffusion Visual Programmers
Cheng Han, James C. Liang, Qifan Wang +5
We introduce the novel Diffusion Visual Programmer (DVP), a neuro-symbolic image translation framework. Our proposed DVP seamlessly embeds a condition-flexible diffusion model with…
Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?
Cheng Han, Qifan Wang, Yiming Cui +4
As the scale of vision models continues to grow, the emergence of Visual Prompt Tuning (VPT) as a parameter-efficient transfer learning technique has gained attention due to its su…
Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning
Shaohua Dong, Yunhe Feng, Qing Yang +3
Multimodal (e.g., RGB-Depth/RGB-Thermal) fusion has shown great potential for improving semantic segmentation in complex scenes (e.g., indoor/low-light conditions). Existing approa…
CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation
Yiming Cui, Cheng Han, Dongfang Liu
The advancement of computer vision has pushed visual analysis tasks from still images to the video domain. In recent years, video instance segmentation, which aims to track and seg…
ClusterFormer: Clustering As A Universal Visual Learner
James C. Liang, Yiming Cui, Qifan Wang +3
This paper presents CLUSTERFORMER, a universal vision model that is based on the CLUSTERing paradigm with TransFORMER. It comprises two novel designs: 1. recurrent cross-attention…