128 citations · 724 across the 72 of their papers we have counts for
77 papers
RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models
Yuhan Chen, Ke Yu, Pengfei Liu +3
Flow-based vision-language-action (VLA) models are highly effective for generalist robot manipulation, yet their reliance on computationally expensive VLM encoding and multi-step i…
3DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization
Yuze Hao, Linchao Zhu, Yi Yang
Inverse design aims to design the input variables of a physical system to optimize a specified objective function, typically formulated as a search or optimization problem. However…
FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
Yunzhu Zhang, Yu Lu, Tianyi Wang +3
Long-form video understanding poses a significant challenge for video large language models (VideoLLMs) due to prohibitively high computational and memory demands. In this paper, w…
Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection
Yucheng Suo, Fan Ma, Kaixin Shen +2
Visual instructions for long-horizon tasks are crucial as they intuitively clarify complex concepts and enhance retention across extended steps. Directly generating a series of ima…
Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data
Shuai Zhao, Yunqiu Xu, Linchao Zhu +1
Large language models~(LLMs) are expected to be helpful, harmless, and honest. In different alignment scenarios, such as safety, confidence, and general preference alignment, binar…
From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment
Yucheng Suo, Fan Ma, Linchao Zhu +3
Multi-modal Large language models (MLLMs) show remarkable ability in video understanding. Nevertheless, understanding long videos remains challenging as the models can only process…
VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing
Xiangpeng Yang, Linchao Zhu, Hehe Fan +1
Recent advancements in diffusion models have significantly improved video generation and editing capabilities. However, multi-grained video editing, which encompasses class-level,…
Noise-Tolerant Hybrid Prototypical Learning with Noisy Web Data
Chao Liang, Linchao Zhu, Zongxin Yang +2
We focus on the challenging problem of learning an unbiased classifier from a large number of potentially relevant but noisily labeled web images given only a few clean labeled ima…
MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs
Yunqiu Xu, Linchao Zhu, Yi Yang
While multimodal large language models (MLLMs) have demonstrated extraordinary vision-language understanding capabilities, their abilities to solve instance-level visual-language p…
Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space
Xihang Yue, Yi Yang, Linchao Zhu
Recent advances in operator learning have produced two distinct approaches for solving partial differential equations (PDEs): attention-based methods offering point-level adaptabil…
FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention
Yu Lu, Yuanzhi Liang, Linchao Zhu +1
Video diffusion models have made substantial progress in various video generation applications. However, training models for long video generation tasks require significant computa…
VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft
Yubo Dong, Xukun Zhu, Zhengzhe Pan +2
In this paper, we aim to evaluate multi-agent systems against complex dependencies, including spatial, causal, and temporal constraints. First, we construct a new benchmark, named…
FragRel: Exploiting Fragment-level Relations in the External Memory of Large Language Models
Xihang Yue, Linchao Zhu, Yi Yang
To process contexts with unlimited length using Large Language Models (LLMs), recent studies explore hierarchically managing the long text. Only several text fragments are taken fr…
DeltaPhi: Physical States Residual Learning for Neural Operators in Data-Limited PDE Solving
Xihang Yue, Yi Yang, Linchao Zhu
The limited availability of high-quality training data poses a major obstacle in data-driven PDE solving, where expensive data collection and resolution constraints severely impact…
AudioScenic: Audio-Driven Video Scene Editing
Kaixin Shen, Ruijie Quan, Linchao Zhu +2
Audio-driven visual scene editing endeavors to manipulate the visual background while leaving the foreground content unchanged, according to the given audio signals. Unlike current…
Neural Interaction Energy for Multi-Agent Trajectory Prediction
Kaixin Shen, Ruijie Quan, Linchao Zhu +2
Maintaining temporal stability is crucial in multi-agent trajectory prediction. Insufficient regularization to uphold this stability often results in fluctuations in kinematic stat…
EVA: Zero-shot Accurate Attributes and Multi-Object Video Editing
Xiangpeng Yang, Linchao Zhu, Hehe Fan +1
Current diffusion-based video editing primarily focuses on local editing (\textit{e.g.,} object/background editing) or global style editing by utilizing various dense correspondenc…
Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval
Yucheng Suo, Fan Ma, Linchao Zhu +1
We study the zero-shot Composed Image Retrieval (ZS-CIR) task, which is to retrieve the target image given a reference image and a description without training on the triplet datas…
Protecting Copyrighted Material with Unique Identifiers in Large Language Model Training
Shuai Zhao, Linchao Zhu, Ruijie Quan +1
A primary concern regarding training large language models (LLMs) is whether they abuse copyrighted online text. With the increasing training data scale and the prevalence of LLMs…
CapHuman: Capture Your Moments in Parallel Universes
Chao Liang, Fan Ma, Linchao Zhu +2
We concentrate on a novel human-centric image synthesis task, that is, given only one reference facial photograph, it is expected to generate specific individual images with divers…
DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval
Xiangpeng Yang, Linchao Zhu, Xiaohan Wang +1
Text-video retrieval is a critical multi-modal task to find the most relevant video for a text query. Although pretrained models like CLIP have demonstrated impressive potential in…
AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agents
Yuanzhi Liang, Linchao Zhu, Yi Yang
Large Language Models (LLMs) have demonstrated their ability to replicate human behaviors across a wide range of scenarios. However, their capability in handling complex, multi-cha…
FlowZero: Zero-Shot Text-to-Video Synthesis with LLM-Driven Dynamic Scene Syntax
Yu Lu, Linchao Zhu, Hehe Fan +1
Text-to-video (T2V) generation is a rapidly growing research area that aims to translate the scenes, objects, and actions within complex video text into a sequence of coherent visu…
Text Augmented Spatial-aware Zero-shot Referring Image Segmentation
Yucheng Suo, Linchao Zhu, Yi Yang
In this paper, we study a challenging task of zero-shot referring image segmentation. This task aims to identify the instance mask that is most related to a referring expression wi…