2 citations · 3 across the 16 of their papers we have counts for
19 papers
Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System
Zixuan Wang, Jia-Ning Li, Yinzhou Tang +5
Recent vision-language-action (VLA) models have shown strong performance on local robot manipulation, yet their success does not readily translate to long-horizon mobile manipulati…
MARS: Systematic Multi-Level Acceleration for World Action Models
Zengyuan Zuo, Yongchang Zhang, Guangyu Zhao +4
World Action Models (WAMs) have emerged as a promising alternative for embodied intelligence by jointly predicting future world states and robot actions. However, their heavy visua…
Scaling GUI Agents with Visual State Transitions
Xiangyan Liu, Kaixin Li, Haonan Wang +6
We introduce State Transition Pretraining (STP) as a new scaling axis for GUI agents. During the STP stage, we continually pretrain a unified multimodal model on visual state trans…
I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications
Dasen Dai, Biao Wu, Meng Fang +2
Recent advances in visual language models have enabled autonomous agents for complex reasoning, tool use, and document understanding. However, existing document agents mainly trans…
DOSE: Data Selection for Multi-Modal LLMs via Off-the-Shelf Models
Biao Wu, Yiwu Zhong, Meng Fang +1
High-quality and diverse multimodal data are essential for improving vision-language models (VLMs), yet existing datasets often contain noisy, redundant, and poorly aligned samples…
PaperVoyager : Building Interactive Web with Visual Language Models
Dasen Dai, Biao Wu, Meng Fang +1
Recent advances in visual language models have enabled autonomous agents for complex reasoning, tool use, and document understanding. However, existing document agents mainly trans…
Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing
Baode Wang, Biao Wu, Weizhen Li +8
Document parsing from scanned images into structured formats remains a significant challenge due to its complexly intertwined elements such as text paragraphs, figures, formulas, a…
UniVid: The Open-Source Unified Video Model
Jiabin Luo, Junhui Lin, Zeyu Zhang +4
Unified video modeling that combines generation and understanding capabilities is increasingly important but faces two key challenges: maintaining semantic faithfulness during flow…
Automotive-ENV: Benchmarking Multimodal Models in Automotive Cockpit Environments
Junfeng Yan, Biao Wu, Meng Fang +1
Multimodal models have demonstrated strong capabilities in web, desktop, and mobile GUI environments, but their performance in automotive cockpit systems remains largely unexplored…
VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery
Jinchao Ge, Tengfei Cheng, Biao Wu +7
Understanding cultural heritage artifacts such as ancient Greek pottery requires expert-level reasoning that remains challenging for current MLLMs due to limited domain-specific da…
WebArxiv: A Reproducible Benchmark for Evaluating Multimodal Web Agents on arXiv Tasks
Zihao Sun, Ling Chen, Zijing Shi
Foundation models now enable autonomous agents to interact with real-world websites, but existing benchmarks emphasize general-purpose browsing, underrepresent research-oriented en…
PresentAgent: Multimodal Agent for Presentation Video Generation
Jingwei Shi, Zeyu Zhang, Biao Wu +4
We present PresentAgent, a multimodal agent that transforms long-form documents into narrated presentation videos. While existing approaches are limited to generating static slides…
Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing
Baode Wang, Biao Wu, Weizhen Li +8
Automated parsing of scanned documents into richly structured, machine-readable formats remains a critical bottleneck in Document AI, as traditional multi-stage pipelines suffer fr…
Enhancing Temporal Sensitivity and Reasoning for Time-Sensitive Question Answering
Wanqi Yang, Yanda Li, Meng Fang +1
Time-Sensitive Question Answering (TSQA) demands the effective utilization of specific temporal contexts, encompassing multiple time-evolving facts, to address time-sensitive quest…
Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motion
Zeyu Zhang, Yiran Wang, Biao Wu +7
In recent years, there has been significant interest in creating 3D avatars and motions, driven by their diverse applications in areas like film-making, video games, AR/VR, and hum…
RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering
Zihan Zhang, Meng Fang, Ling Chen
Adaptive retrieval-augmented generation (ARAG) aims to dynamically determine the necessity of retrieval for queries instead of retrieving indiscriminately to enhance the efficiency…
Turn-Level Active Learning for Dialogue State Tracking
Zihan Zhang, Meng Fang, Fanghua Ye +2
Dialogue state tracking (DST) plays an important role in task-oriented dialogue systems. However, collecting a large amount of turn-by-turn annotated dialogue data is costly and in…
CITB: A Benchmark for Continual Instruction Tuning
Zihan Zhang, Meng Fang, Ling Chen +1
Continual learning (CL) is a paradigm that aims to replicate the human ability to learn and accumulate knowledge continually without forgetting previous knowledge and transferring…
How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances
Zihan Zhang, Meng Fang, Ling Chen +2
Although large language models (LLMs) are impressive in solving various tasks, they can quickly be outdated after deployment. Maintaining their up-to-date status is a pressing conc…