6 citations · 8 across the 24 of their papers we have counts for
15 papers · 1 filter
ReTrace: Cross-Stage Failure Attribution for Self-Improving Robotic Manipulation
Yue Yu, Bin Zhu, Junhui Li +3
General-purpose multimodal foundation models are increasingly capable of directly controlling robots, yet improving their manipulation capabilities through autonomous interaction r…
VideoResearchAgent: Grounded Task Synthesis and Sim-to-Real RL for Open-Web Video Research
Yuhang Zhou, Fei Li, Yuxi Wu +2
Existing deep research agents are designed primarily for text- and image-based web sources, while video reasoning systems typically assume that relevant videos are provided in adva…
LIBERO-VPro: Benchmarking Closed-Loop Visual Robustness of Robotic Foundation Models
Huiqiong Li, Zhiting Mei, Anirudha Majumdar +3
Robotic foundation models achieve impressive performance on standard manipulation benchmarks, yet these evaluations typically assume clean, timely, and consistent visual observatio…
Stable and Efficient Real-World Online VLA Post-Training via Asynchronous Replay-Anchored Policy Improvement
Jiarui Yang, Jiajin Zhang, Bin Zhu +2
Online post-training of vision-language-action (VLA) models requires efficient use of robot interaction and reliable policy improvement from continually collected experience. We pr…
MoWAM: Explicit Future Motion Prediction for Efficient World Action Models
Jiayu Wang, Bin Zhu, Yue Yu +1
World Action Models (WAMs) improve robot policy learning by incorporating future dynamics, yet explicitly generating future videos at inference introduces substantial computational…
VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition
Jiangang Zhu, Zheng Wang, Bin Zhu +2
Multi-expert models have become the dominant paradigm for long-tailed learning, largely attributed to their presumed ability to benefit from expert diversity. However, we revisit t…
StructRL: Structured Action-Space Exploration for Flow-Based VLAs
Jiarui Yang, Bin Zhu, Jingjing Chen +4
Flow-based Vision-Language-Action (VLA) models are now widely used for continuous robotic manipulation, and online reinforcement learning (RL) is emerging as a key technique for ad…
ReGraph: Learning to Generate Recipe Graphs from Food Images
Guoshan Liu, Bin Zhu, Pengkun Jiao +3
Recent Large Multimodal Models (LMMs) have achieved impressive performance in recipe generation from food images.However, cooking is a structured transformation process in which in…
Disentangling Semantic Attention from Structural Bias in the Attention Manifold
Pengkun Jiao, Bin Zhu, Jingjing Chen +1
The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws. Specifically, MLLMs consistently exhibit disprop…
Spatiotemporal Sycophancy: Negation-Based Gaslighting in Video Large Language Models
Ziyao Tang, Pengkun Jiao, Bin Zhu +3
Video Large Language Models (Vid-LLMs) have demonstrated remarkable performance in video understanding tasks, yet their robustness under conversational interaction remains largely…
SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning
Yian Li, Yang Jiao, Bin Zhu +4
Spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, remains a core challenge for multimodal large language…
OSCBench: Benchmarking Object State Change in Text-to-Video Generation
Xianjing Han, Bin Zhu, Shiqi Hu +4
Text-to-video (T2V) generation models have made rapid progress in producing visually high-quality and temporally coherent videos. However, existing benchmarks primarily focus on pe…
RC-NF: Robot-Conditioned Normalizing Flow for Real-Time Anomaly Detection in Robotic Manipulation
Shijie Zhou, Bin Zhu, Jiarui Yang +3
Recent advances in Vision-Language-Action (VLA) models have enabled robots to execute increasingly complex tasks. However, VLA models trained through imitation learning struggle to…
Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration
Ninghao Zhang, Bin Zhu, Shijie Zhou +1
Vision-Language-Action (VLA) models enable robots to perform manipulation tasks directly from natural language instructions and are increasingly viewed as a foundation for generali…
Enhancing Action and Ingredient Modeling for Semantically Grounded Recipe Generation
Guoshan Liu, Bin Zhu, Yian Li +3
Recent advances in Multimodal Large Language Models (MLMMs) have enabled recipe generation from food images, yet outputs often contain semantically incorrect actions or ingredients…