6 citations · 8 across the 24 of their papers we have counts for
29 papers
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…
Dual-LoRA and Quality-Enhanced Pseudo Replay for Multimodal Continual Food Learning
Xinlan Wu, Bin Zhu, Feng Han +2
Food analysis has become increasingly critical for health-related tasks such as personalized nutrition and chronic disease prevention. However, existing large multimodal models (LM…
Efficient Test-Time Retrieval Augmented Generation
Hailong Yin, Bin Zhu, Jingjing Chen +1
Although Large Language Models (LLMs) demonstrate significant capabilities, their reliance on parametric knowledge often leads to inaccuracies. Retrieval Augmented Generation (RAG)…
Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward
Jiarui Yang, Bin Zhu, Jingjing Chen +1
Existing reinforcement learning (RL) methods struggle with long-horizon robotic manipulation tasks, particularly those involving sparse rewards. While action chunking is a promisin…
Benchmarking Gaslighting Negation Attacks Against Reasoning Models
Bin Zhu, Hailong Yin, Jingjing Chen +1
Recent advances in reasoning-centric models promise improved robustness through mechanisms such as chain-of-thought prompting and test-time scaling. However, their ability to withs…
Advancing Food Nutrition Estimation via Visual-Ingredient Feature Fusion
Huiyan Qi, Bin Zhu, Chong-Wah Ngo +2
Nutrition estimation is an important component of promoting healthy eating and mitigating diet-related health risks. Despite advances in tasks such as food classification and ingre…
Efficient Prompt Tuning for Hierarchical Ingredient Recognition
Yinxuan Gui, Bin Zhu, Jingjing Chen +1
Fine-grained ingredient recognition presents a significant challenge due to the diverse appearances of ingredients, resulting from different cutting and cooking methods. While exis…
Don't Deceive Me: Mitigating Gaslighting through Attention Reallocation in LMMs
Pengkun Jiao, Bin Zhu, Jingjing Chen +2
Large Multimodal Models (LMMs) have demonstrated remarkable capabilities across a wide range of tasks. However, their vulnerability to user gaslighting-the deliberate use of mislea…
Benchmarking Gaslighting Negation Attacks Against Multimodal Large Language Models
Bin Zhu, Yinxuan Gui, Huiyan Qi +3
Multimodal Large Language Models (MLLMs) have exhibited remarkable advancements in integrating different modalities, excelling in complex understanding and generation tasks. Despit…
Retrieval Augmented Recipe Generation
Guoshan Liu, Hailong Yin, Bin Zhu +3
Given the potential applications of generating recipes from food images, this area has garnered significant attention from researchers in recent years. Existing works for recipe ge…