2 citations · 7 across the 21 of their papers we have counts for
22 papers
Remember by Asking: Retrieval-Induced Memory Evolution for LLM Agents
Wanqi Zhou, Jiawei Lu, Yang Wang +4
Long-term memory is essential for language agents to maintain coherent and effective behavior over extended, multi-session interactions. Existing memory systems mainly use retrieva…
GraphIR: Architecture-Level Search States for LLM-Guided Neural Architecture Evolution
Zhen Liu, Wanqi Zhou, Shuanghao Bai +3
Large language models (LLMs) enable neural architecture search (NAS) directly over executable neural network programs. However, code-level flexibility does not provide the architec…
ToolAnchor: Anchoring Counterfactual Context to Boost Agentic Tool-use Capability
Weiting Liu, Jieyi Bi, Wanqi Zhou +4
Tool-augmented large language model agents excel at long-horizon tasks, yet they are typically post-trained on fixed toolsets. When tasks demand new tools, these agents struggle to…
Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction
Jiafu Huang, Chao Peng, Chenyang Xu +7
Neural algorithmic reasoning has emerged as a popular research direction. It aims to train neural networks to mimic the step-by-step behavior of classical rule-based algorithms. Mo…
HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation
Shuanghao Bai, Meng Li, Xinyuan Lv +15
Humans achieve complex manipulation through coordinated whole-body control, whereas most Vision-Language-Action (VLA) models treat robot body parts largely independently, making hi…
Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning
Hao Zhou, Tiru Wu, Yan Jiang +3
Multi-modal multi-agent systems (MM-MAS) have gained increasing attention for their capacity to enable complex reasoning and coordination across diverse modalities. As these system…
Assistance Without Interruption: A Benchmark and LLM-based Framework for Non-Intrusive Human-Robot Assistance
Yuedi Zhang, Shuanghao Bai, Wanqi Zhou +4
Human-robot interaction (HRI) has long studied how agents and people coordinate to achieve shared goals. In this work, we formalize and benchmark the non-intrusive assistance as an…
Reshaping Action Error Distributions for Reliable Vision-Language-Action Models
Shuanghao Bai, Dakai Wang, Cheng Chi +8
In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies. Most existing VLA framewor…
Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
Shuanghao Bai, Jing Lyu, Wanqi Zhou +9
Vision-Language-Action (VLA) models benefit from chain-of-thought (CoT) reasoning, but existing approaches incur high inference overhead and rely on discrete reasoning representati…
Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives
Shuanghao Bai, Wenxuan Song, Jiayi Chen +14
Recent advances in vision, language, and multimodal learning have significantly accelerated progress in robotic foundation models, with robotic manipulation remaining one of the mo…
VCoT-Grasp: Grasp Foundation Models with Visual Chain-of-Thought Reasoning for Language-driven Grasp Generation
Haoran Zhang, Shuanghao Bai, Wanqi Zhou +6
Robotic grasping is one of the most fundamental tasks in robotic manipulation, and grasp detection/generation has long been the subject of extensive research. Recently, language-dr…
Towards a Unified Understanding of Robot Manipulation: A Comprehensive Survey
Shuanghao Bai, Wenxuan Song, Jiayi Chen +15
Embodied intelligence has witnessed remarkable progress in recent years, driven by advances in computer vision, natural language processing, and the rise of large-scale multimodal…
NaviAgent: Graph-Driven Bilevel Planning for Scalable Tool Orchestration
Yan Jiang, Hao Zhou, Lizhong GU +4
Large Language Models (LLMs) increasingly act as function-call agents that invoke external tools to tackle tasks beyond their static knowledge. However, they typically invoke tools…
Dual-Path Stable Soft Prompt Generation for Domain Generalization
Yuedi Zhang, Shuanghao Bai, Wanqi Zhou +2
Domain generalization (DG) aims to learn a model using data from one or multiple related but distinct source domains that can generalize well to unseen out-of-distribution target d…
OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation
Can Cui, Pengxiang Ding, Wenxuan Song +10
Dual-system VLA (Vision-Language-Action) architectures have become a hot topic in embodied intelligence research, but there is a lack of sufficient open-source work for further per…
Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation
Shuanghao Bai, Wanqi Zhou, Pengxiang Ding +3
Behavior Cloning (BC) is a widely adopted visual imitation learning method in robot manipulation. Current BC approaches often enhance generalization by leveraging large datasets an…
PromptTA: Prompt-driven Text Adapter for Source-free Domain Generalization
Haoran Zhang, Shuanghao Bai, Wanqi Zhou +2
Source-free domain generalization (SFDG) tackles the challenge of adapting models to unseen target domains without access to source domain data. To deal with this challenging task,…
Jacobian Regularizer-based Neural Granger Causality
Wanqi Zhou, Shuanghao Bai, Shujian Yu +2
With the advancement of neural networks, diverse methods for neural Granger causality have emerged, which demonstrate proficiency in handling complex data, and nonlinear relationsh…
Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective
Wanqi Zhou, Shuanghao Bai, Danilo P. Mandic +2
Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversaria…
Soft Prompt Generation for Domain Generalization
Shuanghao Bai, Yuedi Zhang, Wanqi Zhou +2
Large pre-trained vision language models (VLMs) have shown impressive zero-shot ability on downstream tasks with manually designed prompt. To further adapt VLMs to downstream tasks…
Prompt-based Distribution Alignment for Unsupervised Domain Adaptation
Shuanghao Bai, Min Zhang, Wanqi Zhou +4
Recently, despite the unprecedented success of large pre-trained visual-language models (VLMs) on a wide range of downstream tasks, the real-world unsupervised domain adaptation (U…
Improving Cross-domain Few-shot Classification with Multilayer Perceptron
Shuanghao Bai, Wanqi Zhou, Zhirong Luan +2
Cross-domain few-shot classification (CDFSC) is a challenging and tough task due to the significant distribution discrepancies across different domains. To address this challenge,…