676 citations · 1.5k across the 36 of their papers we have counts for
37 papers
Agentic Designer: Progressive Multi-Agent Collaboration for Structure-Aware Interior Layout Generation
Zhijing Yang, Haocheng Lin, Zhihua Xu +4
Generating realistic interior furniture layouts that strictly adhere to architectural constraints (e.g., walls, doors, and windows) remains a fundamental challenge in automated spa…
TAG: Target-Agnostic Guidance for Stable Object-Centric Inference in Vision-Language-Action Models
Jiaying Zhou, Zhihao Zhan, Ruifeng Zhai +5
Vision--Language--Action (VLA) policies have shown strong progress in mapping language instructions and visual observations to robotic actions, yet their reliability degrades in cl…
Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention
Haijing Liu, Zhiyuan Song, Hefeng Wu +3
Egocentric Referring Video Object Segmentation (Ego-RVOS) aims to segment the specific object actively involved in a human action, as described by a language query, within first-pe…
Enhancing Visual Programming for Visual Reasoning via Probabilistic Graphs
Wentao Wan, Kaiyu Wu, Qingyang Ma +4
Recently, Visual Programming (VP) based on large language models (LLMs) has rapidly developed and demonstrated significant potential in complex Visual Reasoning (VR) tasks. Previou…
Massive Editing for Large Language Models Based on Dynamic Weight Generation
Wentao Wan, Qiqing Lao, Zhiwei Xie +4
Knowledge Editing (KE) is a field that studies how to modify some knowledge in Large Language Models (LLMs) at a low cost (compared to pre-training). Currently, performing large-sc…
E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion
Zhihao Zhan, Jiaying Zhou, Likui Zhang +10
Vision-Language-Action (VLA) models offer a unified framework for robotic manipulation by integrating visual perception, language understanding, and control generation. However, ex…
DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition
Haijing Liu, Tao Pu, Hefeng Wu +2
Open-Vocabulary Multi-Label Recognition (OV-MLR) aims to identify multiple seen and unseen object categories within an image, requiring both precise intra-class localization to pin…
Exploiting Temporal Audio-Visual Correlation Embedding for Audio-Driven One-Shot Talking Head Animation
Zhihua Xu, Tianshui Chen, Zhijing Yang +3
The paramount challenge in audio-driven One-shot Talking Head Animation (ADOS-THA) lies in capturing subtle imperceptible changes between adjacent video frames. Inherently, the tem…
AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay
Ziyi Tang, Zechuan Chen, Jiarui Yang +5
Alpha mining, a critical component in quantitative investment, focuses on discovering predictive signals for future asset returns in increasingly complex financial markets. However…
SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks
Wentao Wan, Zhuojie Yang, Yongcan Chen +6
Deductive reasoning is a crucial logical capability that assists us in solving complex problems based on existing knowledge. Although augmented by Chain-of-Thought prompts, Large L…
Category-Adaptive Cross-Modal Semantic Refinement and Transfer for Open-Vocabulary Multi-Label Recognition
Haijing Liu, Tao Pu, Hefeng Wu +4
Benefiting from the generalization capability of CLIP, recent vision language pre-training (VLP) models have demonstrated the ability to capture a wide range of visual concepts in…
Improving Network Interpretability via Explanation Consistency Evaluation
Hefeng Wu, Hao Jiang, Keze Wang +3
While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often resu…
SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Counting
Hefeng Wu, Yandong Chen, Lingbo Liu +3
The class-agnostic counting (CAC) task has recently been proposed to solve the problem of counting all objects of an arbitrary class with several exemplars given in the input image…
A Stepwise Distillation Learning Strategy for Non-differentiable Visual Programming Frameworks on Visual Reasoning Tasks
Wentao Wan, Nan Kang, Zeqing Wang +3
Recently, Visual Programming (VProg) has emerged as a significant framework for visual reasoning (VR) tasks due to its interpretability and cross-task generality. However, even wit…
Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs
Ziyi Tang, Ruilin Wang, Weixing Chen +6
Despite the progress of foundation models, knowledge-based reasoning remains a persistent challenge due to their limited capacity for knowledge recall and inference. Existing metho…
TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning
Yang Liu, Keze Wang, Lingbo Liu +2
Video self-supervised learning is a challenging task, which requires significant expressive power from the model to leverage rich spatial-temporal knowledge and generate effective…
Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval
Yang Liu, Keze Wang, Haoyuan Lan +1
Attempt to fully discover the temporal diversity and chronological characteristics for self-supervised video representation learning, this work takes advantage of the temporal depe…
Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding
Qingxing Cao, Bailin Li, Xiaodan Liang +2
Though beneficial for encouraging the Visual Question Answering (VQA) models to discover the underlying knowledge by exploiting the input-output correlation beyond image and text c…
Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp
Junfan Lin, Zhongzhan Huang, Keze Wang +3
Although deep reinforcement learning (RL) has been successfully applied to a variety of robotic control tasks, it's still challenging to apply it to real-world tasks, due to the po…
Linguistically Driven Graph Capsule Network for Visual Question Reasoning
Qingxing Cao, Xiaodan Liang, Keze Wang +1
Recently, studies of visual question answering have explored various architectures of end-to-end networks and achieved promising results on both natural and synthetic datasets, whi…
Towards Causality-Aware Inferring: A Sequential Discriminative Approach for Medical Diagnosis
Junfan Lin, Keze Wang, Ziliang Chen +2
Medical diagnosis assistant (MDA) aims to build an interactive diagnostic agent to sequentially inquire about symptoms for discriminating diseases. However, since the dialogue reco…
Instance-Aware Representation Learning and Association for Online Multi-Person Tracking
Hefeng Wu, Yafei Hu, Keze Wang +3
Multi-Person Tracking (MPT) is often addressed within the detection-to-association paradigm. In such approaches, human detections are first extracted in every frame and person traj…
Face Hallucination by Attentive Sequence Optimization with Reinforcement Learning
Yukai Shi, Guanbin Li, Qingxing Cao +2
Face hallucination is a domain-specific super-resolution problem that aims to generate a high-resolution (HR) face image from a low-resolution~(LR) input. In contrast to the existi…
Adaptively Connected Neural Networks
Guangrun Wang, Keze Wang, Liang Lin
This paper presents a novel adaptively connected neural network (ACNet) to improve the traditional convolutional neural networks (CNNs) {in} two aspects. First, ACNet employs a fle…