3.2k citations · 3.9k across the 76 of their papers we have counts for
79 papers
LivingRAG: Augmenting Graph RAG with Experience
Yuzhuo Cui, Zongye Zhang, Qingjie Liu
Graph-based RAG improves multi-hop question answering by organizing evidence as a knowledge graph. However, most existing RAG systems process each query in isolation and discard us…
Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents
Hongxi Yan, Ziyue Huang, Shichao Fan +1
Training large language model agents in long-horizon environments requires assigning credit from sparse terminal outcomes to individual actions. Existing critic-free methods propag…
Models as Tools: An Agentic Coordination Framework for Unified Multimodal Visual Tracking
Wenrui Cai, Yuzhe Li, Qingjie Liu +1
Most current visual trackers adopt a matching-based architecture trained exclusively on tracking datasets, whose performance gains depend heavily on the length of the input context…
FACT: A Simple and Efficient Framework for Active Finetuning
Wenshuai Xu, You Song, Yuzhuo Cui +3
The main goal of active finetuning is to improve a pretrained model's performance on a specific task or domain by finetuning it with carefully selected informative or challenging d…
Semantic-Aware Motion Encoding for Topology-Agnostic Character Animation
Zongye Zhang, Yuzhuo Cui, Qingjie Liu +1
Generalizing motion representation across diverse characters remains challenging due to significant topological variations in skeletal structures across datasets and species, which…
Reasoning-Driven Anomaly Detection and Localization with Image-Level Supervision
Yizhou Jin, Yuezhu Feng, Jinjin Zhang +3
Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning and perceptual abilities for anomaly detection. However, most approaches remain confined to…
Uni-MDTrack: Learning Decoupled Memory and Dynamic States for Parameter-Efficient Visual Tracking in All Modality
Wenrui Cai, Zhenyi Lu, Yuzhe Li +4
With the advent of Transformer-based one-stream trackers that possess strong capability in inter-frame relation modeling, recent research has increasingly focused on how to introdu…
ResWorld: Temporal Residual World Model for End-to-End Autonomous Driving
Jinqing Zhang, Zehua Fu, Zelin Xu +3
The comprehensive understanding capabilities of world models for driving scenarios have significantly improved the planning accuracy of end-to-end autonomous driving frameworks. Ho…
LIBERO-X: Robustness Litmus for Vision-Language-Action Models
Guodong Wang, Chenkai Zhang, Qingjie Liu +4
Reliable benchmarking is critical for advancing Vision-Language-Action (VLA) models, as it reveals their generalization, robustness, and alignment of perception with language-drive…
Beyond Open Vocabulary: Multimodal Prompting for Object Detection in Remote Sensing Images
Shuai Yang, Ziyue Huang, Jiaxin Chen +2
Open-vocabulary object detection in remote sensing commonly relies on text-only prompting to specify target categories, implicitly assuming that inference-time category queries can…
EntroCut: Entropy-Guided Adaptive Truncation for Efficient Chain-of-Thought Reasoning in Small-scale Large Reasoning Models
Hongxi Yan, Qingjie Liu, Yunhong Wang
Large Reasoning Models (LRMs) excel at complex reasoning tasks through extended chain-of-thought generation, but their reliance on lengthy intermediate steps incurs substantial com…
Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM
Yibai Liu, Shihang Wang, Zeming Liu +5
Despite large language models (LLMs) have achieved impressive achievements across numerous tasks, supervised fine-tuning (SFT) remains essential for adapting these models to specia…
XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations
Shichao Fan, Kun Wu, Zhengping Che +12
Recent progress in large-scale robotic datasets and vision-language models (VLMs) has advanced research on vision-language-action (VLA) models. However, existing VLA models still f…
SeeDNorm: Self-Rescaled Dynamic Normalization
Wenrui Cai, Defa Zhu, Qingjie Liu +1
Normalization layer constitutes an essential component in neural networks. In transformers, the predominantly used RMSNorm constrains vectors to a unit hypersphere, followed by dim…
AttriPrompt: Dynamic Prompt Composition Learning for CLIP
Qiqi Zhan, Shiwei Li, Qingjie Liu +1
The evolution of prompt learning methodologies has driven exploration of deeper prompt designs to enhance model performance. However, current deep text prompting approaches suffer…
De-Simplifying Pseudo Labels to Enhancing Domain Adaptive Object Detection
Zehua Fu, Chenguang Liu, Yuyu Chen +3
Despite its significant success, object detection in traffic and transportation scenarios requires time-consuming and laborious efforts in acquiring high-quality labeled data. Ther…
GODBench: A Benchmark for Multimodal Large Language Models in Video Comment Art
Yiming Lei, Chenkai Zhang, Zeming Liu +5
Video Comment Art enhances user engagement by providing creative content that conveys humor, satire, or emotional resonance, requiring a nuanced and comprehensive grasp of cultural…
SeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding
Chenkai Zhang, Yiming Lei, Zeming Liu +5
With the rapid development of Multi-modal Large Language Models (MLLMs), an increasing number of benchmarks have been established to evaluate the video understanding capabilities o…
ContextQFormer: A New Context Modeling Method for Multi-Turn Multi-Modal Conversations
Yiming Lei, Zhizheng Yang, Zeming Liu +5
Multi-modal large language models have demonstrated remarkable zero-shot abilities and powerful image-understanding capabilities. However, the existing open-source multi-modal mode…
Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion
Zongye Zhang, Bohan Kong, Qingjie Liu +1
Generating 3D human motion from text descriptions remains challenging due to the diverse and complex nature of human motion. While existing methods excel within the training distri…
SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation
Zongye Zhang, Wenrui Cai, Qingjie Liu +1
While current skeleton action recognition models demonstrate impressive performance on large-scale datasets, their adaptation to new application scenarios remains challenging. Thes…
Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation
Yongchao Feng, Yajie Liu, Shuai Yang +13
Vision-Language Model (VLM) have gained widespread adoption in Open-Vocabulary (OV) object detection and segmentation tasks. Despite they have shown promise on OV-related tasks, th…
A Survey on Remote Sensing Foundation Models: From Vision to Multimodality
Ziyue Huang, Hongxi Yan, Qiqi Zhan +7
The rapid advancement of remote sensing foundation models, particularly vision and multimodal models, has significantly enhanced the capabilities of intelligent geospatial data int…
OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images
Ziyue Huang, Yongchao Feng, Shuai Yang +3
Remote sensing object detection has made significant progress, but most studies still focus on closed-set detection, limiting generalization across diverse datasets. Open-vocabular…