7 papers
MASTraceBench: Diagnosing Collaboration Gains through Proposal Trajectories in LLM-Based Multi-Agent Systems
Yapeng Li, Songze Li, Shuang Yu +4
LLM-based multi-agent systems (MAS) have shown promise in complex problem solving. As MAS methods diversify, systematic evaluation becomes increasingly challenging. However, existi…
WorldMAP: Bootstrapping Vision-Language Navigation Trajectory Prediction with Generative World Models
Hongjin Chen, Shangyun Jiang, Tonghua Su +4
Vision-language models (VLMs) and generative world models are opening new opportunities for embodied navigation. VLMs are increasingly used as direct planners or trajectory predict…
A Comprehensive Evaluation of LLM Reasoning: From Single-Model to Multi-Agent Paradigms
Yapeng Li, Jiakuo Yu, Zhixin Liu +4
Large Language Models (LLMs) are increasingly deployed as reasoning systems, where reasoning paradigms - such as Chain-of-Thought (CoT) and multi-agent systems (MAS) - play a criti…
Multimodal Continual Instruction Tuning with Dynamic Gradient Guidance
Songze Li, Mingyu Gao, Tonghua Su +2
Multimodal continual instruction tuning enables multimodal large language models to sequentially adapt to new tasks while building upon previously acquired knowledge. However, this…
DUKAE: DUal-level Knowledge Accumulation and Ensemble for Pre-Trained Model-Based Continual Learning
Songze Li, Tonghua Su, Xu-Yao Zhang +2
Pre-trained model-based continual learning (PTMCL) has garnered growing attention, as it enables more rapid acquisition of new knowledge by leveraging the extensive foundational un…
Exploiting Stability-Plasticity Asymmetry in Pretrained Detectors for Incremental Object Detection
Songze Li, Qixing Xu, Tonghua Su +3
Pretrained model-based incremental object detection (PTMIOD) leverages the rich detection priors of pretrained detectors to learn new categories incrementally while preserving dete…
GUSLO: General and Unified Structured Light Optimization
Tinglei Wan, Tonghua Su, Zhongjie Wang
Structured light (SL) 3D reconstruction captures the precise surface shape of objects, providing high-accuracy 3D data essential for industrial inspection and cultural heritage dig…