collaborators

5 papers

cs.AI2026

Cost-Effective Communication: An Auction-based Method for Language Agent Interaction

Yijia Fan, Jusheng Zhang, Kaitong Cai +4

Multi-agent systems (MAS) built on large language models (LLMs) often suffer from inefficient "free-for-all" communication, leading to exponential token costs and low signal-to-noi…

cs.CV2026

Top-Down Semantic Refinement for Image Captioning

Jusheng Zhang, Kaitong Cai, Jing Yang +3

Large Vision-Language Models (VLMs) face an inherent contradiction in image captioning: their powerful single-step generation capabilities often lead to a myopic decision-making pr…

cs.CL2025

DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off

Jusheng Zhang, Yijia Fan, Kaitong Cai +5

This paper introduces DrDiff, a novel framework for long-text generation that overcomes the efficiency-quality trade-off through three core technologies. First, we design a dynamic…

cs.AI2025

HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution

Jinzhou Tang, Jusheng Zhang, Qinhan Lv +4

Autonomous agents play a crucial role in advancing Artificial General Intelligence, enabling problem decomposition and tool orchestration through Large Language Models (LLMs). Howe…

cs.CV2025

TimeCausality: Evaluating the Causal Ability in Time Dimension for Vision Language Models

Zeqing Wang, Shiyuan Zhang, Chengpei Tang +1

Reasoning about temporal causality, particularly irreversible transformations of objects governed by real-world knowledge (e.g., fruit decay and human aging), is a fundamental aspe…