28 citations · 41 across the 16 of their papers we have counts for
17 papers
A Theory of Reliable Self-Evolution for Agent Harnesses
Qianshu Cai, Yonggang Zhang, Jun Nie +6
In harness self-evolution, agents modify their own prompts, code, tools, and orchestration while keeping the underlying language model fixed. Recent work has shown that agents can…
EvolveNet: Collaborative Harness Evolution for Agent Self-Improvement
Jun Nie, Yonggang Zhang, Qianshu Cai +3
An LLM agent can acquire persistent improvements by evolving its harness---the executable program governing model calls, tool use, verification, and recovery---without updating mod…
Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection
Jun Nie, Yonggang Zhang, Tongliang Liu +3
Robust detection of generated images is critical to counter the misuse of generative models. Existing methods primarily depend on learning from human-annotated training datasets, l…
DRNOISE: Benchmarking Deep Research Agents in Misleading Evidence Environments
Jun Nie, Zhiqin Yang, Zhenheng Tang +4
Deep research agents increasingly operate over the open web, where relevant records coexist with redundant summaries, outdated reports, and misleading documents. Existing evaluatio…
A Control Theory of Predictability in Latent World Models
Hanzhe You, Yonggang Zhang, Maohao Ran +6
Latent world models are trained to predict future states in a learned representation and are then deployed inside a planner that selects actions by simulating them forward. Current…
TTHE: Test-Time Harness Evolution
Jun Nie, Yonggang Zhang, Jun Song +5
The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies interm…
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
Qianshu Cai, Yonggang Zhang, Xianzhang Jia +5
Autonomous agentic systems are largely static after deployment: they do not learn from user interactions, and recurring failures persist until the next human-driven update ships a…
Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow
Chengsheng Zhang, Chenghao Sun, Zhining Xie +1
Large Vision-Language Models (LVLMs) represent a significant leap towards empathetic agents, demonstrating remarkable capabilities in emotion understanding. However, the internal m…
Detecting Generated Images by Fitting Natural Image Distributions
Yonggang Zhang, Jun Nie, Xinmei Tian +3
The increasing realism of generated images has raised significant concerns about their potential misuse, necessitating robust detection methods. Current approaches mainly rely on t…
Enhancing Target-unspecific Tasks through a Features Matrix
Fangming Cui, Yonggang Zhang, Xuan Wang +2
Recent developments in prompt learning of large Vision-Language Models (VLMs) have significantly improved performance in target-specific tasks. However, these prompting methods oft…
A Similarity Paradigm Through Textual Regularization Without Forgetting
Fangming Cui, Jan Fong, Rongfei Zeng +2
Prompt learning has emerged as a promising method for adapting pre-trained visual-language models (VLMs) to a range of downstream tasks. While optimizing the context can be effecti…
Epistemic Uncertainty for Generated Image Detection
Jun Nie, Yonggang Zhang, Tongliang Liu +3
We introduce a novel framework for AI-generated image detection through epistemic uncertainty, aiming to address critical security concerns in the era of generative models. Our key…
Interpreting and Improving Large Language Models in Arithmetic Calculation
Wei Zhang, Chaoqun Wan, Yonggang Zhang +4
Large language models (LLMs) have demonstrated remarkable potential across numerous applications and have shown an emergent ability to tackle complex reasoning tasks, such as mathe…
From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
Wei Chen, Zhen Huang, Liang Xie +9
Large Language Models (LLMs) tend to prioritize adherence to user prompts over providing veracious responses, leading to the sycophancy issue. When challenged by users, LLMs tend t…
FedImpro: Measuring and Improving Client Update in Federated Learning
Zhenheng Tang, Yonggang Zhang, Shaohuai Shi +4
Federated Learning (FL) models often experience client drift caused by heterogeneous data, where the distribution of data differs across clients. To address this issue, advanced re…
Robust Training of Federated Models with Extremely Label Deficiency
Yonggang Zhang, Zhiqin Yang, Xinmei Tian +3
Federated semi-supervised learning (FSSL) has emerged as a powerful paradigm for collaboratively training machine learning models using distributed data with label deficiency. Adva…
FedFed: Feature Distillation against Data Heterogeneity in Federated Learning
Zhiqin Yang, Yonggang Zhang, Yu Zheng +4
Federated learning (FL) typically faces data heterogeneity, i.e., distribution shifting among clients. Sharing clients' information has shown great potentiality in mitigating data…