activity
20242026
collaborators

17 papers

cs.AI2026

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?

Dong Yan, Jian Liang, Dapeng Hu +4

Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominantly adopt independent evaluati…

cs.CV2026

USE: A Unified Self-Ensembling Framework for Test-Time Prompt Tuning

Siru Jiang, Jian Liang, Ran He +1

Test-time adaptation (TTA) has emerged as a popular paradigm for improving the performance of vision-language models (e.g., CLIP) on downstream tasks. Among existing CLIP-based TTA…

cs.LG2026

On the Vulnerability of Parameter-Level Defenses to Model Merging

Kuangpu Guo, Qingyan Zheng, Jian Liang +4

The training-free integration of expert models via model merging has exposed significant security risks, enabling free-riders to combine specialized models without authorization. R…

cs.LG2026

Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging

Kuangpu Guo, Aijing Yu, Jian Liang +4

Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training. However, traditional basic merging methods often experience perf…

cs.LG2026

What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time

Dong Yan, Jian Liang, Yanbo Wang +3

Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams by deriving pseudo-rewards from majority vo…

cs.CR2026

Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs

Dong Yan, Jian Liang, Ran He +1

Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid a…