collaborators

8 papers

cs.LG2026

Exploring the Rashomon Set for Concept-Based Models

Shihan Feng, Cheng Zhang, Michael Xi +3

In many machine learning problems, there may exist multiple models that achieve nearly identical predictive performance while relying on fundamentally different internal logic. How…

cs.CL2026

Where You Inject Diversity Matters: A Unified Framework for Diverse Generation

Cheng Zhang, Rui Xin, Chudi Zhong

Open-ended generation tasks often require a set of meaningfully different outputs, yet large language models often produce similar generations. Existing test-time diversity methods…

cs.MA2026

DarwinTOD: LLM-driven Lifelong Self-evolution for Task-oriented Dialog Systems

Shuyu Zhang, Yujie Liu, Xinru Wang +3

Traditional task-oriented dialog systems are unable to evolve from ongoing interactions or adapt to new domains after deployment, that is a critical limitation in real-world dynami…

cs.CL2026

A Decomposition Perspective to Long-context Reasoning for LLMs

Yanling Xiao, Huaibing Xie, Guoliang Zhao +8

Long-context reasoning is essential for complex real-world applications, yet remains a significant challenge for Large Language Models (LLMs). Despite the rapid evolution in long-c…

cs.LG2026

Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective

Justin Lee, Zheda Mai, Jinsu Yoo +3

Machine unlearning--the ability to remove designated concepts from a pre-trained model--has advanced rapidly, particularly for text-to-image diffusion models. However, existing met…

cs.CL2026

CL-bench: A Benchmark for Context Learning

Shihan Dou, Ming Zhang, Zhangyue Yin +24

Current language models (LMs) excel at reasoning over prompts using pre-trained knowledge. However, real-world tasks are far more complex and context-dependent: models must learn f…