1 citations · 1 across the 8 of their papers we have counts for
9 papers
Certified Multi-Turn Robustness for LLM Safety via Compositional Bounds and Safety Persistence
Yang Liu, Bin Chong, Wenkai Yang +9
Large language models (LLMs) are vulnerable to multi-turn jailbreak attacks that progressively manipulate conversation context. Existing certified robustness methods are limited to…
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…
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…
Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs
Kaiser Sun, Xiaochuang Yuan, Hongjun Liu +4
Multimodal large language models (MLLMs) can process text presented as images, yet they often perform worse than when the same content is provided as textual tokens. We systematica…
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…
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…
Parameter-Efficient Construction of the Rashomon Slice for Concept Bottleneck 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…
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…
TaxaDiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generation
Amin Karimi Monsefi, Mridul Khurana, Rajiv Ramnath +3
We propose TaxaDiffusion, a taxonomy-informed training framework for diffusion models to generate fine-grained animal images with high morphological and identity accuracy. Unlike s…