4 papers
Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models
Zhang Wei, Hanxuan Chen, Peilu Hu +19
Red-teaming is becoming a central part of large language model (LLM) safety evaluation, yet current practice still relies heavily on expert-written prompts or fixed benchmark suite…
AdaSD: Adaptive Speculative Decoding for Efficient Language Model Inference
Kuan-Wei Lu, Ding-Yong Hong, Pangfeng Liu +1
Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative…
PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models
Chak-Wing Mak, Guanyu Zhu, Boyi Zhang +16
Modern foundational Multimodal Large Language Models (MLLMs) and video world models have advanced significantly in mathematical, common-sense, and visual reasoning, but their grasp…
Efficient Temporal Consistency in Diffusion-Based Video Editing with Adaptor Modules: A Theoretical Framework
Xinyuan Song, Yangfan He, Sida Li +10
Adapter-based methods are commonly used to enhance model performance with minimal additional complexity, especially in video editing tasks that require frame-to-frame consistency.…