Research

MaskKV exploits mask-token attention signals to evict low-utility KV pairs in diffusion LLMs, shrinking cache budgets while preserving long-context accuracy and increasing throughput.

FreqCa accelerates diffusion models by analyzing frequency dynamics of features across timesteps, reusing low-frequency components and interpolating high-frequency ones with great memory reduction.

A comprehensive survey on data attribution methods, applications, and evaluation protocols that address how training data influences the behaviors of generative AI systems.

This paper evaluates whether modern Vision-Language Models (VLMs) like GPT-4o and Gemini can act as internal world models (WMs)—systems that understand and predict the world.

Given different DNNs trained for the same task, developed a new method to extract interactions that are shared by these DNNs. Experiments show that the extracted interactions can better reflect common ...