2 papers
cs.AI2026
POP: Online Structural Pruning Enables Efficient Inference of Large Foundation Models
Yi Chen, Wonjin Shin, Shuhong Liu +6
Large foundation models (LFMs) achieve strong performance through scaling, yet current structural pruning methods derive fixed pruning decisions during inference, overlooking spars…
eess.IV2025
V-Rex: Real-Time Streaming Video LLM Acceleration via Dynamic KV Cache Retrieval
Donghyuk Kim, Sejeong Yang, Wonjin Shin +1
Streaming video large language models (LLMs) are increasingly used for real-time multimodal tasks such as video captioning, question answering, conversational agents, and augmented…