4 papers
Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective
Jiaming Yang, Chenwei Tang, Liangli Zhen +1
Key-Value (KV) caching is essential for large language model inference, yet its memory overhead poses a critical bottleneck for long-context generation. Existing eviction policies…
Dr. Seg: Revisiting GRPO Training for Visual Large Language Models through Perception-Oriented Design
Haoxiang Sun, Tao Wang, Chenwei Tang +2
Following the success of Group Relative Policy Optimization (GRPO) in foundation LLMs, an increasing number of works have sought to adapt GRPO to Visual Large Language Models (VLLM…
Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval
Yifan Wang, Tao Wang, Chenwei Tang +5
Recently, prompt learning has demonstrated remarkable success in adapting pre-trained Vision-Language Models (VLMs) to various downstream tasks such as image classification. Howeve…
GPT-NAS: Evolutionary Neural Architecture Search with the Generative Pre-Trained Model
Caiyang Yu, Xianggen Liu, Yifan Wang +5
Neural Architecture Search (NAS) has emerged as one of the effective methods to design the optimal neural network architecture automatically. Although neural architectures have ach…