2 papers
cs.CV2026
Less Detail, Better Answers: Degradation-Driven Prompting for VQA
Haoxuan Han, Weijie Wang, Zeyu Zhang +2
Recent advancements in Vision-Language Models (VLMs) have significantly pushed the boundaries of Visual Question Answering (VQA).However,high-resolution details can sometimes becom…
cs.CL2026
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Weian Mao, Xi Lin, Wei Huang +5
Extended reasoning in large language models (LLMs) creates severe KV cache memory bottlenecks. Leading KV cache compression methods estimate KV importance using attention scores fr…