6 papers
DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache Eviction
Aozhong Zhang, Selcuk Gurses, Yanxia Deng +8
Key-value (KV) cache management has become a critical bottleneck for scaling Large Language Models (LLMs) to long-context scenarios due to linear memory growth. While recent evicti…
FlashSinkhorn 2: Block-Sparse Entropic Optimal Transport
Felix X. -F. Ye, Yu Chin Fabian Lim, Naigang Wang +1
Streaming GPU solvers for entropic optimal transport (EOT), such as FlashSinkhorn, avoid storing the dense kernel but still evaluate all point pairs in every Sinkhorn i…
ReDiPrune: Relevance-Diversity Pre-Projection Token Pruning for Efficient Multimodal LLMs
An Yu, Ting Yu Tsai, Zhenfei Zhang +3
Recent multimodal large language models are computationally expensive because Transformers must process a large number of visual tokens. We present ReDiPrune, a training-free token…
RatSeizure: A Benchmark and Saliency-Context Transformer for Rat Seizure Localization
Ting Yu Tsai, An Yu, Lucy Lee +5
Animal models, particularly rats, play a critical role in seizure research for studying epileptogenesis and treatment response. However, progress is limited by the lack of datasets…
FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU
Felix X. -F. Ye, Xingjie Li, An Yu +3
Entropic optimal transport (EOT) via Sinkhorn iterations is widely used in modern machine learning, yet GPU solvers remain inefficient at scale. Tensorized implementations suffer q…
SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM
An Yu, Weiheng Lu, Jian Li +4
Video Moment Retrieval is a task in video understanding that aims to localize a specific temporal segment in an untrimmed video based on a natural language query. Despite recent pr…