6 papers
HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion
Dongyeun Lee, Amir Zandieh, Vahab Mirrokni +2
Video Diffusion Transformers (VDiTs) have demonstrated significant capabilities in high-fidelity video generation. However, their ability to produce long-duration videos is fundame…
KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
Seongjin Cha, Gyuwan Kim, Dongsu Han +2
Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on static heuristics that ignore th…
DNACHUNKER: Learnable Tokenization for DNA Language Models
Taewon Kim, Jihwan Shin, Hyomin Kim +5
DNA language models are increasingly used to represent genomic sequence, yet their effectiveness depends critically on how raw nucleotides are converted into model inputs. Unlike n…
Streaming Attention Approximation via Discrepancy Theory
Ekaterina Kochetkova, Kshiteej Sheth, Insu Han +2
Large language models (LLMs) have achieved impressive success, but their high memory requirements present challenges for long-context token generation. In this paper we study the s…
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs
Insu Han, Zeliang Zhang, Zhiyuan Wang +8
Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance across diverse applications. However, their computational overhead during deployment remains a cri…
PolarQuant: Quantizing KV Caches with Polar Transformation
Insu Han, Praneeth Kacham, Amin Karbasi +2
Large language models (LLMs) require significant memory to store Key-Value (KV) embeddings in their KV cache, especially when handling long-range contexts. Quantization of these KV…