3 papers
cs.LG2026
SPIN: Shadow Predictive Indexer for Sparse Attention
Yao Fu, Jiahan Chang, Cyrus Chang +12
Indexer-based sparse attention reduces the cost of core attention by passing only a fixed, small number of important tokens to it. However, the indexer must still score the entire…
cs.CL2025
Rethinking the Outlier Distribution in Large Language Models: An In-depth Study
Rahul Raman, Khushi Sharma, Sai Qian Zhang
Investigating outliers in large language models (LLMs) is crucial due to their significant impact on various aspects of LLM performance, including quantization and compression. Out…
cs.CL2025
DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding
Yunhai Hu, Tianhua Xia, Zining Liu +6
Speculative decoding (SD) has emerged as a powerful method for accelerating autoregressive generation in large language models (LLMs), yet its integration into vision-language mode…