3 papers
cs.LG2026
From Self-Attention to Connection Laplacian: A Unified Operator View of Transformers
Binbin Lin, Wei Chen, Yalun Li +3
Self-attention is a ubiquitous primitive in modern sequence models, yet its operator-level geometry is only partially understood. We view a token sequence as a vector field over th…
cs.CL2026
HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference
Zhiyuan Shi, Qibo Qiu, Feng Xue +5
The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally…
cs.CL2025
SciPIP: An LLM-based Scientific Paper Idea Proposer
Wenxiao Wang, Lihui Gu, Liye Zhang +7
The rapid advancement of large language models (LLMs) has opened new possibilities for automating the proposal of innovative scientific ideas. This process involves two key phases:…