Retrospective Sparse Attention for Efficient Long-Context Generation
Paper
•
2508.09001
•
Published
•
2
Seonghwan Choi
ryanc
AI & ML interests
NLP, Recommendation system, and Neural net optimization
Recent Activity
authored
a paper
about 1 month ago
Retrospective Sparse Attention for Efficient Long-Context Generation
upvoted
a
paper
about 1 month ago
Reasoning Path Compression: Compressing Generation Trajectories for
Efficient LLM Reasoning
upvoted
a
paper
about 1 month ago
LiteStage: Latency-aware Layer Skipping for Multi-stage Reasoning
Organizations
None yet
authored
a
paper
about 1 month ago