Dongwon Jo

According to our database1, Dongwon Jo authored at least 9 papers between 2020 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection.
CoRR, February, 2026

2025
Retrospective Sparse Attention for Efficient Long-Context Generation.
CoRR, August, 2025

Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning.
CoRR, May, 2025

FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation.
CoRR, February, 2025

2024
Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023
Squeezing Large-Scale Diffusion Models for Mobile.
CoRR, 2023

Leveraging Early-Stage Robustness in Diffusion Models for Efficient and High-Quality Image Synthesis.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022
Computopia and Its Discontents: Dual Narratives in South Korea.
Proceedings of the Prophets of Computing: Visions of Society Transformed by Computing, 2022

2020
"Bursting Circuit Boards": Infrastructures and Technical Practices of Copying in Early Korean Video Game Industry.
Game Stud., 2020


  Loading...