Minsoo Kim
- Papers
- 6
Cite
Notes
Only stored in your browser.
6papers
Authored papers
6InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
arXiv 2025
Agent-as-Judge for Factual Summarization of Long Narratives
arXiv 2025
RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy
arXiv 2024
Token-Scaled Logit Distillation for Ternary Weight Generative Language Models
token-scaled-logit-distillation-for-ternary
Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers
arXiv 2023
Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer Encoders
arXiv 2022
Affiliations
No known affiliations.
Frequent co-authors
10from 6 papers