Sehoon Kim
15 papers · 2021–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🐝 Cross-Pollinator (12) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) 🌈 Renaissance Researcher (5)
🌍
Conference Polyglot
(6)
🌈
Renaissance Researcher
(5)
🤝
Dynamic Duo
(13)
🔥
Unstoppable
(5)
💎
Century Club
(15)
🗃️
Keyword Collector
(56)
⚡
Prolific Year
(5)
Conferences
ICML (5)
NIPS (5)
ACL (2)
ECCV (1)
EMNLP (1)
WACV (1)
Top co-authors
Keywords
inference efficiency
(4)
large language model
(3)
model compression
(3)
transformer architecture
(2)
low-resource learning
(1)
data augmentation
(1)
model distillation
(1)
bert model
(1)
knowledge distillation
(1)
automatic speech recognition
(1)
autoregressive generation
(1)
efficient computing
(1)
computational efficiency
(1)
model pruning
(1)
structured sparsity
(1)
imperative programming
(1)
memory efficiency
(1)
memory optimization
(1)
context length
(1)
text generation
(1)
Papers
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
ICML 2025
Squeezed Attention: Accelerating Long Context Length LLM Inference
ACL 2025
QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache
ICML 2025
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
NIPS 2024
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
ACL 2024
TinyAgent: Function Calling at the Edge
EMNLP 2024
SqueezeLLM: Dense-and-Sparse Quantization
ICML 2024
An LLM Compiler for Parallel Function Calling
ICML 2024
Speculative Decoding with Big Little Decoder
NIPS 2023
Hessian-Aware Pruning and Optimal Neural Implant
WACV 2022
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
NIPS 2022
A Fast Post-Training Pruning Framework for Transformers
NIPS 2022
BigColor: Colorization Using a Generative Color Prior for Natural Images
ECCV 2022
I-BERT: Integer-only BERT Quantization
ICML 2021
Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs
NIPS 2021