Kangwook Lee
~Kangwook_Lee1
23
论文总数
11.5
年均投稿
平均评分
接收情况13/23
会议分布
ICLR
17
ICML
4
COLM
2
发表论文 (23 篇)
202514 篇
4
Multi-Bin Batching for Increasing LLM Inference Throughput
ICLR 2025withdrawn
4
Task Vectors in In-Context Learning: Emergence, Formation, and Benefits
COLM 2025Poster
3
From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data
ICLR 2025Poster
4
Looped Transformers for Length Generalization
ICLR 2025Poster
4
Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
ICML 2025Poster
4
Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance
ICLR 2025Spotlight
4
Encoder-only Next Token Prediction
ICLR 2025Rejected
4
Parameter-Efficient Fine-Tuning of State Space Models
ICLR 2025Rejected
4
Parameter-Efficient Fine-Tuning of State Space Models
ICML 2025Poster
4
In-batch Ensemble Drafting: Toward Fast and Robust Speculative Decoding for Multimodal Language Models
ICLR 2025withdrawn
4
Iterative DPO with An Improvement Model for Fine-tuning Diffusion Models
ICLR 2025withdrawn
4
Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
ICLR 2025Rejected
4
Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
ICML 2025Spotlight
4
VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data
ICML 2025Oral
20249 篇
3
Looped Transformers are Better at Learning Learning Algorithms
ICLR 2024Poster
5
A Theoretical Analysis of In-context Task Retrieval and Learning
ICLR 2024Rejected
4
SODA: Stream Out-of-Distribution Adaptation
ICLR 2024Rejected
4
The Expressive Power of Low-Rank Adaptation
ICLR 2024Poster
4
Can General-Purpose Language Models Emulate a General-Purpose Computer In-Context?
ICLR 2024withdrawn
5
Teaching Arithmetic to Small Transformers
ICLR 2024Poster
4
Can MLLMs Perform Text-to-Image In-Context Learning?
COLM 2024Poster
4
Image Clustering Conditioned on Text Criteria
ICLR 2024Poster
3
FedGP: Buffer-based Gradient Projection for Continual Federated Learning
ICLR 2024Rejected