影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
87.96/100
前 0.7%
全站排名 #463
发表论文28 篇
平均评分
年均产出9.3 篇/年
Kangwook Lee
研究方向
Large language models · Diffusion models · Deep learning · Information theory · Fairness in machine learning · Distributed machine learning
17
Draft-based Approximate Inference for LLMs
ICLR 2026Poster
通讯19
Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games
ICLR 2026Poster
23
ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
ICLR 2026Poster
通讯20
ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning
ICLR 2026Rejected
通讯5
Compress to Think, Decompress to Speak: Dual-Mode Reasoning in Transformers
ICLR 2026Withdrawn
三作19
Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance
ICLR 2025Spotlight
17
Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
ICML 2025Spotlight
15
VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data
ICML 2025Oral
通讯22
Looped Transformers for Length Generalization
ICLR 2025Poster
通讯9
Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
ICML 2025Poster
20
From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data
ICLR 2025Poster
三作14
Task Vectors in In-Context Learning: Emergence, Formation, and Benefits
COLM 2025Poster
三作23
Encoder-only Next Token Prediction
ICLR 2025Rejected
通讯17
Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
ICLR 2025Rejected
11
Parameter-Efficient Fine-Tuning of State Space Models
ICML 2025Poster
通讯30
Parameter-Efficient Fine-Tuning of State Space Models
ICLR 2025Rejected
通讯5
Iterative DPO with An Improvement Model for Fine-tuning Diffusion Models
ICLR 2025Withdrawn
5
Multi-Bin Batching for Increasing LLM Inference Throughput
ICLR 2025Withdrawn
三作6
In-batch Ensemble Drafting: Toward Fast and Robust Speculative Decoding for Multimodal Language Models
ICLR 2025Withdrawn
通讯