Taehyeon Kim
13 papers · 2021–2026 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (31)
π
Trend Setter
π
Century Club Β· Bronze
β‘
Prolific Year Β· Productive
ποΈ
Keyword Collector
(65)
Top co-authors
Research topics
Machine Learning
(10)
Artificial Intelligence
(6)
Core AI
(6)
Deep Learning
(5)
Application Areas
(5)
Learning Types Β· Machine Learning
(5)
Natural Language Processing
(4)
Core Methods
(3)
Learning Types Β· Deep Learning
(3)
Generation
(2)
Optimization & Theory
(2)
Resources & Methods
(2)
Computer Vision
(1)
Analysis
(1)
Architectures
(1)
Keywords
semi-supervised learning
(2)
inference acceleration
(2)
language model
(2)
domain adaptation
(2)
model compression
(2)
semantic segmentation
(1)
reinforcement learning
(1)
transformer architecture
(1)
transfer learning
(1)
autoregressive transformer
(1)
contrastive learning
(1)
game theory
(1)
hierarchical modeling
(1)
object detection
(1)
autoregressive generation
(1)
kl divergence
(1)
knowledge distillation
(1)
pseudo labeling
(1)
progressive learning
(1)
few-shot learning
(1)
Papers
Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking
ACL 2026
MERIT Feedback Elicits Better Bargaining in LLM Negotiators
ACL 2026
Blood Pressure Assisted Cerebral Microbleed Segmentation via Meta-matching
MICCAI 2025
C2: Scalable Auto-Feedback for LLM-based Chart Generation
NAACL 2025
MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation
ICLR 2025
Accelerating Blockwise Parallel Language Models with Draft Refinement
NeurIPS 2024
Block Transformer: Global-to-Local Language Modeling for Fast Inference
NeurIPS 2024
Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions
ICLR 2024
Leveraging Normalization Layer in Adapters with Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning
AAAI 2024
Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters
EMNLP 2024
Navigating Data Heterogeneity in Federated Learning: A Semi-Supervised Federated Object Detection
NeurIPS 2023
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation
IJCAI 2021
FINE Samples for Learning with Noisy Labels
NeurIPS 2021