Jaehyung Kim
31 papers · 2020–2026 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π Conference Polyglot (9) π Academic Marathon (5) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (15)
π
Cross-Pollinator
(15)
π
Renaissance Researcher
(8)
πΊοΈ
Taxonomy Completionist
(61)
π
Grand Slam
π€
Dynamic Duo
(16)
β‘
Prolific Year
(7)
π₯
Unstoppable
(5)
π
Century Club
(26)
π
Trend Setter
ποΈ
Keyword Collector
(113)
β
The Questioner
Conferences
ACL (7)
ICLR (6)
EMNLP (5)
AAAI (3)
ICML (3)
NIPS (3)
CVPR (2)
NAACL (1)
RSS (1)
Top co-authors
Research topics
Keywords
large language model
(9)
language model
(4)
representation learning
(3)
preference learning
(3)
self-supervised learning
(2)
feature learning
(2)
pairwise comparison
(2)
class imbalance
(2)
knowledge retention
(2)
molecular structure
(2)
text classification
(2)
online learning
(1)
semi-supervised learning
(1)
black-box optimization
(1)
action recognition
(1)
few-shot learning
(1)
semantic segmentation
(1)
adversarial robustness
(1)
temporal dynamics
(1)
reinforcement learning
(1)
Papers
Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models
ACL 2026
Learning from the Undesirable: Robust Adaptation of Language Models Without Forgetting
AAAI 2026
EMCEE: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multilingual Context
ACL 2026
Revisit What You See: Revealing Visual Semantics in Vision Tokens to Guide LVLM Decoding
ACL 2026
Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data
ACL 2026
Few-shot Personalization of LLMs with Mis-aligned Responses
NAACL 2025
Structural Reasoning Improves Molecular Understanding of LLM
ACL 2025
Debiasing Online Preference Learning via Preference Feature Preservation
ACL 2025
Improving Chemical Understanding of LLMs via SMILES Parsing
EMNLP 2025
Personalized LLM Decoding via Contrasting Personal Preference
EMNLP 2025
Personalized Language Models via Privacy-Preserving Evolutionary Model Merging
EMNLP 2025
Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
ICLR 2025
ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification
ICML 2025
A low-cost and lightweight 6 DoF bimanual arm for dynamic and contact-rich manipulation
RSS 2025
Online Adaptation of Language Models with a Memory of Amortized Contexts
NIPS 2024
Learning to Correct for QA Reasoning with Black-box LLMs
EMNLP 2024
Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
ICLR 2024
An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks
ICLR 2024
SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
ICLR 2024
Meta-Crafting: Improved Detection of Out-of-Distributed Texts via Crafting Metadata Space (Student Abstract)
AAAI 2024
Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
NIPS 2024
Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning
ICML 2023
infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-information
ACL 2023
RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training
EMNLP 2023
Everyoneβs Voice Matters: Quantifying Annotation Disagreement Using Demographic Information
AAAI 2023
Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation
ICLR 2022
Patch-Level Representation Learning for Self-Supervised Vision Transformers
CVPR 2022
What Makes Better Augmentation Strategies? Augment Difficult but Not too Different
ICLR 2022
Time Is MattEr: Temporal Self-supervision for Video Transformers
ICML 2022
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning
NIPS 2020
M2m: Imbalanced Classification via Major-to-Minor Translation
CVPR 2020