Sukjin Hong
4 papers · 2023–2025 · 4 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Venues
Top co-authors
Research topics
Keywords
model compression
(3)
knowledge distillation
(2)
large language model
(2)
direct preference optimization
(1)
preference alignment
(1)
reinforcement learning from human feedback
(1)
language model
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
error compensation
(1)
intermediate layer distillation
(1)
2-bit inference
(1)
2-bit quantization
(1)
quantization error compensation
(1)
model quantization
(1)
post-training quantization
(1)
Papers
RILQ: Rank-Insensitive LoRA-Based Quantization Error Compensation for Boosting 2-Bit Large Language Model Accuracy
AAAI 2025
Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment
ACL 2024
Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective
EACL 2023
Token-Scaled Logit Distillation for Ternary Weight Generative Language Models
NeurIPS 2023