Alexander Bukharin
9 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Cross-Pollinator (5) π§ Keyword Pioneer π Conference Polyglot (4) π£ Hot Topic Early Bird π Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(12)
π
Triple Crown
Conferences
ICML (3)
NIPS (3)
ICLR (2)
EMNLP (1)
Top co-authors
Keywords
reward learning
(2)
reinforcement learning from human feedback
(2)
uncertainty quantification
(1)
direct preference optimization
(1)
preference optimization
(1)
instruction following
(1)
language model alignment
(1)
instruction tuning
(1)
outlier detection
(1)
model pruning
(1)
score matching
(1)
lipschitz continuity
(1)
robust learning
(1)
distributionally robust optimization
(1)
upper confidence bound
(1)
molecular dynamics
(1)
uncertainty estimation
(1)
stackelberg game
(1)
model optimization
(1)
adversarial regularization
(1)
Papers
HelpSteer2-Preference: Complementing Ratings with Preferences
ICLR 2025
Deep Reinforcement Learning from Hierarchical Preference Design
ICML 2025
Robust Reinforcement Learning from Corrupted Human Feedback
NIPS 2024
Data Diversity Matters for Robust Instruction Tuning
EMNLP 2024
Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
NIPS 2024
Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning
ICLR 2023
Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms
NIPS 2023
Machine Learning Force Fields with Data Cost Aware Training
ICML 2023
PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance
ICML 2022