Haoyuan Sun
9 papers · 2019–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (6) π Academic Marathon (6) π Cross-Pollinator (5)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(19)
π£
Hot Topic Early Bird
Conferences
NIPS (3)
AAAI (1)
ACL (1)
ALT (1)
ICLR (1)
JMLR (1)
L4DC (1)
Top co-authors
Research topics
Keywords
gradient descent
(3)
maximum-margin solution
(2)
mirror descent
(2)
regret analysis
(1)
direct preference optimization
(1)
preference alignment
(1)
divergence minimization
(1)
multimodal learning
(1)
text-to-image generation
(1)
dynamic regret
(1)
reinforcement learning from human feedback
(1)
bregman divergence
(1)
maximum margin
(1)
online convex optimization
(1)
kernel regression
(1)
in-context learning
(1)
strongly convex
(1)
time-varying systems
(1)
domain knowledge
(1)
predictive control
(1)
Papers
On the Role of Transformer Feed-Forward Layers in Nonlinear In-Context Learning
ALT 2026
FloorPlan-LLaMa: Aligning Architectsβ Feedback and Domain Knowledge in Architectural Floor Plan Generation
ACL 2025
Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences Through f-Divergence Minimization
AAAI 2025
Entropy-based Activation Function Optimization: A Method on Searching Better Activation Functions
ICLR 2025
Meta-Learning for Adaptive Control with Automated Mirror Descent
L4DC 2025
A Unified Approach to Controlling Implicit Regularization via Mirror Descent
JMLR 2023
Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently
NIPS 2022
Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems
NIPS 2021
Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimization
NIPS 2019