Fengda Zhang
7 papers · 2023–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (5) π Renaissance Researcher (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (12) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
CVPR (2)
ICML (2)
EMNLP (1)
ICCV (1)
ICLR (1)
Top co-authors
Keywords
reinforcement learning
(2)
text-to-image generation
(2)
semantic alignment
(1)
reinforcement learning from human feedback
(1)
generative augmentation
(1)
model alignment
(1)
mirror descent
(1)
distributionally robust optimization
(1)
diffusion model
(1)
bias mitigation
(1)
language model
(1)
spurious correlation
(1)
sparse reward
(1)
stable diffusion
(1)
attention map
(1)
prompt alignment
(1)
text-image alignment
(1)
object omission
(1)
ai-generated feedback
(1)
reward composition
(1)
Papers
Decoding Correlation-Induced Misalignment in the Stable Diffusion Workflow for Text-to-Image Generation
ICCV 2025
Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
CVPR 2025
D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples
ICML 2025
Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular Data
ICML 2025
Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning
EMNLP 2024
Distributionally Generative Augmentation for Fair Facial Attribute Classification
CVPR 2024
Fairness-aware Contrastive Learning with Partially Annotated Sensitive Attributes
ICLR 2023