Hongyang He
4 papers · 2025–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(2)
🌈
Renaissance Researcher
(5)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
AAAI (1)
ACL (1)
ICCV (1)
WACV (1)
Top co-authors
Keywords
reinforcement learning
(1)
semi-supervised learning
(1)
text-to-image generation
(1)
state space model
(1)
diffusion model
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
representation collapse
(1)
classifier-free guidance
(1)
large vision-language model
(1)
visual token
(1)
vision mamba
(1)
label imbalance
(1)
context-aware attention
(1)
timestep embedding
(1)
bidirectional architecture
(1)
multimodal in-context learning
(1)
attention logit
(1)
self-attention modulation
(1)
Papers
Reinforcement Learning-based Adaptive Control of Classifier-Free Guidance and Timestep Embeddings in Diffusion Models
WACV 2026
Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning
AAAI 2026
MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models
ACL 2026
Semi-ViM: Bidirectional State Space Model for Mitigating Label Imbalance in Semi-Supervised Learning
ICCV 2025