Haoqin Tu
10 papers · 2023–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (14) π Conference Polyglot (7) π Renaissance Researcher (5) π Interdisciplinary Bridge π§ Keyword Pioneer
πΊοΈ
Taxonomy Completionist
(14)
π
Grand Slam
π₯
Mega-Team
(35)
β
The Questioner
(2)
π
Century Club
(10)
β‘
Prolific Year
(5)
Conferences
EMNLP (2)
ICLR (2)
AAAI (1)
ECCV (1)
ICCV (1)
ICML (1)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
multimodal learning
(4)
reward modeling
(1)
transfer learning
(1)
image retrieval
(1)
chain-of-thought reasoning
(1)
model safety
(1)
responsible ai
(1)
safety alignment
(1)
vision language model
(1)
foundation model
(1)
vision-language model
(1)
edge device
(1)
parameter efficiency
(1)
vision encoder
(1)
multimodal reasoning
(1)
image-text alignment
(1)
dataset curation
(1)
process reward
(1)
dialogue system
(1)
model fairness
(1)
Papers
STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
AAAI 2026
Autoregressive Pretraining with Mamba in Vision
ICLR 2025
What If We Recaption Billions of Web Images with LLaMA-3?
ICML 2025
Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability
NAACL 2025
ViLBench: A Suite for Vision-Language Process Reward Modeling
EMNLP 2025
OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning
ICCV 2025
Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning
ICLR 2024
How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
ECCV 2024
VHELM: A Holistic Evaluation of Vision Language Models
NIPS 2024
ReSee: Responding through Seeing Fine-grained Visual Knowledge in Open-domain Dialogue
EMNLP 2023