Hongyi Cai
4 papers · 2025–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(11)
โ
The Questioner
Top co-authors
Research topics
Keywords
efficient inference
(1)
semantic alignment
(1)
instruction tuning
(1)
robot control
(1)
backdoor attack
(1)
text-to-image model
(1)
vision-language model
(1)
retrieval-augmented generation
(1)
multimodal understanding
(1)
diffusion transformer
(1)
vision-language-action model
(1)
data filtering
(1)
knowledge conflict
(1)
confidence score
(1)
centroid clustering
(1)
external context
(1)
quality subset
(1)
trigger-activated bia
(1)
clip-guided training
(1)
confidence reasoning
(1)
Papers
AutoDebias: An Automated Framework for Detecting and Mitigating Backdoor Biases in Text-to-Image Models
CVPR 2026
Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
CVPR 2026
Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning
EMNLP 2025
To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts
ICLR 2025