Xianghao Kong
9 papers · 2022–2026 · 6 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(16)
🐣
Hot Topic Early Bird
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Deep Learning
(6)
Models
(6)
Machine Learning
(5)
Computer Vision
(3)
Artificial Intelligence
(2)
Core AI
(2)
Generation
(2)
Learning Types
(2)
Optimization & Theory · Machine Learning
(2)
Mathematics & Optimization
(1)
Analysis
(1)
Architectures
(1)
Core Methods
(1)
Mathematics
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
diffusion model
(5)
diffusion transformer
(2)
image generation
(2)
video generation
(1)
signal-to-noise ratio
(1)
point cloud
(1)
density estimation
(1)
text-to-image generation
(1)
object localization
(1)
importance sampling
(1)
out-of-distribution detection
(1)
mutual information estimation
(1)
conditional mutual information
(1)
adversarial attack
(1)
visual grounding
(1)
variational inference
(1)
text-to-image model
(1)
denoising model
(1)
mean square error
(1)
model compression
(1)
Papers
Composing Concepts from Images and Videos via Concept-prompt Binding
CVPR 2026
MMG: Mutual Information Estimation via the MMSE Gap in Diffusion
UAI 2026
Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget
CVPR 2025
Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks
ACL 2024
Controllable Navigation Instruction Generation with Chain of Thought Prompting
ECCV 2024
Interpretable Diffusion via Information Decomposition
ICLR 2024
Your Diffusion Model is Secretly a Noise Classifier and Benefits from Contrastive Training
NeurIPS 2024
Information-Theoretic Diffusion
ICLR 2023
3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
CVPR 2022