Xinyuan Wang
13 papers · 2024–2026 · 9 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (27) 💎 Century Club · Bronze ⚡ Prolific Year · Productive
🗃️
Keyword Collector
(61)
Top co-authors
Research topics
Artificial Intelligence
(8)
Machine Learning
(8)
Core AI
(7)
Deep Learning
(4)
Learning Types
(4)
Core Methods
(3)
Models
(3)
Optimization & Theory
(3)
Natural Language Processing
(2)
Application Areas
(2)
Resources & Methods
(2)
Computer Vision
(1)
Mathematics & Optimization
(1)
Architectures
(1)
Bayesian & Probabilistic
(1)
Keywords
large language model
(4)
contrastive learning
(3)
adversarial attack
(2)
diffusion model
(2)
in-context learning
(1)
model selection
(1)
image segmentation
(1)
self-supervised learning
(1)
continual learning
(1)
medical imaging
(1)
embedding space
(1)
kl divergence
(1)
text generation
(1)
dynamic routing
(1)
feature transformation
(1)
natural language understanding
(1)
reinforcement learning from human feedback
(1)
importance sampling
(1)
precision matrix
(1)
model security
(1)
Papers
Brownian Bridge Augmented Surrogate Simulation and Injection Planning for Geological CO2 Storage
AAAI 2026
Efficient KL Divergence Estimation via Truncated Top-K Integration for Large Language Models
ACL 2026
Efficient Post-Training Refinement of Latent Reasoning in Large Language Models
AAAI 2026
PPM-CLIP: Probabilistic Prompt Modeling for Generalizable AI-Generated Image Detection
CVPR 2026
DiffAtlas: GenAI-fying Atlas Segmentation via Image-Mask Diffusion
MICCAI 2025
DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak
EMNLP 2025
Efficient Network Automatic Relevance Determination
ICML 2025
LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models
ICLR 2025
Medical MLLM Is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models
AAAI 2025
MixLLM: Dynamic Routing in Mixed Large Language Models
NAACL 2025
Unsupervised Feature Transformation via In-context Generation, Generator-critic LLM Agents, and Duet-play Teaming
IJCAI 2025
BiPFT: Binary Pre-trained Foundation Transformer with Low-Rank Estimation of Binarization Residual Polynomials
AAAI 2024
PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
ICLR 2024