Xiaomin Li
8 papers · 2025–2026 · 5 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 · Silver
🗺️
Taxonomy Completionist
(25)
⭐
Rising Star
(8)
Top co-authors
Research topics
Artificial Intelligence
(7)
Core AI
(7)
Machine Learning
(6)
Natural Language Processing
(4)
Computer Vision
(3)
Optimization & Theory
(3)
Resources & Methods
(3)
Deep Learning
(2)
Application Areas
(2)
Core Methods
(2)
Generation · Computer Vision
(2)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Analysis
(1)
Generation · Natural Language Processing
(1)
Keywords
reward model
(3)
vision-language model
(2)
text-to-image generation
(2)
contrastive learning
(1)
preference optimization
(1)
determinantal point process
(1)
uncertainty quantification
(1)
safety alignment
(1)
mutual information
(1)
differential entropy
(1)
online reinforcement learning
(1)
bradley-terry model
(1)
reward hacking
(1)
diffusion model
(1)
semantic embedding
(1)
machine unlearning
(1)
semantic segmentation
(1)
3d gaussian splatting
(1)
model quantization
(1)
model compression
(1)
Papers
ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models
AAAI 2026
Selection of LLM Fine-Tuning Data Based on Orthogonal Rules
AAAI 2026
Semantic Volume: Quantifying and Detecting Both External and Internal Uncertainty in LLMs
AAAI 2026
Style-GRPO: Semantic-Aware Preference Optimization for Image Style Transfer Guided by Reward Modeling
CVPR 2026
Catastrophic Failure of LLM Unlearning via Quantization
ICLR 2025
CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting
ICCV 2025
ReNeg: Learning Negative Embedding with Reward Guidance
CVPR 2025
RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHF
ICML 2025