Xiaomin Li
7 papers · 2025–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π Cross-Pollinator (15) π Renaissance Researcher (5) π Conference Polyglot (4) πΊοΈ Taxonomy Completionist (18)
π§
Keyword Pioneer
β
Rising Star
(7)
Conferences
AAAI (3)
CVPR (1)
ICCV (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
contrastive learning
(1)
semantic segmentation
(1)
uncertainty quantification
(1)
text-to-image generation
(1)
safety alignment
(1)
differential entropy
(1)
bradley-terry model
(1)
determinantal point process
(1)
diffusion model
(1)
semantic embedding
(1)
reward hacking
(1)
vision language model
(1)
reward model
(1)
3d gaussian splatting
(1)
classifier-free guidance
(1)
llm fine-tuning
(1)
hallucination detection
(1)
cross-view consistency
(1)
clip text encoder
(1)
reward guidance
(1)
Papers
ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models
AAAI 2026
Semantic Volume: Quantifying and Detecting Both External and Internal Uncertainty in LLMs
AAAI 2026
Selection of LLM Fine-Tuning Data Based on Orthogonal Rules
AAAI 2026
ReNeg: Learning Negative Embedding with Reward Guidance
CVPR 2025
RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHF
ICML 2025
CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting
ICCV 2025
Catastrophic Failure of LLM Unlearning via Quantization
ICLR 2025