kl divergence

Adaptive KL Control for Direct Preference Optimization in Instruction-Following LLMs AAAI 2026 Advances in PAC-Bayesian certification of deep neural networks: tighter closed-form inequalities and optimization of bounds on non-differentiable losses UAI 2026 Almost Linear Convergence under Minimal Score Assumptions: Quantized Transition Diffusion COLT 2026 ASKD: Reinforcement Learning-Style Knowledge Distillation with Quality-Adaptive Skewness AAAI 2026 C³TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation AAAI 2026 Direct Visual Grounding by Directing Attention of Visual Tokens WACV 2026 Efficient KL Divergence Estimation via Truncated Top-K Integration for Large Language Models ACL 2026 Fully Unsupervised Self-debiasing of Text-to-Image Diffusion Models WACV 2026 MARPO: A Reflective Policy Optimization for Multi-Agent Reinforcement Learning AAAI 2026 Meta-GAIN for Missing Data Imputation AAAI 2026 OD-Stega: LLM-Based Relatively Secure Steganography via Optimized Distributions EACL 2026 Optimal Sample Complexity Lower Bounds on Conditional Independence Testing COLT 2026 Optimization Method for Surrogate Function in Spiking Neural Networks Based on Membrane Potential Distribution AAAI 2026 Recovery thresholds for hidden weighted sparse graphs (extended abstract) COLT 2026 SAGE: Structured Attribute-Guided Enhancement for GZSL AAAI 2026 TIM++: Transductive Information Maximization for Few-Shot CLIP AAAI 2026 What Is It Like to Be a Noise? An Entropy-based Gaussian Noise Regularization for Diffusion Models CVPR 2026 A Variational Information Theoretic Approach to Out-of-Distribution Detection ICML 2025 Bounds on L_p Errors in Density Ratio Estimation via f-Divergence Loss Functions ICLR 2025 BTW: A Non-Parametric Variance Stabilization Framework for Multimodal Model Integration EMNLP 2025 Convergence and Divergence of Language Models under Different Random Seeds EMNLP 2025 DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domains EMNLP 2025 Feature Decomposition-Augmentation Network for Multimodal Sentiment Analysis IJCNLP 2025 Generalization of noisy SGD in unbounded non-convex settings ICML 2025 Guaranteed Generation from Large Language Models ICLR 2025