conftrace_

reverse kl divergence

10 papers

Explore in graph

Also known as

RKL RKLD REVERSE KL

Co-occurring keywords · papers mentioning both

knowledge distillation (4) large language model (2) kl divergence (2) variational inference (2) score-based generative modeling (1) discretization scheme (1) gan discriminator (1) mode-seeking behavior (1) dual discriminator (1) self-improving alignment (1)

Papers

On the Convergence of Self-Improving Online LLM Alignment UAI 2026 Balancing Forget Quality and Model Utility: A Reverse KL-Divergence Knowledge Distillation Approach for Better Unlearning in LLMs NAACL 2025 Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator ICML 2025 Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL ACL 2025 Choosy Babies Need One Coach: Inducing Mode-Seeking Behavior in BabyLlama with Reverse KL Divergence CoNLL 2024 Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians ICML 2024 Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions ICML 2023 Learning Continuous Normalizing Flows For Faster Convergence To Target Distribution via Ascent Regularizations ICLR 2023 Probability Distillation: A Caveat and Alternatives UAI 2019 Dual Discriminator Generative Adversarial Nets NeurIPS 2017