Image de couverture de livre

Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yuan, Rui, Khandoga, Mykola, Sankarapu, Vinay Kumar
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization
par: Khandoga, Mykola, et autres
Publié: (2026)

Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands
par: Seth, Pratinav, et autres
Publié: (2026)

Divergence-Augmented Policy Optimization
par: Wang, Qing, et autres
Publié: (2025)

Optimal Stability of KL Divergence under Gaussian Perturbations
par: Pan, Jialu, et autres
Publié: (2026)

On Flow Matching KL Divergence
par: Su, Maojiang, et autres
Publié: (2025)

Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence
par: Zhu, Lingwei, et autres
Publié: (2023)

Interpretability as Alignment: Making Internal Understanding a Design Principle
par: Sengupta, Aadit, et autres
Publié: (2025)

Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliance
par: Seth, Pratinav, et autres
Publié: (2025)

Orion-Bix: Bi-Axial Attention for Tabular In-Context Learning
par: Bouadi, Mohamed, et autres
Publié: (2025)

Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning
par: Bouadi, Mohamed, et autres
Publié: (2025)

On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning
par: Zhang, Yifan, et autres
Publié: (2025)

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
par: Fan, Jiajun, et autres
Publié: (2025)

Distilling Tabular Foundation Models for Structured Health Data
par: Tanna, Aditya, et autres
Publié: (2026)

TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models
par: Tanna, Aditya, et autres
Publié: (2025)

APO: Alpha-Divergence Preference Optimization
par: Zixian, Wang
Publié: (2025)

From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation
par: Wang, Yongqi, et autres
Publié: (2026)

Bidirectional Soft Actor-Critic: Leveraging Forward and Reverse KL Divergence for Efficient Reinforcement Learning
par: Zhang, Yixian, et autres
Publié: (2025)

A Unified Framework for Rethinking Policy Divergence Measures in GRPO
par: Wu, Qingyuan, et autres
Publié: (2026)

Ensembling Tabular Foundation Models - A Diversity Ceiling And A Calibration Trap
par: Tanna, Aditya, et autres
Publié: (2026)

Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality
par: Bouadi, Mohamed, et autres
Publié: (2026)

Data Presentation Over Architecture: Resampling Strategies for Credit Risk Prediction with Tabular Foundation Models
par: Tanna, Aditya, et autres
Publié: (2026)

DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models
par: Sankarapu, Vinay Kumar, et autres
Publié: (2024)

xai_evals : A Framework for Evaluating Post-Hoc Local Explanation Methods
par: Seth, Pratinav, et autres
Publié: (2025)

Bayesian Pseudo-Coresets via Contrastive Divergence
par: Tiwary, Piyush, et autres
Publié: (2023)

Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted Trees
par: Tanna, Aditya, et autres
Publié: (2026)

LLM Safety Alignment is Divergence Estimation in Disguise
par: Haldar, Rajdeep, et autres
Publié: (2025)

Recursive KL Divergence Optimization: A Dynamic Framework for Representation Learning
par: Martin, Anthony D
Publié: (2025)

Rethinking Bregman Divergences in Kronecker-Factored Optimizers
par: Liu, Bing, et autres
Publié: (2026)

AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models
par: Lyngkhoi, R E Zera Marveen, et autres
Publié: (2026)

From Bytes to Borsch: Fine-Tuning Gemma and Mistral for the Ukrainian Language Representation
par: Kiulian, Artur, et autres
Publié: (2024)

Divergence-Suppressing Couplings for Rectified Flow
par: Min, Yimeng, et autres
Publié: (2026)

Convergent World Representations and Divergent Tasks
par: Park, Core Francisco
Publié: (2026)

Rényi Divergence Deep Mutual Learning
par: Huang, Weipeng, et autres
Publié: (2022)

DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning
par: Parekh, Tanmay, et autres
Publié: (2025)

Expert Divergence Learning for MoE-based Language Models
par: Li, Jiaang, et autres
Publié: (2026)

Online Nonconvex Bilevel Optimization with Bregman Divergences
par: Bohne, Jason, et autres
Publié: (2024)

Diverging Flows: Detecting Extrapolations in Conditional Generation
par: Tsakonas, Constantinos, et autres
Publié: (2026)

Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning
par: Li, Xuan, et autres
Publié: (2026)

IDAP++: Advancing Divergence-Based Pruning via Filter-Level and Layer-Level Optimization
par: Samarin, Aleksei, et autres
Publié: (2025)

Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models
par: Yuan, Haonan, et autres
Publié: (2026)