{"total":69,"rows":[{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246,"area":"lr"},{"id":"2406.04314","title":"Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization","created":"2024-06-06","cited_by_count":84,"area":"diffusion"},{"id":"2502.13124","title":"NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions","created":"2025-02-18","cited_by_count":84,"area":"lr"},{"id":"2503.15265","title":"DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning","created":"2025-03-19","cited_by_count":65,"area":"alignment"},{"id":"2404.04925","title":"Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers","created":"2024-04-07","cited_by_count":51,"area":"lr"},{"id":"2410.15522","title":"M-RewardBench: Evaluating Reward Models in Multilingual Settings","created":"2024-10-20","cited_by_count":50,"area":"alignment"},{"id":"2411.04109","title":"Self-Consistency Preference Optimization","created":"2024-11-06","cited_by_count":50,"area":"lr"},{"id":"2505.05408","title":"Crosslingual Reasoning through Test-Time Scaling","created":"2025-05-08","cited_by_count":46,"area":"lr"},{"id":"2502.12057","title":"Culture is Not Trivia: Sociocultural Theory for Cultural NLP","created":"2025-02-17","cited_by_count":40,"area":null},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2502.09457","title":"A Survey of Multilingual Reasoning in Language Models","created":"2025-02-13","cited_by_count":33,"area":"lr"},{"id":"2506.21656","title":"Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs","created":"2025-06-26","cited_by_count":32,"area":"lr"},{"id":"2410.08964","title":"Language Imbalance Driven Rewarding for Multilingual Self-improving","created":"2024-10-11","cited_by_count":28,"area":"synth"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2505.16761","title":"Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning","created":"2025-05-22","cited_by_count":22,"area":"alignment"},{"id":"2410.01335","title":"Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models","created":"2024-10-02","cited_by_count":21,"area":null},{"id":"2505.13141","title":"Language-Specific Latent Process Hinders Cross-Lingual Performance","created":"2025-05-19","cited_by_count":21,"area":null},{"id":"2407.16222","title":"PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment","created":"2024-07-23","cited_by_count":20,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2501.03681","title":"SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment","created":"2025-01-07","cited_by_count":18,"area":"lr"},{"id":"2505.16869","title":"MPO: Multilingual Safety Alignment via Reward Gap Optimization","created":"2025-05-22","cited_by_count":18,"area":"alignment"},{"id":"2510.07300","title":"Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning","created":"2025-10-08","cited_by_count":18,"area":"lr"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2504.01801","title":"Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training","created":"2025-04-02","cited_by_count":16,"area":null},{"id":"2504.05154","title":"CARE: Multilingual Human Preference Learning for Cultural Awareness","created":"2025-04-07","cited_by_count":15,"area":"alignment"},{"id":"2510.27269","title":"Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?","created":"2025-10-31","cited_by_count":12,"area":"lr"},{"id":"2506.05850","title":"Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language Models","created":"2025-06-06","cited_by_count":11,"area":"lr"},{"id":"2509.23659","title":"Aligning LLMs for Multilingual Consistency in Enterprise Applications","created":"2025-09-28","cited_by_count":11,"area":null},{"id":"2501.18457","title":"CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering","created":"2025-01-30","cited_by_count":10,"area":"alignment"},{"id":"2503.04647","title":"Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment","created":"2025-03-06","cited_by_count":9,"area":"alignment"},{"id":"2504.15241","title":"MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety","created":"2025-04-21","cited_by_count":9,"area":"lr"},{"id":"2511.00804","title":"EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment","created":"2025-11-02","cited_by_count":9,"area":"alignment"},{"id":"2601.13262","title":"CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning","created":"2026-01-19","cited_by_count":9,"area":"lr"},{"id":"2602.16660","title":"Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment","created":"2026-02-18","cited_by_count":9,"area":"alignment"},{"id":"2505.21505","title":"How Does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2507.07510","title":"Divergence Minimization Preference Optimization for Diffusion Model Alignment","created":"2025-07-10","cited_by_count":8,"area":"diffusion"},{"id":"2405.01345","title":"The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights","created":"2024-05-02","cited_by_count":7,"area":"lr"},{"id":"2506.11430","title":"Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization","created":"2025-06-13","cited_by_count":7,"area":null},{"id":"2502.17956","title":"Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments","created":"2025-02-25","cited_by_count":6,"area":"lr"},{"id":"2506.16502","title":"Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples","created":"2025-06-19","cited_by_count":6,"area":"alignment"},{"id":"2405.13923","title":"Why Not Transform Chat Large Language Models to Non-English?","created":"2024-05-22","cited_by_count":5,"area":null},{"id":"2601.16390","title":"Cross-Lingual Activation Steering for Multilingual Language Models","created":"2026-01-23","cited_by_count":5,"area":"mechinterp"},{"id":"2602.05940","title":"R3S: Refining and Recovering Reinforcement Signals for Multilingual Understanding and Reasoning","created":"2026-02-05","cited_by_count":5,"area":"lr"},{"id":"2503.18484","title":"Benchmarking and Boosting Multilingual Capabilities of LVLMs via OCR-Centric Reinforcement Learning","created":"2025-03-24","cited_by_count":4,"area":"mllm"},{"id":"2504.10906","title":"Understanding LLMs' Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From","created":"2025-04-15","cited_by_count":4,"area":null},{"id":"2504.14669","title":"Trans-Zero: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data","created":"2025-04-20","cited_by_count":4,"area":"synth"},{"id":"2511.13254","title":"Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2511.07691","title":"CAPO: Confidence Aware Preference Optimization Learning for Multilingual Preferences","created":"2025-11-10","cited_by_count":3,"area":"alignment"},{"id":"2602.00413","title":"Alignment of Diffusion Model and Flow Matching for Text-to-Image Generation","created":"2026-01-31","cited_by_count":3,"area":"diffusion"},{"id":"2506.02461","title":"XToM: Exploring the Multilingual Theory of Mind for Large Language Models","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2509.08541","title":"CM-Align: Consistency-based Multilingual Alignment for Large Language Models","created":"2025-09-10","cited_by_count":2,"area":"alignment"},{"id":"2601.08267","title":"Med-CoReasoner: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning","created":"2026-01-13","cited_by_count":2,"area":"lr"},{"id":"2605.28272","title":"EchoAvatar: Real-time Generative Avatar Animation from Audio Streams","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2607.00485","title":"Efficient Multilingual Reasoning Transfer via Progressive Code-Switching","created":"2026-07-01","cited_by_count":2,"area":"lr"},{"id":"2601.00263","title":"Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation","created":"2026-01-01","cited_by_count":1,"area":null},{"id":"2602.11902","title":"Mitigating Mismatch within Reference-based Preference Optimization","created":"2026-02-12","cited_by_count":1,"area":"alignment"},{"id":"2605.25360","title":"Learning to Route Languages for Multilingual Policy Optimization","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.26293","title":"CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations","created":"2026-05-25","cited_by_count":0,"area":"alignment"},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2607.11736","title":"MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning","created":"2026-07-13","cited_by_count":0,"area":"lr"},{"id":"2608.06347","title":"RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning Transfer","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2608.15964","title":"LLMs Get Smarter from Targeted Synthetic Multilingual Data","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.23149","title":"Language Chain in Alignment: Cross-lingual Ranking Preference Optimization","created":"2026-08-24","cited_by_count":0,"area":"alignment"},{"id":"2609.04409","title":"A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Models","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2610.04899","title":"Rewrite What Matters: Adaptive Multilingual Query Rewriting for Reasoning via Agentic Reinforcement Learning","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}