{"total":27,"rows":[{"id":"2410.15553","title":"Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following","created":"2024-10-21","cited_by_count":102,"area":null},{"id":"2509.07430","title":"The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward","created":"2025-09-09","cited_by_count":37,"area":null},{"id":"2410.02596","title":"Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks","created":"2024-10-03","cited_by_count":11,"area":null},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2501.18537","title":"Loss Functions and Operators Generated by f-Divergences","created":"2025-01-30","cited_by_count":10,"area":null},{"id":"2502.00602","title":"Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing","created":"2025-02-02","cited_by_count":8,"area":null},{"id":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8,"area":null},{"id":"2512.15605","title":"Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction","created":"2025-12-17","cited_by_count":8,"area":null},{"id":"2508.09654","title":"Improving Diversity in Language Models: When Temperature Fails, Change the Loss","created":"2025-08-13","cited_by_count":7,"area":null},{"id":"2409.10825","title":"Unveiling and Mitigating Bias in Large Language Model Recommendations: A Path to Fairness","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2410.19471","title":"Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization","created":"2024-10-25","cited_by_count":5,"area":null},{"id":"2412.14050","title":"Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2509.25837","title":"Distillation of Large Language Models via Concrete Score Matching","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2510.11407","title":"KnowRL: Teaching Language Models to Know What They Know","created":"2025-10-13","cited_by_count":5,"area":null},{"id":"2605.09214","title":"Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2512.16565","title":"Non-Asymptotic Global Convergence of PPO-Clip","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2506.01312","title":"Growing Through Experience: Scaling Episodic Grounding in Language Models","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2511.10165","title":"EPO: Diverse and Realistic Protein Ensemble Generation via Energy Preference Optimization","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2602.08660","title":"Equalized Generative Treatment: Matching f-divergences for Fairness in Generative Models","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2503.01066","title":"Alchemist: Towards the Design of Efficient Online Continual Learning System","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2504.05112","title":"ABCDWaveNet: Advancing Robust Road Ponding Detection in Fog through Dynamic Frequency-Spatial Synergy","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2511.13621","title":"Alpha Divergence Losses for Biometric Verification","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2602.05933","title":"Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2606.17664","title":"Temporal Preference Optimization for Unsupervised Retrieval","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.31664","title":"Sparsity-Inducing Divergence Losses for Biometric Verification","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.27757","title":"Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.19022","title":"TalkMatrix: Generating Character Dialogue that is Both Consistent and Diverse","created":"2026-07-20","cited_by_count":0,"area":null}],"next_cursor":null}