{"total":16,"rows":[{"id":"2006.13198","title":"Spectral Bias and Task-Model Alignment Explain Generalization in Kernel Regression and Infinitely Wide Neural Networks","created":"2020-06-23","cited_by_count":166,"area":"alignment"},{"id":"2407.10490","title":"Learning Dynamics of LLM Finetuning","created":"2024-07-15","cited_by_count":95,"area":"alignment"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2405.17346","title":"Prompt Optimization with Human Feedback","created":"2024-05-27","cited_by_count":35,"area":"alignment"},{"id":"2402.10342","title":"Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization","created":"2024-02-15","cited_by_count":25,"area":"alignment"},{"id":"2510.11978","title":"Learning Dynamics of VLM Finetuning","created":"2025-10-13","cited_by_count":17,"area":"alignment"},{"id":"2403.18742","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","created":"2024-03-27","cited_by_count":15,"area":"alignment"},{"id":"2407.17112","title":"Neural Dueling Bandits: Preference-Based Optimization with Human Feedback","created":"2024-07-24","cited_by_count":7,"area":"alignment"},{"id":"2504.12016","title":"Active Human Feedback Collection via Neural Contextual Dueling Bandits","created":"2025-04-16","cited_by_count":4,"area":"alignment"},{"id":"2507.07723","title":"Stable Preference Optimization: A Bilevel Approach to Catastrophic Preference Shift","created":"2025-07-10","cited_by_count":2,"area":"alignment"},{"id":"2509.13079","title":"When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning","created":"2025-09-16","cited_by_count":2,"area":"alignment"},{"id":"2602.01658","title":"Efficient Adversarial Attacks on High-dimensional Offline Bandits","created":"2026-02-02","cited_by_count":2,"area":"alignment"},{"id":"2603.18258","title":"Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization","created":"2026-03-18","cited_by_count":1,"area":"alignment"},{"id":"2512.02409","title":"Data Curation Through the Lens of Spectral Dynamics: Static Limits, Dynamic Acceleration, and Practical Oracles","created":"2025-12-02","cited_by_count":0,"area":"alignment"},{"id":"2605.23650","title":"Learning Kernel-Based MDPs from Episodic Preferential Feedback","created":"2026-05-22","cited_by_count":0,"area":"alignment"},{"id":"2609.06934","title":"The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists","created":"2026-09-07","cited_by_count":0,"area":"alignment"}],"next_cursor":null}