{"total":18,"rows":[{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154,"area":"alignment"},{"id":"2405.17220","title":"RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness","created":"2024-05-27","cited_by_count":131,"area":"alignment"},{"id":"2411.17451","title":"VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models","created":"2024-11-26","cited_by_count":86,"area":"alignment"},{"id":"2405.19335","title":"X-VILA: Cross-Modality Alignment for Large Language Model","created":"2024-05-29","cited_by_count":46,"area":"alignment"},{"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":"2506.02095","title":"Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences","created":"2025-06-02","cited_by_count":22,"area":"alignment"},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2502.11455","title":"Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training","created":"2025-02-17","cited_by_count":12,"area":"alignment"},{"id":"2501.06761","title":"VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning","created":"2025-01-12","cited_by_count":9,"area":"alignment"},{"id":"2504.12083","title":"Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization","created":"2025-04-16","cited_by_count":7,"area":"alignment"},{"id":"2510.17833","title":"Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage","created":"2025-10-03","cited_by_count":5,"area":"alignment"},{"id":"2509.17116","title":"MCTS-EP: Empowering Embodied Planning with Online Preference Optimization","created":"2025-09-21","cited_by_count":2,"area":"alignment"},{"id":"2510.00647","title":"MCM-DPO: Multifaceted Cross-Modal Direct Preference Optimization for Alt-text Generation","created":"2025-10-01","cited_by_count":0,"area":"alignment"},{"id":"2603.29467","title":"M-MiniGPT4: Multilingual VLLM Alignment via Translated Data","created":"2026-03-31","cited_by_count":0,"area":"alignment"},{"id":"2604.08213","title":"EditCaption: Human-Refined SFT and HAE-DPO for Image Editing Instruction Synthesis","created":"2026-04-09","cited_by_count":0,"area":"alignment"},{"id":"2606.14586","title":"S$^2$COPE: Self-Supervised Concept Discovery via Preference Learning","created":"2026-06-12","cited_by_count":0,"area":"alignment"},{"id":"2607.01144","title":"Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search","created":"2026-07-01","cited_by_count":0,"area":"alignment"}],"next_cursor":null}