{"total":184,"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":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422,"area":"alignment"},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315,"area":"alignment"},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2508.03789","title":"HPSv3: Towards Wide-Spectrum Human Preference Score","created":"2025-08-05","cited_by_count":211,"area":"alignment"},{"id":"2503.05236","title":"Unified Reward Model for Multimodal Understanding and Generation","created":"2025-03-07","cited_by_count":199,"area":"alignment"},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183,"area":"alignment"},{"id":"2303.09618","title":"HIVE: Harnessing Human Feedback for Instructional Visual Editing","created":"2023-03-16","cited_by_count":173,"area":"alignment"},{"id":"2412.21059","title":"VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation","created":"2024-12-30","cited_by_count":156,"area":"alignment"},{"id":"2401.04092","title":"GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation","created":"2024-01-08","cited_by_count":153,"area":"alignment"},{"id":"2406.04312","title":"ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization","created":"2024-06-06","cited_by_count":119,"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":"2402.05369","title":"Noise Contrastive Alignment of Language Models with Explicit Rewards","created":"2024-02-08","cited_by_count":85,"area":"alignment"},{"id":"2310.13639","title":"Contrastive Preference Learning: Learning from Human Feedback without RL","created":"2023-10-20","cited_by_count":79,"area":"alignment"},{"id":"2209.00731","title":"In conversation with Artificial Intelligence: aligning language models with human values","created":"2022-09-01","cited_by_count":62,"area":"alignment"},{"id":"2504.04907","title":"Video-Bench: Human-Aligned Video Generation Benchmark","created":"2025-04-07","cited_by_count":57,"area":"alignment"},{"id":"2412.04814","title":"LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment","created":"2024-12-06","cited_by_count":53,"area":"alignment"},{"id":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2402.18091","title":"Polos: Multimodal Metric Learning from Human Feedback for Image Captioning","created":"2024-02-28","cited_by_count":46,"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":"2503.20823","title":"Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy","created":"2025-03-26","cited_by_count":44,"area":"alignment"},{"id":"2412.15838","title":"Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback","created":"2024-12-20","cited_by_count":39,"area":"alignment"},{"id":"2301.12842","title":"Direct Preference-based Policy Optimization without Reward Modeling","created":"2023-01-30","cited_by_count":36,"area":"alignment"},{"id":"2401.05675","title":"Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation","created":"2024-01-11","cited_by_count":36,"area":"alignment"},{"id":"2303.03751","title":"Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles","created":"2023-03-07","cited_by_count":35,"area":"alignment"},{"id":"2405.17346","title":"Prompt Optimization with Human Feedback","created":"2024-05-27","cited_by_count":35,"area":"alignment"},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2402.03749","title":"Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models","created":"2024-02-06","cited_by_count":28,"area":"alignment"},{"id":"2406.07739","title":"UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback","created":"2024-06-11","cited_by_count":27,"area":"alignment"},{"id":"2410.02197","title":"Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment","created":"2024-10-03","cited_by_count":27,"area":"alignment"},{"id":"2211.11602","title":"Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback","created":"2022-11-21","cited_by_count":26,"area":"alignment"},{"id":"2312.09337","title":"Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences","created":"2023-12-14","cited_by_count":26,"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":"2508.21066","title":"OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning","created":"2025-08-28","cited_by_count":23,"area":"alignment"},{"id":"2512.24551","title":"PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation","created":"2025-12-31","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":"2503.18991","title":"Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment","created":"2025-03-23","cited_by_count":20,"area":"alignment"},{"id":"2512.16899","title":"Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image","created":"2025-12-18","cited_by_count":20,"area":"alignment"},{"id":"2307.01139","title":"SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructions","created":"2023-07-03","cited_by_count":19,"area":"alignment"},{"id":"2404.14313","title":"Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels","created":"2024-04-22","cited_by_count":19,"area":"alignment"},{"id":"2405.19988","title":"Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics","created":"2024-05-30","cited_by_count":19,"area":"alignment"},{"id":"2410.14148","title":"Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment","created":"2024-10-18","cited_by_count":19,"area":"alignment"},{"id":"2501.12273","title":"Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement","created":"2025-01-21","cited_by_count":18,"area":"alignment"},{"id":"2509.23082","title":"Follow-Your-Preference: Towards Preference-Aligned Image Inpainting","created":"2025-09-27","cited_by_count":18,"area":"alignment"},{"id":"2504.13122","title":"VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models","created":"2025-04-17","cited_by_count":17,"area":"alignment"},{"id":"2510.11978","title":"Learning Dynamics of VLM Finetuning","created":"2025-10-13","cited_by_count":17,"area":"alignment"},{"id":"2405.20216","title":"Boost Your Human Image Generation Model via Direct Preference Optimization","created":"2024-05-30","cited_by_count":16,"area":"alignment"},{"id":"2303.13512","title":"Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition","created":"2023-03-23","cited_by_count":15,"area":"alignment"},{"id":"2409.09774","title":"Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization","created":"2024-09-15","cited_by_count":15,"area":"alignment"},{"id":"2412.05095","title":"SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization","created":"2024-12-06","cited_by_count":15,"area":"alignment"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"id":"2507.19002","title":"Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment","created":"2025-07-25","cited_by_count":14,"area":"alignment"},{"id":"2603.28547","title":"GEditBench v2: A Human-Aligned Benchmark for General Image Editing","created":"2026-03-30","cited_by_count":14,"area":"alignment"},{"id":"2511.19217","title":"ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment","created":"2025-11-24","cited_by_count":13,"area":"alignment"},{"id":"2602.02380","title":"Unified Personalized Reward Model for Vision Generation","created":"2026-02-02","cited_by_count":13,"area":"alignment"},{"id":"2511.20256","title":"The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation","created":"2025-11-25","cited_by_count":12,"area":"alignment"},{"id":"2408.11481","title":"VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment","created":"2024-08-21","cited_by_count":11,"area":"alignment"},{"id":"2310.12103","title":"Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization","created":"2023-10-18","cited_by_count":10,"area":"alignment"},{"id":"2401.08672","title":"Concept Alignment","created":"2024-01-09","cited_by_count":10,"area":"alignment"},{"id":"2410.06513","title":"MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learning","created":"2024-10-09","cited_by_count":10,"area":"alignment"},{"id":"2501.04561","title":"OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis","created":"2025-01-08","cited_by_count":10,"area":"alignment"},{"id":"2511.19268","title":"BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment","created":"2025-11-24","cited_by_count":10,"area":"alignment"},{"id":"2604.03037","title":"ARM: Advantage Reward Modeling for Long-Horizon Manipulation","created":"2026-04-03","cited_by_count":10,"area":"alignment"},{"id":"2404.01863","title":"Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models","created":"2024-04-02","cited_by_count":9,"area":"alignment"},{"id":"2406.00024","title":"Embedding-Aligned Language Models","created":"2024-05-24","cited_by_count":9,"area":"alignment"},{"id":"2410.05656","title":"On the Modeling Capabilities of Large Language Models for Sequential Decision Making","created":"2024-10-08","cited_by_count":9,"area":"alignment"},{"id":"2410.20898","title":"David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training","created":"2024-10-28","cited_by_count":9,"area":"alignment"},{"id":"2504.10044","title":"Aligning Anime Video Generation with Human Feedback","created":"2025-04-14","cited_by_count":9,"area":"alignment"},{"id":"2601.03468","title":"Understanding Reward Hacking in Text-to-Image Reinforcement Learning","created":"2026-01-06","cited_by_count":9,"area":"alignment"},{"id":"2308.11171","title":"ViCo: Engaging Video Comment Generation with Human Preference Rewards","created":"2023-08-22","cited_by_count":8,"area":"alignment"},{"id":"2311.07723","title":"Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains","created":"2023-11-13","cited_by_count":8,"area":"alignment"},{"id":"2402.09872","title":"Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community","created":"2024-02-15","cited_by_count":8,"area":"alignment"},{"id":"2411.02470","title":"Benchmarking XAI Explanations with Human-Aligned Evaluations","created":"2024-11-04","cited_by_count":8,"area":"alignment"},{"id":"2602.21655","title":"CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning","created":"2026-02-25","cited_by_count":8,"area":"alignment"},{"id":"2402.10896","title":"PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter","created":"2024-02-16","cited_by_count":7,"area":"alignment"},{"id":"2412.00624","title":"VideoSAVi: Self-Aligned Video Language Models without Human Supervision","created":"2024-12-01","cited_by_count":7,"area":"alignment"},{"id":"2502.01616","title":"Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning","created":"2025-02-03","cited_by_count":7,"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":"2506.09814","title":"DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision","created":"2025-06-11","cited_by_count":7,"area":"alignment"},{"id":"2511.20651","title":"RubricRL: Simple Generalizable Rewards for Text-to-Image Generation","created":"2025-11-25","cited_by_count":7,"area":"alignment"},{"id":"2512.04784","title":"PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling","created":"2025-12-02","cited_by_count":7,"area":"alignment"},{"id":"2512.19680","title":"VA-$\\pi$: Variational Policy Alignment for Pixel-Aware Autoregressive Generation","created":"2025-12-22","cited_by_count":7,"area":"alignment"},{"id":"2408.07772","title":"Out-of-Distribution Learning with Human Feedback","created":"2024-08-14","cited_by_count":6,"area":"alignment"},{"id":"2502.12530","title":"Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations","created":"2025-02-18","cited_by_count":6,"area":"alignment"},{"id":"2505.14185","title":"Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study","created":"2025-05-20","cited_by_count":6,"area":"alignment"},{"id":"2510.18053","title":"Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models","created":"2025-10-20","cited_by_count":6,"area":"alignment"},{"id":"2603.22228","title":"SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation","created":"2026-03-23","cited_by_count":6,"area":"alignment"},{"id":"2505.17910","title":"DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback Learning","created":"2025-05-23","cited_by_count":5,"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":"2602.02033","title":"One Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image Generation","created":"2026-02-02","cited_by_count":5,"area":"alignment"},{"id":"2603.15117","title":"MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledge","created":"2026-03-16","cited_by_count":5,"area":"alignment"},{"id":"2605.06583","title":"Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline","created":"2026-05-07","cited_by_count":5,"area":"alignment"},{"id":"2308.06385","title":"ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF","created":"2023-08-11","cited_by_count":4,"area":"alignment"},{"id":"2411.08923","title":"Aligning Visual Contrastive learning models via Preference Optimization","created":"2024-11-12","cited_by_count":4,"area":"alignment"},{"id":"2505.23950","title":"InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback","created":"2025-05-29","cited_by_count":4,"area":"alignment"},{"id":"2506.06970","title":"Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment","created":"2025-06-08","cited_by_count":4,"area":"alignment"},{"id":"2509.21953","title":"MultiCrafter: High-Fidelity Multi-Subject Generation via Disentangled Attention and Identity-Aware Preference Alignment","created":"2025-09-26","cited_by_count":4,"area":"alignment"},{"id":"2602.09411","title":"K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge","created":"2026-02-10","cited_by_count":4,"area":"alignment"}],"next_cursor":"100"}