{"total":92,"rows":[{"id":"2504.07954","title":"Perception-R1: Pioneering Perception Policy with Reinforcement Learning","created":"2025-04-10","cited_by_count":120,"area":"lr"},{"id":"2501.09695","title":"Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key","created":"2025-01-16","cited_by_count":65,"area":"mllm"},{"id":"2507.05255","title":"Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning","created":"2025-07-07","cited_by_count":34,"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":"2501.16629","title":"CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs","created":"2025-01-28","cited_by_count":31,"area":"mllm"},{"id":"2503.17682","title":"Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback","created":"2025-03-22","cited_by_count":30,"area":"mllm"},{"id":"2505.24871","title":"MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning","created":"2025-05-30","cited_by_count":30,"area":"mllm"},{"id":"2502.13146","title":"Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization","created":"2025-02-18","cited_by_count":29,"area":"mllm"},{"id":"2410.03659","title":"Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models","created":"2024-10-04","cited_by_count":28,"area":"mllm"},{"id":"2410.15334","title":"Modality-Fair Preference Optimization for Trustworthy MLLM Alignment","created":"2024-10-20","cited_by_count":26,"area":"mllm"},{"id":"2503.10480","title":"World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning","created":"2025-03-13","cited_by_count":26,"area":"wm"},{"id":"2503.00361","title":"Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding","created":"2025-03-01","cited_by_count":24,"area":"mllm"},{"id":"2410.09047","title":"Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models","created":"2024-10-11","cited_by_count":23,"area":"mllm"},{"id":"2412.06141","title":"MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization","created":"2024-12-09","cited_by_count":21,"area":"mllm"},{"id":"2505.19616","title":"Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models","created":"2025-05-26","cited_by_count":19,"area":"mllm"},{"id":"2504.05810","title":"PaMi-VDPO: Mitigating Video Hallucinations by Prompt-Aware Multi-Instance Video Preference Learning","created":"2025-04-08","cited_by_count":17,"area":"mllm"},{"id":"2506.01274","title":"ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding","created":"2025-06-02","cited_by_count":16,"area":"mllm"},{"id":"2505.17534","title":"Co-Reinforcement Learning for Unified Multimodal Understanding and Generation","created":"2025-05-23","cited_by_count":15,"area":"lr"},{"id":"2502.01943","title":"DAMA: Data- and Model-aware Alignment of Multi-modal LLMs","created":"2025-02-04","cited_by_count":14,"area":"mllm"},{"id":"2506.11712","title":"Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization","created":"2025-06-13","cited_by_count":14,"area":"mllm"},{"id":"2510.13418","title":"Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation","created":"2025-10-15","cited_by_count":14,"area":"lr"},{"id":"2503.14504","title":"Aligning Multimodal LLM with Human Preference: A Survey","created":"2025-03-18","cited_by_count":13,"area":"mllm"},{"id":"2602.12506","title":"On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2411.11909","title":"SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization","created":"2024-11-17","cited_by_count":10,"area":"mllm"},{"id":"2502.04371","title":"PerPO: Perceptual Preference Optimization via Discriminative Rewarding","created":"2025-02-05","cited_by_count":9,"area":"mllm"},{"id":"2505.19601","title":"Preference Optimization by Estimating the Ratio of the Data Distribution","created":"2025-05-26","cited_by_count":9,"area":"alignment"},{"id":"2509.00723","title":"OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination","created":"2025-08-31","cited_by_count":9,"area":"alignment"},{"id":"2504.01735","title":"AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization","created":"2025-04-02","cited_by_count":8,"area":"mllm"},{"id":"2504.14096","title":"VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment","created":"2025-04-18","cited_by_count":8,"area":"alignment"},{"id":"2506.08022","title":"Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining","created":"2025-05-20","cited_by_count":8,"area":"mllm"},{"id":"2411.17265","title":"Systematic Reward Gap Optimization for Mitigating VLM Hallucinations","created":"2024-11-26","cited_by_count":7,"area":"mllm"},{"id":"2508.20181","title":"Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization","created":"2025-08-27","cited_by_count":7,"area":"mllm"},{"id":"2510.23479","title":"MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding","created":"2025-10-27","cited_by_count":7,"area":"mllm"},{"id":"2605.25343","title":"Toward Native Multimodal Modeling: A Roadmap","created":"2026-05-25","cited_by_count":7,"area":"wm"},{"id":"2502.02810","title":"Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization","created":"2025-02-05","cited_by_count":6,"area":null},{"id":"2504.15619","title":"AdaViP: Aligning Multi-modal LLMs via Adaptive Vision-enhanced Preference Optimization","created":"2025-04-22","cited_by_count":6,"area":"mllm"},{"id":"2602.04486","title":"Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition","created":"2026-02-04","cited_by_count":6,"area":"lr"},{"id":"2603.03192","title":"MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization","created":"2026-03-03","cited_by_count":6,"area":"alignment"},{"id":"2504.01589","title":"Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models","created":"2025-04-02","cited_by_count":5,"area":"mllm"},{"id":"2506.09935","title":"LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning","created":"2025-06-11","cited_by_count":5,"area":"mllm"},{"id":"2508.14264","title":"Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models","created":"2025-08-19","cited_by_count":5,"area":"mllm"},{"id":"2509.25717","title":"Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization","created":"2025-09-30","cited_by_count":5,"area":"mllm"},{"id":"2511.19417","title":"Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration","created":"2025-11-24","cited_by_count":5,"area":"lr"},{"id":"2602.03380","title":"Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization","created":"2026-02-03","cited_by_count":5,"area":"lr"},{"id":"2604.13029","title":"Visual Preference Optimization with Rubric Rewards","created":"2026-04-14","cited_by_count":5,"area":"alignment"},{"id":"2508.01678","title":"Cure or Poison? Embedding Instructions Visually Alters Hallucination in Vision-Language Models","created":"2025-08-03","cited_by_count":4,"area":"mllm"},{"id":"2512.00706","title":"Optimizing LVLMs with On-Policy Data for Effective Hallucination Mitigation","created":"2025-11-30","cited_by_count":4,"area":"mllm"},{"id":"2510.14374","title":"Spatial Preference Rewarding for MLLMs Spatial Understanding","created":"2025-10-16","cited_by_count":3,"area":"mllm"},{"id":"2510.16333","title":"RL makes MLLMs see better than SFT","created":"2025-10-18","cited_by_count":3,"area":"mllm"},{"id":"2512.13240","title":"Reflective Preference Optimization (RPO): Enhancing On-Policy Alignment via Hint-Guided Reflection","created":"2025-12-15","cited_by_count":3,"area":"mllm"},{"id":"2512.22120","title":"See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning","created":"2025-12-26","cited_by_count":3,"area":"lr"},{"id":"2601.00623","title":"DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations","created":"2026-01-02","cited_by_count":3,"area":"mllm"},{"id":"2603.17044","title":"Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models","created":"2026-03-17","cited_by_count":3,"area":"alignment"},{"id":"2505.15963","title":"OViP: Online Vision-Language Preference Learning for VLM Hallucination","created":"2025-05-21","cited_by_count":2,"area":"mllm"},{"id":"2505.19100","title":"ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning","created":"2025-05-25","cited_by_count":2,"area":"lr"},{"id":"2506.03095","title":"DPO Learning with LLMs-Judge Signal for Computer Use Agents","created":"2025-06-03","cited_by_count":2,"area":"mllm"},{"id":"2508.11616","title":"Controlling Multimodal LLMs via Reward-guided Decoding","created":"2025-08-15","cited_by_count":2,"area":"mllm"},{"id":"2512.22183","title":"Unbiased Visual Reasoning with Controlled Visual Inputs","created":"2025-12-19","cited_by_count":2,"area":"lr"},{"id":"2605.23975","title":"Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs","created":"2026-05-13","cited_by_count":2,"area":"alignment"},{"id":"2606.24636","title":"CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning","created":"2026-06-23","cited_by_count":2,"area":"lr"},{"id":"2606.31054","title":"ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs","created":"2026-06-30","cited_by_count":2,"area":"mllm"},{"id":"2606.31933","title":"No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2412.11196","title":"Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal","created":"2024-12-15","cited_by_count":1,"area":"mllm"},{"id":"2412.19005","title":"Enhancing Audiovisual Speech Recognition through Bifocal Preference Optimization","created":"2024-12-26","cited_by_count":1,"area":null},{"id":"2506.02015","title":"OSPO: Object-Centric Self-Improving Preference Optimization for Text-to-Image Generation","created":"2025-05-28","cited_by_count":1,"area":"mllm"},{"id":"2509.24491","title":"Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs","created":"2025-09-29","cited_by_count":1,"area":"mllm"},{"id":"2603.00355","title":"StethoLM: Audio Language Model for Cardiopulmonary Analysis Across Clinical Tasks","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2603.13054","title":"Topo-R1: Detecting Topological Anomalies via Vision-Language Models","created":"2026-03-13","cited_by_count":1,"area":"mllm"},{"id":"2604.23988","title":"Hindsight Preference Optimization for Financial Time Series Advisory","created":"2026-04-27","cited_by_count":1,"area":"alignment"},{"id":"2605.28023","title":"VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.03376","title":"P$^2$-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization","created":"2026-06-02","cited_by_count":1,"area":"mllm"},{"id":"2606.29805","title":"Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation","created":"2026-06-29","cited_by_count":1,"area":"mllm"},{"id":"2607.00247","title":"Adaptive Perturbation Selection for Contrastive Audio Decoding","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2609.21755","title":"ECG Mirage: Revealing and Mitigating the Underutilisation of ECGs in Vision-Language Models for Clinical Prediction","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2507.21584","title":"TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs","created":"2025-07-29","cited_by_count":0,"area":"mllm"},{"id":"2510.03955","title":"Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2510.04196","title":"COSMO-RL: Towards Trustworthy LMRMs via Joint Safety and Stability","created":"2025-10-05","cited_by_count":0,"area":"lr"},{"id":"2510.21093","title":"MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning","created":"2025-10-24","cited_by_count":0,"area":"lr"},{"id":"2510.23253","title":"A Video Is Not Worth a Thousand Words","created":"2025-10-27","cited_by_count":0,"area":"mllm"},{"id":"2511.19023","title":"OrdMoE: Preference Alignment via Hierarchical Expert Group Ranking in Multimodal Mixture-of-Experts LLMs","created":"2025-11-24","cited_by_count":0,"area":"mllm"},{"id":"2603.10300","title":"From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2605.03790","title":"Enhancing Visual Question Answering with Multimodal LLMs via Chain-of-Question Guided Retrieval-Augmented Generation","created":"2026-05-05","cited_by_count":0,"area":"mllm"},{"id":"2605.04874","title":"Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models","created":"2026-05-06","cited_by_count":0,"area":"mllm"},{"id":"2606.12590","title":"Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs","created":"2026-06-10","cited_by_count":0,"area":"mllm"},{"id":"2606.17953","title":"MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias","created":"2026-06-16","cited_by_count":0,"area":"mllm"},{"id":"2606.28401","title":"Vision-driven Preference Synthesis for Mitigating Hallucinations in VLMs","created":"2026-06-24","cited_by_count":0,"area":"mllm"},{"id":"2608.12746","title":"Dual-Stream Cross-Anchor Correction Grounding Long-Form Captions and the Domain Limits of Object-Level Anchors","created":"2026-08-13","cited_by_count":0,"area":"mllm"},{"id":"2609.16601","title":"SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation","created":"2026-09-15","cited_by_count":0,"area":"lr"},{"id":"2609.32185","title":"Contamination, Prior, or Evidence? Decomposing and Training Evidence Use in Whole-Slide Vision-Language Models","created":"2026-09-26","cited_by_count":0,"area":"mllm"},{"id":"2609.32422","title":"MergeHEIR: Mitigating Multimodal Hallucinations as the Tax of Model Merging","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35294","title":"Beyond Saying Less: Fine-Grained Alignment for Informative and Faithful Vision-Language Models","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2609.38285","title":"GaugeVLM: Structuring Spatial Supervision with Measured Geometric Interventions","created":"2026-09-29","cited_by_count":0,"area":"mllm"}],"next_cursor":null}