{"total":67,"rows":[{"id":"2501.00569","title":"Probing Visual Language Priors in VLMs","created":"2024-12-31","cited_by_count":45,"area":"lr"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2506.21656","title":"Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs","created":"2025-06-26","cited_by_count":32,"area":"lr"},{"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":"2507.19024","title":"A Survey of Multimodal Hallucination Evaluation and Detection","created":"2025-07-25","cited_by_count":27,"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":"2509.25373","title":"From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models","created":"2025-09-29","cited_by_count":26,"area":"lr"},{"id":"2605.21924","title":"Visual-Advantage On-Policy Distillation for Vision-Language Models","created":"2026-05-21","cited_by_count":24,"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":"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":"2510.06077","title":"When Thinking Drifts: Evidential Grounding for Robust Video Reasoning","created":"2025-10-07","cited_by_count":16,"area":null},{"id":"2502.13928","title":"Symmetrical Visual Contrastive Optimization: Aligning Vision-Language Models with Minimal Contrastive Images","created":"2025-02-19","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":"2509.23050","title":"Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding","created":"2025-09-27","cited_by_count":14,"area":"mllm"},{"id":"2507.09184","title":"MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models","created":"2025-07-12","cited_by_count":12,"area":"mllm"},{"id":"2504.10143","title":"On the Value of Cross-Modal Misalignment in Multimodal Representation Learning","created":"2025-04-14","cited_by_count":10,"area":null},{"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":"2601.21634","title":"RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoning","created":"2026-01-29","cited_by_count":8,"area":"lr"},{"id":"2412.14487","title":"Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation","created":"2024-12-19","cited_by_count":7,"area":"mllm"},{"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":"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":"2604.14129","title":"Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models","created":"2026-04-15","cited_by_count":6,"area":"mllm"},{"id":"2505.21061","title":"LPOI: Listwise Preference Optimization for Vision Language Models","created":"2025-05-27","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":"2604.13029","title":"Visual Preference Optimization with Rubric Rewards","created":"2026-04-14","cited_by_count":5,"area":"alignment"},{"id":"2506.11162","title":"VIBE: Can a VLM Read the Room?","created":"2025-06-11","cited_by_count":4,"area":null},{"id":"2507.04410","title":"Multimedia Verification Through Multi-Agent Deep Research Multimodal Large Language Models","created":"2025-07-06","cited_by_count":4,"area":"mllm"},{"id":"2509.21997","title":"Exposing Hallucinations To Suppress Them: VLMs Representation Editing With Generative Anchors","created":"2025-09-26","cited_by_count":4,"area":"mllm"},{"id":"2510.10285","title":"Reallocating Attention Across Layers to Reduce Multimodal Hallucination","created":"2025-10-11","cited_by_count":4,"area":"lr"},{"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":"2506.00835","title":"SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning","created":"2025-06-01","cited_by_count":3,"area":"alignment"},{"id":"2510.16333","title":"RL makes MLLMs see better than SFT","created":"2025-10-18","cited_by_count":3,"area":"mllm"},{"id":"2505.14405","title":"Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency","created":"2025-05-20","cited_by_count":2,"area":"mllm"},{"id":"2505.15963","title":"OViP: Online Vision-Language Preference Learning for VLM Hallucination","created":"2025-05-21","cited_by_count":2,"area":"mllm"},{"id":"2505.22396","title":"Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs","created":"2025-05-28","cited_by_count":2,"area":"mllm"},{"id":"2508.03177","title":"SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision","created":"2025-08-05","cited_by_count":2,"area":"mllm"},{"id":"2508.10955","title":"Empowering Multimodal LLMs with External Tools: A Comprehensive Survey","created":"2025-08-14","cited_by_count":2,"area":"mllm"},{"id":"2512.23426","title":"Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision","created":"2025-12-29","cited_by_count":2,"area":"diffusion"},{"id":"2603.12149","title":"Linking Perception, Confidence and Accuracy in MLLMs","created":"2026-03-12","cited_by_count":2,"area":"mllm"},{"id":"2604.21911","title":"When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs","created":"2026-04-23","cited_by_count":2,"area":"mllm"},{"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":"2607.16303","title":"Med-OPD: Improving Medical Vision-Language Models via Evidence-Aware On-Policy Distillation","created":"2026-07-14","cited_by_count":2,"area":"lr"},{"id":"2506.05260","title":"LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs","created":"2025-06-05","cited_by_count":1,"area":"alignment"},{"id":"2602.02341","title":"LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2603.06024","title":"ViewFusion: Structured Spatial Thinking Chains for Multi-View Reasoning","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2604.26419","title":"Delineating Knowledge Boundaries for Honest Large Vision-Language Models","created":"2026-04-29","cited_by_count":1,"area":"mllm"},{"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":"2606.07647","title":"Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation","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":"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":"2601.23222","title":"Region-Normalized DPO for Medical Image Segmentation under Noisy Judges","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.01769","title":"IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination","created":"2026-02-02","cited_by_count":0,"area":"mllm"},{"id":"2603.25145","title":"Learning to Rank Caption Chains for Video-Text Alignment","created":"2026-03-26","cited_by_count":0,"area":"alignment"},{"id":"2605.00323","title":"Online Self-Calibration Against Hallucination in Vision-Language Models","created":"2026-05-01","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":"2605.09443","title":"Through the Lens of Character: Resolving Modality-Role Interference in Multimodal Role-Playing Agent","created":"2026-05-10","cited_by_count":0,"area":"mllm"},{"id":"2605.25036","title":"Language Bias in LVLMs: From In-Depth Analysis to Simple and Effective Mitigation","created":"2026-05-24","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":"2607.17243","title":"LenGuard-GPC: Length Guarding with Guided-Prompt Consistency for Spatial Reasoning Reinforce Learning","created":"2026-07-19","cited_by_count":0,"area":"lr"},{"id":"2608.11024","title":"When Visual Signals Mislead: A Mechanistic Study of Attribute Hallucination in Vision-Language Models","created":"2026-08-11","cited_by_count":0,"area":"mllm"},{"id":"2608.21819","title":"PatchGate: Narrowing the Verbalization Gap with Intrinsic Object Inventories in Frozen Vision-Language Models","created":"2026-08-22","cited_by_count":0,"area":"mllm"},{"id":"2608.22963","title":"Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents","created":"2026-08-24","cited_by_count":0,"area":"mllm"},{"id":"2609.38979","title":"Mitigating Object Hallucination in Large Vision-Language Models via False Discovery Controlled Visual Data Splitting","created":"2026-09-30","cited_by_count":0,"area":"mllm"},{"id":"2609.39120","title":"Is Better Teacher Supervision Enough? Unlocking Student-side Learning in Multimodal On-Policy Distillation","created":"2026-09-30","cited_by_count":0,"area":"distill"}],"next_cursor":null}