{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"2311.16922","title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","created":"2023-11-28","cited_by_count":688},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610},{"id":"2310.14566","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","created":"2023-10-23","cited_by_count":583},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528},{"id":"2311.17911","title":"OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation","created":"2023-11-29","cited_by_count":478},{"id":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359},{"id":"2310.00754","title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","created":"2023-10-01","cited_by_count":316},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293},{"id":"2305.08283","title":"From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models","created":"2023-05-15","cited_by_count":260},{"id":"2509.23661","title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","created":"2025-09-28","cited_by_count":244},{"id":"2403.14003","title":"Multi-Modal Hallucination Control by Visual Information Grounding","created":"2024-03-20","cited_by_count":208},{"id":"2407.21771","title":"Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs","created":"2024-07-31","cited_by_count":179},{"id":"2503.01773","title":"Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas","created":"2025-03-03","cited_by_count":95},{"id":"2503.02199","title":"Words or Vision: Do Vision-Language Models Have Blind Faith in Text?","created":"2025-03-04","cited_by_count":89},{"id":"2402.17700","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","created":"2024-02-27","cited_by_count":79},{"id":"2210.07688","title":"Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training","created":"2022-10-14","cited_by_count":72},{"id":"2312.03729","title":"Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?","created":"2023-11-27","cited_by_count":62},{"id":"2306.01879","title":"Revisiting the Role of Language Priors in Vision-Language Models","created":"2023-06-02","cited_by_count":50},{"id":"2406.04236","title":"Understanding Information Storage and Transfer in Multi-modal Large Language Models","created":"2024-06-06","cited_by_count":49},{"id":"2406.08702","title":"VLind-Bench: Measuring Language Priors in Large Vision-Language Models","created":"2024-06-13","cited_by_count":45},{"id":"2501.00569","title":"Probing Visual Language Priors in VLMs","created":"2024-12-31","cited_by_count":45},{"id":"2503.13107","title":"ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models","created":"2025-03-17","cited_by_count":40},{"id":"2410.08145","title":"Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs","created":"2024-10-10","cited_by_count":38},{"id":"2405.15683","title":"Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs","created":"2024-05-24","cited_by_count":33},{"id":"2410.00193","title":"Do Vision-Language Models Really Understand Visual Language?","created":"2024-09-30","cited_by_count":32},{"id":"2203.12258","title":"Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View","created":"2022-03-23","cited_by_count":31},{"id":"2302.01328","title":"IC3: Image Captioning by Committee Consensus","created":"2023-02-02","cited_by_count":20},{"id":"2104.08376","title":"Concadia: Towards Image-Based Text Generation with a Purpose","created":"2021-04-16","cited_by_count":15},{"id":"1704.07434","title":"Paying Attention to Descriptions Generated by Image Captioning Models","created":"2017-04-24","cited_by_count":12},{"id":"2507.13868","title":"When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models","created":"2025-07-18","cited_by_count":11},{"id":"2604.09364","title":"Arbitration Failure, Not Perceptual Blindness: How Vision-Language Models Resolve Visual-Linguistic Conflicts","created":"2026-04-10","cited_by_count":11},{"id":"2306.08685","title":"World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models","created":"2023-06-14","cited_by_count":10},{"id":"2406.12277","title":"What Matters in Memorizing and Recalling Facts? Multifaceted Benchmarks for Knowledge Probing in Language Models","created":"2024-06-18","cited_by_count":9},{"id":"2406.14492","title":"Does Object Grounding Really Reduce Hallucination of Large Vision-Language Models?","created":"2024-06-20","cited_by_count":9},{"id":"2310.02777","title":"The Role of Linguistic Priors in Measuring Compositional Generalization of Vision-Language Models","created":"2023-10-04","cited_by_count":6},{"id":"2506.17901","title":"PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs","created":"2025-06-22","cited_by_count":5},{"id":"2606.27596","title":"Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding","created":"2026-06-25","cited_by_count":4},{"id":"2605.23482","title":"Multimodal Distribution Matching for Vision-Language Dataset Distillation","created":"2026-05-22","cited_by_count":3},{"id":"2305.14083","title":"Counterfactual Augmentation for Multimodal Learning Under Presentation Bias","created":"2023-05-23","cited_by_count":2},{"id":"2602.05437","title":"Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models","created":"2026-02-05","cited_by_count":2},{"id":"2605.24024","title":"Mitigating Hallucinations in Large Vision-Language Models via Causal Route Gating","created":"2026-05-20","cited_by_count":2},{"id":"2606.08894","title":"Are Reasoning Vision-Language Models Robust to Semantic Visual Distractions?","created":"2026-06-08","cited_by_count":2},{"id":"2508.06530","title":"What Makes \"Good\" Distractors for Object Hallucination Evaluation in Large Vision-Language Models?","created":"2025-08-03","cited_by_count":1},{"id":"2608.22916","title":"Knowing Isn't Always Saying: When Do Spatial Encodings Reach Answers in Vision-Language Models?","created":"2026-08-24","cited_by_count":1}],"next_cursor":null}