{"total":60,"rows":[{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336,"area":"mllm"},{"id":"2309.16292","title":"DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models","created":"2023-09-28","cited_by_count":207,"area":"driving"},{"id":"2206.06336","title":"Language Models are General-Purpose Interfaces","created":"2022-06-13","cited_by_count":97,"area":null},{"id":"2307.01848","title":"Embodied Task Planning with Large Language Models","created":"2023-07-04","cited_by_count":84,"area":null},{"id":"2310.00647","title":"Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning","created":"2023-10-01","cited_by_count":30,"area":"mllm"},{"id":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30,"area":null},{"id":"2312.04316","title":"Towards Knowledge-driven Autonomous Driving","created":"2023-12-07","cited_by_count":29,"area":"driving"},{"id":"2402.19387","title":"SeD: Semantic-Aware Discriminator for Image Super-Resolution","created":"2024-02-29","cited_by_count":26,"area":null},{"id":"2411.12701","title":"When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations","created":"2024-11-19","cited_by_count":20,"area":"safety"},{"id":"2503.19622","title":"Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation","created":"2025-03-25","cited_by_count":20,"area":"lr"},{"id":"2208.13628","title":"Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment","created":"2022-08-29","cited_by_count":19,"area":"mllm"},{"id":"2502.12359","title":"LanP: Rethinking the Impact of Language Priors in Large Vision-Language Models","created":"2025-02-17","cited_by_count":14,"area":"lr"},{"id":"2308.09033","title":"Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks","created":"2023-08-17","cited_by_count":12,"area":null},{"id":"2410.13016","title":"Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge","created":"2024-10-16","cited_by_count":12,"area":null},{"id":"2309.01617","title":"DeViL: Decoding Vision features into Language","created":"2023-09-04","cited_by_count":10,"area":null},{"id":"2309.02155","title":"S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learning","created":"2023-09-05","cited_by_count":10,"area":null},{"id":"2504.13275","title":"ChartQA-X: Generating Explanations for Visual Chart Reasoning","created":"2025-04-17","cited_by_count":10,"area":null},{"id":"2307.14611","title":"TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation","created":"2023-07-27","cited_by_count":9,"area":null},{"id":"2207.11401","title":"Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations","created":"2022-07-23","cited_by_count":8,"area":"mllm"},{"id":"2206.09753","title":"Visualizing and Understanding Contrastive Learning","created":"2022-06-20","cited_by_count":7,"area":null},{"id":"2407.20899","title":"Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach","created":"2024-07-30","cited_by_count":7,"area":null},{"id":"2502.01785","title":"AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis","created":"2025-02-03","cited_by_count":7,"area":"mllm"},{"id":"2212.04231","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","created":"2022-12-08","cited_by_count":6,"area":null},{"id":"2406.19170","title":"The Illusion of Competence: Evaluating the Effect of Explanations on Users' Mental Models of Visual Question Answering Systems","created":"2024-06-27","cited_by_count":6,"area":null},{"id":"2312.13594","title":"Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQA","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2408.04471","title":"What could go wrong? Discovering and describing failure modes in computer vision","created":"2024-08-08","cited_by_count":5,"area":null},{"id":"2308.16349","title":"Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations","created":"2023-08-30","cited_by_count":4,"area":null},{"id":"2311.12391","title":"From Wrong To Right: A Recursive Approach Towards Vision-Language Explanation","created":"2023-11-21","cited_by_count":4,"area":"lr"},{"id":"2403.11150","title":"Training A Small Emotional Vision Language Model for Visual Art Comprehension","created":"2024-03-17","cited_by_count":4,"area":"mllm"},{"id":"2510.14741","title":"DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models","created":"2025-10-16","cited_by_count":4,"area":"lr"},{"id":"2606.28864","title":"On Test-Time Scaling for Vision-Language Models","created":"2026-06-27","cited_by_count":4,"area":"lr"},{"id":"2311.05043","title":"Zero-shot Translation of Attention Patterns in VQA Models to Natural Language","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2509.08461","title":"Adapting Vision-Language Models for Neutrino Event Classification in High-Energy Physics","created":"2025-09-10","cited_by_count":3,"area":"mllm"},{"id":"2404.14830","title":"CoProNN: Concept-based Prototypical Nearest Neighbors for Explaining Vision Models","created":"2024-04-23","cited_by_count":2,"area":null},{"id":"2410.19982","title":"Random Policy Enables In-Context Reinforcement Learning within Trust Horizons","created":"2024-10-25","cited_by_count":2,"area":"deeprl"},{"id":"2410.23744","title":"EchoNarrator: Generating natural text explanations for ejection fraction predictions","created":"2024-10-31","cited_by_count":2,"area":null},{"id":"2411.15605","title":"GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2310.00503","title":"Black-box Attacks on Image Activity Prediction and its Natural Language Explanations","created":"2023-09-30","cited_by_count":1,"area":null},{"id":"2311.10933","title":"Representing visual classification as a linear combination of words","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2410.08469","title":"Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP","created":"2024-10-11","cited_by_count":1,"area":"mllm"},{"id":"2410.13488","title":"Seeing Through VisualBERT: A Causal Adventure on Memetic Landscapes","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2502.00711","title":"VIKSER: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework","created":"2025-02-02","cited_by_count":1,"area":"lr"},{"id":"2507.10585","title":"A Taxonomy for Design and Evaluation of Prompt-Based Natural Language Explanations","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2508.12430","title":"Adversarial Attacks on VQA-NLE: Exposing and Alleviating Inconsistencies in Visual Question Answering Explanations","created":"2025-08-17","cited_by_count":1,"area":null},{"id":"2512.07245","title":"Zero-Shot Textual Explanations via Translating Decision-Critical Features","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2603.23149","title":"Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models","created":"2026-03-24","cited_by_count":1,"area":"wm"},{"id":"2303.02601","title":"Knowledge-Based Counterfactual Queries for Visual Question Answering","created":"2023-03-05","cited_by_count":0,"area":null},{"id":"2303.04388","title":"Interpretable Visual Question Answering Referring to Outside Knowledge","created":"2023-03-08","cited_by_count":0,"area":null},{"id":"2307.06795","title":"Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks","created":"2023-07-13","cited_by_count":0,"area":"mllm"},{"id":"2309.00733","title":"TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models","created":"2023-09-01","cited_by_count":0,"area":null},{"id":"2406.08840","title":"Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2407.18950","title":"Unexplainability of Artificial Intelligence Judgments and Functional Implementation in Kant's Perspective","created":"2024-07-12","cited_by_count":0,"area":null},{"id":"2408.17006","title":"Retrieval-Augmented Natural Language Reasoning for Explainable Visual Question Answering","created":"2024-08-30","cited_by_count":0,"area":"lr"},{"id":"2603.08639","title":"UNBOX: Unveiling Black-box visual models with Natural-language","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.18752","title":"WeNLEX: Weakly Supervised Natural Language Explanations for Multilabel Chest X-ray Classification","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2605.16877","title":"Zero-Shot Faithful Textual Explanations via Directional-Derivative Influence on Predictions","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.18481","title":"OCCAM: Open-set Causal Concept explAnation and Ontology induction for black-box vision Models","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2608.13974","title":"ProFocus: Interpreting Affective Experience in Artistic Images with Progressive Visual Focusing","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.29496","title":"Evaluating Explanation-Driven Vision-Language Reasoning via Generation Order Interventions","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.33713","title":"BIRD: Distilling Decision Boundaries into Rationales for MLLM Adaptation","created":"2026-09-27","cited_by_count":0,"area":"mllm"}],"next_cursor":null}