{"total":36,"rows":[{"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,"area":"mllm"},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363,"area":"mllm"},{"id":"2309.12530","title":"A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance","created":"2023-09-21","cited_by_count":40,"area":"mllm"},{"id":"2306.06354","title":"EventCLIP: Adapting CLIP for Event-based Object Recognition","created":"2023-06-10","cited_by_count":36,"area":"mllm"},{"id":"2406.17126","title":"MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs","created":"2024-06-24","cited_by_count":33,"area":"mllm"},{"id":"2306.02080","title":"Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models","created":"2023-06-03","cited_by_count":31,"area":"mllm"},{"id":"2403.07241","title":"Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations","created":"2024-03-12","cited_by_count":30,"area":"mllm"},{"id":"2403.09193","title":"Can We Talk Models Into Seeing the World Differently?","created":"2024-03-14","cited_by_count":23,"area":"mllm"},{"id":"2407.08966","title":"LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models","created":"2024-07-12","cited_by_count":21,"area":"mllm"},{"id":"2304.03659","title":"Probing Conceptual Understanding of Large Visual-Language Models","created":"2023-04-07","cited_by_count":17,"area":"mllm"},{"id":"2406.00345","title":"DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection","created":"2024-06-01","cited_by_count":14,"area":"mllm"},{"id":"2408.01355","title":"Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs","created":"2024-08-02","cited_by_count":14,"area":"mllm"},{"id":"2410.01534","title":"Toward a Holistic Evaluation of Robustness in CLIP Models","created":"2024-10-02","cited_by_count":13,"area":"mllm"},{"id":"2605.12369","title":"GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization","created":"2026-05-12","cited_by_count":10,"area":"mllm"},{"id":"2311.01441","title":"Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models","created":"2023-11-02","cited_by_count":9,"area":"mllm"},{"id":"2512.15949","title":"The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs","created":"2025-12-17","cited_by_count":3,"area":"mllm"},{"id":"2601.03500","title":"SDCD: Structure-Disrupted Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models","created":"2026-01-07","cited_by_count":3,"area":"mllm"},{"id":"2601.17706","title":"A Computational Approach to Visual Metonymy","created":"2026-01-25","cited_by_count":3,"area":"mllm"},{"id":"2507.22398","title":"On the Reliability of Vision-Language Models Under Adversarial Frequency-Domain Perturbations","created":"2025-07-30","cited_by_count":2,"area":"mllm"},{"id":"2609.00868","title":"The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual Evidence","created":"2026-09-01","cited_by_count":2,"area":"mllm"},{"id":"2503.08368","title":"Debiased Prompt Tuning in Vision-Language Model without Annotations","created":"2025-03-11","cited_by_count":1,"area":"mllm"},{"id":"2606.03795","title":"Beyond Compression: Quantifying Spectral Accessibility in Vision Representations","created":"2026-06-02","cited_by_count":1,"area":"mllm"},{"id":"2507.10442","title":"Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities","created":"2025-07-10","cited_by_count":0,"area":"mllm"},{"id":"2509.06996","title":"Visible Yet Unreadable: A Systematic Blind Spot of Vision Language Models Across Writing Systems","created":"2025-09-04","cited_by_count":0,"area":"mllm"},{"id":"2511.07068","title":"ClusterMine: Robust Label-Free Visual Out-Of-Distribution Detection via Concept Mining from Text Corpora","created":"2025-11-10","cited_by_count":0,"area":"mllm"},{"id":"2511.11831","title":"TopoPerception: A Shortcut-Free Evaluation of Global Visual Perception in Large Vision-Language Models","created":"2025-11-14","cited_by_count":0,"area":"mllm"},{"id":"2512.04395","title":"Fourier-Attentive Representation Learning: A Fourier-Guided Framework for Few-Shot Generalization in Vision-Language Models","created":"2025-12-04","cited_by_count":0,"area":"mllm"},{"id":"2603.26769","title":"Edge Reliability Gap in Vision-Language Models: Quantifying Failure Modes of Compressed VLMs Under Visual Corruption","created":"2026-03-24","cited_by_count":0,"area":"mllm"},{"id":"2604.10528","title":"BareBones: Benchmarking Zero-Shot Geometric Comprehension in VLMs","created":"2026-04-12","cited_by_count":0,"area":"mllm"},{"id":"2604.13803","title":"Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation","created":"2026-04-15","cited_by_count":0,"area":"mllm"},{"id":"2605.00906","title":"Generalized Category Discovery under Domain Shifts: From Vision to Vision-Language Models","created":"2026-04-29","cited_by_count":0,"area":"mllm"},{"id":"2605.13047","title":"Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"id":"2606.05409","title":"Would you still call this Dax? Novel Visual References in VLMs and Humans","created":"2026-06-03","cited_by_count":0,"area":"mllm"},{"id":"2609.00788","title":"Forbid Your Attention: Fooling Multimodal Large Language Models by Selectively Removing Intrinsic Focus in Spectral Domain","created":"2026-09-01","cited_by_count":0,"area":"mllm"},{"id":"2609.31403","title":"Sorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic Layers","created":"2026-09-25","cited_by_count":0,"area":"mllm"},{"id":"2610.15467","title":"Semantic Saliency from Multi-Modal Large Language Model Scene Understanding Maps","created":"2026-10-11","cited_by_count":0,"area":"mllm"}],"next_cursor":null}