{"total":96,"rows":[{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735,"area":"mllm"},{"id":"2412.01720","title":"LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant","created":"2024-12-02","cited_by_count":106,"area":"mllm"},{"id":"2410.14669","title":"NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples","created":"2024-10-18","cited_by_count":97,"area":"mllm"},{"id":"2504.17432","title":"Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs","created":"2025-04-24","cited_by_count":73,"area":"mllm"},{"id":"2403.20312","title":"Learn \"No\" to Say \"Yes\" Better: Improving Vision-Language Models via Negations","created":"2024-03-29","cited_by_count":46,"area":"mllm"},{"id":"2406.11171","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","created":"2024-06-17","cited_by_count":42,"area":"mllm"},{"id":"2411.02537","title":"INQUIRE: A Natural World Text-to-Image Retrieval Benchmark","created":"2024-11-04","cited_by_count":33,"area":"mllm"},{"id":"2410.09733","title":"MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models","created":"2024-10-13","cited_by_count":31,"area":"mllm"},{"id":"2412.08614","title":"Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning","created":"2024-12-11","cited_by_count":31,"area":"mllm"},{"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":"2407.16772","title":"VisMin: Visual Minimal-Change Understanding","created":"2024-07-23","cited_by_count":23,"area":"mllm"},{"id":"2409.17958","title":"The Hard Positive Truth about Vision-Language Compositionality","created":"2024-09-26","cited_by_count":22,"area":"mllm"},{"id":"2308.12898","title":"Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?","created":"2023-08-24","cited_by_count":21,"area":"mllm"},{"id":"2411.10979","title":"VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?","created":"2024-11-17","cited_by_count":18,"area":"mllm"},{"id":"2404.02145","title":"Iterated Learning Improves Compositionality in Large Vision-Language Models","created":"2024-04-02","cited_by_count":17,"area":"mllm"},{"id":"2404.14715","title":"FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction","created":"2024-04-23","cited_by_count":17,"area":"mllm"},{"id":"2404.12652","title":"Pre-trained Vision-Language Models Learn Discoverable Visual Concepts","created":"2024-04-19","cited_by_count":16,"area":"mllm"},{"id":"2409.12969","title":"Seeing Through Their Eyes: Evaluating Visual Perspective Taking in Vision Language Models","created":"2024-09-02","cited_by_count":15,"area":"mllm"},{"id":"2410.03176","title":"Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models","created":"2024-10-04","cited_by_count":15,"area":"mllm"},{"id":"2412.01814","title":"COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training","created":"2024-12-02","cited_by_count":15,"area":"mllm"},{"id":"2412.04378","title":"VladVA: Discriminative Fine-tuning of LVLMs","created":"2024-12-05","cited_by_count":15,"area":"mllm"},{"id":"2403.16442","title":"If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions","created":"2024-03-25","cited_by_count":14,"area":"mllm"},{"id":"2407.13851","title":"X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs","created":"2024-07-18","cited_by_count":14,"area":"mllm"},{"id":"2405.08815","title":"Efficient Vision-Language Pre-training by Cluster Masking","created":"2024-05-14","cited_by_count":13,"area":"mllm"},{"id":"2402.15021","title":"CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models","created":"2024-02-22","cited_by_count":12,"area":"mllm"},{"id":"2502.14113","title":"Object-centric Binding in Contrastive Language-Image Pretraining","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"id":"2412.00142","title":"Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features","created":"2024-11-28","cited_by_count":11,"area":"mllm"},{"id":"2310.08577","title":"Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models","created":"2023-10-12","cited_by_count":9,"area":"mllm"},{"id":"2402.15300","title":"Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding","created":"2024-02-23","cited_by_count":8,"area":"mllm"},{"id":"2503.21851","title":"On Large Multimodal Models as Open-World Image Classifiers","created":"2025-03-27","cited_by_count":8,"area":"mllm"},{"id":"2508.11317","title":"Logic Unseen: Revealing the Logical Blindspots of Vision-Language Models","created":"2025-08-15","cited_by_count":7,"area":"mllm"},{"id":"2510.08919","title":"PHyCLIP: $\\ell_1$-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning","created":"2025-10-10","cited_by_count":7,"area":"mllm"},{"id":"2308.10509","title":"An Examination of the Compositionality of Large Generative Vision-Language Models","created":"2023-08-21","cited_by_count":6,"area":"mllm"},{"id":"2412.09353","title":"Causal Graphical Models for Vision-Language Compositional Understanding","created":"2024-12-12","cited_by_count":6,"area":"mllm"},{"id":"2507.01368","title":"Activation Reward Models for Few-Shot Model Alignment","created":"2025-07-02","cited_by_count":6,"area":"mllm"},{"id":"2412.18404","title":"Extract Free Dense Misalignment from CLIP","created":"2024-12-24","cited_by_count":5,"area":"mllm"},{"id":"2505.24424","title":"Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning","created":"2025-05-30","cited_by_count":5,"area":"mllm"},{"id":"2508.00955","title":"From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model","created":"2025-08-01","cited_by_count":5,"area":"mllm"},{"id":"2508.02329","title":"VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction Editing Data and Long Captions","created":"2025-08-04","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":"2511.20515","title":"HalDec-Bench: Benchmarking Hallucination Detector in Image Captioning","created":"2025-11-25","cited_by_count":5,"area":"mllm"},{"id":"2507.07985","title":"Common Data Properties Limit Object-Attribute Binding in CLIP","created":"2025-07-10","cited_by_count":4,"area":"mllm"},{"id":"2509.22404","title":"RAU: Reference-based Anatomical Understanding with Vision Language Models","created":"2025-09-26","cited_by_count":3,"area":"mllm"},{"id":"2602.01639","title":"ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval","created":"2026-02-02","cited_by_count":3,"area":"mllm"},{"id":"2602.05275","title":"Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs","created":"2026-02-05","cited_by_count":3,"area":"mllm"},{"id":"2406.12321","title":"Automatic benchmarking of large multimodal models via iterative experiment programming","created":"2024-06-18","cited_by_count":2,"area":"mllm"},{"id":"2410.13030","title":"Sensitivity of Generative VLMs to Semantically and Lexically Altered Prompts","created":"2024-10-16","cited_by_count":2,"area":"mllm"},{"id":"2503.21757","title":"Fwd2Bot: LVLM Visual Token Compression with Double Forward Bottleneck","created":"2025-03-27","cited_by_count":2,"area":"mllm"},{"id":"2504.04740","title":"SCRAMBLe : Enhancing Multimodal LLM Compositionality with Synthetic Preference Data","created":"2025-04-07","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":"2605.15951","title":"From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding","created":"2026-05-15","cited_by_count":2,"area":"mllm"},{"id":"2606.24335","title":"Ill-Posed by Design: Probing Evidence Use in VLMs","created":"2026-06-23","cited_by_count":2,"area":"mllm"},{"id":"2607.23052","title":"Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models","created":"2026-07-25","cited_by_count":2,"area":"mllm"},{"id":"2407.15487","title":"In-Context Learning Improves Compositional Understanding of Vision-Language Models","created":"2024-07-22","cited_by_count":1,"area":"mllm"},{"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":"2506.09691","title":"Adding simple structure at inference improves Vision-Language Compositionality","created":"2025-06-11","cited_by_count":1,"area":"mllm"},{"id":"2509.22674","title":"Pathological Truth Bias in Vision-Language Models","created":"2025-09-14","cited_by_count":1,"area":"mllm"},{"id":"2511.23170","title":"PowerCLIP: Powerset Alignment for Contrastive Pre-Training","created":"2025-11-28","cited_by_count":1,"area":"mllm"},{"id":"2602.01370","title":"PolyGen: Fully Synthetic Vision-Language Training via Multi-Generator Ensembles","created":"2026-02-01","cited_by_count":1,"area":"mllm"},{"id":"2603.25891","title":"Few Shots Text to Image Retrieval: New Benchmarking Dataset and Optimization Methods","created":"2026-03-26","cited_by_count":1,"area":"mllm"},{"id":"2604.11496","title":"Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference","created":"2026-04-13","cited_by_count":1,"area":"mllm"},{"id":"2605.30170","title":"Unveiling the Visual Counting Bottleneck in Vision-Language Models","created":"2026-05-28","cited_by_count":1,"area":"mllm"},{"id":"2606.13288","title":"Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality","created":"2026-06-11","cited_by_count":1,"area":"mllm"},{"id":"2607.23271","title":"What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features","created":"2026-07-25","cited_by_count":1,"area":"mllm"},{"id":"2607.23335","title":"The Gate Always Closes: On Injecting Auxiliary Signals into Frozen Vision-Language Models","created":"2026-07-25","cited_by_count":1,"area":"mllm"},{"id":"2608.16805","title":"Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models","created":"2026-08-17","cited_by_count":1,"area":"mllm"},{"id":"2609.06922","title":"BEFORE THE FLIP: Measuring Hidden Score Shifts In Quantized Vision Language Models Before The Answer Changes for Visual Question Answering","created":"2026-09-07","cited_by_count":1,"area":"mllm"},{"id":"2609.22588","title":"Seeing is not Enough: Vision-Language Models Perceive Evidence but Fail to Act","created":"2026-09-18","cited_by_count":1,"area":"mllm"},{"id":"2409.16024","title":"From Goal-Conditioned to Language-Conditioned Agents via Vision-Language Models","created":"2024-09-24","cited_by_count":0,"area":"mllm"},{"id":"2412.15632","title":"A New Method to Capturing Compositional Knowledge in Linguistic Space","created":"2024-12-20","cited_by_count":0,"area":"mllm"},{"id":"2501.09672","title":"CHIRP: A Fine-Grained Benchmark for Open-Ended Response Evaluation in Vision-Language Models","created":"2025-01-16","cited_by_count":0,"area":"mllm"},{"id":"2507.08000","title":"Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models","created":"2025-07-10","cited_by_count":0,"area":"mllm"},{"id":"2509.19207","title":"Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs","created":"2025-09-23","cited_by_count":0,"area":"mllm"},{"id":"2511.16527","title":"Contrastive vision-language learning with paraphrasing and negation","created":"2025-11-20","cited_by_count":0,"area":"mllm"},{"id":"2512.17121","title":"The Effect of Negation on CLIP in Medical Imaging: Limitations of Contrastive Language-Image Pretraining","created":"2025-12-18","cited_by_count":0,"area":"mllm"},{"id":"2601.04824","title":"SOVABench: A Vehicle Surveillance Action Retrieval Benchmark for Multimodal Large Language Models","created":"2026-01-08","cited_by_count":0,"area":"mllm"},{"id":"2601.12430","title":"System-Mediated Attention Imbalances Make Vision-Language Models Say Yes","created":"2026-01-18","cited_by_count":0,"area":"mllm"},{"id":"2601.12809","title":"Left-Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Spatial-Relation Data","created":"2026-01-19","cited_by_count":0,"area":"mllm"},{"id":"2602.02043","title":"Auto-Comp: An Automated Pipeline for Scalable Compositional Probing of Contrastive Vision-Language Models","created":"2026-02-02","cited_by_count":0,"area":"mllm"},{"id":"2602.18729","title":"MiSCHiEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption Alignment","created":"2026-02-21","cited_by_count":0,"area":"mllm"},{"id":"2603.15253","title":"HalDec-Bench: Benchmarking Hallucination Detector in Image Captioning","created":"2026-03-16","cited_by_count":0,"area":"mllm"},{"id":"2604.05971","title":"Is CLIP Cross-Eyed? Revealing and Mitigating Center Bias in the CLIP Family","created":"2026-04-07","cited_by_count":0,"area":"mllm"},{"id":"2604.12335","title":"SynMulti: Synthetic-to-Real Learning for Multimodal Video Understanding","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2604.13313","title":"Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2605.21728","title":"BEiTScore: Reference-free Image Captioning Evaluation with an Efficient Cross-Encoder Model","created":"2026-05-20","cited_by_count":0,"area":"mllm"},{"id":"2605.22651","title":"What Does the Caption Really Say? Counterfactual Phrase Intervention for Compositional Data Selection in Vision-Language Pretraining","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2606.08394","title":"When Correct Decisions Hide Internal Stress: Decision-State Probing in Multimodal Language Models","created":"2026-06-07","cited_by_count":0,"area":"mllm"},{"id":"2607.02593","title":"Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge Distillation","created":"2026-07-01","cited_by_count":0,"area":"mllm"},{"id":"2607.05268","title":"Is the Geometry Doing the Work? An Operating-Point Audit of Hierarchy in Hyperbolic Vision-Language Models","created":"2026-07-06","cited_by_count":0,"area":"mllm"},{"id":"2608.09772","title":"PragMatch: Separating Pragmatic Incongruity from Cross-Modal Mismatch in Large Vision-Language Models","created":"2026-08-10","cited_by_count":0,"area":"mllm"},{"id":"2608.25575","title":"MLLMCLIP: Feature-Level Distillation of MLLM for Robust Vision-Language Representations","created":"2026-08-26","cited_by_count":0,"area":"mllm"},{"id":"2609.20139","title":"Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models","created":"2026-09-17","cited_by_count":0,"area":"mllm"},{"id":"2609.26093","title":"RECAP: Relation Evidence Calibration for Detecting Spatial Relation Hallucinations in Vision-Language Models","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2609.38368","title":"Composition, Not Conversation: VLMs Lose the Scene, Not the Thread","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2610.13910","title":"When VLMs Destroy What They Know: Spatial Representations Fall Below Lexical Priors","created":"2026-10-09","cited_by_count":0,"area":"mllm"},{"id":"2610.17440","title":"Know-Thy-Not: Training-Free Targeted Negation in Dual-Encoder Vision-Language Models","created":"2026-10-12","cited_by_count":0,"area":"mllm"}],"next_cursor":null}