{"total":243,"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":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315,"area":"lr"},{"id":"2310.19785","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","created":"2023-10-30","cited_by_count":254,"area":"lr"},{"id":"2412.01720","title":"LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant","created":"2024-12-02","cited_by_count":106,"area":"mllm"},{"id":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103,"area":null},{"id":"2410.14669","title":"NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples","created":"2024-10-18","cited_by_count":97,"area":"mllm"},{"id":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80,"area":null},{"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":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72,"area":null},{"id":"2508.13073","title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","created":"2025-08-18","cited_by_count":69,"area":"vla"},{"id":"2411.02545","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives","created":"2024-11-04","cited_by_count":58,"area":null},{"id":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57,"area":null},{"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":"2501.00569","title":"Probing Visual Language Priors in VLMs","created":"2024-12-31","cited_by_count":45,"area":"lr"},{"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":"2510.13515","title":"UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning","created":"2025-10-15","cited_by_count":42,"area":null},{"id":"2402.13254","title":"CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples","created":"2024-02-20","cited_by_count":35,"area":"lr"},{"id":"2411.02537","title":"INQUIRE: A Natural World Text-to-Image Retrieval Benchmark","created":"2024-11-04","cited_by_count":33,"area":"mllm"},{"id":"2408.04810","title":"UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling","created":"2024-08-09","cited_by_count":31,"area":"lr"},{"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":"2502.03566","title":"CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally","created":"2025-02-05","cited_by_count":31,"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":"2506.09987","title":"A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs","created":"2025-06-11","cited_by_count":30,"area":"lr"},{"id":"2501.10913","title":"Know \"No\" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP","created":"2025-01-19","cited_by_count":28,"area":null},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2407.16772","title":"VisMin: Visual Minimal-Change Understanding","created":"2024-07-23","cited_by_count":23,"area":"mllm"},{"id":"2506.09284","title":"UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation","created":"2025-06-10","cited_by_count":23,"area":null},{"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":"2406.08164","title":"ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs","created":"2024-06-12","cited_by_count":21,"area":"lr"},{"id":"2503.08723","title":"Is CLIP ideal? No. Can we fix it? Yes!","created":"2025-03-10","cited_by_count":21,"area":null},{"id":"2409.14750","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","created":"2024-09-23","cited_by_count":20,"area":null},{"id":"2403.11821","title":"A Survey on Quality Metrics for Text-to-Image Generation","created":"2024-03-18","cited_by_count":18,"area":null},{"id":"2403.12884","title":"HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning","created":"2024-03-19","cited_by_count":18,"area":"lr"},{"id":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","cited_by_count":18,"area":null},{"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":"2410.05210","title":"Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality","created":"2024-10-07","cited_by_count":17,"area":null},{"id":"2404.12652","title":"Pre-trained Vision-Language Models Learn Discoverable Visual Concepts","created":"2024-04-19","cited_by_count":16,"area":"mllm"},{"id":"2511.04668","title":"SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding","created":"2025-11-06","cited_by_count":16,"area":"lr"},{"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":"2504.10471","title":"MIEB: Massive Image Embedding Benchmark","created":"2025-04-14","cited_by_count":15,"area":null},{"id":"2401.01974","title":"Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers","created":"2024-01-03","cited_by_count":14,"area":"lr"},{"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":"2502.19842","title":"CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation","created":"2025-02-27","cited_by_count":14,"area":null},{"id":"2405.08815","title":"Efficient Vision-Language Pre-training by Cluster Masking","created":"2024-05-14","cited_by_count":13,"area":"mllm"},{"id":"2407.05897","title":"Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models","created":"2024-07-08","cited_by_count":13,"area":null},{"id":"2312.02338","title":"A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2402.15021","title":"CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models","created":"2024-02-22","cited_by_count":12,"area":"mllm"},{"id":"2404.04627","title":"Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement","created":"2024-04-06","cited_by_count":12,"area":"lr"},{"id":"2407.15408","title":"Chronologically Accurate Retrieval for Temporal Grounding of Motion-Language Models","created":"2024-07-22","cited_by_count":12,"area":null},{"id":"2411.11927","title":"FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2502.14113","title":"Object-centric Binding in Contrastive Language-Image Pretraining","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"id":"2503.01167","title":"Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data","created":"2025-03-03","cited_by_count":12,"area":"synth"},{"id":"2401.00094","title":"Generating Enhanced Negatives for Training Language-Based Object Detectors","created":"2023-12-29","cited_by_count":11,"area":null},{"id":"2411.05195","title":"Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder","created":"2024-11-07","cited_by_count":11,"area":"lr"},{"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":"2312.12661","title":"Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pretraining","created":"2023-12-19","cited_by_count":10,"area":null},{"id":"2402.19472","title":"Efficient Lifelong Model Evaluation in an Era of Rapid Progress","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2406.10889","title":"VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment","created":"2024-06-16","cited_by_count":10,"area":"lr"},{"id":"2503.18623","title":"Training-Free Personalization via Retrieval and Reasoning on Fingerprints","created":"2025-03-24","cited_by_count":10,"area":"lr"},{"id":"2505.22079","title":"Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2507.14902","title":"U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs","created":"2025-07-20","cited_by_count":10,"area":null},{"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":"2504.16801","title":"Decoupled Global-Local Alignment for Improving Compositional Understanding","created":"2025-04-23","cited_by_count":9,"area":"distill"},{"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":"2410.00905","title":"Removing Distributional Discrepancies in Captions Improves Image-Text Alignment","created":"2024-10-01","cited_by_count":8,"area":null},{"id":"2503.21851","title":"On Large Multimodal Models as Open-World Image Classifiers","created":"2025-03-27","cited_by_count":8,"area":"mllm"},{"id":"2511.19278","title":"ReMatch: Boosting Representation through Matching for Multimodal Retrieval","created":"2025-11-24","cited_by_count":8,"area":null},{"id":"2405.15164","title":"From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2405.17201","title":"Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View","created":"2024-05-27","cited_by_count":7,"area":"lr"},{"id":"2407.06723","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2407.17960","title":"The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communication","created":"2024-07-25","cited_by_count":7,"area":null},{"id":"2502.20104","title":"New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2503.17080","title":"Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2505.17955","title":"Diffusion Classifiers Understand Compositionality, but Conditions Apply","created":"2025-05-23","cited_by_count":7,"area":"diffusion"},{"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":"2406.09952","title":"BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2412.09353","title":"Causal Graphical Models for Vision-Language Compositional Understanding","created":"2024-12-12","cited_by_count":6,"area":"mllm"},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2507.01368","title":"Activation Reward Models for Few-Shot Model Alignment","created":"2025-07-02","cited_by_count":6,"area":"mllm"},{"id":"2510.07632","title":"Test-Time Matching: Unlocking Compositional Reasoning in Multimodal Models","created":"2025-10-09","cited_by_count":6,"area":"lr"},{"id":"2601.04897","title":"V-FAT: Benchmarking Visual Fidelity Against Text-bias","created":"2026-01-08","cited_by_count":6,"area":"lr"},{"id":"2312.14440","title":"Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks","created":"2023-12-22","cited_by_count":5,"area":"safety"},{"id":"2409.03025","title":"No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning","created":"2024-09-04","cited_by_count":5,"area":null},{"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":"2506.08227","title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","created":"2025-06-09","cited_by_count":5,"area":null},{"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":"2508.20783","title":"Evaluating Compositional Generalisation in VLMs and Diffusion Models","created":"2025-08-28","cited_by_count":5,"area":"diffusion"},{"id":"2509.25717","title":"Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization","created":"2025-09-30","cited_by_count":5,"area":"mllm"}],"next_cursor":"100"}