{"total":20,"rows":[{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838,"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":"2503.16707","title":"Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding","created":"2025-03-20","cited_by_count":13,"area":"mllm"},{"id":"2412.09585","title":"Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation","created":"2024-12-12","cited_by_count":9,"area":"mllm"},{"id":"2609.00111","title":"Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving","created":"2026-08-31","cited_by_count":9,"area":"mllm"},{"id":"2408.06721","title":"Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities","created":"2024-08-13","cited_by_count":6,"area":"mllm"},{"id":"2506.09883","title":"3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation","created":"2025-06-11","cited_by_count":5,"area":"mllm"},{"id":"2506.09935","title":"LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning","created":"2025-06-11","cited_by_count":5,"area":"mllm"},{"id":"2605.16745","title":"EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers","created":"2026-05-16","cited_by_count":3,"area":"mllm"},{"id":"2601.13886","title":"Revisiting Multi-Task Visual Representation Learning","created":"2026-01-20","cited_by_count":2,"area":"mllm"},{"id":"2602.09934","title":"VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization","created":"2026-02-10","cited_by_count":1,"area":"mllm"},{"id":"2603.17228","title":"From Drop-off to Recovery: A Mechanistic Analysis of Segmentation in MLLMs","created":"2026-03-18","cited_by_count":1,"area":"mllm"},{"id":"2604.03296","title":"3D-IDE: 3D Implicit Depth Emergent","created":"2026-03-28","cited_by_count":1,"area":"mllm"},{"id":"2607.01503","title":"Disentangling Pictorial Cue Understanding from Language Bias in VLMs via Depth Ordering Task","created":"2026-07-01","cited_by_count":1,"area":"mllm"},{"id":"2407.13856","title":"Simultaneous Localization and Affordance Prediction of Tasks from Egocentric Video","created":"2024-07-18","cited_by_count":0,"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":"2603.06459","title":"Do Foundation Models Know Geometry? Probing Frozen Features for Continuous Physical Measurement","created":"2026-03-06","cited_by_count":0,"area":"mllm"},{"id":"2606.19915","title":"SpatialSV: Internalizing Interpretable 3D Spatial Awareness in MLLMs via Task-Oriented Visual Supervision","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2608.08904","title":"From Recovery to Drop-off: How Action Post-training Reduces a VLM's Late-Layer Depth Decodability","created":"2026-08-09","cited_by_count":0,"area":"mllm"},{"id":"2610.09517","title":"It Is Not Seeing the Hazard: A Frozen Vision-Language Safety Score Measures Its Caption Bank","created":"2026-10-07","cited_by_count":0,"area":"mllm"}],"next_cursor":null}