{"total":54,"rows":[{"id":"2412.01818","title":"Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs","created":"2024-12-02","cited_by_count":157,"area":"mllm"},{"id":"2506.10100","title":"EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models","created":"2025-06-11","cited_by_count":93,"area":"vla"},{"id":"2503.20384","title":"MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation","created":"2025-03-26","cited_by_count":70,"area":"mllm"},{"id":"2509.22642","title":"WoW: Towards a World omniscient World model Through Embodied Interaction","created":"2025-09-26","cited_by_count":67,"area":"wm"},{"id":"2505.14671","title":"UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens","created":"2025-05-20","cited_by_count":56,"area":null},{"id":"2506.05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","created":"2025-06-05","cited_by_count":51,"area":null},{"id":"2510.24514","title":"Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs","created":"2025-10-28","cited_by_count":43,"area":"lr"},{"id":"2510.23473","title":"Video-Thinker: Sparking \"Thinking with Videos\" via Reinforcement Learning","created":"2025-10-27","cited_by_count":34,"area":"lr"},{"id":"2412.02592","title":"OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation","created":"2024-12-03","cited_by_count":26,"area":"rag"},{"id":"2510.17801","title":"Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain","created":"2025-10-20","cited_by_count":25,"area":"mllm"},{"id":"2602.07624","title":"M2A: Multimodal Memory Agent with Dual-Layer Hybrid Memory for Long-Term Personalized Interactions","created":"2026-02-07","cited_by_count":25,"area":null},{"id":"2505.20199","title":"Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking","created":"2025-05-26","cited_by_count":21,"area":"diffusion"},{"id":"2510.19400","title":"Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes","created":"2025-10-22","cited_by_count":20,"area":"lr"},{"id":"2507.19946","title":"SCALAR: Scale-wise Controllable Visual Autoregressive Learning","created":"2025-07-26","cited_by_count":18,"area":null},{"id":"2505.13928","title":"LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts","created":"2025-05-20","cited_by_count":14,"area":null},{"id":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","cited_by_count":14,"area":null},{"id":"2510.19195","title":"Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks","created":"2025-10-22","cited_by_count":14,"area":"wm"},{"id":"2509.11866","title":"Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding","created":"2025-09-15","cited_by_count":13,"area":null},{"id":"2508.09456","title":"IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding","created":"2025-08-13","cited_by_count":12,"area":"mllm"},{"id":"2505.17020","title":"CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms","created":"2025-05-22","cited_by_count":11,"area":"mllm"},{"id":"2506.14907","title":"PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning","created":"2025-06-17","cited_by_count":11,"area":"lr"},{"id":"2511.10192","title":"Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL","created":"2025-11-13","cited_by_count":11,"area":null},{"id":"2512.07348","title":"MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition","created":"2025-12-08","cited_by_count":10,"area":null},{"id":"2512.12675","title":"Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling","created":"2025-12-14","cited_by_count":10,"area":null},{"id":"2511.23031","title":"From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning","created":"2025-11-28","cited_by_count":9,"area":"lr"},{"id":"2603.20422","title":"PEARL: Personalized Streaming Video Understanding Model","created":"2026-03-20","cited_by_count":9,"area":null},{"id":"2601.06965","title":"Unified Personalized Understanding, Generating and Editing","created":"2026-01-11","cited_by_count":8,"area":"mllm"},{"id":"2602.00971","title":"Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion Reasoning","created":"2026-02-01","cited_by_count":8,"area":"lr"},{"id":"2511.08409","title":"Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs","created":"2025-11-11","cited_by_count":7,"area":"lr"},{"id":"2511.14063","title":"Semantic Context Matters: Improving Conditioning for Autoregressive Models","created":"2025-11-18","cited_by_count":7,"area":null},{"id":"2511.18957","title":"Eevee: Towards Close-up High-resolution Video-based Virtual Try-on","created":"2025-11-24","cited_by_count":7,"area":null},{"id":"2502.10636","title":"USER-VLM 360: Personalized Vision Language Models with User-aware Tuning for Social Human-Robot Interactions","created":"2025-02-15","cited_by_count":6,"area":"mllm"},{"id":"2603.01083","title":"Can Vision Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset Perspective","created":"2026-03-01","cited_by_count":6,"area":"mllm"},{"id":"2602.19127","title":"AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG","created":"2026-02-22","cited_by_count":5,"area":"lr"},{"id":"2503.12999","title":"Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs","created":"2025-03-17","cited_by_count":4,"area":"mllm"},{"id":"2510.22765","title":"Jarvis: Towards Personalized AI Assistant via Personal KV-Cache Retrieval","created":"2025-10-26","cited_by_count":4,"area":"lr"},{"id":"2602.01630","title":"Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks","created":"2026-02-02","cited_by_count":3,"area":"wm"},{"id":"2603.08316","title":"SlowBA: An efficiency backdoor attack towards VLM-based GUI agents","created":"2026-03-09","cited_by_count":3,"area":"agents"},{"id":"2605.10936","title":"Personal Visual Context Learning in Large Multimodal Models","created":"2026-05-11","cited_by_count":3,"area":"mllm"},{"id":"2605.31513","title":"Personalize Your Large Vision-language Models With In-context Prompt Tuning","created":"2026-05-29","cited_by_count":3,"area":"mllm"},{"id":"2508.13692","title":"HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2510.26495","title":"Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration","created":"2025-10-30","cited_by_count":2,"area":"lr"},{"id":"2511.18121","title":"VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging","created":"2025-11-22","cited_by_count":2,"area":"mllm"},{"id":"2512.15560","title":"GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models","created":"2025-12-17","cited_by_count":2,"area":"diffusion"},{"id":"2412.08307","title":"Investigating the Scaling Effect of Instruction Templates for Training Multimodal Language Model","created":"2024-12-11","cited_by_count":1,"area":"mllm"},{"id":"2601.14188","title":"IIR-VLM: In-Context Instance-level Recognition for Large Vision-Language Models","created":"2026-01-20","cited_by_count":1,"area":"mllm"},{"id":"2605.07593","title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2602.19001","title":"Life-Bench: A Benchmark and Knowledge Graph Framework for Multimodal Personalization Beyond Concept Recognition","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2605.08129","title":"Towards Customized Multimodal Role-Play","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.08702","title":"Gate-and-Merge: Zero-shot Compositional Personalization of Vision Language Models","created":"2026-05-09","cited_by_count":0,"area":"mllm"},{"id":"2606.28845","title":"Personalizing MLLMs via Reinforced Multimodal Reference Game","created":"2026-06-27","cited_by_count":0,"area":"mllm"},{"id":"2607.22603","title":"Group Preference Collapse in Personalized Multimodal Large Language Models","created":"2026-06-12","cited_by_count":0,"area":"mllm"},{"id":"2608.28609","title":"Parametric Multimodal User Memory: Storing What Captions Cannot Carry","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2610.15915","title":"VIEWCRAFT: Evolving What Multimodal Agents See and How They Read It","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}