{"total":75,"rows":[{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793,"area":"mllm"},{"id":"2502.13130","title":"Magma: A Foundation Model for Multimodal AI Agents","created":"2025-02-18","cited_by_count":139,"area":"agents"},{"id":"2407.15841","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","created":"2024-07-22","cited_by_count":125,"area":null},{"id":"2409.20566","title":"MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning","created":"2024-09-30","cited_by_count":76,"area":"mllm"},{"id":"2505.14682","title":"UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation","created":"2025-05-20","cited_by_count":32,"area":"mllm"},{"id":"2601.09668","title":"STEP3-VL-10B Technical Report","created":"2026-01-14","cited_by_count":32,"area":null},{"id":"2412.05819","title":"[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs","created":"2024-12-08","cited_by_count":26,"area":"mllm"},{"id":"2503.06063","title":"Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices","created":"2025-03-08","cited_by_count":22,"area":"mllm"},{"id":"2503.10501","title":"TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models","created":"2025-03-13","cited_by_count":19,"area":"mllm"},{"id":"2509.24200","title":"UniVid: The Open-Source Unified Video Model","created":"2025-09-29","cited_by_count":19,"area":null},{"id":"2602.08024","title":"FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging","created":"2026-02-08","cited_by_count":18,"area":"inference"},{"id":"2411.13552","title":"REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents","created":"2024-11-20","cited_by_count":14,"area":null},{"id":"2409.20146","title":"VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection","created":"2024-09-30","cited_by_count":13,"area":"mllm"},{"id":"2606.18112","title":"Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System","created":"2026-06-16","cited_by_count":11,"area":"agents"},{"id":"2601.03928","title":"FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection","created":"2026-01-07","cited_by_count":10,"area":"mllm"},{"id":"2411.11066","title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","created":"2024-11-17","cited_by_count":9,"area":"mllm"},{"id":"2505.14071","title":"Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models","created":"2025-05-20","cited_by_count":9,"area":"mllm"},{"id":"2609.25845","title":"Visual Jev: Accurate and Efficient Decisions from Shared Visual Context","created":"2026-09-22","cited_by_count":9,"area":null},{"id":"2412.03565","title":"INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning","created":"2024-12-04","cited_by_count":8,"area":"mllm"},{"id":"2605.28820","title":"From Pixels to Words -- Towards Native One-Vision Models at Scale","created":"2026-05-27","cited_by_count":8,"area":"mllm"},{"id":"2503.18931","title":"Enhancing Vision Foundation Models via Multimodal Continual Pre-Training","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2512.08374","title":"The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss","created":"2025-12-09","cited_by_count":5,"area":"mllm"},{"id":"2601.07290","title":"VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding","created":"2026-01-12","cited_by_count":5,"area":null},{"id":"2602.09080","title":"Looping Back to Move Forward: Recursive Transformers for Efficient and Flexible Large Multimodal Models","created":"2026-02-09","cited_by_count":5,"area":"mllm"},{"id":"2603.00479","title":"U-VLM: Hierarchical Vision Language Modeling for Report Generation","created":"2026-02-28","cited_by_count":5,"area":"mllm"},{"id":"2407.16198","title":"INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model","created":"2024-07-23","cited_by_count":4,"area":"mllm"},{"id":"2605.00814","title":"Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs","created":"2026-05-01","cited_by_count":4,"area":"mllm"},{"id":"2606.10819","title":"Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks","created":"2026-06-09","cited_by_count":4,"area":"lr"},{"id":"2606.18249","title":"Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification","created":"2026-06-16","cited_by_count":4,"area":null},{"id":"2507.20842","title":"METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models","created":"2025-07-28","cited_by_count":3,"area":"mllm"},{"id":"2601.21798","title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models","created":"2026-01-29","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":"2606.12412","title":"Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models","created":"2026-06-10","cited_by_count":3,"area":"mllm"},{"id":"2506.03928","title":"Vision Remember: Recovering Visual Information in Efficient LVLM with Vision Feature Resampling","created":"2025-06-04","cited_by_count":2,"area":"mllm"},{"id":"2507.09334","title":"Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding","created":"2025-07-12","cited_by_count":2,"area":"mllm"},{"id":"2604.04207","title":"Don't Blink: Evidence Collapse during Multimodal Reasoning","created":"2026-04-05","cited_by_count":2,"area":"lr"},{"id":"2604.22575","title":"SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2604.23996","title":"SMoES: Soft Modality-Guided Expert Specialization in MoE-VLMs","created":"2026-04-27","cited_by_count":2,"area":"mllm"},{"id":"2508.01236","title":"Mitigating Information Loss under High Pruning Rates for Efficient Large Vision Language Models","created":"2025-08-02","cited_by_count":1,"area":"mllm"},{"id":"2512.06013","title":"VAT: Vision Action Transformer by Unlocking Full Representation of ViT","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2601.10710","title":"From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion","created":"2026-01-15","cited_by_count":1,"area":"mllm"},{"id":"2603.02865","title":"Nodes Are Early, Edges Are Late: Probing Diagram Representations in Large Vision-Language Models","created":"2026-03-03","cited_by_count":1,"area":"mllm"},{"id":"2603.26041","title":"Where and How to Prune: An Empirical Study of Visual Token Pruning for GUI Agent Navigation","created":"2026-03-27","cited_by_count":1,"area":"agents"},{"id":"2605.07447","title":"Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs","created":"2026-05-08","cited_by_count":1,"area":"mllm"},{"id":"2605.12258","title":"Instruction Lens Score: Your Instruction Contributes a Powerful Object Hallucination Detector for Multimodal Large Language Models","created":"2026-05-12","cited_by_count":1,"area":"mllm"},{"id":"2606.25546","title":"Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography","created":"2026-06-24","cited_by_count":1,"area":"mllm"},{"id":"2608.01899","title":"SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models","created":"2026-08-03","cited_by_count":1,"area":"lr"},{"id":"2609.34949","title":"VD-DeepStack: Bridging Visual Comparison and Language Reasoning for Few-Shot Anomaly Detection","created":"2026-09-28","cited_by_count":1,"area":"lr"},{"id":"2501.00619","title":"A Study on Context Length and Efficient Transformers for Biomedical Image Analysis","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2508.16527","title":"Towards Open World Detection: A Survey","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2510.03370","title":"InstructPLM-mu: 1-Hour Fine-Tuning of ESM2 Beats ESM3 in Protein Mutation Predictions","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2601.10104","title":"MathDoc: Benchmarking Structured Extraction and Active Refusal on Noisy Mathematics Exam Papers","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2602.00505","title":"Sparse Shortcuts: Facilitating Efficient Fusion in Multimodal Large Language Models","created":"2026-01-31","cited_by_count":0,"area":"mllm"},{"id":"2603.20020","title":"Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR","created":"2026-03-20","cited_by_count":0,"area":"lr"},{"id":"2604.00754","title":"Stochastic Attention: Connectome-Inspired Randomized Routing for Expressive Linear-Time Attention","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.02689","title":"Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2605.00371","title":"GaMMA: Towards Joint Global-Temporal Music Understanding in Large Multimodal Models","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.02262","title":"WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization","created":"2026-05-04","cited_by_count":0,"area":"inference"},{"id":"2605.08975","title":"Latency Analysis and Optimization of Alpamayo 1 via Efficient Trajectory Generation","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.10537","title":"Mela: Test-Time Memory Consolidation based on Transformation Hypothesis","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.04433","title":"Stateful Visual Encoders for Vision-Language Models","created":"2026-06-03","cited_by_count":0,"area":"mllm"},{"id":"2606.11792","title":"MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models","created":"2026-06-10","cited_by_count":0,"area":"mllm"},{"id":"2606.20077","title":"The Hidden Evolution of Disguised Visual Context inside the VLM","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.24051","title":"DriveStack-VLA: Render-Teacher Alignment for BEV-Based DeepStack Vision-Language-Action Model","created":"2026-06-23","cited_by_count":0,"area":"mllm"},{"id":"2607.16243","title":"RobustMAD: Evaluating Real-World Robustness of Multimodal Small Language Models for Deployable Anomaly Detection Assistants","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.23504","title":"MemVLN: Episodic and Procedural Memory for Vision-and-Language Navigation","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.00561","title":"Through the LENS: Local Geometric Decomposition of Vision-Language Model Representations","created":"2026-08-01","cited_by_count":0,"area":"mllm"},{"id":"2608.05616","title":"TruthLens: Object Hallucination Detection via Self-Evaluating Truthfulness Scores in LVLMs","created":"2026-08-06","cited_by_count":0,"area":"mllm"},{"id":"2608.07585","title":"LAVE: Latent Visual Evidence-Enhanced Planning for Video Tool-use Agents","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.08630","title":"VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling","created":"2026-08-09","cited_by_count":0,"area":"mllm"},{"id":"2609.32780","title":"OmniMoE-VL: A Sparse Vision-Language Model with Coupled Visual-Depth Routing","created":"2026-09-26","cited_by_count":0,"area":"mllm"},{"id":"2609.37096","title":"Why MLLMs Struggle to Count: Overcoming Individuation and Aggregation Bottlenecks with ConvStack","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2610.12942","title":"In-Context Learning Can Help Vision-Language Models Overcome Training Priors","created":"2026-10-09","cited_by_count":0,"area":"mllm"},{"id":"2610.15660","title":"Sparse All-Layer Connector for Domain Generalised Semantic Segmentation","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.18598","title":"Rethinking Projector Training in Multimodal LLMs","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}