{"total":27,"rows":[{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692,"area":"mllm"},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263,"area":"mllm"},{"id":"2310.08825","title":"From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models","created":"2023-10-13","cited_by_count":98,"area":"mllm"},{"id":"2406.12275","title":"VoCo-LLaMA: Towards Vision Compression with Large Language Models","created":"2024-06-18","cited_by_count":79,"area":"mllm"},{"id":"2311.17618","title":"ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Model","created":"2023-11-29","cited_by_count":39,"area":"mllm"},{"id":"2412.09616","title":"V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding","created":"2024-12-12","cited_by_count":28,"area":"mllm"},{"id":"2407.17453","title":"VILA$^2$: VILA Augmented VILA","created":"2024-07-24","cited_by_count":25,"area":"mllm"},{"id":"2409.09086","title":"Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPU","created":"2024-09-11","cited_by_count":20,"area":"mllm"},{"id":"2410.17856","title":"ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting","created":"2024-10-23","cited_by_count":20,"area":"mllm"},{"id":"2407.14506","title":"On Pre-training of Multimodal Language Models Customized for Chart Understanding","created":"2024-07-19","cited_by_count":13,"area":"mllm"},{"id":"2312.04960","title":"MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness","created":"2023-12-08","cited_by_count":12,"area":"mllm"},{"id":"2505.18413","title":"LatentLLM: Attention-Aware Joint Tensor Compression","created":"2025-05-23","cited_by_count":7,"area":"mllm"},{"id":"2607.11388","title":"StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure","created":"2026-07-13","cited_by_count":7,"area":"mllm"},{"id":"2312.07553","title":"Hijacking Context in Large Multi-modal Models","created":"2023-12-07","cited_by_count":6,"area":"mllm"},{"id":"2602.00746","title":"Can Vision-Language Models Handle Long-Context Code? An Empirical Study on Visual Compression","created":"2026-01-31","cited_by_count":5,"area":"mllm"},{"id":"2505.23121","title":"ContextQFormer: A New Context Modeling Method for Multi-Turn Multi-Modal Conversations","created":"2025-05-29","cited_by_count":3,"area":"mllm"},{"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":"2510.16333","title":"RL makes MLLMs see better than SFT","created":"2025-10-18","cited_by_count":3,"area":"mllm"},{"id":"2310.00500","title":"Self-Supervised Open-Ended Classification with Small Visual Language Models","created":"2023-09-30","cited_by_count":2,"area":"mllm"},{"id":"2505.21465","title":"ID-Align: RoPE-Conscious Position Remapping for Dynamic High-Resolution Adaptation in Vision-Language Models","created":"2025-05-27","cited_by_count":2,"area":"mllm"},{"id":"2604.12537","title":"MODIX: A Training-Free Multimodal Information-Driven Positional Index Scaling for Vision-Language Models","created":"2026-04-14","cited_by_count":2,"area":"mllm"},{"id":"2504.04772","title":"Feedback-Enhanced Hallucination-Resistant Vision-Language Model for Real-Time Scene Understanding","created":"2025-04-07","cited_by_count":1,"area":"mllm"},{"id":"2510.01009","title":"POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency","created":"2025-10-01","cited_by_count":1,"area":"mllm"},{"id":"2602.23153","title":"Efficient Encoder-Free Fourier-based 3D Large Multimodal Model","created":"2026-02-26","cited_by_count":1,"area":"mllm"},{"id":"2407.10743","title":"Scaling 3D Reasoning with LMMs to Large Robot Mission Environments Using Datagraphs","created":"2024-07-15","cited_by_count":0,"area":"mllm"},{"id":"2510.25067","title":"DRIP: Dynamic patch Reduction via Interpretable Pooling","created":"2025-10-29","cited_by_count":0,"area":"mllm"},{"id":"2610.01192","title":"FlashBack: Knowing When to Remember in Streaming Vision-Language Models","created":"2026-10-01","cited_by_count":0,"area":"mllm"}],"next_cursor":null}