{"total":18,"rows":[{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109,"area":"mllm"},{"id":"2412.19326","title":"Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment","created":"2024-12-26","cited_by_count":29,"area":"mllm"},{"id":"2404.08958","title":"AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning","created":"2024-04-13","cited_by_count":22,"area":"mllm"},{"id":"2508.10922","title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","created":"2025-08-07","cited_by_count":20,"area":"mllm"},{"id":"2511.07049","title":"From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge","created":"2025-11-10","cited_by_count":9,"area":"mllm"},{"id":"2603.12254","title":"Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing","created":"2026-03-12","cited_by_count":9,"area":"mllm"},{"id":"2510.26027","title":"Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders","created":"2025-10-29","cited_by_count":6,"area":"mllm"},{"id":"2503.18712","title":"LLaVAction: evaluating and training multi-modal large language models for action understanding","created":"2025-03-24","cited_by_count":3,"area":"mllm"},{"id":"2412.04729","title":"Espresso: High Compression For Rich Extraction From Videos for Your Vision-Language Model","created":"2024-12-06","cited_by_count":2,"area":"mllm"},{"id":"2505.14405","title":"Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency","created":"2025-05-20","cited_by_count":2,"area":"mllm"},{"id":"2512.17012","title":"4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation","created":"2025-12-18","cited_by_count":2,"area":"mllm"},{"id":"2601.21078","title":"Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization","created":"2026-01-28","cited_by_count":1,"area":"mllm"},{"id":"2604.18134","title":"Can LLM-Generated Text Empower Surgical Vision-Language Pre-training?","created":"2026-04-20","cited_by_count":1,"area":"mllm"},{"id":"2604.03302","title":"Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models","created":"2026-03-30","cited_by_count":0,"area":"mllm"},{"id":"2604.04419","title":"BoxComm: Benchmarking Category-Aware Commentary Generation and Narration Rhythm in Boxing","created":"2026-04-06","cited_by_count":0,"area":"mllm"},{"id":"2605.28229","title":"VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transfer","created":"2026-05-27","cited_by_count":0,"area":"mllm"},{"id":"2606.21607","title":"T-MOR: Learning Motion-Aware Skeleton Representations for Human Action Recognition","created":"2026-06-19","cited_by_count":0,"area":"mllm"},{"id":"2607.10797","title":"Compositional Context Fine-Tuning Vision-Language Model for Complex Assembly Action Understanding from Videos","created":"2026-07-12","cited_by_count":0,"area":"mllm"}],"next_cursor":null}