{"total":53,"rows":[{"id":"2604.27393","title":"MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction","created":"2026-04-30","cited_by_count":78,"area":"mllm"},{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2512.02231","title":"See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models","created":"2025-12-01","cited_by_count":20,"area":"mllm"},{"id":"2603.06577","title":"Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion","created":"2026-03-06","cited_by_count":13,"area":"mllm"},{"id":"2602.14122","title":"EgoSound: Benchmarking Sound Understanding in Egocentric Videos","created":"2026-02-15","cited_by_count":11,"area":"mllm"},{"id":"2604.11244","title":"Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding","created":"2026-04-13","cited_by_count":8,"area":"mllm"},{"id":"2606.10738","title":"Spatial-Omni: Spatial Audio Understanding Integration in Multimodal LLMs via FOA Encoding","created":"2026-06-09","cited_by_count":7,"area":"mllm"},{"id":"2604.11102","title":"OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video","created":"2026-04-13","cited_by_count":6,"area":"mllm"},{"id":"2512.16250","title":"AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding","created":"2025-12-18","cited_by_count":4,"area":"mllm"},{"id":"2512.01512","title":"MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages","created":"2025-12-01","cited_by_count":3,"area":"mllm"},{"id":"2601.21666","title":"SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding","created":"2026-01-29","cited_by_count":3,"area":"mllm"},{"id":"2603.00595","title":"UNICBench: UNIfied Counting Benchmark for MLLM","created":"2026-02-28","cited_by_count":3,"area":"mllm"},{"id":"2606.07953","title":"Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines","created":"2026-06-06","cited_by_count":3,"area":"mllm"},{"id":"2606.24286","title":"AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression","created":"2026-06-23","cited_by_count":3,"area":"mllm"},{"id":"2607.01667","title":"Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning","created":"2026-07-02","cited_by_count":3,"area":"mllm"},{"id":"2511.14336","title":"ArchMap: Arch-Flattening and Knowledge-Guided Vision Language Model for Tooth Counting and Structured Dental Understanding","created":"2025-11-18","cited_by_count":2,"area":"mllm"},{"id":"2511.19529","title":"Vidi2.5: Large Multimodal Models for Video Understanding and Creation","created":"2025-11-24","cited_by_count":2,"area":"mllm"},{"id":"2602.17799","title":"Enabling Training-Free Text-Based Remote Sensing Segmentation","created":"2026-02-19","cited_by_count":2,"area":"mllm"},{"id":"2606.08239","title":"When No Answer Is Correct: Diagnosing Absent Answer Detection for MLLMs in Video Understanding","created":"2026-06-06","cited_by_count":2,"area":"mllm"},{"id":"2606.28551","title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","created":"2026-06-26","cited_by_count":2,"area":"mllm"},{"id":"2609.00550","title":"Same Semantics, Different Outcome: On the Modality Robustness of Multimodal LLMs under Knowledge Conflict","created":"2026-09-01","cited_by_count":2,"area":"mllm"},{"id":"2511.17962","title":"VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment","created":"2025-11-22","cited_by_count":1,"area":"mllm"},{"id":"2511.19969","title":"M$^3$Prune: Hierarchical Communication Graph Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented Generation","created":"2025-11-25","cited_by_count":1,"area":"mllm"},{"id":"2602.23730","title":"Unlocking Cognitive Capabilities and Analyzing the Perception-Logic Trade-off","created":"2026-02-27","cited_by_count":1,"area":"mllm"},{"id":"2603.22763","title":"ENC-Bench: A Benchmark for Evaluating Multimodal Large Language Models in Electronic Navigational Chart Understanding","created":"2026-03-24","cited_by_count":1,"area":"mllm"},{"id":"2604.13073","title":"OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs","created":"2026-03-20","cited_by_count":1,"area":"mllm"},{"id":"2605.09996","title":"Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization","created":"2026-05-11","cited_by_count":1,"area":"mllm"},{"id":"2605.18104","title":"Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction","created":"2026-05-18","cited_by_count":1,"area":"mllm"},{"id":"2605.22109","title":"Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?","created":"2026-05-21","cited_by_count":1,"area":"mllm"},{"id":"2606.10147","title":"From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs","created":"2026-06-08","cited_by_count":1,"area":"mllm"},{"id":"2510.09586","title":"Vision Language Models: A Survey of 26K Papers","created":"2025-10-10","cited_by_count":0,"area":"mllm"},{"id":"2511.18314","title":"AnyExperts: On-Demand Expert Allocation for Multimodal Language Models with Mixture of Expert","created":"2025-11-23","cited_by_count":0,"area":"mllm"},{"id":"2512.20136","title":"M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation","created":"2025-12-23","cited_by_count":0,"area":"mllm"},{"id":"2603.15467","title":"Evaluating Time Awareness and Cross-modal Active Perception of Large Models via 4D Escape Room Task","created":"2026-03-16","cited_by_count":0,"area":"mllm"},{"id":"2605.07478","title":"AudioFace: Language-Assisted Speech-Driven Facial Animation with Multimodal Language Models","created":"2026-05-08","cited_by_count":0,"area":"mllm"},{"id":"2605.09152","title":"Meow-Omni 1: A Multimodal Large Language Model for Feline Ethology","created":"2026-05-09","cited_by_count":0,"area":"mllm"},{"id":"2605.19329","title":"RE-VLM: Event-Augmented Vision-Language Model for Scene Understanding","created":"2026-05-19","cited_by_count":0,"area":"mllm"},{"id":"2605.21852","title":"Seizure-Semiology-Suite (S3): A Clinically Multimodal Dataset, Benchmark, and Models for Seizure Semiology Understanding","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2606.07541","title":"Multimodal Large Language Models as Synthetic Participants in Video-Based Studies: An Evaluation","created":"2026-05-01","cited_by_count":0,"area":"mllm"},{"id":"2606.16137","title":"XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Models","created":"2026-06-15","cited_by_count":0,"area":"mllm"},{"id":"2607.02119","title":"An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation","created":"2026-07-02","cited_by_count":0,"area":"mllm"},{"id":"2607.02680","title":"K9-Bench: Evaluating Multimodal LLMs on Canine-Centric Videos","created":"2026-07-02","cited_by_count":0,"area":"mllm"},{"id":"2608.04586","title":"Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders","created":"2026-08-05","cited_by_count":0,"area":"mllm"},{"id":"2608.14651","title":"Evaluating Multimodal LLMs across Text and Audio Modalities for Accessible Disaster Assistance","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2608.18132","title":"Alignment Is All You Need: Instruction-Free Training for General Audio-Language Models","created":"2026-07-28","cited_by_count":0,"area":"mllm"},{"id":"2608.25529","title":"Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios","created":"2026-08-26","cited_by_count":0,"area":"mllm"},{"id":"2609.00206","title":"Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.09852","title":"$S^3$-Bench: Evaluating Speech Interaction Models as Scientific Voice Assistants","created":"2026-09-09","cited_by_count":0,"area":"mllm"},{"id":"2609.26513","title":"Virtual Encoders in Multimodal Transformers","created":"2026-09-22","cited_by_count":0,"area":"mllm"},{"id":"2609.37515","title":"Hierarchical Compression of Vision-Language Model Benchmarks","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2610.11410","title":"Cognition-Oriented Emotion Tracing from Causes to Consequences in Real-World Social Scenes","created":"2026-10-08","cited_by_count":0,"area":"mllm"},{"id":"2610.15129","title":"GesBench: When and Where Do Multimodal Language Models Perceive Social Meaning?","created":"2026-10-10","cited_by_count":0,"area":"mllm"},{"id":"2610.17856","title":"MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision","created":"2026-10-13","cited_by_count":0,"area":"mllm"}],"next_cursor":null}