{"total":60,"rows":[{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2307.03917","title":"On decoder-only architecture for speech-to-text and large language model integration","created":"2023-07-08","cited_by_count":145,"area":null},{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118,"area":null},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107,"area":null},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2311.16208","title":"InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery","created":"2023-11-27","cited_by_count":86,"area":null},{"id":"2307.01848","title":"Embodied Task Planning with Large Language Models","created":"2023-07-04","cited_by_count":84,"area":null},{"id":"2502.04328","title":"Ola: Pushing the Frontiers of Omni-Modal Language Model","created":"2025-02-06","cited_by_count":83,"area":null},{"id":"2309.13963","title":"Connecting Speech Encoder and Large Language Model for ASR","created":"2023-09-25","cited_by_count":80,"area":null},{"id":"2310.09424","title":"SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation","created":"2023-10-13","cited_by_count":76,"area":null},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2405.03770","title":"Foundation Models for Video Understanding: A Survey","created":"2024-05-06","cited_by_count":46,"area":null},{"id":"2312.10763","title":"M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts","created":"2023-12-17","cited_by_count":32,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2404.05052","title":"Facial Affective Behavior Analysis with Instruction Tuning","created":"2024-04-07","cited_by_count":26,"area":null},{"id":"2402.12025","title":"Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?","created":"2024-02-19","cited_by_count":23,"area":null},{"id":"2402.05457","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","created":"2024-02-08","cited_by_count":22,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2405.10025","title":"Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models","created":"2024-05-16","cited_by_count":14,"area":null},{"id":"2412.02158","title":"Agri-LLaVA: Knowledge-Infused Large Multimodal Assistant on Agricultural Pests and Diseases","created":"2024-12-03","cited_by_count":14,"area":null},{"id":"2503.22906","title":"SocialGen: Modeling Multi-Human Social Interaction with Language Models","created":"2025-03-28","cited_by_count":14,"area":null},{"id":"2603.01840","title":"FireRed-OCR Technical Report","created":"2026-03-02","cited_by_count":13,"area":null},{"id":"2306.10765","title":"Path to Medical AGI: Unify Domain-specific Medical LLMs with the Lowest Cost","created":"2023-06-19","cited_by_count":12,"area":null},{"id":"2312.03668","title":"Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition","created":"2023-12-06","cited_by_count":10,"area":null},{"id":"2310.02050","title":"Tuning Large language model for End-to-end Speech Translation","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2502.12478","title":"MSE-Adapter: A Lightweight Plugin Endowing LLMs with the Capability to Perform Multimodal Sentiment Analysis and Emotion Recognition","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2502.19548","title":"When Large Language Models Meet Speech: A Survey on Integration Approaches","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2410.01812","title":"From Text to Multimodality: Exploring the Evolution and Impact of Large Language Models in Medical Practice","created":"2024-09-14","cited_by_count":8,"area":null},{"id":"2308.09970","title":"Tackling Vision Language Tasks Through Learning Inner Monologues","created":"2023-08-19","cited_by_count":7,"area":null},{"id":"2312.06363","title":"MMICT: Boosting Multi-Modal Fine-Tuning with In-Context Examples","created":"2023-12-11","cited_by_count":7,"area":null},{"id":"2409.08907","title":"Affective Computing Has Changed: The Foundation Model Disruption","created":"2024-09-13","cited_by_count":7,"area":null},{"id":"2411.14842","title":"Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Audio-Language Models","created":"2024-11-22","cited_by_count":7,"area":null},{"id":"2507.23511","title":"MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2501.02370","title":"Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison","created":"2025-01-04","cited_by_count":5,"area":null},{"id":"2410.03798","title":"Self-Powered LLM Modality Expansion for Large Speech-Text Models","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2503.01261","title":"Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2408.00624","title":"SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data","created":"2024-08-01","cited_by_count":3,"area":null},{"id":"2409.07889","title":"BLens: Contrastive Captioning of Binary Functions using Ensemble Embedding","created":"2024-09-12","cited_by_count":3,"area":null},{"id":"2409.08680","title":"NEST-RQ: Next Token Prediction for Speech Self-Supervised Pre-Training","created":"2024-09-13","cited_by_count":3,"area":null},{"id":"2504.15509","title":"SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2407.04482","title":"Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Models","created":"2024-07-05","cited_by_count":2,"area":null},{"id":"2411.07691","title":"New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2503.10211","title":"Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2505.18115","title":"Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2506.08774","title":"Multimodal Representation Alignment for Cross-modal Information Retrieval","created":"2025-06-10","cited_by_count":2,"area":null},{"id":"2405.16501","title":"User-Friendly Customized Generation with Multi-Modal Prompts","created":"2024-05-26","cited_by_count":1,"area":null},{"id":"2504.03235","title":"Enhancing Traffic Incident Response through Sub-Second Temporal Localization with HybridMamba","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2509.23109","title":"AttAnchor: Guiding Cross-Modal Token Alignment in VLMs with Attention Anchors","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2510.27208","title":"Multi-Modal Feature Fusion for Spatial Morphology Analysis of Traditional Villages via Hierarchical Graph Neural Networks","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2308.11217","title":"Federated Learning in Big Model Era: Domain-Specific Multimodal Large Models","created":"2023-08-22","cited_by_count":0,"area":null},{"id":"2310.18390","title":"Entity Embeddings : Perspectives Towards an Omni-Modality Era for Large Language Models","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2511.11777","title":"Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2511.22455","title":"Beyond Real versus Fake Towards Intent-Aware Video Analysis","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2606.22352","title":"On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning","created":"2026-06-21","cited_by_count":0,"area":null}],"next_cursor":null}