{"total":91,"rows":[{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608,"area":null},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560,"area":null},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"area":null},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518,"area":null},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225,"area":null},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186,"area":null},{"id":"2401.12794","title":"Benchmarking LLMs via Uncertainty Quantification","created":"2024-01-23","cited_by_count":126,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"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":"2309.16058","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","created":"2023-09-27","cited_by_count":93,"area":null},{"id":"2403.10228","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","created":"2024-03-15","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":"2309.13963","title":"Connecting Speech Encoder and Large Language Model for ASR","created":"2023-09-25","cited_by_count":80,"area":null},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"area":null},{"id":"2307.03025","title":"Style Over Substance: Evaluation Biases for Large Language Models","created":"2023-07-06","cited_by_count":70,"area":null},{"id":"2401.13923","title":"Towards 3D Molecule-Text Interpretation in Language Models","created":"2024-01-25","cited_by_count":66,"area":null},{"id":"2401.10334","title":"DrugAssist: A Large Language Model for Molecule Optimization","created":"2023-12-28","cited_by_count":59,"area":null},{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51,"area":null},{"id":"2310.06671","title":"Making Large Language Models Perform Better in Knowledge Graph Completion","created":"2023-10-10","cited_by_count":48,"area":null},{"id":"2404.12353","title":"V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning","created":"2024-04-18","cited_by_count":46,"area":null},{"id":"2406.08100","title":"Multimodal Table Understanding","created":"2024-06-12","cited_by_count":44,"area":null},{"id":"2503.06073","title":"GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images","created":"2025-03-08","cited_by_count":39,"area":null},{"id":"2407.15838","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","created":"2024-07-22","cited_by_count":38,"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":"2406.08402","title":"Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models","created":"2024-06-12","cited_by_count":31,"area":null},{"id":"2312.16602","title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","created":"2023-12-27","cited_by_count":29,"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":"2405.12564","title":"ProtT3: Protein-to-Text Generation for Text-based Protein Understanding","created":"2024-05-21","cited_by_count":25,"area":null},{"id":"2409.17692","title":"MIO: A Foundation Model on Multimodal Tokens","created":"2024-09-26","cited_by_count":24,"area":null},{"id":"2311.07536","title":"A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering","created":"2023-11-13","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":"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":"2404.08677","title":"PMG : Personalized Multimodal Generation with Large Language Models","created":"2024-04-07","cited_by_count":19,"area":null},{"id":"2403.13499","title":"Improved Baselines for Data-efficient Perceptual Augmentation of LLMs","created":"2024-03-20","cited_by_count":18,"area":null},{"id":"2410.00168","title":"SSR: Alignment-Aware Modality Connector for Speech Language Models","created":"2024-09-30","cited_by_count":16,"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":"2412.16524","title":"LLaVA-SLT: Visual Language Tuning for Sign Language Translation","created":"2024-12-21","cited_by_count":14,"area":null},{"id":"2503.01725","title":"HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization","created":"2025-03-03","cited_by_count":14,"area":null},{"id":"2307.13693","title":"Evaluating Large Language Models for Radiology Natural Language Processing","created":"2023-07-25","cited_by_count":12,"area":null},{"id":"2307.02971","title":"On the Cultural Gap in Text-to-Image Generation","created":"2023-07-06","cited_by_count":10,"area":null},{"id":"2406.15885","title":"The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models","created":"2024-06-22","cited_by_count":10,"area":null},{"id":"2504.02061","title":"Aligned Better, Listen Better for Audio-Visual Large Language Models","created":"2025-04-02","cited_by_count":10,"area":null},{"id":"2604.02605","title":"Do Audio-Visual Large Language Models Really See and Hear?","created":"2026-04-03","cited_by_count":9,"area":null},{"id":"2505.20873","title":"Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2401.04057","title":"Unveiling Bias in Fairness Evaluations of Large Language Models: A Critical Literature Review of Music and Movie Recommendation Systems","created":"2024-01-08","cited_by_count":7,"area":null},{"id":"2402.04527","title":"RA-Rec: An Efficient ID Representation Alignment Framework for LLM-based Recommendation","created":"2024-02-07","cited_by_count":7,"area":null},{"id":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"area":null},{"id":"2507.18531","title":"IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning","created":"2025-07-24","cited_by_count":7,"area":null},{"id":"2402.10555","title":"SPAR: Personalized Content-Based Recommendation via Long Engagement Attention","created":"2024-02-16","cited_by_count":6,"area":null},{"id":"2412.12661","title":"MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants","created":"2024-12-17","cited_by_count":6,"area":null},{"id":"2503.09321","title":"DAVE: Diagnostic benchmark for Audio Visual Evaluation","created":"2025-03-12","cited_by_count":6,"area":null},{"id":"2506.10395","title":"Pisces: An Auto-regressive Foundation Model for Image Understanding and Generation","created":"2025-06-12","cited_by_count":5,"area":null},{"id":"2512.04532","title":"PhyVLLM: Physics-Guided Video Language Model with Motion-Appearance Disentanglement","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2401.06792","title":"LightHouse: A Survey of AGI Hallucination","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2412.06967","title":"Effective Text Adaptation for LLM-based ASR through Soft Prompt Fine-Tuning","created":"2024-12-09","cited_by_count":4,"area":null},{"id":"2505.17114","title":"RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2603.01776","title":"FreeAct: Freeing Activations for LLM Quantization","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2311.13053","title":"Beyond Text: Unveiling Multimodal Proficiency of Large Language Models with MultiAPI Benchmark","created":"2023-11-21","cited_by_count":3,"area":null},{"id":"2406.05496","title":"Generalist Multimodal AI: A Review of Architectures, Challenges and Opportunities","created":"2024-06-08","cited_by_count":3,"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":"2408.14595","title":"Surprisingly Fragile: Assessing and Addressing Prompt Instability in Multimodal Foundation Models","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2410.19896","title":"FLAASH: Flow-Attention Adaptive Semantic Hierarchical Fusion for Multi-Modal Tobacco Content Analysis","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2502.06846","title":"Prot2Chat: Protein LLM with Early-Fusion of Text, Sequence and Structure","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2605.04045","title":"Audio-Visual Intelligence in Large Foundation Models","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2403.19833","title":"ChatTracer: Large Language Model Powered Real-time Bluetooth Device Tracking System","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2406.17272","title":"A Comprehensive Solution to Connect Speech Encoder and Large Language Model for ASR","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2409.16005","title":"Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2410.07405","title":"Exploring Efficient Foundational Multi-modal Models for Video Summarization","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2410.13268","title":"Roadmap towards Superhuman Speech Understanding using Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2411.05903","title":"Towards Multi-Modal Mastery: A 4.5B Parameter Truly Multi-Modal Small Language Model","created":"2024-11-08","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":"2509.04606","title":"Sample-efficient Integration of New Modalities into Large Language Models","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2603.04128","title":"Crab$^{+}$: A Scalable and Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2310.06594","title":"On the Evaluation and Refinement of Vision-Language Instruction Tuning Datasets","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2403.18451","title":"CoRAST: Towards Foundation Model-Powered Correlated Data Analysis in Resource-Constrained CPS and IoT","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2412.14965","title":"Movie2Story: A framework for understanding videos and telling stories in the form of novel text","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2505.00275","title":"AdCare-VLM: Towards a Unified and Pre-aligned Latent Representation for Healthcare Video Understanding","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2509.25739","title":"LieHMR: Autoregressive Human Mesh Recovery with $SO(3)$ Diffusion","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2602.07077","title":"CALM: Class-Conditional Sparse Attention Vectors for Large Audio-Language Models","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2604.23284","title":"Au-M-ol: A Unified Model for Medical Audio and Language Understanding","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2608.24845","title":"LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.26317","title":"Modality Maturity Index: A benchmark for assessing multimodal capabilities of omni models","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2610.09408","title":"TiTok: Audio-Visual LLM for Multi-Segment Temporal Grounding","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}