{"list":"other","total":75,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"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},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"id":"2312.06742","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","created":"2023-12-11","cited_by_count":197},{"id":"2404.13628","title":"Mixture of LoRA Experts","created":"2024-04-21","cited_by_count":181},{"id":"2402.07871","title":"Scaling Laws for Fine-Grained Mixture of Experts","created":"2024-02-12","cited_by_count":173},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173},{"id":"2102.06657","title":"End-to-end Audio-visual Speech Recognition with Conformers","created":"2021-02-12","cited_by_count":151},{"id":"2309.05444","title":"Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning","created":"2023-09-11","cited_by_count":150},{"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},{"id":"2307.11795","title":"Prompting Large Language Models with Speech Recognition Abilities","created":"2023-07-21","cited_by_count":140},{"id":"2408.15998","title":"Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders","created":"2024-08-28","cited_by_count":139},{"id":"2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","created":"2025-07-14","cited_by_count":133},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129},{"id":"2303.14307","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","created":"2023-03-25","cited_by_count":114},{"id":"2402.08846","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity","created":"2024-02-13","cited_by_count":88},{"id":"2310.07707","title":"MatFormer: Nested Transformer for Elastic Inference","created":"2023-10-11","cited_by_count":85},{"id":"2405.17430","title":"Matryoshka Multimodal Models","created":"2024-05-27","cited_by_count":84},{"id":"2312.09979","title":"LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin","created":"2023-12-15","cited_by_count":82},{"id":"2309.13963","title":"Connecting Speech Encoder and Large Language Model for ASR","created":"2023-09-25","cited_by_count":80},{"id":"2201.01763","title":"Robust Self-Supervised Audio-Visual Speech Recognition","created":"2022-01-05","cited_by_count":75},{"id":"1802.06424","title":"End-to-end Audiovisual Speech Recognition","created":"2018-02-18","cited_by_count":73},{"id":"2305.14705","title":"Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models","created":"2023-05-24","cited_by_count":65},{"id":"1810.00108","title":"Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture","created":"2018-09-28","cited_by_count":64},{"id":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60},{"id":"2405.16039","title":"MoEUT: Mixture-of-Experts Universal Transformers","created":"2024-05-25","cited_by_count":59},{"id":"2405.14297","title":"Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models","created":"2024-05-23","cited_by_count":56},{"id":"2405.19315","title":"Matryoshka Query Transformer for Large Vision-Language Models","created":"2024-05-29","cited_by_count":50},{"id":"2410.07524","title":"Upcycling Large Language Models into Mixture of Experts","created":"2024-10-10","cited_by_count":49},{"id":"2503.04130","title":"STORM: Token-Efficient Long Video Understanding for Multimodal LLMs","created":"2025-03-06","cited_by_count":49},{"id":"2212.06246","title":"Jointly Learning Visual and Auditory Speech Representations from Raw Data","created":"2022-12-12","cited_by_count":47},{"id":"2303.08536","title":"Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring","created":"2023-03-15","cited_by_count":42},{"id":"2409.12319","title":"Large Language Models are Strong Audio-Visual Speech Recognition Learners","created":"2024-09-18","cited_by_count":42},{"id":"1501.05396","title":"Deep Multimodal Learning for Audio-Visual Speech Recognition","created":"2015-01-22","cited_by_count":38},{"id":"2406.10082","title":"Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation","created":"2024-06-14","cited_by_count":36},{"id":"2401.10446","title":"Large Language Models are Efficient Learners of Noise-Robust Speech Recognition","created":"2024-01-19","cited_by_count":31},{"id":"2502.05172","title":"Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient","created":"2025-02-07","cited_by_count":31},{"id":"2402.15151","title":"Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing","created":"2024-02-23","cited_by_count":30},{"id":"2410.14731","title":"MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection","created":"2024-10-16","cited_by_count":29},{"id":"2207.06020","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","created":"2022-07-13","cited_by_count":24},{"id":"2212.05301","title":"Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning","created":"2022-12-10","cited_by_count":22},{"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},{"id":"2503.11315","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","created":"2025-03-14","cited_by_count":19},{"id":"2410.00168","title":"SSR: Alignment-Aware Modality Connector for Speech Language Models","created":"2024-09-30","cited_by_count":16},{"id":"2411.02256","title":"Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs","created":"2024-11-04","cited_by_count":15},{"id":"2410.03752","title":"Efficient Streaming LLM for Speech Recognition","created":"2024-10-02","cited_by_count":12},{"id":"2403.14402","title":"XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception","created":"2024-03-21","cited_by_count":11},{"id":"2503.06362","title":"Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs","created":"2025-03-09","cited_by_count":11},{"id":"2503.01359","title":"DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models","created":"2025-03-03","cited_by_count":10},{"id":"2503.06273","title":"Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations","created":"2025-03-08","cited_by_count":9},{"id":"2312.03694","title":"Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers","created":"2023-12-06","cited_by_count":8},{"id":"2306.10563","title":"Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition","created":"2023-06-18","cited_by_count":7},{"id":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7},{"id":"2507.10800","title":"ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference","created":"2025-07-14","cited_by_count":7}],"next_cursor":null}