{"total":31,"rows":[{"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":"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,"area":null},{"id":"2503.21408","title":"VALLR: Visual ASR Language Model for Lip Reading","created":"2025-03-27","cited_by_count":11,"area":null},{"id":"2510.22603","title":"Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMs","created":"2025-10-26","cited_by_count":11,"area":null},{"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,"area":null},{"id":"2508.05149","title":"Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages","created":"2025-08-07","cited_by_count":7,"area":null},{"id":"2511.11124","title":"AV-Dialog: Spoken Dialogue Models with Audio-Visual Input","created":"2025-11-14","cited_by_count":5,"area":null},{"id":"2502.01547","title":"mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2505.11352","title":"LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2510.23276","title":"A Cocktail-Party Benchmark: Multi-Modal dataset and Comparative Evaluation Results","created":"2025-10-27","cited_by_count":4,"area":null},{"id":"2511.07253","title":"Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2604.21905","title":"Low-Rank Adaptation Redux for Large Models","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2606.07435","title":"The Lipreading Gap: Do VSR Models Perceive Visual Speech Like Human Lipreaders?","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2601.18396","title":"Noise-Robust AV-ASR Using Visual Features Both in the Whisper Encoder and Decoder","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2603.22915","title":"When AVSR Meets Video Conferencing: Dataset, Degradation, and the Hidden Mechanism Behind Performance Collapse","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2506.02012","title":"Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2508.20476","title":"Towards Inclusive Communication: A Unified Framework for Generating Spoken Language from Sign, Lip, and Audio","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2510.13281","title":"Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2602.19316","title":"Pay Attention to CTC: Fast and Robust Pseudo-Labelling for Unified Speech Recognition","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2603.12046","title":"Dr. SHAP-AV: Decoding Relative Modality Contributions via Shapley Attribution in Audio-Visual Speech Recognition","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2607.22100","title":"MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2511.06288","title":"ELEGANCE: Efficient LLM Guidance for Audio-Visual Target Speech Extraction","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2605.28456","title":"Diffusion Large Language Models for Visual Speech Recognition","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.06532","title":"GOPAgen: Codec-Aware Agentic Long-Video Understanding with Structured Memory","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.29632","title":"VIB-AVSR: Variational Information Bottleneck for Noise-Robust LLM-Based Audio-Visual Speech Recognition","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2608.17102","title":"Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.26213","title":"Attention-Guided Reliability Scaling for Contrastive Decoding in Robust Audio-Visual Speech Recognition","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.10366","title":"AVSRBench: A Multi-Condition AVSR Benchmark","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.10394","title":"Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.20839","title":"Curriculum-Based Noise Adaptation for Phoneme-to-Text Reconstruction in Visual Speech Recognition","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2610.19559","title":"Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}