论文解读
OmniFit: Bridging Modalities via Layer-Adaptive Token Compression for Omnimodal Large Language Models
音视频理解 | 6.3/10
多模态模型
论文解读
PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios
音视频问答 | 7.3/10
论文解读
PRIM：Cooperative Dynamic Token Compression for Efficient Large Multimodal Models
音视频理解 | 3.6/10
论文解读
Probing Cross-modal Information Hubs in Audio-Visual LLMs
音视频理解 | 7.2/10
论文解读
SAM Audio: Segment Anything in Audio
音频分离 | 9.2/10
论文解读
Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis
音视频生成 | 7.2/10
论文解读
SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
音频修复 | 8/10
论文解读
Stable Spectral Copula Alignment for Robust Multimodal Learning
鲁棒性 | 5.2/10
论文解读
STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits
音视频生成 | 6.8/10
论文解读
T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation
音视频生成 | 7.9/10
论文解读
TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
音视频理解 | 9.4/10
论文解读
Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
音视频理解 | 5.3/10
论文解读
V-LynX: Token Interface Alignment for Video+X LLMs
音视频问答 | 7.8/10
论文解读
video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM
音视频问答 | 7.3/10
论文解读
Zero-Shot Rankability: Revealing Latent Ordinal Structure in Multimodal Large Language Models via Language
音视频理解 | 6.8/10
论文解读
A global predicted-fMRI drive signal from TRIBE does not predict YouTube replay heatmaps
音视频理解 | 7.7/10
论文解读
An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation
语音合成 | 6.8/10
论文解读
Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
音视频理解 | 7.2/10
论文解读
ASR-Agnostic Multimodal Spectrotemporal Modeling for Early Dementia Detection
多模态模型 | 7.4/10
论文解读
AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation
语音合成 | 6.5/10