论文解读
TINY BUT MIGHTY: A SOFTWARE-HARDWARE CO- DESIGN APPROACH FOR EFFICIENT MULTIMODAL IN- FERENCE ON BATTERY-POWERED SMALL DEVICES
多模态模型 | 7.0/10
多模态模型
论文解读
TRIBE: TRImodal Brain Encoder for whole-brain fMRI response prediction
脑编码 | 9.5/10
论文解读
TripleSumm: Adaptive Triple-Modality Fusion for Video Summarization
视频摘要 | 8.5/10
论文解读
UALM: Unified Audio Language Model for Understanding, Generation and Reasoning
音频生成 | 8.5/10
论文解读
VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Video
基准测试 | 7.0/10
论文解读
WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM
音频检索 | 8.0/10
论文解读
WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
音频问答 | 7.0/10
论文解读
XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models
基准测试 | 7.5/10
论文解读
YuE: Scaling Open Foundation Models for Long-Form Music Generation
音乐生成 | 7.5/10
每日研究速递
语音/音乐/音频论文速递 2026-05-04
共分析 14 篇语音/AI 论文
每日研究速递
语音/音乐/音频论文速递 2026-05-03
共分析 13 篇语音/AI 论文
论文解读
A Hidden Semantic Bottleneck in Conditional Embeddings of Diffusion Transformers
生成模型 | 6.5/10
论文解读
AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer
音频生成 | 7.5/10
论文解读
AudioX: A Unified Framework for Anything-to-Audio Generation
音频生成 | 7.5/10
论文解读
Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?
音乐生成 | 8.5/10
论文解读
AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization
情感识别 | 7.5/10
论文解读
AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration
音视频 | 8.0/10
论文解读
Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models
多模态模型 | 7.0/10
论文解读
Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal Reasoning
多模态推理 | 8.5/10
论文解读
Data-Centric Lessons To Improve Speech-Language Pretraining
语音问答 | 8.0/10