论文解读
Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs
模型评估 | 8.0/10
多模态模型
论文解读
Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation
多模态模型评估 | 5.5/10
论文解读
jina-embeddings-v5-omni: Text-Geometry-Preserving Multimodal Embeddings via Frozen-Tower Composition
多模态检索 | 7.5/10
论文解读
OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
音视频生成 | 6.9/10
论文解读
AllocMV: Optimal Resource Allocation for Music Video Generation via Structured Persistent State
音乐视频生成 | 4.8/10
论文解读
EAR: Enhancing Uni-Modal Representations for Weakly Supervised Audio-Visual Video Parsing
音频事件检测 | 5.8/10
论文解读
Mitigating Multimodal Inconsistency via Cognitive Dual-Pathway Reasoning for Intent Recognition
意图识别 | 7.0/10
论文解读
Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization
基准测试 | 6.5/10
论文解读
Probing Cross-modal Information Hubs in Audio-Visual LLMs
模型分析 | 6.5/10
论文解读
Separate First, Fuse Later: Mitigating Cross-Modal Interference in Audio-Visual LLMs Reasoning with Modality-Specific Chain-of-Thought
音视频问答 | 6.0/10
论文解读
MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes
MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes
论文解读
Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs
Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs
每日研究速递
语音/音乐/音频论文速递 2026-05-11
共分析 12 篇语音/AI 论文
论文解读
Audio-Visual Intelligence in Large Foundation Models
跨模态 | 8.0/10
论文解读
X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction
移动代理 | 6.5/10
每日研究速递
语音/音乐/音频论文速递 2026-05-09
共分析 3 篇语音/AI 论文
论文解读
Modality-Aware Contrastive and Uncertainty-Regularized Emotion Recognition
语音情感识别 | 8.0/10
论文解读
JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions
音频质量评估 | 8.5/10
论文解读
OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models
音频分类 | 7.5/10
论文解读
To Fuse or to Drop? Dual-Path Learning for Resolving Modality Conflicts in Multimodal Emotion Recognition
语音情感识别 | 8.0/10