论文解读
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs
音视频 | 7.0/10
音视频
论文解读
MMTB: Evaluating Terminal Agents on Multimedia-File Tasks
基准测试 | 60/10
论文解读
OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models
音视频 | 7.0/10
论文解读
FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries
音频检索 | 6.0/10
论文解读
Do Joint Audio-Video Generation Models Understand Physics?
Do Joint Audio-Video Generation Models Understand Physics?
论文解读
Audio-Visual Intelligence in Large Foundation Models
跨模态 | 8.0/10
论文解读
AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner
视频编辑 | 8.0/10
论文解读
AsymK-Talker: Real-Time and Long-Horizon Talking Head Generation via Asymmetric Kernel Distillation
语音合成 | 7.5/10
论文解读
BRITE: A Benchmark for Reliable and Interpretable T2V Evaluation on Implausible Scenarios
基准测试 | 7.5/10
论文解读
Delayed Commitment for Representation Readiness in Stage-wise Audio-Visual Learning
音视频 | 7.5/10
论文解读
Multimodal Confidence Modeling in Audio-Visual Quality Assessment
音视频 | 7.0/10
论文解读
AlignSep: Temporally-Aligned Video-Queried Sound Separation with Flow Matching
音频分离 | 7.5/10
论文解读
Can Vision-Language Models Answer Face to Face Questions in the Real-World?
音频问答 | 8.0/10
论文解读
Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention
语音分离 | 7.5/10
论文解读
Human Behavior Atlas: Benchmarking Unified Psychological And Social Behavior Understanding
多模态模型 | 8.5/10
会议任务专题
ICLR 2026 - 音视频
共 4 篇 ICLR 2026 音视频 方向论文
论文解读
Instilling an Active Mind in Avatars via Cognitive Simulation
音视频 | 7.0/10
论文解读
JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization
音视频 | 8.5/10
论文解读
JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation
音视频 | 9.0/10
论文解读
Pay Attention to CTC: Fast and Robust Pseudo-Labelling for Unified Speech Recognition
语音识别 | 8.0/10