MTSS replaces monolithic video captions with factorized streams and relational grounding, yielding reported gains in understanding benchmarks and generation consistency.
Av-dit: Effi- cient audio-visual diffusion transformer for joint audio and video generation
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
PhyAVBench provides the first systematic benchmark and metric for audio-physics grounding in T2AV, I2AV, and V2A models using controlled prompt pairs and real video ground truth.
VideoASMR-Bench shows state-of-the-art VLMs fail to reliably detect AI-generated ASMR videos from real ones, though humans can still identify the fakes relatively easily.
SyncDPO improves temporal synchronization in video-audio joint generation using DPO with efficient on-the-fly negative sample construction and curriculum learning.
AdaCluster delivers a training-free adaptive query-key clustering framework for sparse attention in video DiTs, yielding 1.67-4.31x inference speedup with negligible quality loss on CogVideoX-2B, HunyuanVideo, and Wan-2.1.
citing papers explorer
-
Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding
MTSS replaces monolithic video captions with factorized streams and relational grounding, yielding reported gains in understanding benchmarks and generation consistency.
-
PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation
PhyAVBench provides the first systematic benchmark and metric for audio-physics grounding in T2AV, I2AV, and V2A models using controlled prompt pairs and real video ground truth.
-
VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?
VideoASMR-Bench shows state-of-the-art VLMs fail to reliably detect AI-generated ASMR videos from real ones, though humans can still identify the fakes relatively easily.
-
SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning
SyncDPO improves temporal synchronization in video-audio joint generation using DPO with efficient on-the-fly negative sample construction and curriculum learning.
-
AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation
AdaCluster delivers a training-free adaptive query-key clustering framework for sparse attention in video DiTs, yielding 1.67-4.31x inference speedup with negligible quality loss on CogVideoX-2B, HunyuanVideo, and Wan-2.1.
- MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation
- OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation