Text-to-audio (TTA) generation has advanced rapidly in generation quality and instruction following. However, representative systems often require around a billion parameters, limiting deployment on resource-constrained devices. This paper introduces TinyAudio, a compact flow-matching-based TTA model for low-resource d...
Jun-Xi Liu, Xi-Quan Li, Wen-Hao Guan et al.· 0 citations
Natural audio-visual interaction is emerging as an important interface for AI assistants, allowing users to communicate through speech and vision rather than carefully composed text prompts. However, existing benchmarks of interactive capabilities still focus primarily on response quality, leaving a more fundamental qu...
Qi Chen, Yunfei Chu, Haolin He et al.· 1 citation· ⚡1
EmoDialogue, a bilingual dataset providing necessary fine-grained supervision through response pairs with rigorously defined EI gradations, and EmoS, a specialized evaluator model optimized via Supervised Fine-Tuning and Group Relative Policy Optimization, are introduced, establishing a foundational framework for advan...
Junyu Wang, Si-Yuan Zhang, Peiyuan Jiang et al.· 1 citation
This work presents \method, a training-free sparse-attention system that improves the distributed execution efficiency of adaptive sparse attention under multi-GPU sequence parallelism.
Hao Liu, Chenghua Huang, Ye Huang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
