4 papers
MVQA-68K: A Multi-dimensional and Causally-annotated Dataset with Quality Interpretability for Video Assessment
Yanyun Pu, Kehan Li, Zeyi Huang +2
With the rapid advancement of video generation models such as Sora, video quality assessment (VQA) is becoming increasingly crucial for selecting high-quality videos from large-sca…
T2I-ConBench: Text-to-Image Benchmark for Continual Post-training
Zhehao Huang, Yuhang Liu, Yixin Lou +7
Continual post-training adapts a single text-to-image diffusion model to learn new tasks without incurring the cost of separate models, but naive post-training causes forgetting of…
Talk is Not Always Cheap: Promoting Wireless Sensing Models with Text Prompts
Zhenkui Yang, Zeyi Huang, Ge Wang +3
Wireless signal-based human sensing technologies, such as WiFi, millimeter-wave (mmWave) radar, and Radio Frequency Identification (RFID), enable the detection and interpretation o…
Ascend HiFloat8 Format for Deep Learning
Yuanyong Luo, Zhongxing Zhang, Richard Wu +16
This preliminary white paper proposes a novel 8-bit floating-point data format HiFloat8 (abbreviated as HiF8) for deep learning. HiF8 features tapered precision. For normal value e…