6 papers
CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits
Xue-Jian Gao, Deng Pan, Yueming Su +12
AI agents are now capable of writing, compiling, and iteratively optimizing low-level operator kernels on different hardware platforms. Existing benchmarks, however, focus almost e…
PrefSQA: Pairwise Preference Prediction for Speech Quality Assessment and the Critical Role of High Quality Datasets
Junyi Fan, Donald S. Williamson
Mean opinion scores (MOS) are widely used for speech quality assessment, yet scalar labels are sensitive to rater variability and listening test differences. This introduces labeli…
Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference
Lingchao Zheng, Yuwei Fan, Jun Li +5
Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-precision for matrix multiplicatio…
FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement
Wenshuo Gao, Junyi Fan, Jiangyue Zeng +1
Video relighting with background replacement is a challenging task critical for applications in film production and creative media. Existing methods struggle to balance temporal co…
From the perspective of perceptual speech quality: The robustness of frequency bands to noise
Junyi Fan, Donald S. Williamson
Speech quality is one of the main foci of speech-related research, where it is frequently studied with speech intelligibility, another essential measurement. Band-level perceptual…
JSQA: Speech Quality Assessment with Perceptually-Inspired Contrastive Pretraining Based on JND Audio Pairs
Junyi Fan, Donald Williamson
Speech quality assessment (SQA) is often used to learn a mapping from a high-dimensional input space to a scalar that represents the mean opinion score (MOS) of the perceptual spee…