Related papers: Sensitivity-Aware Finetuning for Accuracy Recovery…

The post-training quantization (PTQ) challenge of bringing quantized neural net accuracy close to original has drawn much attention driven by industry demand. Many of the methods emphasize optimization of a specific degree-of-freedom (DoF),…

Permanent faults induced due to imperfections in the manufacturing process of Deep Neural Network (DNN) accelerators are a major concern, as they negatively impact the manufacturing yield of the chip fabrication process. Fault-aware…

This work analyzes how attention-based Bidirectional Long Short-Term Memory (BLSTM) models adapt to noise-augmented speech. We identify crucial components for noise adaptation in BLSTM models by freezing model components during fine-tuning.…

While LLM-based TTS models exhibit zero-shot emotion and speaker cloning, their cloning fidelity and pronunciation clarity degrade on unseen domains. Fine-tuning is essential for adaptation, yet uniform approaches overlook specific…

Fine-tuning pre-trained language models such as BERT has become a common practice dominating leaderboards across various NLP tasks. Despite its recent success and wide adoption, this process is unstable when there are only a small number of…

Quantization-Aware Training (QAT) is one of the prevailing neural network compression solutions. However, its stability has been challenged for yielding deteriorating performances as the quantization error is inevitable. We find that the…

Fixed-point (FXP) inference has proven suitable for embedded devices with limited computational resources, and yet model training is continually performed in floating-point (FLP). FXP training has not been fully explored and the non-trivial…

Benefit from the quick development of deep learning techniques, salient object detection has achieved remarkable progresses recently. However, there still exists following two major challenges that hinder its application in embedded…

Deep features are a cornerstone of computer vision research, capturing image semantics and enabling the community to solve downstream tasks even in the zero- or few-shot regime. However, these features often lack the spatial resolution to…

Advancements in monaural speech enhancement (SE) techniques have greatly improved the perceptual quality of speech. However, integrating these techniques into automatic speech recognition (ASR) systems has not yielded the expected…

Quantization is one of the core components in lossy image compression. For neural image compression, end-to-end optimization requires differentiable approximations of quantization, which can generally be grouped into three categories:…

Transfer learning has become a popular task adaptation method in the era of foundation models. However, many foundation models require large storage and computing resources, which makes off-the-shelf deployment impractical. Post-training…

Deploying Automatic Speech Recognition (ASR) models on memory-constrained edge devices requires aggressive low-bit weight quantization. Layer-wise post-training quantization is practical and effective, but it suffers from cross-layer error…

Large language models exhibit strong reasoning capabilities, yet often rely on shortcuts such as surface pattern matching and answer memorization rather than genuine logical inference. We propose Shortcut-Aware Reasoning Training (SART), a…

An increasing number of software applications incorporate runtime Deep Neural Networks (DNNs) to process sensor data and return inference results to humans. Effective deployment of DNNs in these interactive scenarios requires meeting…

Full fine-tuning is a popular approach to adapt Transformer-based pre-trained large language models to a specific downstream task. However, the substantial requirements for computational power and storage have discouraged its widespread…

Large language models (LLMs) have achieved remarkable success across various tasks but face deployment challenges due to their massive computational demands. While post-training pruning methods like SparseGPT and Wanda can effectively…

With the rapid growth in the use of fine-tuning for large language models (LLMs), optimizing fine-tuning while keeping inference efficient has become highly important. However, this is a challenging task as it requires improvements in all…

The selective fixed-filter strategy is popular in industrial applications involving active noise control (ANC) technology, which circumvents the time-consuming online learning process by selecting the best-matched pre-trained control…

In quantum machine field, detecting two-dimensional (2D) materials in Silicon chips is one of the most critical problems. Instance segmentation can be considered as a potential approach to solve this problem. However, similar to other deep…