Search Results for author:
Found 18 papers, 5 papers with code
Token and Head Adaptive Transformers for Efficient Natural Language Processing
While pre-trained language models like BERT have achieved impressive results on various natural language processing tasks, deploying them on resource-restricted devices is challenging due to their intensive computational cost and memory footprint.
Learning to Maximize Mutual Information for Chain-of-Thought Distillation
Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment.
To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now
Our results demonstrate the effectiveness and efficiency merits of UnlearnDiffAtk over the state-of-the-art adversarial prompt generation method and reveal the lack of robustness of current safety-driven unlearning techniques when applied to DMs.
Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter
To further expand the applications of multilingual artificial intelligence assistants and facilitate international communication, it is essential to enhance the performance of multilingual speech recognition, which is a crucial component of speech interaction.
CPPF: A contextual and post-processing-free model for automatic speech recognition
To address this issue, we draw inspiration from the multifaceted capabilities of LLMs and Whisper, and focus on integrating multiple ASR text processing tasks related to speech recognition into the ASR model.
AntM$^{2}$C: A Large Scale Dataset For Multi-Scenario Multi-Modal CTR Prediction
3) AntM$^{2}$C provides 1 billion CTR data with 200 features, including 200 million users and 6 million items.
BatchGNN: Efficient CPU-Based Distributed GNN Training on Very Large Graphs
We present BatchGNN, a distributed CPU system that showcases techniques that can be used to efficiently train GNNs on terabyte-sized graphs.
Learning Reduced-Order Models for Cardiovascular Simulations with Graph Neural Networks
Our numerical results demonstrate the accuracy and generalizability of our method in physiological geometries comprising a variety of anatomies and boundary conditions.
Text-Visual Prompting for Efficient 2D Temporal Video Grounding
In this paper, we study the problem of temporal video grounding (TVG), which aims to predict the starting/ending time points of moments described by a text sentence within a long untrimmed video.
Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization
To reduce the peak latency, we propose a simple and novel method named peak-first regularization, which utilizes a frame-wise knowledge distillation function to force the probability distribution of the CTC model to shift left along the time axis instead of directly modifying the calculation process of CTC loss and gradients.
Two-Stream UNET Networks for Semantic Segmentation in Medical Images
Recent advances of semantic image segmentation greatly benefit from deeper and larger Convolutional Neural Network (CNN) models.
CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR
The simulation module is jointly trained with the ASR model using a self-supervised loss; the ASR model is optimized with the usual ASR loss, e. g., CTC-CRF as used in our experiments.
An Empirical Study of Language Model Integration for Transducer based Speech Recognition
Based on the DR method, we propose a low-order density ratio method (LODR) by replacing the estimation with a low-order weak language model.
Dynamic-TinyBERT: Boost TinyBERT's Inference Efficiency by Dynamic Sequence Length
Additionally, a separate model must be trained for each inference scenario with its distinct computational budget.
Learning Speaker Embedding with Momentum Contrast
Momentum Contrast (MoCo) is a recently proposed unsupervised representation learning framework, and has shown its effectiveness for learning good feature representation for downstream vision tasks.
CRF-LSTM Text Mining Method Unveiling the Pharmacological Mechanism of Off-target Side Effect of Anti-Multiple Myeloma Drugs
Sequence labeling of biomedical entities, e. g., side effects or phenotypes, was a long-term task in BioNLP and MedNLP communities.
A Note on Kaldi's PLDA Implementation
Some explanations to Kaldi's PLDA implementation to make formula derivation easier to catch.
A CUDA-Based Real Parameter Optimization Benchmark
Benchmarking is key for developing and comparing optimization algorithms.
