Search Results for author:
Found 8 papers, 1 papers with code
Speak & Improve Challenge 2025: Tasks and Baseline Systems
Linked with the challenge, the Speak & Improve (S&I) Corpus 2025 is being pre-released, a dataset of L2 learner English data with holistic scores and language error annotation, collected from open (spontaneous) speaking tests on the Speak & Improve learning platform.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
LDACP: Long-Delayed Ad Conversions Prediction Model for Bidding Strategy
To alleviate the issue of discontinuity in one-hot hard labels, the Bucket Classification Module with label Smoothing method (BCMS) converts one-hot hard labels into non-normalized soft labels, then fits these soft labels by minimizing classification loss and regression loss.
Breast tumor classification based on self-supervised contrastive learning from ultrasound videos
Further, we assessed the dependence of our pretrained model on the number of labeled data and revealed that <100 samples were required to achieve an AUC of 0. 901.
Learn and Don't Forget: Adding a New Language to ASR Foundation Models
If only adaptation parameters are used, the language capabilities are maintained but at the cost of performance in the new language.
Cross-Lingual Transfer Learning for Speech Translation
By fine-tuning the Whisper decoder with only English-to-Chinese speech translation data, improved performance for translation to Chinese can be obtained for multiple languages, in addition to English.
The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks
In our research, we propose a novel attack, Janus, which exploits the fine-tuning interface to recover forgotten PIIs from the pre-training data in LLMs.
Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
Finally, we perform both theoretical and experimental analysis, showing that the GRASP enhancement does not reduce the effectiveness of the stealthy attacks against the backdoor detection methods based on weight analysis, as well as other backdoor mitigation methods without using detection.
Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models
Our idea is to retrain a given DNN model on randomly labeled clean data, to induce a CF on the model, leading to a sudden forget on both primary and backdoor tasks; then we recover the primary task by retraining the randomized model on correctly labeled clean data.
