English
Related papers

Related papers: Output Embedding Centering for Stable LLM Pretrain…

200 papers

In spite of the dominant performances of deep neural networks, recent works have shown that they are poorly calibrated, resulting in over-confident predictions. Miscalibration can be exacerbated by overfitting due to the minimization of the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Bingyuan Liu , Ismail Ben Ayed , Adrian Galdran , Jose Dolz

(Stochastic) bilevel optimization is a frequently encountered problem in machine learning with a wide range of applications such as meta-learning, hyper-parameter optimization, and reinforcement learning. Most of the existing studies on…

Machine Learning · Computer Science 2023-03-16 Meng Ding , Mingxi Lei , Yunwen Lei , Di Wang , Jinhui Xu

Two techniques provide the fabric of the Cambridge University Engineering Department's (CUED) entry to the WMT19 evaluation campaign: elastic weight consolidation (EWC) and different forms of language modelling (LMs). We report substantial…

Computation and Language · Computer Science 2019-06-14 Felix Stahlberg , Danielle Saunders , Adria de Gispert , Bill Byrne

Prior research on out-of-distribution detection (OoDD) has primarily focused on single-modality models. Recently, with the advent of large-scale pretrained vision-language models such as CLIP, OoDD methods utilizing such multi-modal…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Jeonghyeon Kim , Sangheum Hwang

Embedding models have been an effective learning paradigm for high-dimensional data. However, one open issue of embedding models is that their representations (latent factors) often result in large parameter space. We observe that existing…

Machine Learning · Computer Science 2021-12-15 Xupeng Miao , Hailin Zhang , Yining Shi , Xiaonan Nie , Zhi Yang , Yangyu Tao , Bin Cui

This paper focuses on resolving stability hallucinations (e.g., repetitive or omitted speech) in LLM-based Text-to-Speech (TTS) models by improving and leveraging the attention mechanism. First, we analyzed the alignment mechanism between…

Sound · Computer Science 2026-02-16 ShiMing Wang , ZhiHao Du , Yang Xiang , TianYu Zhao , Han Zhao , Qian Chen , XianGang Li , HanJie Guo , ZhenHua Ling

When applying imitation learning techniques to fit a policy from expert demonstrations, one can take advantage of prior stability/robustness assumptions on the expert's policy and incorporate such control-theoretic prior knowledge…

Optimization and Control · Mathematics 2021-03-25 Aaron Havens , Bin Hu

In adversarial machine learning, neural networks suffer from a significant issue known as robust overfitting, where the robust test accuracy decreases over epochs (Rice et al., 2020). Recent research conducted by Xing et al.,2021; Xiao et…

Machine Learning · Computer Science 2024-05-06 Jiancong Xiao , Jiawei Zhang , Zhi-Quan Luo , Asuman Ozdaglar

This paper aims to compare different regularization strategies to address a common phenomenon, severe overfitting, in embedding-based neural networks for NLP. We chose two widely studied neural models and tasks as our testbed. We tried…

Computation and Language · Computer Science 2015-08-18 Hao Peng , Lili Mou , Ge Li , Yunchuan Chen , Yangyang Lu , Zhi Jin

Overfitting widely exists in adversarial robust training of deep networks. An effective remedy is adversarial weight perturbation, which injects the worst-case weight perturbation during network training by maximizing the classification…

Machine Learning · Computer Science 2022-05-31 Chaojian Yu , Bo Han , Mingming Gong , Li Shen , Shiming Ge , Bo Du , Tongliang Liu

The inherent safety alignment of Large Language Models (LLMs) is prone to erosion during fine-tuning, even when using seemingly innocuous datasets. While existing defenses attempt to mitigate this via data selection, they typically rely on…

Machine Learning · Computer Science 2026-01-13 Haozhong Wang , Zhuo Li , Yibo Yang , He Zhao , Hongyuan Zha , Dandan Guo

Training large language models (LLMs) presents numerous challenges, including gradient instability and loss spikes. These phenomena can lead to catastrophic divergence, requiring costly checkpoint restoration and data batch skipping.…

Machine Learning · Computer Science 2025-04-04 Abhay Kumar , Louis Owen , Nilabhra Roy Chowdhury , Fabian Güra

This paper addresses the critical issue of miscalibration in CLIP-based model adaptation, particularly in the challenging scenario of out-of-distribution (OOD) samples, which has been overlooked in the existing literature on CLIP…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Balamurali Murugesan , Julio Silva-Rodriguez , Ismail Ben Ayed , Jose Dolz

Human guidance in reinforcement learning (RL) is often impractical for large-scale applications due to high costs and time constraints. Large Language Models (LLMs) offer a promising alternative to mitigate RL sample inefficiency and…

Machine Learning · Computer Science 2024-11-25 Maryam Shoaeinaeini , Brent Harrison

While Large Language Models (LLMs) have achieved remarkable capabilities, they unintentionally memorize sensitive data, posing critical privacy and security risks. Machine unlearning is pivotal for mitigating these risks, yet existing…

Machine Learning · Computer Science 2026-02-03 Pengyu Li , Lingling Zhang , Zhitao Gao , Yanrui Wu , Yuxuan Dong , Huan Liu , Bifan Wei , Jun Liu

Training Large Language Models (LLMs) typically involves a two-stage pipeline at the output layer: hidden states are projected into vocabulary logits via a linear transformation (lm_head), followed by cross-entropy loss computation against…

Machine Learning · Computer Science 2025-11-25 Jianbing Dong , Jianbin Chang

Large language models (LLMs) solve problems more accurately and interpretably when instructed to work out the answer step by step using a ``chain-of-thought'' (CoT) prompt. One can also improve LLMs' performance on a specific task by…

Learning robust feature representation from large-scale noisy faces stands out as one of the key challenges in high-performance face recognition. Recent attempts have been made to cope with this challenge by alleviating the intra-class…

Computer Vision and Pattern Recognition · Computer Science 2022-08-10 Bingqi Ma , Guanglu Song , Boxiao Liu , Yu Liu

The problem of interest here is the study of brain functional and effective connectivity based on non-invasive EEG-MEG inverse solution time series. These signals generally have low spatial resolution, such that an estimated signal at any…

Iterative learning control (ILC) is a control strategy for repetitive tasks wherein information from previous runs is leveraged to improve future performance. Optimization-based ILC (OB-ILC) is a powerful design framework for constrained…

Systems and Control · Electrical Eng. & Systems 2022-05-27 Dominic Liao-McPherson , Efe C. Balta , Alisa Rupenyan , John Lygeros