English
Related papers

Related papers: Entropy-Based Adaptive Weighting for Self-Training

200 papers

Continual Instruction Tuning (CIT) is adopted to continually instruct Large Models to follow human intent data by data. It is observed that existing gradient update would heavily destroy the performance on previous datasets during CIT…

Machine Learning · Computer Science 2025-12-15 Jingyang Qiao , Zhizhong Zhang , Xin Tan , Yanyun Qu , Shouhong Ding , Yuan Xie

Chain-of-thought (CoT) reasoning improves large language model performance on complex tasks, but often produces excessively long and inefficient reasoning traces. Existing methods shorten CoTs using length penalties or global entropy…

Artificial Intelligence · Computer Science 2026-04-08 Xuan Xiong , Huan Liu , Li Gu , Zhixiang Chi , Yue Qiu , Yuanhao Yu , Yang Wang

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…

Evolution Strategies (ES) emerged as a scalable alternative to popular Reinforcement Learning (RL) techniques, providing an almost perfect speedup when distributed across hundreds of CPU cores thanks to a reduced communication overhead.…

Machine Learning · Statistics 2018-11-13 Víctor Campos , Xavier Giro-i-Nieto , Jordi Torres

Auto-encoding Variational Bayes (AEVB) is a powerful and general algorithm for fitting latent variable models (a promising direction for unsupervised learning), and is well-known for training the Variational Auto-Encoder (VAE). In this…

Machine Learning · Computer Science 2022-08-17 Yang Zhi-Han

Explainability of neural network prediction is essential to understand feature importance and gain interpretable insight into neural network performance. However, explanations of neural network outcomes are mostly limited to visualization,…

Machine Learning · Computer Science 2023-07-13 Arnab Neelim Mazumder , Niall Lyons , Ashutosh Pandey , Avik Santra , Tinoosh Mohsenin

Training on model-generated synthetic data is a promising approach for finetuning LLMs, but it remains unclear when it helps or hurts. In this paper, we investigate this question for math reasoning via an empirical study, followed by…

Machine Learning · Computer Science 2024-06-21 Amrith Setlur , Saurabh Garg , Xinyang Geng , Naman Garg , Virginia Smith , Aviral Kumar

Incremental learning aims to adapt to new sets of categories over time with minimal computational overhead. Prior work often addresses this task by training efficient task-specific adaptors that modify frozen layer weights or features to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Nazia Tasnim , Bryan A. Plummer

In this paper, we propose a stochastic optimization method that adaptively controls the sample size used in the computation of gradient approximations. Unlike other variance reduction techniques that either require additional storage or the…

Optimization and Control · Mathematics 2017-11-01 Raghu Bollapragada , Richard Byrd , Jorge Nocedal

Tool use extends large language models beyond parametric knowledge, but reliable execution requires balancing appropriate reasoning depth with strict structural validity. We approach this problem from a case-based perspective to present…

Artificial Intelligence · Computer Science 2026-05-15 Renning Pang , Tian Lan , Leyuan Liu , Piao Tong , Sheng Cao , Xiaosong Zhang

Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose \textit{Value Explicit Pretraining} (VEP), a method that learns generalizable representations…

Machine Learning · Computer Science 2026-05-04 Kiran Lekkala , Henghui Bao , Sumedh A. Sontakke , Erdem Biyik , Laurent Itti

Drawing on theoretical insights, we advocate an error-based thresholding (EBT) mechanism for learned ISTA (LISTA), which utilizes a function of the layer-wise reconstruction error to suggest a specific threshold for each observation in the…

Machine Learning · Computer Science 2023-12-20 Ziang Li , Kailun Wu , Yiwen Guo , Changshui Zhang

Despite the remarkable capabilities of large language models, current training paradigms inadvertently foster \textit{sycophancy}, i.e., the tendency of a model to agree with or reinforce user-provided information even when it's factually…

Artificial Intelligence · Computer Science 2025-09-23 Mohammad Beigi , Ying Shen , Parshin Shojaee , Qifan Wang , Zichao Wang , Chandan Reddy , Ming Jin , Lifu Huang

Adversarial training has been shown to be one of the most effective approaches to improve the robustness of deep neural networks. It is formalized as a min-max optimization over model weights and adversarial perturbations, where the weights…

Machine Learning · Computer Science 2022-03-14 Gaojie Jin , Xinping Yi , Wei Huang , Sven Schewe , Xiaowei Huang

This paper explores adaptive variance reduction methods for stochastic optimization based on the STORM technique. Existing adaptive extensions of STORM rely on strong assumptions like bounded gradients and bounded function values, or suffer…

Optimization and Control · Mathematics 2024-10-24 Wei Jiang , Sifan Yang , Yibo Wang , Lijun Zhang

Despite recent advancements in Machine Learning, many tasks still involve working in low-data regimes which can make solving natural language problems difficult. Recently, a number of text augmentation techniques have emerged in the field…

Computation and Language · Computer Science 2023-02-27 Congcong Wang , Gonzalo Fiz Pontiveros , Steven Derby , Tri Kurniawan Wijaya

The scaling of model and data sizes has reshaped the AI landscape, establishing finetuning pretrained models as the standard paradigm for solving downstream tasks. However, dominant finetuning methods typically rely on weight adaptation,…

Machine Learning · Computer Science 2026-01-16 Leyang Hu , Matteo Gamba , Randall Balestriero

As an adaptive, interpretable, robust, and accurate meta-algorithm for arbitrary differentiable loss functions, gradient tree boosting is one of the most popular machine learning techniques, though the computational expensiveness severely…

Machine Learning · Computer Science 2019-11-21 Daniel Chao Zhou , Zhongming Jin , Tong Zhang

Automated Essay Scoring (AES) has emerged to prominence in response to the growing demand for educational automation. Providing an objective and cost-effective solution, AES standardises the assessment of extended responses. Although…

Computers and Society · Computer Science 2025-12-15 Abhirup Chakravarty

Many problems in astrophysics cover multiple orders of magnitude in spatial and temporal scales. While simulating systems that experience rapid changes in these conditions, it is essential to adapt the (time-) step size to capture the…

Instrumentation and Methods for Astrophysics · Physics 2025-02-19 Veronica Saz Ulibarrena , Simon Portegies Zwart