English
Related papers

Related papers: Entropy-Guided Token Dropout: Training Autoregress…

200 papers

Large language model (LLM) tokenizers act as structured compressors: by mapping text to discrete token sequences, they determine token count (and thus compute and context usage) and the statistical structure seen by downstream models.…

Information Theory · Computer Science 2026-01-15 Mete Erdogan , Abhiram Gorle , Shubham Chandak , Mert Pilanci , Tsachy Weissman

Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM reliability. While prior entropy-based attacks maximize…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Mengqi He , Xinyu Tian , Xin Shen , Jinhong Ni , Shu Zou , Zhaoyuan Yang , Jing Zhang

Asynchronous learning protocols have regained attention lately, especially in the Federated Learning (FL) setup, where slower clients can severely impede the learning process. Herein, we propose \texttt{AsyncDrop}, a novel asynchronous FL…

Machine Learning · Computer Science 2022-10-31 Chen Dun , Mirian Hipolito , Chris Jermaine , Dimitrios Dimitriadis , Anastasios Kyrillidis

We trained 13,440 large language models and found that entropy minimization requires only a single unlabeled data and 10 steps optimization to achieve performance improvements comparable to or even greater than those obtained using…

Computation and Language · Computer Science 2025-08-22 Zitian Gao , Lynx Chen , Haoming Luo , Joey Zhou , Bryan Dai

To train robust deep neural networks (DNNs), we systematically study several target modification approaches, which include output regularisation, self and non-self label correction (LC). Two key issues are discovered: (1) Self LC is the…

Machine Learning · Computer Science 2021-06-03 Xinshao Wang , Yang Hua , Elyor Kodirov , David A. Clifton , Neil M. Robertson

Recent advancements have shown that reinforcement learning (RL) can substantially improve the reasoning abilities of large language models (LLMs). The effectiveness of such RL training, however, depends critically on the exploration space…

Computation and Language · Computer Science 2026-03-17 Haoyuan Wu , Hai Wang , Jiajia Wu , Jinxiang Ou , Keyao Wang , Weile Chen , Zihao Zheng , Bei Yu

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards…

In structured prediction, the goal is to jointly predict many output variables that together encode a structured object -- a path in a graph, an entity-relation triple, or an ordering of objects. Such a large output space makes learning…

Machine Learning · Computer Science 2022-01-28 Kareem Ahmed , Eric Wang , Kai-Wei Chang , Guy Van den Broeck

Dynamic retrieval-augmented generation (RAG) allows large language models (LLMs) to fetch external knowledge on demand, offering greater adaptability than static RAG. A central challenge in this setting lies in determining the optimal…

Computation and Language · Computer Science 2025-11-14 Bo Li , Tian Tian , Zhenghua Xu , Hao Cheng , Shikun Zhang , Wei Ye

This paper aims to establish an entropy-regularized value-based reinforcement learning method that can ensure the monotonic improvement of policies at each policy update. Unlike previously proposed lower-bounds on policy improvement in…

Machine Learning · Computer Science 2020-08-26 Lingwei Zhu , Takamitsu Matsubara

Neural language models often struggle with low-resource languages due to the limited availability of training data, making tokens from these languages rare in the training set. This paper addresses a specific challenge during training: rare…

Computation and Language · Computer Science 2026-02-02 Galim Turumtaev

Recent advances in large language models (LLMs) have demonstrated significant potential in hardware design automation, particularly in using natural language to synthesize Register-Transfer Level (RTL) code. Despite this progress, a gap…

Machine Learning · Computer Science 2026-02-26 Jiahe Shi , Zhengqi Gao , Ching-Yun Ko , Duane Boning

Acoustic Scene Classification (ASC) faces challenges in generalizing across recording devices, particularly when labeled data is limited. The DCASE 2024 Challenge Task 1 highlights this issue by requiring models to learn from small labeled…

Sound · Computer Science 2026-02-02 Peihong Zhang , Yuxuan Liu , Zhixin Li , Rui Sang , Yiqiang Cai , Yizhou Tan , Shengchen Li

Test-time reinforcement learning generates multiple candidate answers via repeated rollouts and performs online updates using pseudo-labels constructed by majority voting. To reduce overhead and improve exploration, prior work introduces…

Machine Learning · Computer Science 2026-05-28 Chu Zhao , Enneng Yang , Yuting Liu , Jianzhe Zhao , Guibing Guo

Despite rapid advancements, machine learning, particularly deep learning, is hindered by the need for large amounts of labeled data to learn meaningful patterns without overfitting and immense demands for computation and storage, which…

Machine Learning · Computer Science 2025-06-30 Xiaobo Zhao , Aaron Hurst , Panagiotis Karras , Daniel E. Lucani

The success of the machine learning field has reliably depended on training on large datasets. While effective, this trend comes at an extraordinary cost. This is due to two deeply intertwined factors: the size of models and the size of…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Shriram M Sathiyanarayanan , Xinyue Hao , Shihao Hou , Yang Lu , Laura Sevilla-Lara , Anurag Arnab , Shreyank N Gowda

Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second.…

Computation and Language · Computer Science 2025-09-03 Jialong Zuo , Guangyan Zhang , Minghui Fang , Shengpeng Ji , Xiaoqi Jiao , Jingyu Li , Yiwen Guo , Zhou Zhao

Current language models (LMs) use a fixed, static subword tokenizer. This default choice typically results in degraded efficiency and language capabilities, especially in languages other than English. To address this issue, we challenge the…

Computation and Language · Computer Science 2025-06-12 Darius Feher , Ivan Vulić , Benjamin Minixhofer

Pretrained language models have achieved remarkable success in natural language understanding. However, fine-tuning pretrained models on limited training data tends to overfit and thus diminish performance. This paper presents Bi-Drop, a…

Computation and Language · Computer Science 2023-10-24 Shoujie Tong , Heming Xia , Damai Dai , Runxin Xu , Tianyu Liu , Binghuai Lin , Yunbo Cao , Zhifang Sui

Training long-context language models to capture long-range dependencies requires specialized data construction. Current approaches, such as generic text concatenation or heuristic-based variants, frequently fail to guarantee genuine…

Computation and Language · Computer Science 2025-10-06 Junlong Jia , Ziyang Chen , Xing Wu , Chaochen Gao , Zijia Lin , Debing Zhang , Songlin Hu , Binghui Guo
‹ Prev 1 4 5 6 7 8 10 Next ›