English
Related papers

Related papers: Suppressing Final Layer Hidden State Jumps in Tran…

200 papers

Conventional anti-jamming method mostly rely on frequency hopping to hide or escape from jammer. These approaches are not efficient in terms of bandwidth usage and can also result in a high probability of jamming. Different from existing…

Machine Learning · Computer Science 2021-03-29 Ali Pourranjbar , Georges Kaddoum , Aidin Ferdowsi , Walid Saad

We study how information propagates in decoder-only Transformers, which are the architectural backbone of most existing frontier large language models (LLMs). We rely on a theoretical signal propagation analysis -- specifically, we analyse…

The use of low-rank adaptation (LoRA) with frozen pretrained language models (PLMs) has become increasing popular as a mainstream, resource-efficient modeling approach for memory-constrained hardware. In this study, we first explore how to…

Transformers have the capacity to act as supervised learning algorithms: by properly encoding a set of labeled training ("in-context") examples and an unlabeled test example into an input sequence of vectors of the same dimension, the…

Machine Learning · Computer Science 2024-12-16 Spencer Frei , Gal Vardi

Recent research has demonstrated that transformers, particularly linear attention models, implicitly execute gradient-descent-like algorithms on data provided in-context during their forward inference step. However, their capability in…

Machine Learning · Computer Science 2024-10-31 Max Vladymyrov , Johannes von Oswald , Mark Sandler , Rong Ge

Although transformer-based models have shown exceptional empirical performance, the fundamental principles governing their training dynamics are inadequately characterized beyond configuration-specific studies. Inspired by empirical…

Machine Learning · Computer Science 2025-10-09 Zheng-An Chen , Tao Luo

Large language models (LLMs), despite their powerful capabilities, suffer from factual hallucinations where they generate verifiable falsehoods. We identify a root of this issue: the imbalanced data distribution in the pretraining corpus,…

Computation and Language · Computer Science 2026-02-03 Langming Liu , Kangtao Lv , Haibin Chen , Weidong Zhang , Yejing Wang , Shilei Liu , Xin Tong , Yujin Yuan , Yongwei Wang , Wenbo Su , Bo Zheng

Fine-tuned transformer models have shown superior performances in many natural language tasks. However, the large model size prohibits deploying high-performance transformer models on resource-constrained devices. This paper proposes a…

Computation and Language · Computer Science 2024-10-01 Zi Yang , Samridhi Choudhary , Siegfried Kunzmann , Zheng Zhang

Recent work in continual learning has highlighted the beneficial effect of resampling weights in the last layer of a neural network (``zapping"). Although empirical results demonstrate the effectiveness of this approach, the underlying…

Machine Learning · Computer Science 2025-07-03 Lapo Frati , Neil Traft , Jeff Clune , Nick Cheney

Practitioners have consistently observed three puzzling phenomena in transformer-based large language models (LLMs): attention sinks, value-state drains, and residual-state peaks, collectively referred to as extreme-token phenomena. These…

Machine Learning · Computer Science 2024-11-08 Tianyu Guo , Druv Pai , Yu Bai , Jiantao Jiao , Michael I. Jordan , Song Mei

Differentially Private (DP) learning has seen limited success for building large deep learning models of text, and straightforward attempts at applying Differentially Private Stochastic Gradient Descent (DP-SGD) to NLP tasks have resulted…

Machine Learning · Computer Science 2022-11-11 Xuechen Li , Florian Tramèr , Percy Liang , Tatsunori Hashimoto

Recently, large language models (LLMs) have advanced recommendation systems (RSs), and recent works have begun to explore how to integrate LLMs into industrial RSs. While most approaches deploy LLMs offline to generate and pre-cache…

Information Retrieval · Computer Science 2026-04-22 Yunjia Xi , Menghui Zhu , Jianghao Lin , Bo Chen , Ruiming Tang , Yong Yu , Weinan Zhang

Low-rank optimization has emerged as a promising approach to enabling memory-efficient training of large language models (LLMs). Existing low-rank optimization methods typically project gradients onto a low-rank subspace, reducing the…

Machine Learning · Computer Science 2025-12-15 Haochen Zhang , Junze Yin , Guanchu Wang , Zirui Liu , Lin F. Yang , Tianyi Zhang , Anshumali Shrivastava , Vladimir Braverman

Several recent works demonstrate that transformers can implement algorithms like gradient descent. By a careful construction of weights, these works show that multiple layers of transformers are expressive enough to simulate iterations of…

Machine Learning · Computer Science 2023-11-13 Kwangjun Ahn , Xiang Cheng , Hadi Daneshmand , Suvrit Sra

We present a new paradigm for fine-tuning large-scale visionlanguage pre-trained models on downstream task, dubbed Prompt Regularization (ProReg). Different from traditional fine-tuning which easily overfits to the downstream task data,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Beier Zhu , Yulei Niu , Saeil Lee , Minhoe Hur , Hanwang Zhang

Training deep neural networks for classification often includes minimizing the training loss beyond the zero training error point. In this phase of training, a "neural collapse" behavior has been observed: the variability of features…

Machine Learning · Computer Science 2023-05-30 Tom Tirer , Haoxiang Huang , Jonathan Niles-Weed

Recent developments in Transformers have opened new interesting areas of research in partially observable reinforcement learning tasks. Results from late 2019 showed that Transformers are able to outperform LSTMs on both memory intense and…

Machine Learning · Computer Science 2020-04-09 Shakti Kumar , Jerrod Parker , Panteha Naderian

Analyzing the similarity of internal representations has been an important technique for understanding the behavior of deep neural networks. Most existing methods for analyzing the similarity between representations of high dimensions, such…

Artificial Intelligence · Computer Science 2025-05-26 Jiachen Jiang , Jinxin Zhou , Zhihui Zhu

Pre-trained large language models (LLMs) exhibit impressive mathematical reasoning capabilities, yet how they compute basic arithmetic, such as addition, remains unclear. This paper shows that pre-trained LLMs add numbers using Fourier…

Machine Learning · Computer Science 2024-06-06 Tianyi Zhou , Deqing Fu , Vatsal Sharan , Robin Jia

End-to-end spoken language understanding (SLU) systems benefit from pretraining on large corpora, followed by fine-tuning on application-specific data. The resulting models are too large for on-edge applications. For instance, BERT-based…

Computation and Language · Computer Science 2022-06-30 Pu Wang , Hugo Van hamme