English
Related papers

Related papers: Efficient Pre-Training with Token Superposition

200 papers

Early action prediction seeks to anticipate an action before it fully unfolds, but limited visual evidence makes this task especially challenging. We introduce EAST, a simple and efficient framework that enables a model to reason about…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Iva Sović , Ivan Martinović , Marin Oršić

Soft prompt tuning techniques have recently gained traction as an effective strategy for the parameter-efficient tuning of pretrained language models, particularly minimizing the required adjustment of model parameters. Despite their…

Computation and Language · Computer Science 2024-06-11 MohammadAli SadraeiJavaeri , Ehsaneddin Asgari , Alice Carolyn McHardy , Hamid Reza Rabiee

Self-supervised methods have achieved remarkable success in transfer learning, often achieving the same or better accuracy than supervised pre-training. Most prior work has done so by increasing pre-training computation by adding complex…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Skanda Koppula , Yazhe Li , Evan Shelhamer , Andrew Jaegle , Nikhil Parthasarathy , Relja Arandjelovic , João Carreira , Olivier Hénaff

Although LLMs have demonstrated improved performance by scaling parallel test-time compute, doing so relies on generating reasoning paths that are both diverse and accurate. For challenging problems, the forking tokens that trigger diverse…

Computation and Language · Computer Science 2026-03-03 Sheng Jia , Xiao Wang , Shiva Prasad Kasiviswanathan

The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Jingfeng Yao , Yuda Song , Yucong Zhou , Xinggang Wang

Language models significantly benefit from context tokens, such as prompts or scratchpads. They perform better when prompted with informative instructions, and they acquire new reasoning capabilities by generating a scratch-pad before…

Computation and Language · Computer Science 2022-10-03 Charlie Snell , Dan Klein , Ruiqi Zhong

Recent advances in one-shot semi-supervised learning have lowered the barrier for deep learning of new applications. However, the state-of-the-art for semi-supervised learning is slow to train and the performance is sensitive to the choices…

Machine Learning · Computer Science 2020-12-07 Helena E. Liu , Leslie N. Smith

Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet representative subset of training data from the larger pool, such that…

Computation and Language · Computer Science 2024-12-10 Tingyu Xia , Bowen Yu , Kai Dang , An Yang , Yuan Wu , Yuan Tian , Yi Chang , Junyang Lin

In recent years, attention-based models have excelled across various domains but remain vulnerable to backdoor attacks, often from downloading or fine-tuning on poisoned datasets. Many current methods to mitigate backdoors in NLP models…

Cryptography and Security · Computer Science 2025-01-07 Yidong Ding , Jiafei Niu , Ping Yi

We propose a novel scheme to use the Levenshtein Transformer to perform the task of word-level quality estimation. A Levenshtein Transformer is a natural fit for this task: trained to perform decoding in an iterative manner, a Levenshtein…

Computation and Language · Computer Science 2021-09-17 Shuoyang Ding , Marcin Junczys-Dowmunt , Matt Post , Philipp Koehn

Deep learning is experiencing a rise in large-scale models. Training large-scale models is costly, prompting researchers to train large-scale models on commodity servers that more researchers can access. The massive number of parameters…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-01 Shengwei Li , Zhiquan Lai , Dongsheng Li , Yanqi Hao , Weijie Liu , Keshi Ge , Xiaoge Deng , Kai Lu

Current approaches to reducing undesired capabilities in language models are largely post hoc, and can thus be easily bypassed by adversaries. A natural alternative is to shape capabilities during pretraining itself. On the proxy task of…

Machine Learning · Computer Science 2026-02-03 Neil Rathi , Alec Radford

Pre-trained language models, such as BERT, have achieved significant accuracy gain in many natural language processing tasks. Despite its effectiveness, the huge number of parameters makes training a BERT model computationally very…

Computation and Language · Computer Science 2020-11-30 Cheng Yang , Shengnan Wang , Chao Yang , Yuechuan Li , Ru He , Jingqiao Zhang

We present a simple approach to improve direct speech-to-text translation (ST) when the source language is low-resource: we pre-train the model on a high-resource automatic speech recognition (ASR) task, and then fine-tune its parameters…

Computation and Language · Computer Science 2019-03-01 Sameer Bansal , Herman Kamper , Karen Livescu , Adam Lopez , Sharon Goldwater

Real-world applications are stretching context windows to hundreds of thousand of tokens while Large Language Models (LLMs) swell from billions to trillions of parameters. This dual expansion send compute and memory costs skyrocketing,…

Computation and Language · Computer Science 2025-12-12 Ling Xing , Alex Jinpeng Wang , Rui Yan , Xiangbo Shu , Jinhui Tang

Prompting has recently been shown as a promising approach for applying pre-trained language models to perform downstream tasks. We present Multi-Stage Prompting (MSP), a simple and automatic approach for leveraging pre-trained language…

Computation and Language · Computer Science 2022-03-18 Zhixing Tan , Xiangwen Zhang , Shuo Wang , Yang Liu

Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on hand-engineered prompts, recent works learn prompts using the…

Computer Vision and Pattern Recognition · Computer Science 2022-09-16 Manli Shu , Weili Nie , De-An Huang , Zhiding Yu , Tom Goldstein , Anima Anandkumar , Chaowei Xiao

We study continued training and supervised fine-tuning (SFT) of a language model (LM) to make effective use of long-context information. We first establish a reliable evaluation protocol to guide model development -- instead of perplexity…

Computation and Language · Computer Science 2025-12-04 Tianyu Gao , Alexander Wettig , Howard Yen , Danqi Chen

We introduce TwIST, a distributed training framework for efficient large language model (LLM) sparsification. TwIST trains multiple subnetworks in parallel, periodically aggregates their parameters, and resamples new subnetworks during…

Machine Learning · Computer Science 2025-11-07 Michael Menezes , Barbara Su , Xinze Feng , Yehya Farhat , Hamza Shili , Anastasios Kyrillidis

Recent advancements in language models (LMs) have marked a shift toward the growing importance of post-training. Yet, post-training approaches such as supervised fine-tuning (SFT) do not guarantee the effective use of knowledge acquired…

Computation and Language · Computer Science 2025-10-30 Chunyuan Deng , Ruidi Chang , Hanjie Chen