English
Related papers

Related papers: Future Lens: Anticipating Subsequent Tokens from a…

200 papers

Deeply learned representations are the state-of-the-art descriptors for face recognition methods. These representations encode latent features that are difficult to explain, compromising the confidence and interpretability of their…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Matheus Alves Diniz , William Robson Schwartz

We seek to understand how the representations of individual tokens and the structure of the learned feature space evolve between layers in deep neural networks under different learning objectives. We focus on the Transformers for our…

Computation and Language · Computer Science 2019-09-05 Elena Voita , Rico Sennrich , Ivan Titov

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

Proactive and agentic control in Sixth-Generation (6G) Open Radio Access Networks (O-RAN) requires control-grade prediction under stringent Near-Real-Time (Near-RT) latency and computational constraints. While Transformer-based models are…

Networking and Internet Architecture · Computer Science 2026-01-27 Farhad Rezazadeh , Hatim Chergui , Mehdi Bennis , Houbing Song , Lingjia Liu , Dusit Niyato , Merouane Debbah

We propose Next Concept Prediction (NCP), a generative pretraining paradigm built on top of Next Token Prediction (NTP). NCP predicts discrete concepts that span multiple tokens, thereby forming a more challenging pretraining objective. Our…

Computation and Language · Computer Science 2026-02-10 Yuliang Liu , Yunchong Song , Yixuan Wang , Kewen Ge , Alex Lamb , Qipeng Guo , Kai Chen , Bowen Zhou , Zhouhan Lin

We uncover a latent capacity for introspection in a Qwen 32B model, demonstrating that the model can detect when concepts have been injected into its earlier context and identify which concept was injected. While the model denies injection…

Artificial Intelligence · Computer Science 2026-02-27 Theia Pearson-Vogel , Martin Vanek , Raymond Douglas , Jan Kulveit

Large transformer models are known to produce high-norm tokens. In vision transformers (ViTs), such tokens have been mathematically modeled through the singular vectors of the linear approximations of layers. However, in large language…

Computation and Language · Computer Science 2025-07-01 Haoqi Wang , Tong Zhang , Mathieu Salzmann

Forecasting tasks using large datasets gathering thousands of heterogeneous time series is a crucial statistical problem in numerous sectors. The main challenge is to model a rich variety of time series, leverage any available external…

Machine Learning · Computer Science 2024-04-18 Etienne David , Jean Bellot , Sylvain Le Corff

With the attention mechanism, transformers achieve significant empirical successes. Despite the intuitive understanding that transformers perform relational inference over long sequences to produce desirable representations, we lack a…

Machine Learning · Computer Science 2024-04-02 Yufeng Zhang , Boyi Liu , Qi Cai , Lingxiao Wang , Zhaoran Wang

Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that the information needed to…

Computation and Language · Computer Science 2022-05-12 Nishant Subramani , Nivedita Suresh , Matthew E. Peters

Speculative decoding has emerged as a pivotal technique to accelerate LLM inference by employing a lightweight draft model to generate candidate tokens that are subsequently verified by the target model in parallel. However, while this…

Computation and Language · Computer Science 2026-02-26 Yuetao Chen , Xuliang Wang , Xinzhou Zheng , Ming Li , Peng Wang , Hong Xu

Deep latent variable models have achieved significant empirical successes in model-based reinforcement learning (RL) due to their expressiveness in modeling complex transition dynamics. On the other hand, it remains unclear theoretically…

Machine Learning · Computer Science 2023-03-08 Tongzheng Ren , Chenjun Xiao , Tianjun Zhang , Na Li , Zhaoran Wang , Sujay Sanghavi , Dale Schuurmans , Bo Dai

Learning good representations of historical contexts is one of the core challenges of reinforcement learning (RL) in partially observable environments. While self-predictive auxiliary tasks have been shown to improve performance in fully…

Machine Learning · Computer Science 2025-03-11 Jeongyeol Kwon , Liu Yang , Robert Nowak , Josiah Hanna

Autoregressive language models (LMs) generate one token at a time, yet human reasoning operates over higher-level abstractions - sentences, propositions, and concepts. This contrast raises a central question- Can LMs likewise learn to…

Computation and Language · Computer Science 2025-10-14 Hyeonbin Hwang , Byeongguk Jeon , Seungone Kim , Jiyeon Kim , Hoyeon Chang , Sohee Yang , Seungpil Won , Dohaeng Lee , Youbin Ahn , Minjoon Seo

Autoregressive decoding in language models is inherently slow, generating only one token per forward pass. We propose Parallel Token Prediction (PTP), a general-purpose framework for predicting multiple tokens in a single model call. PTP…

Computation and Language · Computer Science 2026-03-06 Felix Draxler , Justus Will , Farrin Marouf Sofian , Theofanis Karaletsos , Sameer Singh , Stephan Mandt

Transformer has been widely used for self-supervised pre-training in Natural Language Processing (NLP) and achieved great success. However, it has not been fully explored in visual self-supervised learning. Meanwhile, previous methods only…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Zhaowen Li , Zhiyang Chen , Fan Yang , Wei Li , Yousong Zhu , Chaoyang Zhao , Rui Deng , Liwei Wu , Rui Zhao , Ming Tang , Jinqiao Wang

Decoder-only transformers have become the standard architecture for large language models (LLMs) due to their strong performance. Recent studies suggest that, in pre-trained LLMs, early, middle, and late layers may serve distinct roles:…

Computation and Language · Computer Science 2025-10-15 Xuan Luo , Weizhi Wang , Xifeng Yan

Next-token prediction (NTP) has driven the success of large language models (LLMs), but it struggles with long-horizon reasoning, planning, and creative writing, with these limitations largely attributed to teacher-forced training.…

Predicting the future is a fantasy but practicality work. It is the key component to intelligent agents, such as self-driving vehicles, medical monitoring devices and robotics. In this work, we consider generating unseen future frames from…

Computer Vision and Pattern Recognition · Computer Science 2019-01-08 Guohao Ying , Yingtian Zou , Lin Wan , Yiming Hu , Jiashi Feng

In textual information extraction and other sequence labeling tasks it is now common to use recurrent neural networks (such as LSTM) to form rich embedded representations of long-term input co-occurrence patterns. Representation of output…

Computation and Language · Computer Science 2017-08-03 Dung Thai , Shikhar Murty , Trapit Bansal , Luke Vilnis , David Belanger , Andrew McCallum
‹ Prev 1 4 5 6 7 8 10 Next ›