English
Related papers

Related papers: Closed-Loop Transformers: Autoregressive Modeling …

200 papers

Systems for knowledge-intensive tasks such as open-domain question answering (QA) usually consist of two stages: efficient retrieval of relevant documents from a large corpus and detailed reading of the selected documents to generate…

Computation and Language · Computer Science 2022-12-06 Zhengbao Jiang , Luyu Gao , Jun Araki , Haibo Ding , Zhiruo Wang , Jamie Callan , Graham Neubig

Reasoning is a key component of language understanding in Large Language Models. While Chain-of-Thought prompting enhances performance via explicit intermediate steps, it suffers from sufficient token overhead and a fixed reasoning…

Computation and Language · Computer Science 2025-11-18 Xinyuan Wang , Dongjie Wang , Wangyang Ying , Haoyue Bai , Nanxu Gong , Sixun Dong , Kunpeng Liu , Yanjie Fu

In Large Language Model (LLM) inference, early-exit refers to stopping computation at an intermediate layer once the prediction is sufficiently confident, thereby reducing latency and cost. However, recent LLMs adopt improved pretraining…

Computation and Language · Computer Science 2026-03-26 Rui Wei , Rui Du , Hanfei Yu , Devesh Tiwari , Jian Li , Zhaozhuo Xu , Hao Wang

We develop an input delay-compensating feedback law for linear switched systems with time-dependent switching. Because the future values of the switching signal, which are needed for constructing an exact predictor-feedback law, may be…

Systems and Control · Electrical Eng. & Systems 2025-03-19 Andreas Katsanikakis , Nikolaos Bekiaris-Liberis , Delphine Bresch-Pietri

Conventional deep models predict a test sample with a single forward propagation, which, however, may not be sufficient for predicting hard-classified samples. On the contrary, we human beings may need to carefully check the sample many…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Shuaicheng Niu , Jiaxiang Wu , Yifan Zhang , Guanghui Xu , Haokun Li , Peilin Zhao , Junzhou Huang , Yaowei Wang , Mingkui Tan

Equilibrium Propagation (EP) is a biologically inspired learning algorithm for convergent recurrent neural networks, i.e. RNNs that are fed by a static input x and settle to a steady state. Training convergent RNNs consists in adjusting the…

Machine Learning · Computer Science 2019-06-03 Maxence Ernoult , Julie Grollier , Damien Querlioz , Yoshua Bengio , Benjamin Scellier

While looped transformers (termed as Looped-Attn) often outperform standard transformers (termed as Single-Attn) on complex reasoning tasks, the mechanism for this advantage remains underexplored. In this paper, we explain this phenomenon…

Machine Learning · Computer Science 2026-01-07 Zixuan Gong , Yong Liu , Jiaye Teng

Recently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence hinders its further improvement…

Computation and Language · Computer Science 2019-04-08 Jie Hao , Xing Wang , Baosong Yang , Longyue Wang , Jinfeng Zhang , Zhaopeng Tu

Chain of Thought (CoT) prompting has been shown to significantly improve the performance of large language models (LLMs), particularly in arithmetic and reasoning tasks, by instructing the model to produce intermediate reasoning steps.…

Machine Learning · Computer Science 2025-03-03 Jianhao Huang , Zixuan Wang , Jason D. Lee

Large Language Models (LLMs) are trained with next-token prediction, implemented in autoregressive Transformers via causal masking for parallelism. This creates a subtle misalignment: residual connections tie activations to the current…

Computation and Language · Computer Science 2026-03-03 Jonathan Lys , Vincent Gripon , Bastien Pasdeloup , Axel Marmoret , Lukas Mauch , Fabien Cardinaux , Ghouthi Boukli Hacene

Deep equilibrium models (DEQs) have proven to be very powerful for learning data representations. The idea is to replace traditional (explicit) feedforward neural networks with an implicit fixed-point equation, which allows to decouple the…

Machine Learning · Computer Science 2023-04-25 Bac Nguyen , Lukas Mauch

Neural NLP models are often miscalibrated and overconfident, assigning high confidence to incorrect predictions and failing to express uncertainty during internal evidence aggregation. This undermines selective prediction and high-stakes…

Artificial Intelligence · Computer Science 2026-03-11 Elias Hossain , Shubhashis Roy Dipta , Subash Neupane , Rajib Rana , Ravid Shwartz-Ziv , Ivan Garibay , Niloofar Yousefi

In a real life process evolving over time, the relationship between its relevant variables may change. Therefore, it is advantageous to have different inference models for each state of the process. Asymmetric hidden Markov models fulfil…

Machine Learning · Computer Science 2023-05-16 Carlos Puerto-Santana , Pedro Larrañaga , Concha Bielza

Latent Chain-of-Thought (Latent CoT) models promise efficient reasoning via continuous representations, yet exhibit puzzling performance inconsistencies: excelling at exploration (ProsQA: 97.0%) but failing at computation (GSM8K: 34.1%). We…

Artificial Intelligence · Computer Science 2026-02-03 Jiaxuan Zou , Yaozhong Xiong , Yong Liu

Autoregressive (AR) models remain the standard for natural language generation but still suffer from high latency due to strictly sequential decoding. Recent diffusion-inspired approaches, such as LlaDA and Dream, mitigate this by…

Computation and Language · Computer Science 2025-10-16 Qinglin Zhu , Yizhen Yao , Runcong Zhao , Yanzheng Xiang , Amrutha Saseendran , Chen Jin , Philip Teare , Bin Liang , Yulan He , Lin Gui

Early-exiting neural networks enable adaptive inference by allowing inputs to exit at intermediate classifiers, reducing computation for easy samples while maintaining high accuracy. In practice, exits can be trained sequentially by…

Machine Learning · Computer Science 2026-05-08 Alaa Zniber , Ouassim Karrakchou , Mounir Ghogho

The Transformer architecture excels in a variety of language modeling tasks, outperforming traditional neural architectures such as RNN and LSTM. This is partially due to its elimination of recurrent connections, which allows for parallel…

Computation and Language · Computer Science 2024-09-24 Xiang Zhang , Muhammad Abdul-Mageed , Laks V. S. Lakshmanan

We propose an approach for improving sequence modeling based on autoregressive normalizing flows. Each autoregressive transform, acting across time, serves as a moving frame of reference, removing temporal correlations, and simplifying the…

Machine Learning · Computer Science 2022-03-09 Joseph Marino , Lei Chen , Jiawei He , Stephan Mandt

Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens. Consequently, they lack an inherent incentive to compress history into compact latent states with…

Self-referential learning -- training a model on data it generated itself -- promises boundless scalability but chronically suffers from model collapse: language models degenerate into repetitive text, GANs drop modes, and…

Machine Learning · Computer Science 2025-12-18 Jingwei Chen