English
Related papers

Related papers: Exact Expressive Power of Transformers with Paddin…

200 papers

Recent advancements in cognitive science and multi-round reasoning techniques for Large Language Models (LLMs) suggest that iterative thinking processes improve problem-solving performance in complex tasks. Inspired by this, approaches like…

Artificial Intelligence · Computer Science 2025-03-06 Chenhui Xu , Dancheng Liu , Jiajie Li , Amir Nassereldine , Zhaohui Li , Jinjun Xiong

Transformers have impressive generalization capabilities on tasks with a fixed context length. However, they fail to generalize to sequences of arbitrary length, even for seemingly simple tasks such as duplicating a string. Moreover, simply…

Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermediate step must be generated as a discrete token. Latent reasoning reduces visible token…

Computation and Language · Computer Science 2026-05-11 Xuan Li , Yining Wang , Yuchen Liu , Guanjun Liu , Delai Qiu , Shengping Liu , Jiaen Liang , Wei Huang , Jun Yu , Junnan Zhu

Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly stemming from communication bottlenecks in attention…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-12-31 Zongwu Wang , Fangxin Liu , Mingshuai Li , Li Jiang

Continuous chain-of-thought has been shown to be effective in saving reasoning tokens for large language models. By reasoning with continuous latent thought tokens, continuous CoT is able to perform implicit reasoning in a compact manner.…

Computation and Language · Computer Science 2026-02-27 Haoyi Wu , Zhihao Teng , Kewei Tu

Chain of Thought (CoT) reasoning enhances language models' performance but often leads to inefficient "overthinking" on simple problems. We identify that existing approaches directly penalizing reasoning length fail to account for varying…

Computation and Language · Computer Science 2025-05-22 Junjie Yang , Ke Lin , Xing Yu

We propose an efficient approach to train large diffusion models with masked transformers. While masked transformers have been extensively explored for representation learning, their application to generative learning is less explored in…

Computer Vision and Pattern Recognition · Computer Science 2024-03-06 Hongkai Zheng , Weili Nie , Arash Vahdat , Anima Anandkumar

Large language models have demonstrated an impressive ability to perform factual recall. Prior work has found that transformers trained on factual recall tasks can store information at a rate proportional to their parameter count. In our…

Machine Learning · Computer Science 2024-12-10 Eshaan Nichani , Jason D. Lee , Alberto Bietti

Modern large language models generate text autoregressively, producing tokens one at a time. To study the learnability of such systems, Joshi et al. (COLT 2025) introduced a PAC-learning framework for next-token generators, the primitive…

Machine Learning · Computer Science 2026-04-21 Steve Hanneke , Idan Mehalel , Shay Moran

A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer…

Computation and Language · Computer Science 2024-02-07 Aydar Bulatov , Yuri Kuratov , Yermek Kapushev , Mikhail S. Burtsev

Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through…

Computation and Language · Computer Science 2025-10-06 Wenrui Bao , Zhiben Chen , Dan Xu , Yuzhang Shang

Chain-of-thought (CoT) is a method that enables language models to handle complex reasoning tasks by decomposing them into simpler steps. Despite its success, the underlying mechanics of CoT are not yet fully understood. In an attempt to…

Machine Learning · Computer Science 2023-11-09 Yingcong Li , Kartik Sreenivasan , Angeliki Giannou , Dimitris Papailiopoulos , Samet Oymak

Chain-of-Thought (CoT) reasoning is a critical capability for large language models (LLMs), enabling them to tackle com- plex multi-step tasks. While base LLMs, pre-trained on general text corpora, often struggle with reasoning due to a…

Computation and Language · Computer Science 2025-11-25 Zijian Wang , Yanxiang Ma , Chang Xu

Recently, inference-time scaling of chain-of-thought (CoT) has been demonstrated as a promising approach for addressing multi-modal reasoning tasks. While existing studies have predominantly centered on text-based thinking, the integration…

Computation and Language · Computer Science 2025-05-27 Yujie Lin , Ante Wang , Moye Chen , Jingyao Liu , Hao Liu , Jinsong Su , Xinyan Xiao

It has been observed that transformers with greater depth (that is, more layers) have more capabilities, but can we establish formally which capabilities are gained? We answer this question with a theoretical proof followed by an empirical…

Computation and Language · Computer Science 2026-01-21 Andy Yang , Michaël Cadilhac , David Chiang

The autoregressive nature of large language models (LLMs) fundamentally limits inference speed, as each forward pass generates only a single token and is often bottlenecked by memory bandwidth. Speculative decoding has emerged as a…

Machine Learning · Computer Science 2025-12-02 Zihao An , Huajun Bai , Ziqiong Liu , Dong Li , Emad Barsoum

Implicit models, an emerging model class, compute outputs by iterating a single parameter block to a fixed point. This architecture realizes an infinite-depth, weight-tied network that trains with constant memory, significantly reducing…

Machine Learning · Computer Science 2026-04-01 Jialin Liu , Lisang Ding , Stanley Osher , Wotao Yin

Although dominant in natural language processing, transformer-based models remain challenged by the task of long-sequence processing, because the computational cost of self-attention operations in transformers swells quadratically with the…

Computation and Language · Computer Science 2024-07-08 Jiawen Xie , Pengyu Cheng , Xiao Liang , Yong Dai , Nan Du

Chain-of-Thought (CoT) prompting has been widely recognized for its ability to enhance reasoning capabilities in large language models (LLMs). However, our study reveals a surprising contradiction to this prevailing perspective within the…

Computation and Language · Computer Science 2025-11-04 Tianshi Zheng , Yixiang Chen , Chengxi Li , Chunyang Li , Qing Zong , Haochen Shi , Baixuan Xu , Yangqiu Song , Ginny Y. Wong , Simon See

We develop a general mathematical framework to analyze scaling regimes and derive explicit analytic solutions for gradient flow (GF) in large learning problems. Our key innovation is a formal power series expansion of the loss evolution,…

Machine Learning · Computer Science 2026-02-05 Dmitry Yarotsky , Eugene Golikov , Yaroslav Gusev