English
Related papers

Related papers: Transformers Struggle to Learn to Search

200 papers

The pretrain-transfer paradigm, which underpins the success of large language models (LLMs), has demonstrated the immense power of creating foundation models that learn generalizable representations from vast datasets. However, extending…

Machine Learning · Computer Science 2025-09-30 Yunhao Liang , Pujun Zhang , Yuan Qu , Shaochong Lin , Zuo-jun Max Shen

Transformers have demonstrated exceptional in-context learning capabilities, yet the theoretical understanding of the underlying mechanisms remains limited. A recent work (Elhage et al., 2021) identified a ``rich'' in-context mechanism…

Machine Learning · Computer Science 2025-01-30 Mingze Wang , Ruoxi Yu , Weinan E , Lei Wu

Transformers have theoretical limitations in modeling certain sequence-to-sequence tasks, yet it remains largely unclear if these limitations play a role in large-scale pretrained LLMs, or whether LLMs might effectively overcome these…

Machine Learning · Computer Science 2025-10-24 Mayank Jobanputra , Yana Veitsman , Yash Sarrof , Aleksandra Bakalova , Vera Demberg , Ellie Pavlick , Michael Hahn

Graph learning has become essential in various domains, including recommendation systems and social network analysis. Graph Neural Networks (GNNs) have emerged as promising techniques for encoding structural information and improving…

Machine Learning · Computer Science 2024-10-10 Lianghao Xia , Ben Kao , Chao Huang

Using Large Language Models (LLMs) to process graph-structured data is an active research area, yet current state-of-the-art approaches typically rely on multi-step pipelines with Graph Neural Network (GNN) encoders that compress rich…

Machine Learning · Computer Science 2026-05-12 Dario Vajda

Transformers serve as the foundational architecture for large language and video generation models, such as GPT, BERT, SORA and their successors. Empirical studies have demonstrated that real-world data and learning tasks exhibit…

Machine Learning · Computer Science 2026-05-19 Zhaiming Shen , Alex Havrilla , Rongjie Lai , Alexander Cloninger , Wenjing Liao

We show that a constant number of self-attention layers can efficiently simulate, and be simulated by, a constant number of communication rounds of Massively Parallel Computation. As a consequence, we show that logarithmic depth is…

Machine Learning · Computer Science 2024-02-15 Clayton Sanford , Daniel Hsu , Matus Telgarsky

The Transformer architecture has become a dominant choice in many domains, such as natural language processing and computer vision. Yet, it has not achieved competitive performance on popular leaderboards of graph-level prediction compared…

Machine Learning · Computer Science 2021-11-25 Chengxuan Ying , Tianle Cai , Shengjie Luo , Shuxin Zheng , Guolin Ke , Di He , Yanming Shen , Tie-Yan Liu

Transformer networks are the de facto standard architecture in natural language processing. To date, there are no theoretical analyses of the Transformer's ability to capture tree structures. We focus on the ability of Transformer networks…

Computation and Language · Computer Science 2021-12-23 Qi He , João Sedoc , Jordan Rodu

The transformer architecture has shown remarkable success in various domains, such as natural language processing and computer vision. When it comes to graph learning, transformers are required not only to capture the interactions between…

Machine Learning · Computer Science 2024-01-30 Van Thuy Hoang , O-Joun Lee

Long-context modeling presents a significant challenge for transformer-based large language models (LLMs) due to the quadratic complexity of the self-attention mechanism and issues with length extrapolation caused by pretraining exclusively…

Computation and Language · Computer Science 2024-05-24 Chenghao Yang , Zi Yang , Nan Hua

Neural networks gain capabilities during training, but the internal changes that precede capability acquisition are not well understood. In particular, the relationship between geometric change and behavioral change, and the effect of task…

Machine Learning · Computer Science 2026-04-03 Jayadev Billa

In the pursuit of reducing the number of trainable parameters in deep transformer networks, we employ Reinforcement Learning to dynamically select layers during training and tie them together. Every few iterations, the RL agent is asked…

Machine Learning · Computer Science 2024-01-24 Tamir David Hay , Lior Wolf

Recently, pure transformer-based models have shown great potentials for vision tasks such as image classification and detection. However, the design of transformer networks is challenging. It has been observed that the depth, embedding…

Computer Vision and Pattern Recognition · Computer Science 2021-07-02 Minghao Chen , Houwen Peng , Jianlong Fu , Haibin Ling

In recent years, large language models (LLMs) have emerged as promising candidates for graph tasks. Many studies leverage natural language to describe graphs and apply LLMs for reasoning, yet most focus narrowly on performance benchmarks…

Machine Learning · Computer Science 2026-01-28 Yuxiang Wang , Xinnan Dai , Wenqi Fan , Yao Ma

Transformers demonstrate significant advantages as the building block of modern LLMs. In this work, we study the capacities of Transformers in performing unsupervised learning. We show that multi-layered Transformers, given a sufficiently…

Machine Learning · Statistics 2025-01-14 Yihan He , Yuan Cao , Hong-Yu Chen , Dennis Wu , Jianqing Fan , Han Liu

Large language models exhibit surprising emergent generalization properties, yet also struggle on many simple reasoning tasks such as arithmetic and parity. This raises the question of if and when Transformer models can learn the true…

Machine Learning · Computer Science 2023-10-25 Hattie Zhou , Arwen Bradley , Etai Littwin , Noam Razin , Omid Saremi , Josh Susskind , Samy Bengio , Preetum Nakkiran

In the last decade, the generalization and adaptation abilities of deep learning models were typically evaluated on fixed training and test distributions. Contrary to traditional deep learning, large language models (LLMs) are (i) even more…

Computation and Language · Computer Science 2024-10-17 Fırat Öncel , Matthias Bethge , Beyza Ermis , Mirco Ravanelli , Cem Subakan , Çağatay Yıldız

We argue that Transformers are essentially graph-to-graph models, with sequences just being a special case. Attention weights are functionally equivalent to graph edges. Our Graph-to-Graph Transformer architecture makes this ability…

Computation and Language · Computer Science 2023-10-30 James Henderson , Alireza Mohammadshahi , Andrei C. Coman , Lesly Miculicich

Finding relevant prior art is crucial when deciding whether to file a new patent application or invalidate an existing patent. However, searching for prior art is challenging due to the large number of patent documents and the need for…

Information Retrieval · Computer Science 2025-08-15 Krzysztof Daniell , Igor Buzhinsky , Sebastian Björkqvist
‹ Prev 1 3 4 5 6 7 10 Next ›