English
Related papers

Related papers: Training-Free Looped Transformers

200 papers

Mixture of Experts (MoE) is able to scale up vision transformers effectively. However, it requires prohibiting computation resources to train a large MoE transformer. In this paper, we propose Residual Mixture of Experts (RMoE), an…

Computer Vision and Pattern Recognition · Computer Science 2022-10-05 Lemeng Wu , Mengchen Liu , Yinpeng Chen , Dongdong Chen , Xiyang Dai , Lu Yuan

Masked self-supervised vision transformers have become a dominant pretraining paradigm, yet their substantial model size poses significant challenges for resource-constrained deployment and efficient transfer learning. A fundamental…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Peihao Xiang , Kaida Wu , Ou Bai

Scaling transformers has led to significant breakthroughs in many domains, leading to a paradigm in which larger versions of existing models are trained and released on a periodic basis. New instances of such models are typically trained…

Scaling Transformer to a large scale without using some technical tricks such as learning rate warump and using an obviously lower learning rate is an extremely challenging task, and is increasingly gaining more attention. In this paper, we…

Machine Learning · Computer Science 2025-05-29 Xianbiao Qi , Yelin He , Jiaquan Ye , Chun-Guang Li , Bojia Zi , Xili Dai , Qin Zou , Rong Xiao

Frozen encoder--decoder language models are stateless: the latent representation is discarded after every forward pass, so no information persists across sessions. This paper presents a \textbf{proof-of-concept pilot study} showing that…

Machine Learning · Computer Science 2026-03-18 Hong Jeong

Large Multimodal Models (LMMs) have demonstrated impressive capabilities in visual-language tasks but face significant deployment challenges due to their high computational demands. While recent token reduction methods show promise for…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Bingxin Xu , Yuzhang Shang , Yunhao Ge , Qian Lou , Yan Yan

Scaling video diffusion transformers is fundamentally bottlenecked by two compounding costs: the expensive quadratic complexity of attention per step, and the iterative sampling steps. In this work, we propose EFlow, an efficient few-step…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Dogyun Park , Yanyu Li , Sergey Tulyakov , Anil Kag

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

The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive…

Machine Learning · Computer Science 2022-09-21 Timo Lohrenz , Björn Möller , Zhengyang Li , Tim Fingscheidt

Often, constraints arise in deployment settings where even lightweight parameter updates e.g. parameter-efficient fine-tuning could induce model shift or tuning instability. We study test-time adaptation of foundation models for few-shot…

Machine Learning · Statistics 2026-02-04 Tahir Qasim Syed , Behraj Khan

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…

Machine Learning · Computer Science 2020-02-19 Nikita Kitaev , Łukasz Kaiser , Anselm Levskaya

Yield Multi-Corner Analysis validates circuits across 25+ Process-Voltage-Temperature corners, resulting in a combinatorial simulation cost of $O(K \times N)$ where $K$ denotes corners and $N$ exceeds $10^4$ samples per corner. Existing…

Machine Learning · Computer Science 2026-03-16 Wei W. Xing , Kaiqi Huang , Jiazhan Liu , Hong Qiu , Shan Shen

Massively pre-trained transformer models are computationally expensive to fine-tune, slow for inference, and have large storage requirements. Recent approaches tackle these shortcomings by training smaller models, dynamically reducing the…

Machine Learning · Computer Science 2021-10-07 Andreas Rücklé , Gregor Geigle , Max Glockner , Tilman Beck , Jonas Pfeiffer , Nils Reimers , Iryna Gurevych

Multimodal instruction tuning is the de facto recipe for adapting vision language models (VLMs), yet instruction data are highly redundant, making data selection critical for training efficiency. Existing methods derive selection signals…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Mingkang Dong , Hongyi Cai , Xiwen Lei , Jie Li , Tao Zhang , Muxin Pu

We investigate whether post-trained capabilities can be transferred across models without retraining, with a focus on transfer across different model scales. We propose the Master Key Hypothesis, which states that model capabilities…

Machine Learning · Computer Science 2026-05-07 Rishab Balasubramanian , Pin-Jie Lin , Rituraj Sharma , Anjie Fang , Fardin Abdi , Viktor Rozgic , Zheng Du , Mohit Bansal , Tu Vu

Self-attention mechanism is the key of the Transformer but often criticized for its computation demands. Previous token pruning works motivate their methods from the view of computation redundancy but still need to load the full network and…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Sihao Lin , Pumeng Lyu , Dongrui Liu , Tao Tang , Xiaodan Liang , Andy Song , Xiaojun Chang

Machine learning is widely believed to be one of the most promising practical applications of quantum computing. Existing quantum machine learning schemes typically employ a quantum-classical hybrid approach that relies crucially on…

Quantum Physics · Physics 2025-02-11 Qi Ye , Shuangyue Geng , Zizhao Han , Weikang Li , L. -M. Duan , Dong-Ling Deng

Residual networks, as discrete approximations of Ordinary Differential Equations (ODEs), have inspired significant advancements in neural network design, including multistep methods, high-order methods, and multi-particle dynamical systems.…

Computation and Language · Computer Science 2024-11-06 Bei Li , Tong Zheng , Rui Wang , Jiahao Liu , Qingyan Guo , Junliang Guo , Xu Tan , Tong Xiao , Jingbo Zhu , Jingang Wang , Xunliang Cai

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Machine Learning · Computer Science 2025-06-05 Peng Wang , Yifu Lu , Yaodong Yu , Druv Pai , Qing Qu , Yi Ma

Recent work using pretrained transformers has shown impressive performance when fine-tuned with data from the downstream problem of interest. However, they struggle to retain that performance when the data characteristics changes. In this…

Machine Learning · Computer Science 2023-11-30 Martin Wistuba , Prabhu Teja Sivaprasad , Lukas Balles , Giovanni Zappella