English
Related papers

Related papers: An Adversarial Example for Direct Logit Attributio…

200 papers

Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity. We show that these metrics can be misleading, as models can appear to…

Computation and Language · Computer Science 2026-05-19 Xiaoyu Xu , Xiang Yue , Yang Liu , Qingqing Ye , Huadi Zheng , Peizhao Hu , Minxin Du , Haibo Hu

Recent studies have identified "retrieval heads" in Large Language Models (LLMs) responsible for extracting information from input contexts. However, prior works largely rely on static statistics aggregated across datasets, identifying…

Computation and Language · Computer Science 2026-05-11 Yuping Lin , Zitao Li , Yue Xing , Pengfei He , Yingqian Cui , Yaliang Li , Bolin Ding , Jingren Zhou , Jiliang Tang

FlashAttention (Dao, 2023) effectively reduces the quadratic peak memory usage to linear in training transformer-based large language models (LLMs) on a single GPU. In this paper, we introduce DISTFLASHATTN, a distributed memory-efficient…

Machine Learning · Computer Science 2024-04-02 Dacheng Li , Rulin Shao , Anze Xie , Eric P. Xing , Xuezhe Ma , Ion Stoica , Joseph E. Gonzalez , Hao Zhang

Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism concerning the sequence length. This…

Machine Learning · Computer Science 2024-02-27 Yury Nahshan , Joseph Kampeas , Emir Haleva

Large Language Models (LLMs) exhibit strong implicit personalization ability, yet most existing approaches treat this behavior as a black box, relying on prompt engineering or fine tuning on user data. In this work, we adopt a mechanistic…

Computation and Language · Computer Science 2026-04-27 Weixu Zhang , Ye Yuan , Changjiang Han , Yuxing Tian , Zipeng Sun , Linfeng Du , Jikun Kang , Hong Kang , Xue Liu , Haolun Wu

The great success of Transformer-based models benefits from the powerful multi-head self-attention mechanism, which learns token dependencies and encodes contextual information from the input. Prior work strives to attribute model decisions…

Computation and Language · Computer Science 2021-02-26 Yaru Hao , Li Dong , Furu Wei , Ke Xu

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami

Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert…

Robotics · Computer Science 2025-04-24 Amber Xie , Oleh Rybkin , Dorsa Sadigh , Chelsea Finn

Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators.…

Machine Learning · Computer Science 2025-04-11 Shaoyuan Chen , Wencong Xiao , Yutong Lin , Mingxing Zhang , Yingdi Shan , Jinlei Jiang , Kang Chen , Yongwei Wu

Balancing accuracy and latency on high-resolution images is a critical challenge for lightweight models, particularly for Transformer-based architectures that often suffer from excessive latency. To address this issue, we introduce…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Junzhou Li , Manqi Zhao , Yilin Gao , Zhiheng Yu , Yin Li , Dongsheng Jiang , Li Xiao

Offloading communication to existing direct memory access (DMA) engines, available on most state-of-the-art commercial GPUs, has emerged as an interesting and low-cost solution to efficiently overlap computation and communication in machine…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-13 Suchita Pati , Shaizeen Aga , Mahzabeen Islam , Ryan Quach , Saleel Kudchadker , Mohamed Assem Ibrahim

Hallucinations in large language models (LLMs) produce fluent continuations that are not supported by the prompt, especially under minimal contextual cues and ambiguity. We introduce Distributional Semantics Tracing (DST), a model-native…

Computation and Language · Computer Science 2026-03-17 Gagan Bhatia , Somayajulu G Sripada , Kevin Allan , Jacobo Azcona

Masked diffusion language models (MDLMs) generate text via iterative masked-token denoising, enabling mask-parallel decoding and distinct controllability and efficiency tradeoffs from autoregressive LLMs. Yet, efficient representation-level…

Computation and Language · Computer Science 2026-03-31 Adi Shnaidman , Erin Feiglin , Osher Yaari , Efrat Mentel , Amit Levi , Raz Lapid

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to Autoregressive Models (ARMs), utilizing parallel decoding to overcome sequential bottlenecks. However, existing research focuses primarily on kernel-level…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-16 Jiakun Fan , Yanglin Zhang , Xiangchen Li , Dimitrios S. Nikolopoulos

Transfer learning through fine-tuning a pre-trained neural network with an extremely large dataset, such as ImageNet, can significantly accelerate training while the accuracy is frequently bottlenecked by the limited dataset size of the new…

Machine Learning · Computer Science 2020-05-14 Xingjian Li , Haoyi Xiong , Hanchao Wang , Yuxuan Rao , Liping Liu , Zeyu Chen , Jun Huan

Transformer models exhibit in-context learning: the ability to accurately predict the response to a novel query based on illustrative examples in the input sequence. In-context learning contrasts with traditional in-weights learning of…

Machine Learning · Computer Science 2023-12-07 Gautam Reddy

Vision-Language-Action (VLA) models have achieved remarkable progress in robotic manipulation by mapping multimodal observations and instructions directly to actions. However, they typically mimic expert trajectories without predictive…

LayerNorm is a critical component in modern large language models (LLMs) for stabilizing training and ensuring smooth optimization. However, it introduces significant challenges in mechanistic interpretability, outlier feature suppression,…

Machine Learning · Computer Science 2024-11-19 Nandan Kumar Jha , Brandon Reagen

Recent guidance methods in diffusion models steer reverse sampling by perturbing the model to construct an implicit weak model and guide generation away from it. Among these approaches, attention perturbation has demonstrated strong…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Donghoon Ahn , Jiwon Kang , Sanghyun Lee , Minjae Kim , Jaewon Min , Wooseok Jang , Sangwu Lee , Sayak Paul , Susung Hong , Seungryong Kim

We identify a strong equivalence between neural network based machine learning (ML) methods and the formulation of statistical data assimilation (DA), known to be a problem in statistical physics. DA, as used widely in physical and…

Machine Learning · Computer Science 2017-10-23 H. D. I. Abarbanel , P. J. Rozdeba , S. Shirman
‹ Prev 1 8 9 10 Next ›