English
Related papers

Related papers: GRALIS: A Unified Canonical Framework for Linear A…

200 papers

Existing reasoning data curation pipelines score whole samples, treating every intermediate step as equally valuable. In reality, steps within a trace contribute very unevenly, and selecting reasoning data well requires assessing them…

Artificial Intelligence · Computer Science 2026-05-14 Junjie Li , Ziao Wang , NingXuan Ma , Jianghong Ma , Xiaofeng Zhang

Inference-time sparsification is a promising path to deploy large language models (LLMs) on resource-constrained devices, yet existing training-free methods typically estimate feedforward network (FFN) neuron importance from the input…

In this paper, we demonstrate how to enhance the validity of causal inference with unstructured high-dimensional treatments like texts, by leveraging the power of generative Artificial Intelligence (GenAI). Specifically, we propose to use a…

Applications · Statistics 2025-09-09 Kosuke Imai , Kentaro Nakamura

Self-supervised learning has shown its great potential to extract powerful visual representations without human annotations. Various works are proposed to deal with self-supervised learning from different perspectives: (1) contrastive…

Computer Vision and Pattern Recognition · Computer Science 2022-07-06 Chenxin Tao , Honghui Wang , Xizhou Zhu , Jiahua Dong , Shiji Song , Gao Huang , Jifeng Dai

No methods currently exist for making arbitrary neural networks fair. In this work we introduce GRAD, a new and simplified method to producing fair neural networks that can be used for auto-encoding fair representations or directly with…

Machine Learning · Statistics 2018-07-03 Edward Raff , Jared Sylvester

Integrated Gradients (IG) is a widely adopted feature attribution method that satisfies desirable axiomatic properties. However, the choice of integration path significantly affects the quality of attributions, and the standard…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Soyeon Kim , Seongwoo Lim , Kyowoon Lee , Jaesik Choi

Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one. Thus, to enhance the performance, fine-tuning and…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Beier Zhu , Kaihua Tang , Qianru Sun , Hanwang Zhang

Recent development of neural implicit function has shown tremendous success on high-quality 3D shape reconstruction. However, most works divide the space into inside and outside of the shape, which limits their representing power to…

Computer Vision and Pattern Recognition · Computer Science 2024-04-10 Jianglong Ye , Yuntao Chen , Naiyan Wang , Xiaolong Wang

We derive an exact, prediction-specific instance-attribution method for fitted gradient boosting machines (GBMs) trained with squared-error loss, with the learned tree structure held fixed. Each prediction can be written as a weighted sum…

Machine Learning · Computer Science 2026-04-14 Paul Geertsema , Helen Lu

We introduce Graph Normalization (GN), a principled dynamical system on graphs that serves as a differentiable approximation engine for the NP-hard Maximum Weight Independent Set (MWIS) problem. MWIS encompasses many combinatorial…

Machine Learning · Computer Science 2026-05-08 Laurent Guigues

Class Activation Mapping (CAM) methods are widely used to visualize neural network decisions, yet their underlying mechanisms remain incompletely understood. To enhance the understanding of CAM methods and improve their explainability, we…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Huaiguang Cai

We introduce a new tool for interpreting neural net responses, namely full-gradients, which decomposes the neural net response into input sensitivity and per-neuron sensitivity components. This is the first proposed representation which…

Machine Learning · Computer Science 2019-12-04 Suraj Srinivas , Francois Fleuret

Pruning at Initialisation methods discover sparse, trainable subnetworks before training, but their theoretical mechanisms remain elusive. Existing analyses are often limited to finite-width statistics, lacking a rigorous characterisation…

Machine Learning · Computer Science 2026-02-09 Hoang Pham , The-Anh Ta , Long Tran-Thanh

The paper surveys recent progresses in understanding the dynamics and loss landscape of the gradient flow equations associated to deep linear neural networks, i.e., the gradient descent training dynamics (in the limit when the step size…

Machine Learning · Computer Science 2025-11-14 Joel Wendin , Claudio Altafini

We discuss a way to find a well behaved baseline for attribution methods that work by feeding a neural network with a sequence of interpolated inputs between two given inputs. Then, we test it with our novel Riemann-Stieltjes Integrated…

Computer Vision and Pattern Recognition · Computer Science 2022-04-14 Miguel Lerma , Mirtha Lucas

Neural networks are becoming increasingly better at tasks that involve classifying and recognizing images. At the same time techniques intended to explain the network output have been proposed. One such technique is the Gradient-based Class…

Computer Vision and Pattern Recognition · Computer Science 2022-05-24 Mirtha Lucas , Miguel Lerma , Jacob Furst , Daniela Raicu

Robust correlation estimation is essential in high-dimensional settings, particularly when data are contaminated by outliers or exhibit heavy-tailed behavior. Many robust loss functions of practical interest-such as those involving…

Applications · Statistics 2025-06-19 Priyam Das

Visual search, recommendation, and contrastive similarity learning power technologies that impact billions of users worldwide. Modern model architectures can be complex and difficult to interpret, and there are several competing techniques…

Machine Learning · Computer Science 2022-03-17 Mark Hamilton , Scott Lundberg , Lei Zhang , Stephanie Fu , William T. Freeman

Saliency methods can aid understanding of deep neural networks. Recent years have witnessed many improvements to saliency methods, as well as new ways for evaluating them. In this paper, we 1) present a novel region-based attribution…

Computer Vision and Pattern Recognition · Computer Science 2019-08-22 Andrei Kapishnikov , Tolga Bolukbasi , Fernanda Viégas , Michael Terry

The dominant paradigm for relation prediction in knowledge graphs involves learning and operating on latent representations (i.e., embeddings) of entities and relations. However, these embedding-based methods do not explicitly capture the…

Machine Learning · Computer Science 2020-02-13 Komal K. Teru , Etienne Denis , William L. Hamilton
‹ Prev 1 3 4 5 6 7 10 Next ›