Related papers: Test-Time Training with KV Binding Is Secretly Lin…

Generalizing deep learning models to unknown target domain distribution with low latency has motivated research into test-time training/adaptation (TTT/TTA). Existing approaches often focus on improving test-time training performance under…

Temporal difference learning (TD) is a simple iterative algorithm used to estimate the value function corresponding to a given policy in a Markov decision process. Although TD is one of the most widely used algorithms in reinforcement…

Q-Learning is a fundamental off-policy reinforcement learning (RL) algorithm that has the objective of approximating action-value functions in order to learn optimal policies. Nonetheless, it has difficulties in reconciling bias with…

Time series analysis is critical for emerging net- work intelligent control and management functions. However, existing statistical-based and shallow machine learning models have shown limited prediction capabilities on multivariate time…

Machine learning (ML) is a promising approach for performing challenging quantum-information tasks such as device characterization, calibration and control. ML models can train directly on the data produced by a quantum device while…

Knowledge tracing (KT) is a field of study that predicts the future performance of students based on prior performance datasets collected from educational applications such as intelligent tutoring systems, learning management systems, and…

Test-time adaptation (TTA) aims to fine-tune a trained model online using unlabeled testing data to adapt to new environments or out-of-distribution data, demonstrating broad application potential in real-world scenarios. However, in this…

Enabling low precision implementations of deep learning models, without considerable performance degradation, is necessary in resource and latency constrained settings. Moreover, exploiting the differences in sensitivity to quantization…

Test-Time Training (TTT) proposes to adapt a pre-trained network to changing data distributions on-the-fly. In this work, we propose the first TTT method for 3D semantic segmentation, TTT-KD, which models Knowledge Distillation (KD) from…

Self-attention learns pairwise interactions to model long-range dependencies, yielding great improvements for video action recognition. In this paper, we seek a deeper understanding of self-attention for temporal modeling in videos. We…

The predominant approach to Visual Question Answering (VQA) demands that the model represents within its weights all of the information required to answer any question about any image. Learning this information from any real training set…

Test-Time Adaptation (TTA) enables pre-trained models to adjust to distribution shift by learning from unlabeled test-time streams. However, existing methods typically treat these streams as independent samples, overlooking the supervisory…

Transformers have emerged as a compelling architecture for sequential decision-making by modeling trajectories via self-attention. In reinforcement learning (RL), they enable return-conditioned control without relying on value function…

Knowledge tracing (KT) is a crucial task in computer-aided education and intelligent tutoring systems, predicting students' performance on new questions from their responses to prior ones. An accurate KT model can capture a student's…

The quadratic computational complexity of the attention mechanism in current Large Language Models (LLMs) renders inference with long contexts prohibitively expensive. To address this challenge, various approaches aim to retain critical…

Knowledge Tracing (KT) is a critical task in online learning for modeling student knowledge over time. Despite the success of deep learning-based KT models, which rely on sequences of numbers as data, most existing approaches fail to…

To tackle the huge computational demand of large foundation models, activation-aware compression techniques without retraining have been introduced. However, since these methods highly rely on calibration data, domain shift issues may arise…

Since the publication of the original Transformer architecture (Vaswani et al. 2017), Transformers revolutionized the field of Natural Language Processing. This, mainly due to their ability to understand timely dependencies better than…

Key-value (KV) caching plays an essential role in accelerating decoding for transformer-based autoregressive large language models (LLMs). However, the amount of memory required to store the KV cache can become prohibitive at long sequence…

Learning to solve sequential tasks with recurrent models requires the ability to memorize long sequences and to extract task-relevant features from them. In this paper, we study the memorization subtask from the point of view of the design…