Related papers: Scalable Cross-Entropy Loss for Sequential Recomme…
Large language model post-training relies on reinforcement learning to improve model capability and alignment quality. However, the off-policy training paradigm introduces distribution shift, which often pushes the policy beyond the trust…
Collaborative filtering (CF) is widely searched in recommendation with various types of solutions. Recent success of Graph Convolution Networks (GCN) in CF demonstrates the effectiveness of modeling high-order relationships through graphs,…
Optical Character Recognition (OCR) is fundamental to Vision-Language Models (VLMs) and high-quality data generation for LLM training. Yet, despite progress in average OCR accuracy, state-of-the-art VLMs still struggle with detecting…
The continuing advancement of memory technology has not only fueled a surge in performance, but also substantially exacerbate reliability challenges. Traditional solutions have primarily focused on improving the efficiency of protection…
Contrastive loss is a powerful approach for representation learning, where larger batch sizes enhance performance by providing more negative samples to better distinguish between similar and dissimilar data. However, scaling batch sizes is…
Optimal decision making requires that classifiers produce uncertainty estimates consistent with their empirical accuracy. However, deep neural networks are often under- or over-confident in their predictions. Consequently, methods have been…
The amount of manually labeled data is limited in medical applications, so semi-supervised learning and automatic labeling strategies can be an asset for training deep neural networks. However, the quality of the automatically generated…
Collaborative Edge Computing (CEC) is an effective method that improves the performance of Mobile Edge Computing (MEC) systems by offloading computation tasks from busy edge servers (ESs) to idle ones. However, ESs usually belong to…
Deep neural networks are able to memorize noisy labels easily with a softmax cross-entropy (CE) loss. Previous studies attempted to address this issue focus on incorporating a noise-robust loss function to the CE loss. However, the…
Reinforcement learning (RL) has become a powerful paradigm for optimizing large language models (LLMs) to handle complex reasoning tasks. A core challenge in this process lies in managing policy entropy, which reflects the balance between…
We identify empirical scaling laws for the cross-entropy loss in four domains: generative image modeling, video modeling, multimodal image$\leftrightarrow$text models, and mathematical problem solving. In all cases autoregressive…
We introduce a goal-oriented strategy for multiscale computations performed using the Multiscale Finite Element Method (MsFEM). In a previous work, we have shown how to use, in the MsFEM framework, the concept of Constitutive Relation Error…
We present a graph sampling and coarsening scheme (gSC) for computing lower and upper bounds for large-scale supply chain models. An edge sampling scheme is used to build a low-complexity problem that is used to finding an approximate (but…
Embedding techniques have become essential components of large databases in the deep learning era. By encoding discrete entities, such as words, items, or graph nodes, into continuous vector spaces, embeddings facilitate more efficient…
Continual Reinforcement Learning (CRL) is essential for developing agents that can learn, adapt, and accumulate knowledge over time. However, a fundamental challenge persists as agents must strike a delicate balance between plasticity,…
Log parsing, a vital task for interpreting the vast and complex data produced within software architectures faces significant challenges in the transition from academic benchmarks to the industrial domain. Existing log parsers, while highly…
There has been a growing interest in benchmarking sequential recommendation models and reproducing/improving existing models. For example, Rendle et al. improved matrix factorization models by tuning their parameters and hyperparameters.…
Fine-grained visual classification (FGVC) aims to distinguish the sub-classes of the same category and its essential solution is to mine the subtle and discriminative regions. Convolution neural networks (CNNs), which employ the cross…
Reinforcement learning-based preference optimization is increasingly used to align list-wise generative recommenders with complex, multi-objective user feedback, yet existing optimizers such as Gradient-Bounded Policy Optimization (GBPO)…
Graph representation learning has attracted lots of attention recently. Existing graph neural networks fed with the complete graph data are not scalable due to limited computation and memory costs. Thus, it remains a great challenge to…