arXiv:2503.08643v3 Announce Type: replace-cross Abstract: Curse of Dimensionality is an unavoidable challenge in statistical probability models, yet diffusion models seem to overcome this limitation, achieving impressive results in high-dimensional data generation. Diffusion models assume that they can learn the statistical…
arXiv:2509.25475v1 Announce Type: new Abstract: Interpretability of Deep Neural Networks (DNNs) is a growing field driven by the study of vision and language models. Yet, some use cases, like image captioning, or domains like Deep Reinforcement Learning (DRL), require complex…
arXiv:2505.20295v3 Announce Type: replace-cross Abstract: The common approach to communicate a large language model’s (LLM) uncertainty is to add a percentage number or a hedging word to its response. But is this all we can do? Instead of generating a…
Sentences that are highly dissimilar from anything we’ve seen before are more likely to be remembered accurately.
arXiv:2410.19378v2 Announce Type: replace-cross Abstract: We propose a deep mixture of multimodal hierarchical variational auto-encoders called MMHVAE that synthesizes missing images from observed images in different modalities. MMHVAE’s design focuses on tackling four challenges: (i) creating a complex latent representation…
arXiv:2505.18186v2 Announce Type: replace-cross Abstract: The fidelity with which neural networks can now generate content such as music presents a scientific opportunity: these systems appear to have learned implicit theories of such content’s structure through statistical learning alone. This offers…
arXiv:2503.12649v3 Announce Type: replace Abstract: Model merging has emerged as a promising approach for multi-task learning (MTL), offering a data-efficient alternative to conventional fine-tuning. However, with the rapid development of the open-source AI ecosystem and the increasing availability of fine-tuned…
arXiv:2509.06346v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts (MoE) has become a key architecture for scaling large language models (LLMs) efficiently. Recent fine-grained MoE designs introduce hundreds of experts per layer, with multiple experts activated per token, enabling stronger specialization. However,…
arXiv:2509.26397v1 Announce Type: cross Abstract: Neural scaling laws are driving the machine learning community toward training ever-larger foundation models across domains, assuring high accuracy and transferable representations for extrapolative tasks. We test this promise in quantum chemistry by scaling model…
arXiv:2304.11127v4 Announce Type: replace Abstract: Recent scientific advances require complex experiment design, necessitating the meticulous tuning of many experiment parameters. Tree-structured Parzen estimator (TPE) is a widely used Bayesian optimization method in recent parameter tuning frameworks such as Hyperopt and…
