Related papers: Decomposing the Generalization Gap in PROTAC Activ…
We propose a network architecture capable of reliably estimating uncertainty of regression based predictions without sacrificing accuracy. The current state-of-the-art uncertainty algorithms either fall short of achieving prediction…
Accurately predicting mortality risk in intensive care unit (ICU) patients is essential for clinical decision-making. Although large language models (LLMs) show strong potential in structured medical prediction tasks, their outputs may…
The Predictive Associative Memory (PAM) framework posits that useful relationships often connect items that co-occur in shared contexts rather than items that appear similar in embedding space. A contrastive MLP trained on co-occurrence…
Traditionally, most of the existing attribute learning methods are trained based on the consensus of annotations aggregated from a limited number of annotators. However, the consensus might fail in settings, especially when a wide spectrum…
Identifying immune checkpoint inhibitor (ICI) studies in genomic repositories like Gene Expression Omnibus (GEO) is vital for cancer research yet remains challenging due to semantic ambiguity, extreme class imbalance, and limited labeled…
The predictive quality of machine learning models is typically measured in terms of their (approximate) expected prediction error or the so-called Area Under the Curve (AUC) for a particular data distribution. However, when the models are…
Labeled data for imitation learning of theorem proving in large libraries of formalized mathematics is scarce as such libraries require years of concentrated effort by human specialists to be built. This is particularly challenging when…
Constructing atomic models from cryo-electron microscopy (cryo-EM) maps is a crucial yet intricate task in structural biology. While advancements in deep learning, such as convolutional neural networks (CNNs) and graph neural networks…
Adversarial training is extensively utilized to improve the adversarial robustness of deep neural networks. Yet, mitigating the degradation of standard generalization performance in adversarial-trained models remains an open problem. This…
AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs while their internal reasoning is misaligned. We thus…
We present a latent variable model for classification that provides a novel probabilistic interpretation of neural network softmax classifiers. We derive a variational objective to train the model, analogous to the evidence lower bound…
Gradient-based learning algorithms have an implicit simplicity bias which in effect can limit the diversity of predictors being sampled by the learning procedure. This behavior can hinder the transferability of trained models by (i)…
Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks (Yuan et al., 2024, Chen et al., 2024). In this work we…
Loss functions play an important role in training deep-network-based object detectors. The most widely used evaluation metric for object detection is Average Precision (AP), which captures the performance of localization and classification…
Understanding what constitutes high-quality pre-training data remains a central question in language model training. In this work, we investigate whether benchmark performance is primarily driven by the degree of statistical pattern overlap…
Speculative decoding accelerates large language model inference by proposing tokens with a lightweight draft model and selectively accepting them using a target model. This work introduces DropMatch, a novel approach that matches draft…
Link prediction is a paradigmatic and challenging problem in network science, which attempts to uncover missing links or predict future links, based on known topology. A fundamental but still unsolved issue is how to choose proper metrics…
The past decade's "cryoEM revolution" has produced exponential growth in high-resolution structural data through advances in cryogenic electron microscopy (cryoEM) and tomography (cryoET). Deep learning integration into structural…
Dropout, a simple and effective way to train deep neural networks, has led to a number of impressive empirical successes and spawned many recent theoretical investigations. However, the gap between dropout's training and inference phases,…
In domains such as molecular and protein generation, physical systems exhibit inherent symmetries that are critical to model. Two main strategies have emerged for learning invariant distributions: designing equivariant network architectures…