22 papers · ranked by Valyu relevance
Aial Sobeh, Simone Shamay-Tsoory, Bruno Kluwe-Schiavon, Giorgio Manenti
Human behavior is shaped by a pervasive motive to align with others, manifesting across a wide range of tendencies-from motor synchrony and emotional contagion to convergence in beliefs and choices. Existing accounts explain how alignment arises through predictive coding and observation-execution mechanisms, but they…
Mario Treviño, Nathaly Martín, Andrea Barrera, Inmaculada Márquez + 1 more
Highlights What are the main findings?1. Successful interception exhibits within-trial, speed-dependent shifts between predictive and reactive control in both gaze and manual trajectories. 2. Target occlusion reduces predictive alignment, whereas cursor occlusion has a limited impact, indicating strong reliance on…
Corentin Lobet, Francesca Chiaromonte
Feature attribution is the dominant paradigm for explaining deep neural networks. However, most existing methods only loosely reflect the model's prediction-making process, thereby merely white-painting the black box. We argue that explanatory alignment is a key aspect of trustworthiness in prediction tasks…
Mohammad Asadi, Soheil Hor, Bardiya Akhbari, Jack W. O'Sullivan + 5 more
Retrieval-augmented forecasting promises to adapt frozen Time Series Foundation Models (TSFMs) to new domains without fine-tuning, but recent methods typically rely on learned fusion modules, i.e., trained adapters that merge retrieved examples into the backbone's forecast, based on the assumption that frozen backbones…
Nimrod Serok, Ksenia Polonsky, Haim Ashkenazy, Itay Mayrose + 2 more
Multiple sequence alignment (MSA) inference is a central task in molecular evolution and comparative genomics, and the reliability of downstream analyses, including phylogenetic inference, depends critically on alignment quality. Despite this importance, most widely used MSA methods optimize the sum-of-pairs (SP)…
Tiejin Chen, Xiaoou Liu, Vishnu Nandam, Kuan-Ru Liou + 1 more
Preference-based alignment like Reinforcement Learning from Human Feedback (RLHF) learns from pairwise preferences, yet the labels are often noisy and inconsistent. Existing uncertainty-aware approaches weight preferences, but ignore a more fundamental factor: the reliability of the answers being compared. To address…
Moisés Santos, Peter van der Putten, Bernhard Pfahringer, Carlos Soares
We propose Rashomon Alignment (RA), a new measure to assess functional similarity between two models. Existing functional similarity measures are distributional, quantifying differences between outputs of models applied to real-world data. However, these measures can be regarded as ecologically valid only for regions…
Yuhan Huang, Huanran Chen, Yinpeng Dong
Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and reinforcement learning from human feedback, the alignment is often fragile under subsequent fine-tuning. Existing explanations either attribute alignment fragility to gradient geometry or characterize it as a…
Nimrod Serok, Ksenia Polonsky, Haim Ashkenazy, Itay Mayrose + 3 more
Multiple sequence alignment (MSA) inference is a central task in molecular evolution and comparative genomics, and the reliability of downstream analyses, including phylogenetic inference, depends critically on alignment quality. Despite this importance, most widely used MSA methods optimize the sum-of-pairs (SoP)…
Alexis Molina, Xinyi Zhang
Predicting single-cell responses to genetic perturbations could reveal the vast combinatorial space of perturbations and cellular contexts that is infeasible to measure experimentally, yet current deep learning models generalize poorly and often fail to outperform simple baselines. Here we demonstrate that…
Ni Yang, Rui He, Philipp Homan, Iris Sommer + 2 more
Large language models (LLMs) reliably predict neural activity during language comprehension and transformer depth has been interpreted as mirroring hierarchical cortical organization. However, it remains unclear whether such alignment extends to subcortical regions, overlaps spatially across languages, and what the…
Mattis Bodynek, Lucía Martín-Fernández, Julia Haag, Ben Bettisworth + 1 more
Multiple Sequence Alignment (MSA) constitutes an important and frequent operation in molecular sequence data analysis. There exist numerous tools, algorithms, and criteria to infer an MSA. This plethora of available approaches to MSA may induced an ensemble of divergent MSAs for the same underlying unaligned sequence…
Yixiao Zhai, Zitong Zhang, Zhen Li
The reliability of multiple sequence alignment (MSA) results directly determines the credibility of the conclusions drawn from biological research. However, MSA is inherently an NP-hard problem, making it theoretically impossible to guarantee a globally optimal solution. Consequently, in addition to developing more…
Authors not listed
Theoretical prediction of enantioselectivity for broad range of substrates in a given reaction has long been a formidable challenge, traditionally replaced by labor-intensive screening of multiple conditions. Until recently this remained an unaddressed problem in asymmetric catalysis under data-limited scenarios, yet…
Horia Todor, Lili M Kim, Jürgen Jänes, Hannah N Burkhart + 3 more
Accurate prediction of protein complex structures by AlphaFold3 and similar programs has been used to predict the presence of protein-protein interactions (PPIs), but this technique has never been applied to an entire genome due to onerous computational requirements and questionable utility. Here we present pooled-PPI…
Chris L.B. Graham, Liam Cremona, Robin Little, Christopher. D. A. Rodrigues
Multiple sequence alignment (MSA) data underlies current principles in protein folding and protein-protein interaction prediction, from which large language models (LLMs) in tandem with protein datasets, can predict protein structure. However, what is missing are user-friendly tools that enable researchers to predict…
Vasiliki Tassopoulou, Charis Stamouli, Haochang Shou, George J. Pappas + 1 more
Despite recent progress in predicting biomarker trajectories from real clinical data, uncertainty in the predictions poses high-stakes risks (e.g., misdiagnosis) that limit their clinical deployment. To enable safe and reliable use of such predictions in healthcare, we introduce a conformal method for…
Authors not listed
Machine learning (ML) models are increasingly used in quantum chemistry, but their reliability hinges on uncertainty quantification (UQ). In this study, we compare two prominent UQ paradigms—Deep Evidential Regression (DER) and Deep Ensembles—on the QM9 and WS22 datasets, with a specific emphasis on the role of post…
Authors not listed
This research investigates predicting the Highest Occupied Molecular Orbital and the Lowest Unoccupied Molecular Orbital (HOMO-LUMO; short HL) gap of natural compounds, a crucial property for understanding molecular electronic behavior relevant to cheminformatics and materials science. To address the high computational…
Moruf A. Adeagbo, Valdete M. Gonçalves-Almeida, Sandro C. Izidoro, Sabrina A. Silveira
Protein–protein interactions (PPIs) play a central role in elucidating cellular mechanisms. However, a substantial gap remains in current prediction models, as they frequently overlook the structural and physicochemical context governing molecular binding, thereby limiting predictive accuracy. To address this…
Authors not listed
Accurately predicting chemical reaction yields in silico is a long-standing goal in organic chemistry that, if achieved, would revolutionize synthesis design, op-timization, and discovery. The vast reaction data within scientific literature rep-resents a rich resource for training predictive machine learning models…
Faiza Hasin, Michele Minervini, Corrado Mencar, Giuseppe Ventrella + 3 more
Introduction The interaction between guide RNAs (gRNAs) and target DNA sequences is a critical factor in the effectiveness of CRISPR/Cas9 (Clustered Regularly Interspaced Short Palindromic Repeats/CRISPR-associated protein 9) gene editing. Predicting these interactions accurately necessitates models that offer…