BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Carla P. Gomes

Carla P. Gomes contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine LearningArtificial Intelligencecond-mat.mtrl-sciphysics.comp-phComputer VisionMultiagent Systemsphysics.chem-phphysics.ins-det

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
14works
0followers
8topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

14 published item(s)

preprint2026arXiv

Autonomous Materials Exploration by Integrating Automated Phase Identification and AI-Assisted Human Reasoning

Autonomous experimentation holds the potential to accelerate materials development by combining artificial intelligence (AI) with modular robotic platforms to explore extensive combinatorial chemical and processing spaces. Such self-driving laboratories can not only increase the throughput of repetitive experiments, but also incorporate human domain expertise to drive the search towards user-defined objectives, including improved materials performance metrics. We present an autonomous materials synthesis extension to SARA, the Scientific Autonomous Reasoning Agent, utilizing phase information provided by an automated probabilistic phase labeling algorithm to expedite the search for targeted phase regions. By incorporating human input into an expanded SARA-H (SARA with human-in-the-loop) framework, we enhance the efficiency of the underlying reasoning process. Using synthetic benchmarks, we demonstrate the efficiency of our AI implementation and show that the human input can contribute to significant improvement in sampling efficiency. We conduct experimental active learning campaigns using robotic processing of thin-film samples of several oxide material systems, including Bi$_2$O$_3$, SnO$_x$, and Bi-Ti-O, using lateral-gradient laser spike annealing to synthesize and kinetically trap metastable phases. We showcase the utility of human-in-the-loop autonomous experimentation for the Bi-Ti-O system, where we identify extensive processing domains that stabilize $δ$-Bi$_2$O$_3$ and Bi$_2$Ti$_2$O$_7$, explore dwell-dependent ternary oxide phase behavior, and provide evidence confirming predictions that cationic substitutional doping of TiO$_2$ with Bi inhibits the unfavorable transformation of the metastable anatase to the ground-state rutile phase. The autonomous methods we have developed enable the discovery of new materials and new understanding of materials synthesis and properties.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Divergence-Suppressing Couplings for Rectified Flow

The promise of Rectified Flow rests on producing self-generated couplings whose trajectories are straight, or nearly so. In practice, trajectories generated by the base flow model can bend and intertwine, and the resulting coupling inherits this distortion. In this paper, we identify that such trajectory entanglement is often associated with regions of nonzero divergence in the learned velocity field, where local expansion or contraction distorts trajectories and steers particles away from their ideal endpoints. We then propose divergence-suppressing couplings for Rectified Flow, an offline correction that attenuate the divergent component of the learned velocity during coupling generation. The correction is paid only once per coupling pair and amortized over training, so deployment runs plain Euler at identical wall-clock cost to standard Rectified Flow. Empirically, this offline modification yields consistent improvements on 2D synthetic benchmarks and on image generation.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

FEAT: Free energy Estimators with Adaptive Transport

We present Free energy Estimators with Adaptive Transport (FEAT), a novel framework for free energy estimation -- a critical challenge across scientific domains. FEAT leverages learned transports implemented via stochastic interpolants and provides consistent, minimum-variance estimators based on escorted Jarzynski equality and controlled Crooks theorem, alongside variational upper and lower bounds on free energy differences. Unifying equilibrium and non-equilibrium methods under a single theoretical framework, FEAT establishes a principled foundation for neural free energy calculations. Experimental validation on toy examples, molecular simulations, and quantum field theory demonstrates improvements over existing learning-based methods. Our PyTorch implementation is available at https://github.com/jiajunhe98/FEAT.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Learning Unbiased Permutations via Flow Matching

Learning permutations is fundamental to sorting, ranking, and matching, but existing differentiable methods based on entropy-regularized Sinkhorn produce a single softened solution and collapse under ambiguity. We present PermFlow, a conditional flow matching framework that operates directly on the affine subspace of matrices with unit row and column sums. A closed-form tangent-space projector preserves these constraints exactly along every trajectory, by construction rather than through iterative correction, and a nearest-target coupling routes distinct noisy initializations toward distinct valid permutations. The result is a model that captures multimodal permutation distributions rather than collapsing them to a single mode. On a visual sorting task with blended-digit ambiguity and a symmetric linear assignment problem, PermFlow achieves high accuracy on unambiguous inputs and recovers both valid permutations under ambiguity, where Sinkhorn-based baselines structurally fail.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A GNN-RNN Approach for Harnessing Geospatial and Temporal Information: Application to Crop Yield Prediction

Climate change is posing new challenges to crop-related concerns including food insecurity, supply stability and economic planning. As one of the central challenges, crop yield prediction has become a pressing task in the machine learning field. Despite its importance, the prediction task is exceptionally complicated since crop yields depend on various factors such as weather, land surface, soil quality as well as their interactions. In recent years, machine learning models have been successfully applied in this domain. However, these models either restrict their tasks to a relatively small region, or only study over a single or few years, which makes them hard to generalize spatially and temporally. In this paper, we introduce a novel graph-based recurrent neural network for crop yield prediction, to incorporate both geographical and temporal knowledge in the model, and further boost predictive power. Our method is trained, validated, and tested on over 2000 counties from 41 states in the US mainland, covering years from 1981 to 2019. As far as we know, this is the first machine learning method that embeds geographical knowledge in crop yield prediction and predicts the crop yields at county level nationwide. We also laid a solid foundation for the comparison with other machine learning baselines by applying well-known linear models, tree-based models, deep learning methods and comparing their performance. Experiments show that our proposed method consistently outperforms the existing state-of-the-art methods on various metrics, validating the effectiveness of geospatial and temporal information.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Density of States Prediction for Materials Discovery via Contrastive Learning from Probabilistic Embeddings

Machine learning for materials discovery has largely focused on predicting an individual scalar rather than multiple related properties, where spectral properties are an important example. Fundamental spectral properties include the phonon density of states (phDOS) and the electronic density of states (eDOS), which individually or collectively are the origins of a breadth of materials observables and functions. Building upon the success of graph attention networks for encoding crystalline materials, we introduce a probabilistic embedding generator specifically tailored to the prediction of spectral properties. Coupled with supervised contrastive learning, our materials-to-spectrum (Mat2Spec) model outperforms state-of-the-art methods for predicting ab initio phDOS and eDOS for crystalline materials. We demonstrate Mat2Spec's ability to identify eDOS gaps below the Fermi energy, validating predictions with ab initio calculations and thereby discovering candidate thermoelectrics and transparent conductors. Mat2Spec is an exemplar framework for predicting spectral properties of materials via strategically incorporated machine learning techniques.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification

Multi-label classification (MLC) is a prediction task where each sample can have more than one label. We propose a novel contrastive learning boosted multi-label prediction model based on a Gaussian mixture variational autoencoder (C-GMVAE), which learns a multimodal prior space and employs a contrastive loss. Many existing methods introduce extra complex neural modules like graph neural networks to capture the label correlations, in addition to the prediction modules. We find that by using contrastive learning in the supervised setting, we can exploit label information effectively in a data-driven manner, and learn meaningful feature and label embeddings which capture the label correlations and enhance the predictive power. Our method also adopts the idea of learning and aligning latent spaces for both features and labels. In contrast to previous works based on a unimodal prior, C-GMVAE imposes a Gaussian mixture structure on the latent space, to alleviate the posterior collapse and over-regularization issues. C-GMVAE outperforms existing methods on multiple public datasets and can often match other models' full performance with only 50% of the training data. Furthermore, we show that the learnt embeddings provide insights into the interpretation of label-label interactions.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Is High Variance Unavoidable in RL? A Case Study in Continuous Control

Reinforcement learning (RL) experiments have notoriously high variance, and minor details can have disproportionately large effects on measured outcomes. This is problematic for creating reproducible research and also serves as an obstacle for real-world applications, where safety and predictability are paramount. In this paper, we investigate causes for this perceived instability. To allow for an in-depth analysis, we focus on a specifically popular setup with high variance -- continuous control from pixels with an actor-critic agent. In this setting, we demonstrate that variance mostly arises early in training as a result of poor "outlier" runs, but that weight initialization and initial exploration are not to blame. We show that one cause for early variance is numerical instability which leads to saturating nonlinearities. We investigate several fixes to this issue and find that one particular method is surprisingly effective and simple -- normalizing penultimate features. Addressing the learning instability allows for larger learning rates, and significantly decreases the variance of outcomes. This demonstrates that the perceived variance in RL is not necessarily inherent to the problem definition and may be addressed through simple architectural modifications.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Monitoring Vegetation From Space at Extremely Fine Resolutions via Coarsely-Supervised Smooth U-Net

Monitoring vegetation productivity at extremely fine resolutions is valuable for real-world agricultural applications, such as detecting crop stress and providing early warning of food insecurity. Solar-Induced Chlorophyll Fluorescence (SIF) provides a promising way to directly measure plant productivity from space. However, satellite SIF observations are only available at a coarse spatial resolution, making it impossible to monitor how individual crop types or farms are doing. This poses a challenging coarsely-supervised regression (or downscaling) task; at training time, we only have SIF labels at a coarse resolution (3km), but we want to predict SIF at much finer spatial resolutions (e.g. 30m, a 100x increase). We also have additional fine-resolution input features, but the relationship between these features and SIF is unknown. To address this, we propose Coarsely-Supervised Smooth U-Net (CS-SUNet), a novel method for this coarse supervision setting. CS-SUNet combines the expressive power of deep convolutional networks with novel regularization methods based on prior knowledge (such as a smoothness loss) that are crucial for preventing overfitting. Experiments show that CS-SUNet resolves fine-grained variations in SIF more accurately than existing methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Towards Deeper Deep Reinforcement Learning with Spectral Normalization

In computer vision and natural language processing, innovations in model architecture that increase model capacity have reliably translated into gains in performance. In stark contrast with this trend, state-of-the-art reinforcement learning (RL) algorithms often use small MLPs, and gains in performance typically originate from algorithmic innovations. It is natural to hypothesize that small datasets in RL necessitate simple models to avoid overfitting; however, this hypothesis is untested. In this paper we investigate how RL agents are affected by exchanging the small MLPs with larger modern networks with skip connections and normalization, focusing specifically on actor-critic algorithms. We empirically verify that naively adopting such architectures leads to instabilities and poor performance, likely contributing to the popularity of simple models in practice. However, we show that dataset size is not the limiting factor, and instead argue that instability from taking gradients through the critic is the culprit. We demonstrate that spectral normalization (SN) can mitigate this issue and enable stable training with large modern architectures. After smoothing with SN, larger models yield significant performance improvements -- suggesting that more "easy" gains may be had by focusing on model architectures in addition to algorithmic innovations.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Zero Training Overhead Portfolios for Learning to Solve Combinatorial Problems

There has been an increasing interest in harnessing deep learning to tackle combinatorial optimization (CO) problems in recent years. Typical CO deep learning approaches leverage the problem structure in the model architecture. Nevertheless, the model selection is still mainly based on the conventional machine learning setting. Due to the discrete nature of CO problems, a single model is unlikely to learn the problem entirely. We introduce ZTop, which stands for Zero Training Overhead Portfolio, a simple yet effective model selection and ensemble mechanism for learning to solve combinatorial problems. ZTop is inspired by algorithm portfolios, a popular CO ensembling strategy, particularly restart portfolios, which periodically restart a randomized CO algorithm, de facto exploring the search space with different heuristics. We have observed that well-trained models acquired in the same training trajectory, with similar top validation performance, perform well on very different validation instances. Following this observation, ZTop ensembles a set of well-trained models, each providing a unique heuristic with zero training overhead, and applies them, sequentially or in parallel, to solve the test instances. We show how ZTopping, i.e., using a ZTop ensemble strategy with a given deep learning approach, can significantly improve the performance of the current state-of-the-art deep learning approaches on three prototypical CO domains, the hardest unique-solution Sudoku instances, challenging routing problems, and the graph maximum cut problem, as well as on multi-label classification, a machine learning task with a large combinatorial label space.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Optical Identification of Materials Transformations in Oxide Thin Films

Recent advances in high-throughput experimentation for combinatorial studies have accelerated the discovery and analysis of materials across a wide range of compositions and synthesis conditions. However, many of the more powerful characterization methods are limited by speed, cost, availability, and/or resolution. To make efficient use of these methods, there is value in developing approaches for identifying critical compositions and conditions to be used as a-priori knowledge for follow-up characterization with high-precision techniques, such as micron-scale synchrotron based X-ray diffraction (XRD). Here we demonstrate the use of optical microscopy and reflectance spectroscopy to identify likely phase-change boundaries in thin film libraries. These methods are used to delineate possible metastable phase boundaries following lateral-gradient Laser Spike Annealing (lg-LSA) of oxide materials. The set of boundaries are then compared with definitive determinations of structural transformations obtained using high-resolution XRD. We demonstrate that the optical methods detect more than 95% of the structural transformations in a composition-gradient La-Mn-O library and a Ga$_2$O$_3$ sample, both subject to an extensive set of lg-LSA anneals. Our results provide quantitative support for the value of optically-detected transformations as a priori data to guide subsequent structural characterization, ultimately accelerating and enhancing the efficient implementation of $μ$m-resolution XRD experiments.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning

Despite significant progress in general AI planning, certain domains remain out of reach of current AI planning systems. Sokoban is a PSPACE-complete planning task and represents one of the hardest domains for current AI planners. Even domain-specific specialized search methods fail quickly due to the exponential search complexity on hard instances. Our approach based on deep reinforcement learning augmented with a curriculum-driven method is the first one to solve hard instances within one day of training while other modern solvers cannot solve these instances within any reasonable time limit. In contrast to prior efforts, which use carefully handcrafted pruning techniques, our approach automatically uncovers domain structure. Our results reveal that deep RL provides a promising framework for solving previously unsolved AI planning problems, provided a proper training curriculum can be devised.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Task-Based Learning via Task-Oriented Prediction Network with Applications in Finance

Real-world applications often involve domain-specific and task-based performance objectives that are not captured by the standard machine learning losses, but are critical for decision making. A key challenge for direct integration of more meaningful domain and task-based evaluation criteria into an end-to-end gradient-based training process is the fact that often such performance objectives are not necessarily differentiable and may even require additional decision-making optimization processing. We propose the Task-Oriented Prediction Network (TOPNet), an end-to-end learning scheme that automatically integrates task-based evaluation criteria into the learning process via a learnable surrogate loss function, which directly guides the model towards the task-based goal. A major benefit of the proposed TOPNet learning scheme lies in its capability of automatically integrating non-differentiable evaluation criteria, which makes it particularly suitable for diversified and customized task-based evaluation criteria in real-world tasks. We validate the performance of TOPNet on two real-world financial prediction tasks, revenue surprise forecasting and credit risk modeling. The experimental results demonstrate that TOPNet significantly outperforms both traditional modeling with standard losses and modeling with hand-crafted heuristic differentiable surrogate losses.

0 citations0 reviewsNo code linkedOpen access