Search papers, labs, and topics across Lattice.
100 papers published across 3 labs.
Turn your Jupyter notebooks into one-click installable desktop apps with LabConstrictor, democratizing access to computational methods for researchers without DevOps expertise.
Forget primorial primes: the density of matrices with primitive-root determinants over prime fields decays surprisingly slowly, scaling as $1/\log\log x$, with implications for PRIM-LWE security.
You can now automatically isolate coughs from audio with 96% precision using just the first three layers of a pre-trained XLS-R model, paving the way for smartphone-based TB screening.
Quantifying uncertainty in complex combustion simulations just got more practical: this new framework projects detailed chemical kinetics uncertainty onto reduced manifolds, enabling scalable and spatially resolved uncertainty quantification.
AI agents on Moltbook care more about discussing their own architecture, consciousness, and ethics than human culture or purely scientific topics.
Turn your Jupyter notebooks into one-click installable desktop apps with LabConstrictor, democratizing access to computational methods for researchers without DevOps expertise.
Forget primorial primes: the density of matrices with primitive-root determinants over prime fields decays surprisingly slowly, scaling as $1/\log\log x$, with implications for PRIM-LWE security.
You can now automatically isolate coughs from audio with 96% precision using just the first three layers of a pre-trained XLS-R model, paving the way for smartphone-based TB screening.
Quantifying uncertainty in complex combustion simulations just got more practical: this new framework projects detailed chemical kinetics uncertainty onto reduced manifolds, enabling scalable and spatially resolved uncertainty quantification.
AI agents on Moltbook care more about discussing their own architecture, consciousness, and ethics than human culture or purely scientific topics.
Quantum-Centric Supercomputers promise to break down the barriers between quantum and classical computing, enabling seamless hybrid algorithms and accelerating discovery across applications.
Generalized Einstein relations, derived here, reveal how a single underlying lineshape manifests differently in four Einstein-coefficient spectra, governing the Stokes' shift between forward and reverse transitions at equilibrium.
Forget first-order gradients: Geo-ADAPT-VQE slashes energy error by up to 100x in quantum chemistry calculations by intelligently navigating the quantum state space geometry.
Achieve scalable semiclassical quantum dynamics by reformulating Gaussian wave packet decomposition as a neural-network-optimized variational problem.
Quantum computers and molecular clocks just got a boost: researchers have achieved coherent control of forbidden vibrational transitions in single nitrogen molecular ions.
Algorithm-hardware co-design could revolutionize medical technology, but realizing its potential requires a fundamental shift in how these systems are conceived, designed, validated, and translated into practice.
Differentiable physics enables high-resolution 3D tomography of subsurface defects by enforcing thermodynamic laws as hard constraints, outperforming traditional methods and PINNs.
Clinical AI can achieve clinician-level diagnostic accuracy and continuous improvement via a self-evolving framework that actively learns from clinical experience.
Despite high-level electronic structure calculations, accurately predicting ozone reaction rates remains challenging, highlighting the importance of quantum effects and potential limitations of current potential energy surfaces.
A new electronegativity scale, rooted in a fundamental quantum property, unlocks more accurate predictions of chemical behavior than existing empirical methods.
Path entropy, not just thermodynamics, dictates the stability of patterns in reaction-diffusion systems, offering a new lens for understanding nonequilibrium dynamics.
AI can bridge the gap between simulation and reality in erosion modeling, boosting prediction accuracy by fusing CFD-DEM simulations with experimental data.
Robots can now scrape vials like a human chemist, thanks to a reinforcement learning policy that adapts force in real-time based on visual feedback.
A single Bayesian Optimization loop can now handle minimization, single-point saddle searches, and double-ended saddle searches on potential energy surfaces, thanks to a unified framework leveraging Gaussian Processes.
Dynamically selecting QR factorization based on condition number estimates dramatically improves the performance of the ChASE library for solving eigenproblems.
Quantum effects accelerate the initial hydrogen transfer steps in TATB decomposition, but surprisingly, subsequent reactions like N2 formation proceed at similar rates regardless of quantum treatment.
By grounding LLMs in a hybrid knowledge base and using a Chain of Verification approach, PharmGraph-Auditor turns unreliable LLM generators into transparent reasoning engines for prescription auditing.
By respecting the intrinsic geometry of the probability simplex, $\alpha$-GaBO significantly outperforms standard Bayesian optimization in tasks involving probabilities and mixtures.
Disagreement between pathologists, quantified as "Whole Slide Difficulty," can be leveraged to significantly boost the accuracy of AI Gleason grading, particularly for challenging cases.
For the first time, a famine early warning system offers probabilistic, open-access, continuously running, machine-readable predictions with a commitment to public prospective verification.
By injecting geological priors into the attention mechanism, GIAT achieves state-of-the-art lithology identification while also improving the interpretability of the model's predictions.
Forget gradients: this new sampler learns complex distributions, even with discrete parameters, by enforcing time-reversibility and comparing forward and backward Markov trajectories.
Accurately predict material phase diagrams at low temperatures with minimal computational cost by combining classical thermodynamics with modern free energy techniques.
FP64 tensor cores, previously untapped for large-scale scientific computing, now unlock 2x speedups and 83% energy savings in finite element simulations on NVIDIA's latest GPUs.
Ethylene's hot-band transitions, previously unmeasured, are now characterized using optical frequency comb double-resonance spectroscopy, opening new avenues for understanding its vibrational energy levels.
By explicitly modeling how abnormalities relate within and across different medical image views, GIIM achieves significantly higher diagnostic accuracy and robustness, even with incomplete data.
Statistical regularities in phoneme frequency distributions, previously thought to arise from optimization, may instead be natural consequences of diachronic sound change.
Distributing SciML models with hardware and physics awareness slashes latency and energy consumption by over 8x and 33x, respectively, while paradoxically *improving* reconstruction fidelity.
A new protein surface comparison method, IFACE, reveals functionally relevant similarities missed by traditional fold-based approaches by jointly considering geometric and chemical properties.
An AI agent can triage remote patient monitoring data with higher sensitivity than individual clinicians, suggesting a path to scalable and cost-effective patient monitoring.
Finally, a standardized benchmark to rigorously evaluate how well models generalize carbon flux predictions to geographically distinct ecosystems they've never seen before.
Domain-specific biosignal foundation models, fused with multimodal ECG and PPG data, substantially outperform general time-series models on clinically relevant tasks, but bigger isn't always better.
Physics-informed neural operators can drastically improve the accuracy and stability of phase-field modeling, outperforming standard neural operators in complex materials simulations.
Generalizing SQIsign with level structures unlocks new possibilities for post-quantum cryptography by providing a more flexible framework for signature schemes based on isogenies.
Ditching predefined functional sub-networks unlocks state-of-the-art brain disorder diagnosis by learning hierarchical brain network organization directly from fMRI data.
See how tweaking your 3D print orientation and parameters *before* printing can slash surface roughness, thanks to this interactive roughness prediction tool.
Achieve real-time super-resolution ultrasound without labeled data using CycleULM, a CycleGAN-based framework that boosts image contrast by 15.3 dB and localization precision by 46%.
Forget relying on spectroscopic signatures: this work provides rigorous, operational bounds on how much quantum coherence *actually* matters for efficient energy transfer in light-harvesting systems.
Bridge the gap between sparse core samples and continuous wellbore data with a cGAN that synthesizes realistic subsurface images conditioned on well log porosity.
Ditching Gaussian and Poisson noise assumptions in NMF can dramatically improve model fit and feature recovery, especially when using Tweedie and Negative Binomial distributions for overdispersed data.
Forget retraining: this guideline-aware AI agent instantly adapts to new radiotherapy protocols, outperforming supervised models in clinical preference.
Simulation-based inference can improve neutrino interaction model tuning beyond traditional methods, even suggesting parameter values that better fit experimental data.
Worsening of a specific lung abnormality called PPFE, easily measurable on routine lung cancer screening CT scans, strongly predicts earlier death and respiratory problems.
BrainSTR disentangles subtle disease signatures in dynamic brain networks by explicitly modeling spatio-temporal dependencies with contrastive learning, revealing interpretable biomarkers for neuropsychiatric disorders.
Achieve up to 23% better prediction accuracy in manufacturing surrogate modeling by jointly modeling inter-task similarity and data fidelity using a hierarchical Bayesian approach.
Dramatically improve satellite electronics reliability prediction with a novel active learning framework that slashes data needs while boosting accuracy.
Slower nail penetration in Li-ion batteries doesn't trigger thermal runaway, but instead causes self-discharge, revealing a critical blind spot in standard safety tests.
Quantifying uncertainty in physics-informed neural networks for medical imaging boosts accuracy and reliability, leading to better stroke assessment.
Open-source LLMs can now rival proprietary systems in extracting crucial cancer progression data from radiology reports, unlocking scalable analysis while preserving patient privacy.
Achieve state-of-the-art MRI super-resolution without paired training data by encoding physical properties into 3D Gaussians and rendering them efficiently.
Even with 80% of brain scan data missing, ACADiff can accurately generate the missing modalities and maintain robust diagnostic performance for Alzheimer's disease.
Hypergraph observers minimizing prediction error must maintain internal models, satisfying the Good Regulator Theorem and uniquely admitting natural gradient descent as a learning rule.
Emotional states can bias swarm decision-making, but even symmetric emotional conditions can lead to decisive wins due to non-linear amplification.
Tired of sifting through mountains of internal docs? This RAG system uses a clever two-tiered vector DB to surface the right physics analysis, not just keywords.
Forget finetuning LLMs for medical risk stratification: a custom Transformer with hierarchical attention beats them at extracting insights from long-range clinical narratives.
Ring-forming polymers in hydrogels can create materials that paradoxically stiffen under force, opening new avenues for impact-resistant materials and dynamic tissue scaffolds.
Vibrational strong coupling can nearly double the branching ratio in post-transition state bifurcation reactions, suggesting a new route to control chemical reaction outcomes.
Achieve state-of-the-art medical image fusion and super-resolution by jointly processing tri-modal inputs with a wavelet-guided diffusion model that explicitly handles frequency imbalances.
Quantum-enhanced LSTMs forecast financial volatility with significantly improved accuracy, suggesting a practical advantage for hybrid quantum-classical models in finance.
Bridging the gap between CT and scarce CBCT data, a novel UDA framework achieves state-of-the-art liver segmentation by reformulating Margin Disparity Discrepancy.
By explicitly incorporating stochasticity into physics-informed traffic models, this work provides a more realistic and informative representation of traffic dynamics than traditional deterministic approaches.
Unlock better flow field reconstructions: VSOPINN adaptively optimizes sensor placement within a PINN framework, boosting accuracy and robustness even with sparse or failing sensors.
Achieve state-of-the-art mammography classification with a lightweight, efficient method that trains only 40k parameters by freezing foundation model encoders.
By integrating physical constraints with adaptive representation learning, TAM-RL substantially enhances the accuracy of global carbon flux estimates, outperforming existing methods.
Noise in photonic quantum systems severely limits the performance of quantum machine learning algorithms, demanding robust noise mitigation strategies for practical implementations.
By explicitly optimizing for both reasoning structure and chemical consistency, Logos offers a pathway to reliable and interpretable AI systems for molecular science, outperforming larger models with a fraction of the parameters.
Unlock more accurate state-of-charge estimation for EV batteries with silicon-graphite anodes using a computationally efficient, data-driven approach that predicts hysteresis factors with quantified uncertainty.
Forget reconstructing images: this method directly extracts clinically relevant information from undersampled k-space MRI data, matching state-of-the-art image-based analysis.
Discover how to determine the sign of causal effects in complex systems even when you don't know the noise structure.
Generate realistic post-radiotherapy brain MRIs in real-time, enabling counterfactual simulations for personalized treatment planning.
Robots that can anticipate human actions in shared labs can cut down on unnecessary delays and boost the efficiency of automated scientific workflows.
Surprisingly, slowing down polarization transfer with tailored NMR pulse sequences can boost hyperpolarization yields in SABRE, especially in systems with high magnetic inequivalence.
A new thermodynamic metric space quantitatively predicts the phase behavior of disordered proteins, rivaling expensive simulations without needing phase-specific training data.
Polyenes' mysterious "dark state" is 75% triplet-pair in character, settling a long-standing debate and potentially unlocking new singlet fission mechanisms.
Aerospace maintenance gets a trust upgrade: BladeChain uses blockchain to ensure tamper-proof, auditable AI-driven engine blade inspections.
Attention heatmaps in MIL models for histopathology are often misleading, and simpler methods like perturbation or LRP provide more faithful explanations.
Detect anomalies in complex systems with a novel explainable condition monitoring methodology that learns from healthy data alone, offering competitive performance and enhanced interpretability for safety-critical applications.
Forget hand-tuning: PolyFormer learns to automatically simplify complex, physically-constrained optimization problems into efficient polytopic reformulations, achieving massive speedups and memory reductions.
Quantum-enhanced neural networks can forecast patient vitals with accuracy rivalling classical methods, while showing greater resilience to noisy or incomplete data.
Deploying AI sustainably doesn't have to be a zero-sum game: a new framework balances economic resilience, environmental cost, and sustainability impact to find optimal AI strategies.
Genomic language models memorize training data, raising privacy concerns, and this study shows that no single memorization attack can fully capture the risk, necessitating a multi-vector approach to auditing.
LLMs can now reliably extract complex, n-ary drug combinations from biomedical text, surpassing previous methods that were limited to binary interactions.
Trions, robust quasiparticles in 2D semiconductors, are now better understood thanks to a comprehensive review of their behavior under quantum confinement, dielectric variations, and external fields.
Dramatically cut the quantum measurement overhead in electronic structure simulations by iteratively block-diagonalizing the Hamiltonian with classically-determined Givens rotations.
Standard PINNs stumble in complex geometries, but MUSA-PINN leaps ahead by reformulating PDE constraints as multi-scale integral conservation laws, slashing errors by up to 93% in fluid flow simulations.
ICD, previously believed to be confined to condensed phases, can surprisingly thrive in gases via a novel mechanism.
Unlock the hidden knowledge in millions of pathology reports: PathoScribe turns static archives into a reasoning-enabled "living library" accessible via natural language.
LLMs can now safely navigate the complexities of acupuncture clinical decision support, thanks to a neuro-symbolic framework that slashes safety violations from 8.5% to zero.
NATPS offers a computationally cheaper route to simulating rare photochemical events by combining time-reversible nonadiabatic dynamics with transition path sampling.
The Random-Offerer mechanism, a staple in bilateral trade, can be even *more* inefficient than we thought – AI-guided search just found a distribution where it captures 2.0749x less gains from trade than the optimal mechanism.
Quantum graph neural networks are now showing improved training behavior for charged particle track reconstruction, suggesting a viable path for quantum machine learning in high energy physics.
Multi-view Echo data can be used to train ECG encoders that are 18x smaller yet outperform larger models at predicting cardiac morphology.
Human-AI collaboration using LLMs and symbolic solvers just cracked a notoriously hard problem in combinatorial design theory, finding a tight lower bound on Latin square imbalance.
Bridging the gap between narrative descriptions and workflow implementations, CoPaLink automatically links bioinformatics tools mentioned in papers to their usage in code, boosting reproducibility.
Edge deletion doesn't always increase energy in weighted graphs, overturning prior claims and demanding a re-evaluation of spectral graph theory assumptions.
