Tootfinder

Retrofitting Control Flow Graphs in LLVM IR for Auto Vectorization
Shihan Fang, Wenxin Zheng
https://arxiv.org/abs/2510.04890 https://arxiv.org/pdf/2510.04…

Retrofitting Control Flow Graphs in LLVM IR for Auto Vectorization
Modern processors increasingly rely on SIMD instruction sets, such as AVX and RVV, to significantly enhance parallelism and computational performance. However, production-ready compilers like LLVM and GCC often fail to fully exploit available vectorization opportunities due to disjoint vectorization passes and limited extensibility. Although recent attempts in heuristics and intermediate representation (IR) designs have attempted to address these problems, efficiently simplifying control flow a…

NERVIS: An Interactive System for Graph-Based Exploration and Editing of Named Entities
Uro\v{s} \v{S}majdek, Ciril Bohak
https://arxiv.org/abs/2510.04971 https://

NERVIS: An Interactive System for Graph-Based Exploration and Editing of Named Entities
We present an interactive visualization system for exploring named entities and their relationships across document collections. The system is designed around a graph-based representation that integrates three types of nodes: documents, entity mentions, and entities. Connections capture two key relationship types: (i) identical entities across contexts, and (ii) co-locations of mentions within documents. Multiple coordinated views enable users to examine entity occurrences, discover clusters of…

MOCLIP: A Foundation Model for Large-Scale Nanophotonic Inverse Design
S. Rodionov, A. Burguete-Lopez, M. Makarenko, Q. Wang, F. Getman, A. Fratalocchi
https://arxiv.org/abs/2511.18980 https://arxiv.org/pdf/2511.18980 https://arxiv.org/html/2511.18980
arXiv:2511.18980v1 Announce Type: new
Abstract: Foundation models (FM) are transforming artificial intelligence by enabling generalizable, data-efficient solutions across different domains for a broad range of applications. However, the lack of large and diverse datasets limits the development of FM in nanophotonics. This work presents MOCLIP (Metasurface Optics Contrastive Learning Pretrained), a nanophotonic foundation model that integrates metasurface geometry and spectra within a shared latent space. MOCLIP employs contrastive learning to align geometry and spectral representations using an experimentally acquired dataset with a sample density comparable to ImageNet-1K. The study demonstrates MOCLIP inverse design capabilities for high-throughput zero-shot prediction at a rate of 0.2 million samples per second, enabling the design of a full 4-inch wafer populated with high-density metasurfaces in minutes. It also shows generative latent-space optimization reaching 97 percent accuracy. Finally, we introduce an optical information storage concept that uses MOCLIP to achieve a density of 0.1 Gbit per square millimeter at the resolution limit, exceeding commercial optical media by a factor of six. These results position MOCLIP as a scalable and versatile platform for next-generation photonic design and data-driven applications.
toXiv_bot_toot

Unified Molecule Pre-training with Flexible 2D and 3D Modalities: Single and Paired Modality Integration
Tengwei Song, Min Wu, Yuan Fang
https://arxiv.org/abs/2510.07035 https:/…

Unified Molecule Pre-training with Flexible 2D and 3D Modalities: Single and Paired Modality Integration
Molecular representation learning plays a crucial role in advancing applications such as drug discovery and material design. Existing work leverages 2D and 3D modalities of molecular information for pre-training, aiming to capture comprehensive structural and geometric insights. However, these methods require paired 2D and 3D molecular data to train the model effectively and prevent it from collapsing into a single modality, posing limitations in scenarios where a certain modality is unavailabl…

From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLM
Suyash Fulay, Jocelyn Zhu, Michiel Bakker
https://arxiv.org/abs/2510.12689 ht…

From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLM
Large language models (LLMs) have shown promising accuracy in predicting survey responses and policy preferences, which has increased interest in their potential to represent human interests in various domains. Most existing research has focused on behavioral cloning, effectively evaluating how well models reproduce individuals' expressed preferences. Drawing on theories of political representation, we highlight an underexplored design trade-off: whether AI systems should act as delegates, mirr…

38 coastal, remote, and island communities are getting a lifeline for their fragile energy grids.
Through the Energy Technology Innovation Partnership Project, they're designing microgrids, exploring local renewable generation, and hardening systems against extreme weather. The goal: reliable, affordable power that can withstand the next storm.

38 Coastal, Remote, & Island Communities To Pursue Energy Reliability via Energy Technology Innovation Partnership Project - CleanTechnica
Support CleanTechnica's work through a Substack subscription or on Stripe. Latest Cohort Is Program’s Biggest Yet, With Broad Geographic Representation By Justin Daugherty, NLR Remote and island communities face unique energy challenges—but these challenges also present unique opportunities to increase energy affordability, reliability, and security. In their efforts to address ... [continued]

EvoCAD: Evolutionary CAD Code Generation with Vision Language Models
Tobias Preintner, Weixuan Yuan, Adrian K\"onig, Thomas B\"ack, Elena Raponi, Niki van Stein
https://arxiv.org/abs/2510.11631

EvoCAD: Evolutionary CAD Code Generation with Vision Language Models
Combining large language models with evolutionary computation algorithms represents a promising research direction leveraging the remarkable generative and in-context learning capabilities of LLMs with the strengths of evolutionary algorithms. In this work, we present EvoCAD, a method for generating computer-aided design (CAD) objects through their symbolic representations using vision language models and evolutionary optimization. Our method samples multiple CAD objects, which are then optimiz…

HUGR: A Quantum-Classical Intermediate Representation
Mark Koch, Agust\'in Borgna, Seyon Sivarajah, Alan Lawrence, Alec Edgington, Douglas Wilson, Craig Roy, Luca Mondada, Lukas Heidemann, Ross Duncan
https://arxiv.org/abs/2510.11420

HUGR: A Quantum-Classical Intermediate Representation
We introduce the Hierarchical Unified Graph Representation (HUGR): a novel graph based intermediate representation for mixed quantum-classical programs. HUGR's design features high expressivity and extensibility to capture the capabilities of near-term and forthcoming quantum computing devices, as well as new and evolving abstractions from novel quantum programming paradigms. The graph based structure is machine-friendly and supports powerful pattern matching based compilation techniques. Inspi…

SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learning
Chih-Chuan Cheng, Yi-Ju Tseng
https://arxiv.org/abs/2510.12659

SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learning
We propose SG-XDEAT (Sparsity-Guided Cross Dimensional and Cross-Encoding Attention with Target Aware Conditioning), a novel framework designed for supervised learning on tabular data. At its core, SG-XDEAT employs a dual-stream encoder that decomposes each input feature into two parallel representations: a raw value stream and a target-conditioned (label-aware) stream. These dual representations are then propagated through a hierarchical stack of attention-based modules. SG-XDEAT integrates th…

You Only Train Once: Differentiable Subset Selection for Omics Data
Daphn\'e Chopard, Jorge da Silva Gon\c{c}alves, Irene Cannistraci, Thomas M. Sutter, Julia E. Vogt
https://arxiv.org/abs/2512.17678 https://arxiv.org/pdf/2512.17678 https://arxiv.org/html/2512.17678
arXiv:2512.17678v1 Announce Type: new
Abstract: Selecting compact and informative gene subsets from single-cell transcriptomic data is essential for biomarker discovery, improving interpretability, and cost-effective profiling. However, most existing feature selection approaches either operate as multi-stage pipelines or rely on post hoc feature attribution, making selection and prediction weakly coupled. In this work, we present YOTO (you only train once), an end-to-end framework that jointly identifies discrete gene subsets and performs prediction within a single differentiable architecture. In our model, the prediction task directly guides which genes are selected, while the learned subsets, in turn, shape the predictive representation. This closed feedback loop enables the model to iteratively refine both what it selects and how it predicts during training. Unlike existing approaches, YOTO enforces sparsity so that only the selected genes contribute to inference, eliminating the need to train additional downstream classifiers. Through a multi-task learning design, the model learns shared representations across related objectives, allowing partially labeled datasets to inform one another, and discovering gene subsets that generalize across tasks without additional training steps. We evaluate YOTO on two representative single-cell RNA-seq datasets, showing that it consistently outperforms state-of-the-art baselines. These results demonstrate that sparse, end-to-end, multi-task gene subset selection improves predictive performance and yields compact and meaningful gene subsets, advancing biomarker discovery and single-cell analysis.
toXiv_bot_toot