搜索结果：Odin

Text-attributed graphs require models to effectively combine strong textual understanding with structurally informed reasoning. Existing approaches either rely on GNNs--limited by over-smoothing and hop-dependent diffusion--or employ Transformers that overlook graph topology and treat nodes as isolated sequences. We propose Odin (Oriented Dual-module INtegration), a new architecture that injects graph structure into Transformers at selected depths through an oriented dual-module mechanism. Unlike message-passing GNNs, Odin does not rely on multi-hop diffusion; instead, multi-hop structures are integrated at specific Transformer layers, yielding low-, mid-, and high-level structural abstraction aligned with the model's semantic hierarchy. Because aggregation operates on the global [CLS] representation, Odin fundamentally avoids over-smoothing and decouples structural abstraction from neighborhood size or graph topology. We further establish that Odin's expressive power strictly contains that of both pure Transformers and GNNs. To make the design efficient in large-scale or low-resource settings, we introduce Light Odin, a lightweight variant that preserves the same layer-aligned str

NL2SQL (natural language to SQL) systems translate natural language into SQL queries, allowing users with no technical background to interact with databases and create tools like reports or visualizations. While recent advancements in large language models (LLMs) have significantly improved NL2SQL accuracy, schema ambiguity remains a major challenge in enterprise environments with complex schemas, where multiple tables and columns with semantically similar names often co-exist. To address schema ambiguity, we introduce ODIN, a NL2SQL recommendation engine. Instead of producing a single SQL query given a natural language question, ODIN generates a set of potential SQL queries by accounting for different interpretations of ambiguous schema components. ODIN dynamically adjusts the number of suggestions based on the level of ambiguity, and ODIN learns from user feedback to personalize future SQL query recommendations. Our evaluation shows that ODIN improves the likelihood of generating the correct SQL query by 1.5-2$\times$ compared to baselines.

We present Odin, the first production-deployed graph intelligence engine for autonomous discovery of meaningful patterns in knowledge graphs without prior specification. Unlike retrieval-based systems that answer predefined queries, Odin guides exploration through the COMPASS (Composite Oriented Multi-signal Path Assessment) score, a novel metric that combines (1) structural importance via Personalized PageRank, (2) semantic plausibility through Neural Probabilistic Logic Learning (NPLL) used as a discriminative filter rather than generative model, (3) temporal relevance with configurable decay, and (4) community-aware guidance through GNN-identified bridge entities and inter-community affinity scores. This multi-signal integration, particularly the bridge scoring mechanism, addresses the "echo chamber" problem where graph exploration becomes trapped in dense local communities. We formalize the autonomous discovery problem, prove theoretical properties of our scoring function, and demonstrate that beam search with multi-signal guidance achieves $O(b \cdot h)$ complexity while maintaining high recall compared to exhaustive exploration. To our knowledge, Odin represents the first aut

We investigated Lyman-continuum (LyC) emission from Lyman-$α$ emitters (LAEs) at $z=4.5$, identified in the One-hundred-deg$^2$ DECam Imaging in Narrowbands (ODIN) survey. Of the 7,498 LAEs (4,101 in COSMOS and 3,397 in XMM-LSS), we excluded LAEs that are either likely low-z objects or contaminated by neighboring sources. Additional background modeling process with thorough quality assessments leaves a final sample of 851 galaxies. We then performed forced photometry on $u/u^*$-band images from the CFHT large area $u$-band deep survey (CLAUDS) to measure their LyC fluxes. This represents the largest sample of $z=4.5$ LAEs searched for such a purpose. Within this sample, we identified 12 `gold' and 39 `silver' LyC-emitting candidates, with LyC fluxes detected of $>3σ$ and between $2σ$ and $3σ$, respectively, in the range of 5.16--55.29 nJy. No LyC signal is detected in the weighted mean stack of the final sample ($0.20 \pm 0.37$ nJy). Given the UVC magnitudes of LAEs in our sample, the expected LyC emission is likely below the detection limit even when stacking the full sample of ODIN LAEs. Nevertheless, having a large sample of LAEs remains valuable for identifying individual Ly

The Euler Characteristic Curve (ECC) records the Euler characteristic of a linearly embedded cell complex as a function of filtration height in a given direction, and the Euler Characteristic Transform (ECT) is the injective shape descriptor obtained by collecting ECCs over many directions. How the ECT is encoded for a neural network is itself an inductive bias, conventionally fixed by discretizing each ECC. We introduce a continuous encoding: for each direction and each vertex it records the net Euler-characteristic change attributed to that vertex, producing a per-direction token sequence that a small transformer maps to a feature vector. We separate the resulting pipeline into two stages on orthogonal axes: an ECC encoder that acts within each direction, mapping its curve to a fixed-length vector, and an ECT representation that acts across directions, aggregating the per-direction vectors into one. We study six ECT representation architectures spanning a range of inductive biases, from a structure-agnostic feedforward baseline to convolutional and complex-valued models that preserve equivariance under planar rotations. Across six classification benchmarks covering point clouds,

Ly$α$ blobs (LABs) are large, spatially extended Ly$α$-emitting objects whose nature remains unclear. Their statistical properties such as number densities and luminosity functions are still uncertain because of small sample sizes and large cosmic variance. The One-hundred-deg$^2$ DECam Imaging in Narrowbands (ODIN) survey, with its large volume, offers an opportunity to overcome these limitations. We describe our LAB selection method and present 112 new LABs in the 9 deg$^2$ E-COSMOS field. We begin with the conventional LAB selection approach, cross-matching LAEs with extended Ly$α$ sources, yielding 89 LAB candidates. To obtain a more complete LAB sample, we introduce a new selection pipeline that models all galaxies detected in deep broadband imaging, subtracts them from the narrowband image, and then directly detects extended Ly$α$ emission. This method successfully identifies 23 additional low-surface-brightness LABs which could otherwise be missed by the conventional method. The number density of ODIN LABs near an ODIN protocluster ($n=7.5\times10^{-5}$ cMpc$^{-3}$) is comparable to that found in the SSA22 proto-cluster and is four times higher than the average across the fi

Integration of CPU and GPU technologies is a key enabler for modern AI and graphics workloads, combining control-oriented processing with massive parallel compute capability. As systems evolve toward chiplet-based architectures, pre-silicon validation of tightly coupled CPU-GPU subsystems becomes increasingly challenging due to complex validation framework setup, large design scale, high concurrency, non-deterministic execution, and intricate protocol interactions at chiplet boundaries, often resulting in long integration cycles. This paper presents a replay-driven validation methodology developed during the integration of a CPU subsystem, multiple Xe GPU cores, and a configurable Network-on-Chip (NoC) within a foundational SoC building block targeting the ODIN integrated chiplet architecture. By leveraging deterministic waveform capture and replay across both simulation and emulation using a single design database, complex GPU workloads and protocol sequences can be reproduced reliably at the system level. This approach significantly accelerates debug, improves integration confidence, and enables end-to-end system boot and workload execution within a single quarter, demonstrating

Protoclusters represent sites of accelerated galaxy formation and extreme astrophysical activity characteristic of dense environments. Identifying massive protoclusters and mapping their spatial structures are therefore crucial first steps in understanding how the large-scale environment influences galaxy evolution. We combine wide-field Ly$α$ imaging from the ODIN survey with extensive DESI and ancillary spectroscopy across the extended COSMOS and XMM-LSS fields ($\approx$14 deg$^2$) to search for massive protoclusters. We confirm six systems at $z\approx 2.4$ and $z\approx 3.1$, reconstruct their three-dimensional structures, estimate descendant halo masses, and, for one structure at $z\approx 3.12$, demonstrate that overlapping narrowband filters ($NB497$ and $N501$) provide accurate redshift tomography for emission-line galaxies. One protocluster at $z\approx 2.45$ overlaps with one of the LATIS tomographic fields, enabling direct comparison between galaxy and H {\sc i} overdensities traced by Ly$α$ forest absorption. Another at $z\approx 3.12$ hosts a massive quiescent galaxy ($M_{\ast} \approx 1.2 \times 10^{11}M_\odot$), indicating early quenching in a dense environment. By

We analyze the rest-frame optical (~8000 Å) morphologies and star formation activity of Lyα emitters (LAEs) at redshifts $2.4$, $3.1$, and $4.5$, identified in the ODIN survey. To compare their physical properties with those of other galaxies, we construct a comparison sample of typical star-forming galaxies (SFGs) at similar redshifts from the COSMOS2025 catalog. Using the \textit{JWST}/NIRCam images from the COSMOS-Web survey, we measure the rest-frame optical sizes and Sérsic indices. We first examine their size-mass relations and find that LAEs at all three redshifts have smaller sizes than typical SFGs, with the size difference decreasing at higher redshifts. We also find that LAEs tend to have larger Sérsic indices at $z=2.4$ and $3.1$ than typical SFGs, but the difference becomes weaker at $z=4.5$. These trends are qualitatively reproduced in the Horizon Run 5 cosmological hydrodynamical simulation. We then investigate star formation activity and find that LAEs exhibit higher star formation rates than typical SFGs at all redshifts considered. Finally, we examine the connection between Lyα emission and galaxy structure, finding that the rest-frame equivalent width (REW) of th

We investigate if systems of multiple Lyman-alpha emitters (LAEs) can serve as a proxy for dark matter halo mass, assess how their radiative properties relate to the underlying halo conditions, and explore the physics of star formation activity in LAEs and its relation to possible physically related companions. We use data from the One-hundred-deg$^2$ DECam Imaging in Narrowbands (ODIN) survey, which targets LAEs in three narrow redshift slices. We identify physically associated LAE multiples in the COSMOS field at $z = 2.4$, $z = 3.1$, and $z=4.5$, and use a mock catalog from the IllustrisTNG100 simulation to assess the completeness and contamination affecting the resulting sample of LAE multiples. We then study their statistical and radiative properties as a function of multiplicity, where we adopt the term multiplicity to refer to the number of physically associated LAEs. We find a strong correlation between LAE multiplicity and host halo mass in the mocks, with higher multiplicity systems preferentially occupying more massive halos. In both ODIN and the mock sample, we find indications that the mean Ly$α$ luminosity and UV magnitude of LAEs in multiples increase with multiplici

In this work, we test the frequent assumption that Lyman Alpha Emitting galaxies (LAEs) are experiencing their first major burst of star formation at the time of observation. To this end, we identify 74 LAEs from the ODIN Survey with rest-UV-through-NIR photometry from UVCANDELS. For each LAE, we perform non-parametric star formation history (SFH) reconstruction using the Dense Basis Gaussian process-based method of spectral energy distribution fitting. We find that a strong majority (67%) of our LAE SFHs align with the frequently assumed archetype of a first major star formation burst, with at most modest star formation rates (SFRs) in the past. However, the rest of our LAE SFHs have significant amounts of star formation in the past, with 28% exhibiting earlier bursts of star formation with the ongoing burst having the highest SFR (dominant bursts), and the final 5% having experienced their highest SFR in the past (non-dominant bursts). Combining the SFHs indicating first and dominant bursts, ~95% of LAEs are experiencing their largest burst yet -- a formative burst. We also find that the fraction of total stellar mass created in the last 200 Myr is ~1.3 times higher in LAEs than

Network slicing plays a crucial role in realizing 5G/6G advances, enabling diverse Service Level Agreement (SLA) requirements related to latency, throughput, and reliability. Since network slices are deployed end-to-end (E2E), across multiple domains including access, transport, and core networks, it is essential to efficiently decompose an E2E SLA into domain-level targets, so that each domain can provision adequate resources for the slice. However, decomposing SLAs is highly challenging due to the heterogeneity of domains, dynamic network conditions, and the fact that the SLA orchestrator is oblivious to the domain's resource optimization. In this work, we propose Odin, a Bayesian Optimization-based solution that leverages each domain's online feedback for provably-efficient SLA decomposition. Through theoretical analyses and rigorous evaluations, we demonstrate that Odin's E2E orchestrator can achieve up to 45% performance improvement in SLA satisfaction when compared with baseline solutions whilst reducing overall resource costs even in the presence of noisy feedback from the individual domains.

The One-hundred-deg$^2$ DECam Imaging in Narrowbands (ODIN) survey is carrying out a systematic search for protoclusters during Cosmic Noon, using Ly$α$-emitting galaxies (LAEs) as tracers. Once completed, ODIN aims to identify hundreds of protoclusters at redshifts of 2.4, 3.1, and 4.5 across seven extragalactic fields, covering a total area of up to 91~deg$^2$. In this work, we report strong clustering of high-redshift protoclusters through the protocluster-LAE cross-correlation function measurements of 150 protocluster candidates at $z~=~2.4$ and 3.1, identified in two ODIN fields with a total area of 13.9 deg$^2$. At $z~=~2.4$ and 3.1, respectively, the inferred protocluster biases are $6.6^{+1.3}_{-1.1}$ and $6.1^{+1.3}_{-1.1}$, corresponding to mean halo masses of $\log \langle M /M_\odot\rangle = 13.53^{+0.21}_{-0.24}$ and $12.96^{+0.28}_{-0.33}$. By the present day, these protoclusters are expected to evolve into virialized galaxy clusters with a mean mass of $\sim$ $10^{14.5}~M_\odot$. By comparing the observed number density of protoclusters to that of halos with the measured clustering strength, we find that our sample is highly complete. Finally, the similar descendant

The ubiquity and relative ease of discovery make $2\lesssim z\lesssim 5$ Ly$α$ emitting galaxies (LAEs) ideal tracers for cosmology. In addition, because Ly$α$ is a resonance line, but frequently observed at large equivalent width, it is potentially a probe of galaxy evolution. The LAE Ly$α$ luminosity function (LF) is an essential measurement for making progress on both of these aspects. Although several studies have computed the LAE LF, very few have delved into how the function varies with environment. The large area and depth of the One-hundred-deg$^2$ DECam Imaging in Narrowbands (ODIN) survey makes such measurements possible at the cosmic noon redshifts of z~2.4, ~3.1, and ~4.5. In this initial work, we present algorithms to rigorously compute the LAE LF and test our methods on the ~16,000 ODIN LAEs found in the extended COSMOS field. Using these limited samples, we find slight evidence that protocluster environments either suppress the numbers of very faint and very bright LAEs or enhance medium-bright LAEs in comparison to the field. We also find that the LF decreases in number density and evolves towards a steeper faint-end slope over cosmic time from z~4.5 to z~2.4.

State-of-the-art models on contemporary 3D segmentation benchmarks like ScanNet consume and label dataset-provided 3D point clouds, obtained through post processing of sensed multiview RGB-D images. They are typically trained in-domain, forego large-scale 2D pre-training and outperform alternatives that featurize the posed RGB-D multiview images instead. The gap in performance between methods that consume posed images versus post-processed 3D point clouds has fueled the belief that 2D and 3D perception require distinct model architectures. In this paper, we challenge this view and propose ODIN (Omni-Dimensional INstance segmentation), a model that can segment and label both 2D RGB images and 3D point clouds, using a transformer architecture that alternates between 2D within-view and 3D cross-view information fusion. Our model differentiates 2D and 3D feature operations through the positional encodings of the tokens involved, which capture pixel coordinates for 2D patch tokens and 3D coordinates for 3D feature tokens. ODIN achieves state-of-the-art performance on ScanNet200, Matterport3D and AI2THOR 3D instance segmentation benchmarks, and competitive performance on ScanNet, S3DIS a

To understand the formation and evolution of massive cosmic structures, studying them at high redshift, in the epoch when they formed the majority of their mass is essential. The One-hundred-deg$^2$ DECam Imaging in Narrowbands (ODIN) survey is undertaking the widest-area narrowband program to date, to use Ly$α$-emitting galaxies (LAEs) to trace the large-scale structure (LSS) of the Universe on the scale of 10 - 100 cMpc at three cosmic epochs. In this work, we present results at $z$ = 3.1 based on early ODIN data in the COSMOS field. We identify and characterize protoclusters and cosmic filaments using multiple methods and discuss their strengths and weaknesses. We then compare our observations against the IllustrisTNG suite of cosmological hydrodynamical simulations. The two are in excellent agreement, with a similar number and angular size of structures identified above a specified density threshold. We are able to recover the simulated protoclusters with $\log$(M$_{z=0}$/$M_\odot$) $\gtrsim$ 14.4 in $\sim$ 60% of the cases. With these objects we show that the descendant masses of the protoclusters in our sample can be estimated purely based on our 2D measurements, finding a me

The opioid crisis has been one of the most critical society concerns in the United States. Although the medication assisted treatment (MAT) is recognized as the most effective treatment for opioid misuse and addiction, the various side effects can trigger opioid relapse. In addition to MAT, the dietary nutrition intervention has been demonstrated its importance in opioid misuse prevention and recovery. However, research on the alarming connections between dietary patterns and opioid misuse remain under-explored. In response to this gap, in this paper, we first establish a large-scale multifaceted dietary benchmark dataset related to opioid users at the first attempt and then develop a novel framework - i.e., namely Opioid Misuse Detection with Interpretable Dietary Patterns (Diet-ODIN) - to bridge heterogeneous graph (HG) and large language model (LLM) for the identification of users with opioid misuse and the interpretation of their associated dietary patterns. Specifically, in Diet-ODIN, we first construct an HG to comprehensively incorporate both dietary and health-related information, and then we devise a holistic graph learning framework with noise reduction to fully capitaliz

Across the life sciences, an ongoing effort over the last 50 years has made data and methods more reproducible and transparent. This openness has led to transformative insights and vastly accelerated scientific progress. For example, structural biology and genomics have undertaken systematic collection and publication of protein sequences and structures over the past half-century, and these data have led to scientific breakthroughs that were unthinkable when data collection first began. We believe that neuroscience is poised to follow the same path, and that principles of open data and open science will transform our understanding of the nervous system in ways that are impossible to predict at the moment. To this end, new social structures along with active and open scientific communities are essential to facilitate and expand the still limited adoption of open science practices in our field. Unified by shared values of openness, we set out to organize a symposium for Open Data in Neuroscience (ODIN) to strengthen our community and facilitate transformative neuroscience research at large. In this report, we share what we learned during this first ODIN event. We also lay out plans f

We study the problem of processing continuous k nearest neighbor (CkNN) queries over moving objects on road networks, which is an essential operation in a variety of applications. We are particularly concerned with scenarios where the object densities in different parts of the road network evolve over time as the objects move. Existing methods on CkNN query processing are ill-suited for such scenarios as they utilize index structures with fixed granularities and are thus unable to keep up with the evolving object densities. In this paper, we directly address this problem and propose an object density aware index structure called ODIN that is an elastic tree built on a hierarchical partitioning of the road network. It is equipped with the unique capability of dynamically folding/unfolding its nodes, thereby adapting to varying object densities. We further present the ODIN-KNN-Init and ODIN-KNN-Inc algorithms for the initial identification of the kNNs and the incremental update of query result as objects move. Thorough experiments on both real and synthetic datasets confirm the superiority of our proposal over several baseline methods.