arXiv:2607.01205v1 Announce Type: new Abstract: We present Linkify, a framework for learning from interface-augmented assembly graphs to enable context-aware part retrieval in mechanical assemblies. While recent generative AI methods for CAD have focused largely on isolated parts or monolithic assemblies, the rich geometric information at the interfaces between parts, where function is realized, remains underexplored. We address this gap by recomputing high-fidelity interface geometry for the Fusion 360 Gallery Assembly dataset, correcting missing and erroneous contacts, and generating point-cloud representations of local contact regions. Using this data, we construct assembly graphs whose nodes encode part geometry and whose edges encode interface geometry via a pretrained point-cloud encoder. On top of this representation, we train a Graph Attention Network based on GATv2 to solve a masked part prediction task: given an assembly with one part held out, the model predicts the class of the missing component from a large vocabulary of geometrically clustered parts, thereby approximating a realistic part-retrieval scenario. Compared to non-graph baselines such as logistic regression and k-nearest neighbors operating on aggregated node features, Linkify achieves higher Top-K accuracy and F1 scores. Ablation studies on graph connectivity, edge attributes, and attention mechanisms demonstrate that accurate contact computation and dynamic attention over interfaces are critical for performance. Our corrected interface dataset and training pipeline, released publicly, provide a foundation for future interface-aware models for assembly retrieval, validation, and generative design.
Science Journals
arXiv:2507.12415v2 Announce Type: replace Abstract: Code performance optimization is paramount in real-world software engineering and critical for production-level systems. While Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and bug fixing, their proficiency in enhancing code performance at the repository level remains largely unexplored. To address this gap, we introduce SWE-Perf, the first benchmark specifically designed to systematically evaluate LLMs on code performance optimization tasks within authentic repository contexts. SWE-Perf comprises 140 carefully curated instances, each derived from performance-improving pull requests from popular GitHub repositories. Each benchmark instance includes the relevant codebase, target functions, performance-related tests, expert-authored patches, and executable environments. Through a comprehensive evaluation of representative methods that span file-level and repo-level approaches (e.g., Agentless and OpenHands), we reveal a substantial capability gap between existing LLMs and expert-level optimization performance, highlighting critical research opportunities in this emerging field.
arXiv:2607.00293v1 Announce Type: new Abstract: Achieving true artificial general intelligence requires foundation models capable of integrating new modalities without forgetting prior knowledge. However, accommodating continuous generative objectives alongside discrete understanding tasks causes severe gradient conflicts. Existing architectures, including standard Mixture-of-Experts (MoE), are highly susceptible to representation overwriting. Even structurally partitioned paradigms like Mixture-of-Transformers (MoT) remain vulnerable to catastrophic forgetting, severely impeding multimodal scalability. In this work, we introduce Rosetta, a composable native multimodal pretraining framework designed for seamless and non-destructive modality expansion. Rosetta adopts a modular paradigm where core foundational knowledge is preserved within global shared experts, while modality-specific capabilities are distributed across plug-and-play experts. To guarantee non-destructive composition, we propose Momentum-Anchored Orthogonal Projection (MAOP). MAOP leverages the optimizer's momentum state as an implicit semantic anchor, selectively neutralizing conflicting gradient components from new modalities while preserving synergistic updates. Extensive evaluations demonstrate that, while standard MoE and MoT architectures suffer catastrophic forgetting of previously acquired knowledge, Rosetta robustly preserves established language and visual understanding. Furthermore, it delivers superior image generation and unlocks cross-modal synergy, paving the way for truly composable and unified multimodal foundation models. To facilitate further multimodal research, we release our code and checkpoints to the community. Project page at https://rosetta-lmm.github.io/.
arXiv:2607.01213v1 Announce Type: new Abstract: Open-source libraries and tools are widely reused, but compatibility maintenance is expensive. Once maintainers leave, useful repositories can stop working as runtimes and dependencies evolve. We study whether LLM agents can adapt old repositories to modern environments, a task we call compatibility rescue. Unlike bug repair, compatibility rescue starts from a repository that worked in its original environment but fails after ecosystem drift. RepoRescue gives agents only the repository and its failing modern environment; the agent must diagnose the failure, locate affected code, and produce a source-code rescue that restores the historical test suite. We build RepoRescue from 193 Python and 122 Java repositories, each verified to pass historically and fail after modernization. We evaluate five deployed agent systems on Python and three on Java. Beyond full-patch pass rate, we rerun patches after removing test-file edits to measure source-only repair, add a runtime-enforced regime that blocks test edits, and validate practical use for repositories whose suites pass after rescue. We find that Claude Code systems sometimes edit failing tests even when prompted not to; with runtime blocking, Kimi still rescues 41.5% of repositories. Systems are complementary: their union reaches 62.7%, exceeding the best single system by 10.9 points. Difficulty concentrates in cross-file coordination: on 14 repositories requiring coordinated whole-codebase changes, GPT-5.2 through Codex passes all 14, while every Claude Code system passes at most two. Finally, a passing suite is only an initial signal: among 34 unmaintained Python candidates whose suites pass after rescue, 22 work in realistic scenarios and 12 pass bug-hunt with patches that address the compatibility failure. RepoRescue benchmarks compatibility rescue with source-only auditing, runtime enforcement, practical validation, and reasoning labels.
arXiv:2607.00213v1 Announce Type: new Abstract: This paper introduces the Federated Sovereign Transport Protocol (FSTP), a synchronization boundary and transport layer for federated networks in which nodes have heterogeneous privacy requirements. Existing federation protocols leave data confinement to operator policy: they define message formats and delivery semantics but impose no structural constraint on what a conforming server may emit. FSTP addresses this gap by making data confinement a property of the protocol itself. The central mechanism is a synchronization agent whose output type set is formally closed. Raw internal data cannot appear in any federation message because the constraint is enforced by the Rust type system at compile time, not by a runtime check. A contextual identity model derives a separate, unlinkable identifier for each federation relationship, preventing cross-context correlation structurally. A Blocklace-based event substrate provides tamper-evident, partially ordered logging with synchronization cost proportional to the symmetric difference between node states, and supports data erasure without breaking the hash chain. The result is proof without exposure: a federation participant can verify that a process occurred, that a credential is authentic, and that an outcome is uncorrupted without accessing the internal data that produced these artifacts. FSTP is developed as the inter-node transport layer of Velyzor, a governance platform for institutions with demanding confidentiality requirements. The specification and reference implementation are released as open-source infrastructure under Apache 2.0; source code and figures accompany this paper.
arXiv:2607.01222v1 Announce Type: new Abstract: Recent 3D generative models can synthesize high-quality geometry but often struggle to reproduce intricate textures from reference images, largely due to the scarcity of large-scale 3D training data with rich surface appearance. In contrast, visual generative models are trained on datasets several orders of magnitude larger and excel at modeling complex visual patterns. Motivated by this gap, we introduce Ink3D, a framework that bridges 3D generation with large-scale video generative models to synthesize extremely complex textures. Ink3D first reconstructs a white-mesh geometry using an off-the-shelf 3D generation model. It then employs OrbitPainter, a conditional video generative model, to produce dense orbit-scan videos capturing object appearance across viewpoints. To convert these views into coherent textures, we introduce TextureOptimizer, a neural baking module that integrates dense multi-view observations while mitigating geometry inconsistencies arising from video generation. By decoupling geometry and texture synthesis and leveraging large-scale pretrained video priors, Ink3D enables significantly richer and more faithful texture generation than prior approaches.
arXiv:2607.00850v1 Announce Type: new Abstract: Most self-supervised learning (SSL) methods encourage invariance across augmentations, but strict flip invariance can suppress informative left--right correspondences in approximately bilateral data such as medical images and human faces. We propose Mirror-Fusion-Augmented Self-Supervised Learning (MFASSL), a Vision Transformer framework that injects a soft reflection prior into standard SSL without redesigning the backbone. MFASSL constructs mirror-paired views aligned to an estimated symmetry axis and introduces a lightweight Mirror-Fusion Attention (MFA) module for adaptive token-level interaction between mirrored regions while preserving asymmetric cues. The base SSL objective is further coupled with reflection-consistency and mid-layer token-alignment losses. Across CheXpert, BraTS, CelebA-HQ, and WFLW, MFASSL improves downstream performance, calibration, and reflection robustness over MoCo-v3, DINO, and MAE baselines under matched ViT-B/16 settings. It also achieves stronger and more consistent gains than recent equivariant SSL approaches with only approximately 2.7\% additional parameters. These results show that lightweight geometry-aware priors can effectively complement invariance-based SSL.
arXiv:2607.00908v1 Announce Type: new Abstract: Mixed-precision quantization (MPQ) has become a key technique for deploying large language models under stringent memory and compute constraints. We first identify a phenomenon that we term the Perplexity Illusion: layers ranked as important by perplexity-based sensitivity show little rank correlation with those that are most influential for complex reasoning performance, with Kendall $\tau \approx 0$ in our analysis. We further reveal an Alignment-Diversity Tradeoff: using only target-task calibration data can degrade post-quantization performance, whereas incorporating general-domain data stabilizes sensitivity estimation and improves robustness across tasks. Based on these observations, we propose TASA (Task-Aware Sensitivity Analysis), a two-level framework that jointly optimizes calibration-data composition and mixed-precision bit allocation. Specifically, TASA searches for a calibration-data mixture using a training-free gradient-trace alignment criterion, and then aggregates perplexity and reasoning-oriented sensitivity signals to guide both inter-layer and intra-layer bit allocation. Experiments on LLaMA-3-8B and Qwen2.5-7B reveal a precision inversion: appropriately allocated 3.5-bit models can match or surpass less task-aware 4-bit baselines. At an average precision of 3.5 bits, TASA matches or outperforms several competitive 4-bit uniform baselines in aggregate accuracy, and improves over the strongest W3 baseline on GSM8K by more than 20 absolute points on LLaMA-3-8B. These results show that calibration-data composition substantially affects task-sensitive quantization, a factor underexplored in prior work.
arXiv:2607.01234v1 Announce Type: new Abstract: In the last decade, Russia's strategic arsenal has pivoted towards a reliance on exotic nuclear-weapon delivery systems. One such system, the Burevestnik (NATO: 9M730) is claimed to be a nuclear-powered, nuclear-armed cruise missile capable of nearly indefinite flight. The air-breathing nuclear propulsion system used in this missile is unique, and its attributes are generally unfamiliar to both the aerospace and nuclear-security communities. To better understand the Burevestnik, and the potential of air-breathing nuclear propulsion systems generally, we have developed a nuclear-aircraft modeling toolkit capable of constraining the missile's performance characteristics. Using this framework, we conclude that the Burevestnik is a subsonic cruise missile system measuring $9.5 \pm 0.32$~m in length, with a $5.6 \pm 0.18$~m wingspan, likely powered by a direct-cycle nuclear turbojet (our calculations almost entirely exclude the possibility of a nuclear ramjet). Under these assumptions, our models predict a reactor thermal power of $4.3\pm 1.3$~MWth at cruise, with peak power demand during climb and terminal maneuvering exceeding $15$~MWth, which may be met with a supplemental chemical interburner. Monte Carlo simulations show that escaping neutrons will generate in excess of 5~TBq of gaseous radionuclides per MW-hr of flight, including isotopes such as $^{41}Ar$, $^{85m}Kr$, $^{83m}Kr$ and $^{14}C$, some of which may be detectable using existing monitoring networks.
arXiv:2607.00263v1 Announce Type: cross Abstract: The Chromatic Sum problem asks, given a graph $G$ and an integer $k$, whether $G$ admits a colouring $c$ with sum $\sum_{v\in V}c(v) \leq k$. We study the complexity of Chromatic Sum on graph classes defined by some set of forbidden graphs. First, we show that three known frameworks fully classify the complexity of Chromatic Sum on $HH$-minor-free graphs and $HH$-topological-minor-free graphs for any set of graphs $HH$, and on $HH$-subgraph-free graphs for any finite set of graphs $HH$. To show this, we prove a new NP-completeness result for Chromatic Sum on certain subdivisions of planar subcubic graphs. Next, we consider other containment relations. We formalise a novel framework of problems that are NP-complete for planar graphs as well as for graphs of bounded independence number. For every problem in this framework, we obtain an almost complete complexity classification on $H$-induced-minor-free graphs, $H$-induced-topological-minor-free graphs, and $H$-free graphs for every graph $H$. We show that Chromatic Sum belongs to this framework, as do several other problems. We also define a more fine-grained framework for the induced subgraph relation. We apply this to obtain a complete complexity classification for Chromatic Sum on $H$-free graphs, as well as for several other problems. We justify the choice of this framework by proving that Chromatic Sum is NP-complete for graphs of clique-width at most $3$. This result complements a known polynomial-time result for graphs of clique-width at most $2$.
arXiv:2607.00956v1 Announce Type: new Abstract: Time-series models are often evaluated by what they can forecast or classify, but those scores do not show whether their representations preserve the process state a user may want to inspect: event timing, phase, amplitude, frequency, or regime variables. We introduce Aionoscope, a generator-based diagnostic tool for debugging latent-state accessibility in frozen time-series representations. Aionoscope separates process generation from observation rendering, producing seeded synthetic streams with exact categorical and dense labels across mixture complexity and nuisance variation. We instantiate Aionoscope as Primitive Process Mixtures and evaluate 37 model-plus-adapter systems with a common pooled linear-probe protocol. The main result is a mismatch between coarse and fine-grained accessibility. Most systems make component presence easy to recover, but expose dense process state much less reliably: the highest observed dense-probe row reaches 0.689 mean masked $R^2$, while a dense-feature oracle reaches 0.999. This is the failure mode Aionoscope is designed to surface: a representation can look informative at the level of "what kind of signal is present" while hiding the timing, phase, amplitude, frequency, or regime variables needed for debugging.
arXiv:2604.18483v2 Announce Type: replace Abstract: We present a boundary integral formulation for steadily propagating semi-infinite plane strain tensile and shear fractures in poroelastic media. By combining fundamental solutions of plane strain poroelasticity for an instantaneous fluid source and instantaneous edge dislocations (normal and slip modes) with temporal and spatial superposition principles, we derive boundary integral equations for steadily moving fractures under the adopted hydraulic boundary conditions. These equations relate the tractions (normal and shear stresses) and the pore fluid pressure on the fracture surfaces to the fracture opening, slip, and the fluid displacement function. Assuming prescribed traction and pore fluid pressure profiles, we develop a numerical methodology to solve the governing equations for fracture opening, slip, and the fluid displacement function. The formulation is systematically verified on several relevant problems, including a tensile fracture with exponential normal loading, a stress-free tensile fracture with an imposed exponential pore fluid pressure, and a shear fracture under uniform shear loading over a finite region, demonstrating excellent agreement with analytical and semi-analytical solutions. The resulting boundary integral framework provides an accurate and efficient tool for analyzing semi-infinite steadily propagating cracks in permeable poroelastic media. By supplementing the formulation with appropriate closure relations and additional physics, such as lubrication flow in hydraulic fractures or frictional strength evolution in shear fractures, it can be used to investigate a broad range of coupled fracture-fluid problems. The approach may also be adapted to other classes of elasto-diffusive problems by modifying the underlying physical parameters.
arXiv:2607.01001v1 Announce Type: new Abstract: Radiomics is the established approach for CT-based lung cancer phenotyping, yet comparisons with foundation models rarely isolate contributions of feature extractor, classification head, and segmentation choice, or test cross-cohort robustness. We benchmark five feature extractors (Curia, Curia-2, DINOv3, Radiomics2D, Radiomics3D), seven classification heads (TabPFN, TabICL, XGBoost, CatBoost, Random Forest, logistic regression, Ridge), and three segmentation regimes on five tasks: tumor volume and stage classification, 2-year survival prediction, histology classification, and age prediction. Models are trained on LUNG1 (n=338) and evaluated on an internal test set (n=84) and the external LUNG2 cohort (n=211), with worst-case cross-cohort performance as the primary metric. The dominant design factor is task-dependent: segmentation drives volume and stage classification, while classifier choice drives survival, histology, and age prediction. Radiomics is competitive for tumor volume, tumor stage and survival (partly due to label-derivation effects for the former); Curia variants reach comparable peak scores for survival; DINOv3 falls slightly short across tasks. Patch and slice aggregation have negligible impact. We recommend Curia with tumor segmentation and a CatBoost head as a safe default, achieving the best mean rank across the three primary clinical tasks, though task-specific selection consistently outperforms any cross-task default. When tumor delineations are unavailable, Curia-2 with lung segmentation and logistic regression offers a competitive alternative. All pipelines use a two-stage design suited to small cohort sizes where end-to-end fine-tuning would risk overfitting.
arXiv:2607.01002v1 Announce Type: new Abstract: In long-context use, large language models frequently synthesize answers from the meaning of a relevant context span rather than literally copy-pasting them. Identifying which attention heads perform this synthesis matters for interpreting long-context model behavior. Yet existing detectors miss these heads by construction: they reward heads whose attended token matches the generated token, a literal-copy criterion that captures where a head reads but not what it writes through its output-value (OV) circuit, the very mechanism that carries non-literal retrieval. We introduce Logit-Contribution Scoring (LOCOS), a write-aware detector that scores each head by the projection of its OV-circuit output onto the answer-token unembedding direction, contrasting needle and off-needle source positions in a single forward pass. Across three model families (Qwen3, Gemma-3, OLMo-3.1), mean-ablating the top LOCOS heads on the NoLiMa non-literal retrieval benchmark collapses ROUGE-L at lower head counts than prior attention-based detections; on Qwen3-8B, ablating 50 heads drives ROUGE-L from 0.401 to 0.000 while the strongest baseline still retains 0.292. The selected heads are retrieval-specific: parametric recall and arithmetic reasoning stay at baseline under the same ablation. On Qwen3-8B, the same ablation also drops MuSiQue from 0.55 to 0.08 and BABI-Long from 0.62 to 0.20, while a random-heads control stays within 0.05 of baseline.
arXiv:2507.10540v3 Announce Type: replace Abstract: The rapid advancement of large language models (LLMs) has created a diverse landscape of models, each excelling at different tasks. This diversity drives researchers to employ multiple LLMs in practice, leaving behind valuable multi-LLM log data. This naturally leads to the question of whether such logs can be fully leveraged to fuse LLMs' complementary capabilities. Although prior work has explored various strategies for integrating multiple LLMs, we argue that practical fusion must meet two essential requirements: (1) compatibility with real-world serving scenarios (e.g., local and API-based serving), and (2) flexibility to operate at different stages of the LLM pipeline to meet varied user needs (e.g., fine-tuning and inference stages). To this end, we introduce LLMFusionBench, a large-scale benchmark for LLM fusion that spans 14 tasks across five domains, with responses from 20 open-source LLMs (8B--671B) totaling 103M tokens. Building on LLMFusionBench, we propose FusionFactory, a systematic framework with three elaborated levels: (1) query-level fusion via tailored LLM routers, (2) thought-level fusion leveraging retrieved abstract reasoning templates, and (3) model-level fusion via distillation from top-ranked responses. Experiments show that FusionFactory consistently outperforms the best individual LLM across all 14 benchmarks, with the optimal fusion configuration varying across benchmarks, highlighting the promise of multi-LLM log data as a practical foundation for fusing diverse LLM capabilities.
arXiv:2508.02167v3 Announce Type: replace Abstract: Coarse Grained Reconfigurable Arrays (CGRAs) present both high flexibility and efficiency, making them well-suited for the acceleration of intensive workloads. Nevertheless, a key barrier towards their widespread adoption is posed by CGRA compilation, which must cope with a multi-dimensional space spanning both the spatial and the temporal domains. Indeed, state-of-the-art compilers are limited in scope as they mostly deal with the data flow of applications, while having little or no support for control flow. Hence, they mostly target the mapping of single loops and/or delegate the management of control flow divergences to ad-hoc hardware units. Conversely, in this paper we show that control flow can be effectively managed and optimized at the compilation level, allowing for a broad set of applications to be targeted while being hardware-agnostic and achieving high performance. We embody our methodology in a modular compilation framework consisting of transformation and optimization passes, enabling support for applications with arbitrary control flows running on abstract CGRA meshes. We also introduce a novel mapping methodology that acts as a compilation back-end, addressing the limitations in available CGRA hardware resources and guaranteeing a feasible solution in the compilation process. Our framework achieves up to 2.1X speedups over state-of-the-art approaches, purely through compilation optimizations.
arXiv:2509.06679v3 Announce Type: replace Abstract: Time has entered the domain of topological phases in the field of non-Hermitian physics. Previous studies have relied on periodic modulation in time to make an intuitive connection to established spatial topological invariants, albeit with energy and momentum exchanged. This connection has revealed the potential for topological interface states along the time axis, analogous to those in spatial models. In this work, we uncover a theoretical framework describing such topological interface states along the time axis, with no underlying connection to spatial models nor need for periodic driving. This new framework uncovers that this phenomenon -- the robust localisation of waves at an interface -- appears in every system that has parity-time symmetry and two coupled modes or bands, regardless of its spatial dimensionality. The topological nature of this localisation is understood by the identification of certain topological phases that are specific to parity-time-symmetric models of two coupled modes. Our theoretical framework can be applied to all existing experimental observations, notably including photonic time crystals, and serves as a foundation for future experiments in areas in which the topological localisation of waves in time has yet to be studied.
arXiv:2509.17314v4 Announce Type: replace Abstract: Software increasingly relies on the emergent capabilities of Large Language Models (LLMs), from natural language understanding to program analysis and generation. Yet testing them on specific tasks remains difficult and costly: many prompts lack ground truths, forcing reliance on human judgments, while existing test adequacy measures typically rely on output uncertainty and thus are only available after full inference. A key challenge is to assess how useful a test input is in a way that reflects the demands of the task, ideally before even generating any output. We introduce Clotho, a task-specific, pre-generation test adequacy measure that estimates input difficulty directly from LLM hidden states. Given a large pool of unlabelled inputs for a specific task, Clotho uses a Gaussian Mixture Model (GMM) to adaptively sample the most informative cases for human labelling. Based on this reference set the GMM can then rank unseen inputs by their likelihood of failure. In our empirical evaluation across eight benchmark tasks and three open-weight LLMs, Clotho can predict failures with a ROC-AUC of 0.716, after labelling reference sets that are on average only 5.4% of inputs. It does so without generating any outputs, thereby significantly reducing LLM execution costs compared to output-based uncertainty or confidence measures. Comparison of Clotho and these post-generation adequacy measures shows that the two approaches complement each other. Crucially, we show that adequacy scores learnt from open-weight LLMs transfer effectively to proprietary models, extending the applicability of the approach. When prioritising test inputs for proprietary models, Clotho increases the average number of failing inputs from 18.7 to 42.5 out of 100, compared to random prioritisation.
arXiv:2606.03137v2 Announce Type: replace Abstract: LLM-based multi-agent simulation offers a promising way to study social interaction, deliberation, and collective opinion dynamics. However, many existing dialogue simulation frameworks represent interaction mainly as observable turn exchange or aggregated outputs, leaving the internal evaluative processes behind silence, speaking intention, and public expression difficult to examine. We introduce TBS (Think-Before-Speak), an interval-based multi-agent simulation framework that separates agents' private reasoning from public utterance generation. At each interval, all agents update structured internal states based on the shared dialogue history and their own memory. These states include dissonance-related appraisal, perceived opinion climate, perceived isolation risk, response strategy, and willingness to speak. The orchestrator then resolves competing speaking intentions and commits one utterance to the public dialogue, allowing internal evaluation and public interaction to co-evolve over time. We evaluate TBS in simulated town hall discussions on a climate-related policy issue. Results show that TBS produces coherent internal-state traces and that these traces vary systematically across turn-allocation, silence, and memory conditions. Dissonance-related appraisal increases agents' willingness to speak, whereas silence-pressure appraisal decreases it. Once speaking intention is formed, public expression is shaped mainly by turn-allocation rules. These findings suggest that TBS supports mechanism-sensitive social simulation by making the pathway from internal evaluation to public expression observable and analyzable.
arXiv:2607.00191v1 Announce Type: new Abstract: Collaborative-perception enables multi-robot systems to enhance situational awareness by sharing perceptual information. Existing collaborative-perception systems face an inherent trade-off between communication bandwidth requirements and perception accuracy, where methods that exchange more information achieve better perception results at the cost of increased communication overhead. However, real-world communication networks impose bandwidth constraints that require minimizing communication overhead without sacrificing perception performance. To address this challenge, we propose HydraCollab, an adaptive collaborative-perception framework that (i) selectively transmits the most informative sensor features and (ii) dynamically employs collaboration strategies (intermediate or late) based on spatial confidence maps. Extensive evaluations on the V2X-R, V2X-Radar and UAV3D-mini datasets demonstrate that HydraCollab achieves the best overall trade-off between accuracy and communication cost among existing collaborative-perception methods. Relative to SOTA Where2comm, HydraCollab uses only 41% of the bandwidth on V2X-R and 26% on V2X-Radar while improving performance by 0.78% and 0.75% respectively. Our code and models are available at https://github.com/AICPS/HydraCollab.
arXiv:2607.00581v1 Announce Type: new Abstract: Sparse tangent portfolio optimization aims to learn an interpretable, low-cardinality portfolio in the tangency direction of the mean-variance frontier. However, the associated cardinality-constrained formulation is NP-hard, and standard predict-then-optimize pipelines often misalign forecasting accuracy with downstream portfolio quality. We propose an end-to-end decision-focused learning framework that reformulates Sharpe ratio maximization as a Disciplined Parametrized Programming (DPP)-compliant convex programming layer and replaces discrete selection with a smooth top-$k$ operator enforcing an exact cardinality $k$. This enables gradient flow through prediction, asset selection, and re-optimization, allowing the predictive model to directly optimize portfolio performance. Across four major equity markets, our method achieves competitive and often superior out-of-sample Sharpe ratios compared with historical and prediction-focused baselines, with particularly strong gains in larger asset universes. Our \href{https://github.com/feuerwerksh/Diffble-card-SR}{code} is publicly available.
arXiv:2606.27525v2 Announce Type: cross Abstract: The 2024 Department of Justice antitrust complaint against RealPage, Inc. named five major residential REITs for coordinating algorithmic rent pricing across hundreds of thousands of apartment units in major US metropolitan areas. This paper studies whether census-tract-level corporate landlord concentration (CLC), measured from SEC EDGAR 10-K property filings geocoded to census tracts, the first such application in the literature, is associated with rent growth 2019-2023, and whether that association is larger in majority-minority neighborhoods. Rent outcomes are measured using the Zillow Observed Rent Index (ZORI). To account for the possibility that corporate landlords preferentially locate in neighborhoods already seeing rent appreciation, all regressions control for a fully novel Algorithmic Housing Burden Index (AHBI), a composite of pre-existing rent burden and market tightness from ACS data. Across 665 census tracts in ten US metropolitan areas, doubling REIT concentration is associated with 2.8 percentage points higher rent growth (p = 0.086, p = 0.030, HC1 robust). This association is significantly stronger in majority-minority tracts. Within the same metro, high-CLC majority-minority tracts are associated with 5.9 percentage points higher rent growth than comparable white tracts (p = 0.039). An XGBoost model predicts 44 percent of out-of-sample rent growth variance, with SHAP analysis independently confirming that CLC's contribution is positive in minority tracts and negative in white tracts. Taken all together, these findings provide the first tract-level evidence consistent with corporate landlord concentration being associated with disproportionately higher rent growth in communities of color.
arXiv:2510.24186v2 Announce Type: replace Abstract: Molecular docking is a cornerstone of drug discovery for unveiling the mechanism of ligand-receptor interactions. With the recent advances of deep learning (DL), AI-powered molecular docking methods have achieved higher accuracy for binding pose prediction and virtual screening compared with classical physics-based methods. However, there is still a scarcity of approaches to strike a balance among accuracy, computational efficiency, and rigorous physical validity of the output conformations. In the previous two versions of DSDP, we demonstrated the effectiveness of guiding conformation sampling with the gradient of an analytic scoring function. As the third version, TRIDS was devised as an AI-native docking framework that expand the similar strategy to unify conformation sampling and docking processes with DL-based model for improving accuracy of docking and screening. Furthermore, it is tailored for seamless cooperation of AI and physics to guarantee the physical validity of predicted binding poses. Being user-friendly, TRIDS predicts the binding site, parses multiple file formats, and supports Python programming and PyMOL graphical interaction. It improves docking accuracy and passes physical validation with high computational efficiency, i.e. a single docking task is done in a fraction of second while maintaining a highly lightweight GPU memory footprint of merely hundreds of megabytes, facilitating high-throughput virtual screening in reality. As a proof of concept, TRIDS allowed us to obtain hit compounds with novel scaffolds for tumor necrosis factor-alpha (TNF{\alpha}) inhibitor through a large-scale virtual screening.
arXiv:2607.00470v1 Announce Type: cross Abstract: We investigate a forecasting framework based on a simple discrete-time dynamic model with coefficients varying in time. The parameters of the model are recovered within a deep learning framework, which makes it possible to retain a transparent parametric structure while simultaneously accounting for complex and nonstationary patterns in the observed phenomenon. Our analysis covers two specifications of the noise process. Besides the standard Gaussian setting, we also consider Laplace-distributed noise, which can offer a more adequate description in the presence of heavier tails and sharper local fluctuations. For both cases, we formulate the predictive scheme of the model and analyze the associated uncertainty quantification, including the construction of prediction intervals. The results illustrate that a relatively simple model, when combined with time-dependent parameter estimation, can serve as a mathematically tractable and practically flexible tool for forecasting complex dynamics under different noise assumptions. The general model is stated for TVAR($p$), while the prediction-interval formulas and the numerical experiments are developed for the TVAR(1) case.
arXiv:2511.13460v2 Announce Type: replace Abstract: Statistical model checking delivers quantitative verification results with statistical guarantees. It scales to model sizes and model types that are out of reach for exhaustive, analytical techniques. So far, it has been used to evaluate one property value at a time only. Many practical problems, however, require finding the Pareto front of optimal tradeoffs between multiple objectives. In this paper, we present the first statistical model checking approach for such multi-objective Pareto queries, based on lightweight strategy sampling. We introduce an incremental scheme that almost surely converges to a statistically sound confidence band around the true Pareto front in the long run. To obtain a close underapproximation of the true front in finite time, we propose three heuristic approaches that try to make the best of an a-priori fixed sampling budget. We implement our new techniques in the modes simulator of the Modest Toolset, and show their effectiveness on benchmarks from the literature.