Link sign prediction in signed bipartite graphs, which are extensively utilized across diverse domains such as social networks and recommendation systems, has recently emerged as a pivotal challenge. However, significant space and time complexities associated with the scalability of bipartite graphs pose substantial challenges, particularly in large-scale environments. To address these issues, this paper introduces the SignFlow Bipartite Subgraph Network (SBSN), balancing sublinear training memory growth through a heuristic subgraph extraction method integrated with a novel message passing module, with optimal inference efficiency achieved via the node feature distillation module. Our subgraph sampling approach reduces the graph size by focusing on neighborhoods around target links and employs an optimized directed message passing mechanism to aggregate critical structural patterns. This mechanism allows SBSN to efficiently learn rich local structural patterns essential for accurate sign prediction. Furthermore, to overcome the inefficiency of subgraph sampling-based models during inference, SBSN incorporates a node feature distillation module after the first training stage.

Recently, Graph Neural Controlled Differential Equations (Graph Neural CDEs) successfully adapted Neural CDEs from paths on Euclidean domains to paths on graph domains. Building on this foundation, we introduce Permutation Equivariant Neural Graph CDEs, which project Graph Neural CDEs onto permutation equivariant function spaces. This significantly reduces the model's parameter count without compromising representational power, resulting in more efficient training and improved generalisation. We empirically demonstrate the advantages of our approach through experiments on simulated dynamical systems and real-world tasks, showing improved performance in both interpolation and extrapolation scenarios.

This paper presents PartCAD, a novel framework for reconstructing CAD modeling sequences directly from point clouds by projection-guided, part-aware geometry reasoning.

Data errors, corruptions, and poisoning attacks during training pose a major threat to the reliability of modern AI systems. While extensive effort has gone into empirical mitigations, the evolving nature of attacks and the complexity of data require a more principled, provable approach to robustly learn on such data--and to understand how perturbations influence the final model. Hence, we introduce MIBPCert, a novel certification method based on mixed-integer bilinear programming (MIBP) that computes sound, deterministic bounds to provide provable robustness even under complex threat models. By computing the set of parameters reachable through perturbed or manipulated data, we can predict all possible outcomes and guarantee robustness. To make solving this optimization problem tractable, we propose a novel relaxation scheme that bounds each training step without sacrificing soundness. We demonstrate the applicability of our approach to continuous and discrete data, as well as different threat models--including complex ones that were previously out of reach.

Human ability estimation is essential for educational assessment, career advancement, and professional certification. Adaptive Testing systems can improve estimation efficiency by selecting fewer, targeted questions, and are widely used in exams, e.g., GRE, GMAT, and Duolingo English Test. However, selecting an optimal subset of questions remains a challenging nested optimization problem. Existing methods rely on costly approximations or data-intensive training, making them unsuitable for today's large-scale and complex testing environments. Thus, we propose a Closed-Form solution for question subset selection in Adaptive Testing. It directly minimizes ability estimation error by reducing ability parameter's gradient bias while maintaining Hessian stability, which enables a simple greedy algorithm for question selection. Moreover, it can quantify the impact of human behavioral perturbations on ability estimation. Extensive experiments on large-scale educational datasets demonstrate that it reduces the number of required questions by 10% compared to SOTA methods, while maintaining the same estimation accuracy.

Most multimodal models treat every negative pair alike, ignoring the ambiguous negatives that differ from the positive by only a small detail. We propose BoundaryA ware Curriculum with Local Attention(BACL), a lightweight add-on that turns these borderline cases into a curriculum signal. ABoundary-aware Negative Sampler gradually raises difficulty, while a Contrastive Local Attention loss highlights where the mismatch occurs. The two modules are fully differentiable and work with any off-the-shelf dual encoder. Theory predicts a fast O(1/n) error rate; practice shows up to +32 % R@1 over CLIP and new SOTA on four large-scale benchmarks, all without extra labels.

Terrifying stomach cancer explosion sweeps the US: After fitness influencer's shock death, experts reveal subtle early signs that are too often ignored... and lifestyle tweaks that can PREVENT it Actress, 43, announces she is expecting with sweet video after detailing'complicated' journey to motherhood and hope of having third child Trump foe Rosie O'Donnell to replace Jimmy Kimmel as he steps back from his show Deadly secrets of gorgeous California enclave where college girls were killed by a'sneaker'... now experts say they could have been SAVED The other women left devastated by Jelly Roll's divorce: Why his daughter is now'disgusted'... as Bunnie's baby bombshell rocks Nashville The shaming of America's original mommy influencer after tragedy that divided the nation: Bode Miller's wife Morgan breaks cover to reveal agonizing regret that still haunts her since daughter's drowning Trump boasts there's'no limits' to his power and posts bizarre memo by fake historian comparing him to Hitler More young Americans are living with their parents than ever before... and there is a shocking reason behind the boomerang trend I was mortified when my husband always said no to sex. Then I realised the mistake I was making. This is the change that's completely transformed marital love-making in middle age: ALICE SNAPE Revealed: Hero, 24, who saved man's LIFE in dramatic rescue during New York Knicks victory parade after defying cops' orders: 'I'm just another New Yorker' REVEALED: Gavin Newsom steered millions of dollars of donations to nonprofits connected to his wife... as Trump's DOJ probes couple The shingles vaccine could lower dementia risk'by up to a quarter' - but scientists are still puzzled why Farce of Obama's $850m'monstrosity': As clucking liberal elite cheer Barack's grand opening, outraged Chicago locals tell HARRIET ALEXANDER awkward truth about library Why turnips MUST be in your grocery cart if you're trying to lose weight Taco Bell's finally fixes a glaring menu gap - and brings back a fan favorite after years Mom thought popular'natural' health supplement was safer than Xanax. She took it... then never woke up. Don't make the same mistake Mother and child in critical condition after being swallowed into ocean by ANOTHER monstrous California wave... just days after college students were killed by breaker'I was taken from school and trained to fly UFOs with my mind,' claims child genius A former gifted child has come forward with claims that he was removed from public school and secretly trained to develop psychic abilities for military and UFO-related applications.

Is the war entering a new phase? Russia has renewed its strikes on Ukraine, killing three people including an eight-year-old girl, Ukrainian officials said. The Russian strikes on Friday come a day after Ukraine launched its biggest-ever drone attack on Moscow, killing a different eight-year-old girl and sparking an inferno at a major oil refinery, according to Russian officials. Between late Thursday and early Friday, Russia launched 90 drones at Ukraine, according to the Ukrainian air force. "An eight-year-old girl was killed. These are the consequences of this morning's enemy attack on Pavlohrad," Oleksandr Ganzha, the governor of Ukraine's central Dnipropetrovsk region, said.

Generalized policy and execution efficiency constitute the two critical challenges in robotic manipulation. While recent foundation policies benefit from the commonsense reasoning capabilities of internet-scale pretrained vision-language models (VLMs), they often suffer from low execution frequency. To mitigate this dilemma, dual-system approaches have been proposed to leverage a VLM-based System 2 module for handling high-level decision-making, and a separate System 1 action module for ensuring real-time control. However, existing designs maintain both systems as separate models, limiting System 1 from fully leveraging the rich pretrained knowledge from the VLM-based System 2. In this work, we propose Fast-in-Slow (FiS), a unified dual-system vision-language-action (VLA) model that embeds the System 1 execution module within the VLM-based System 2 by partially sharing parameters. This innovative paradigm not only enables high-frequency execution in System 1, but also facilitates coordination between multimodal reasoning and execution components within a single foundation model of System 2. Given their fundamentally distinct roles within FiS-VLA, we design the two systems to incorporate heterogeneous modality inputs alongside asynchronous operating frequencies, enabling both fast and precise manipulation. To enable coordination between the two systems, a dual-aware co-training strategy is proposed that equips System 1 with action generation capabilities while preserving System 2's contextual understanding to provide stable latent conditions for System 1. For evaluation, FiS-VLA outperforms previous state-of-the-art methods by 8% in simulation and 11% in realworld tasks in terms of average success rate, while achieving a 117.7 Hz control frequency with action chunk set to eight.

Text-3DScene Retrieval (T3SR) aims to retrieve relevant scenes using linguistic queries. Although traditional T3SR methods have made significant progress in capturing fine-grained associations, they implicitly assume that query descriptions are information-complete. In practical deployments, however, limited by the capabilities of users and models, it is difficult or even impossible to directly obtain a perfect textual query suiting the entire scene and model, thereby leading to performance degradation. To address this issue, we propose a novel Interactive Text-3D Scene Retrieval Method (IDeal), which promotes the enhancement of the alignment between texts and 3D scenes through continuous interaction. To achieve this, we present an Interactive Retrieval Refinement framework (IRR), which employs a questioner to pose contextually relevant questions to an answerer in successive rounds that either promote detailed probing or encourage exploratory divergence within scenes. Upon the iterative responses received from the answerer, IRR adopts a retriever to perform both feature-level and semantic-level information fusion, facilitating scene-level interaction and understanding for more precise re-rankings. To bridge the domain gap between queries and interactive texts, we propose an Interaction Adaptation Tuning strategy (IAT).