Science & Mathematics

Tabular data is widely used in scientific applications, where complex layouts, including multi-level headers, merged cells, captions, and footnotes, make information extraction difficult. This is particularly important in pharmacokinetics (PK), where values must be correctly associated with the drug, species, dose, administration route, unit, and experimental condition. Parameter-efficient fine-tuning methods such as Low-Rank Adaptation (LoRA) reduce adaptation cost but do not explicitly incorporate relationships between table values and surrounding headers. We introduce HARP-LoRA, a hierarchy-conditioned rank projection method for low-rank adaptation in scientific table understanding. HARP-LoRA extends projected LoRA by constructing token-specific intrinsic representations from the row- and column-header hierarchies of each data token. These representations condition the low-rank down-projection, incorporating hierarchical context while keeping the pretrained model and random projection tensors frozen. We evaluate HARP-LoRA on 950 manually annotated PK tables from 587 scientific articles and on WikiTableQuestions (WikiTQ) using Llama~3.2 3B, Llama~3.1 8B, and Gemma~3 27B. With Llama~3.1 8B, HARP-LoRA achieves a PK F1-score of 57.64\% and WikiTQ accuracy of 53.15\%, improving over LoRA by 1.42 and 6.56 points, respectively. With Gemma~3 27B, it achieves the best PK F1-score of 70.63\% and WikiTQ accuracy of 56.87\%. These results use only 172K, 197K, and 547K trainable parameters, far fewer than LoRA and TableLoRA. Overall, conditioning lightweight adapters on table-header hierarchies improves extraction from scientific tables and reasoning over flatter general-domain tables while maintaining parameter efficiency. Code is available at: https://github.com/hosseinsholehrasa/HARP-LoRA

A central limitation of modern machine learning systems is the lack of formal certificates guaranteeing their behavior beyond empirical, sample-based evaluation. Sum-of-squares (SOS) methods provide such guarantees by certifying polynomial inequalities over continuous domains via semidefinite programming (SDP). While prior work has introduced SDP layers as differentiable components in neural networks, repeated learning calls can lose the computational benefit of the forward program's sparse representation. We propose Sparse SOS Layers, differentiable value layers whose backward passes reuse the local coordinates of the forward solve. Under a fixed template and learned objective coefficients, each layer avoids building dense certificates and reuses its sparse structure across training steps. Compared with existing methods, our approach achieves up to 2.7 times speedup in total warm-call time, with nearly 100 times lower memory usage (1.7 vs. 160 GiB) for relatively large problem sizes for the tested dense parameterization. Experiments cover sparse polynomial certification, pendulum control, combinatorial relaxations, robotics projection, oscillator chains, and pose graph synchronization. A design study achieves zero certified violations across unseen problem instances and sizes, while requiring roughly 7 times fewer optimization solves than estimating gradients by perturbing the objective coefficients and re-solving the problem (finite differences). These results show that sparse certificate values can be effectively integrated into learning pipelines when the backward pass respects the verifier's structure.

A chunky gold-tone chain necklace bought online for 2.43 USD was photographed four ways: worn with formal attire against a wood-panelled wall, worn at a party, worn with casual clothing in a recycling yard, and laid flat with no person present. We asked six frontier language models to estimate its price in 1,164 independent and sequential API sessions (4,604 logged rows) and compared estimates across settings. Among the four models that answered image prompts, the same necklace was priced 1.9 to 3.3 times higher in the formal photograph than in the flat-lay (all p < 0.01). Against the yard photograph, the ratio ranged from 1.23 (Grok 4.5, not significant) to 3.57 (Kimi K3), with Claude Fable 5 at 3.32. A text-only version of the task, in which the setting is described in words, produced formal-to-yard ratios of 2.2 to 3.9 in all six models, so the effect does not require pixels. Flat-lay estimates themselves were 7.8 to 18.7 times the receipt price, so part of any headline "outfit multiplier" computed against the receipt is baseline overestimate, not a context effect. A single instruction to ignore clothing and setting significantly reduced the effect in one model (ratio of ratios 0.77, 95% CI 0.65 to 0.91) and not detectably in the others; telling the model the photo came from a company website or a personal account changed nothing significant. Asked afterward whether a different outfit would have changed their number, Claude Fable 5 said yes in 24 of 24 sessions, GPT-5.6 in 69%, and GPT-4o in 18%, while GPT-4o also refused 79% of image estimation prompts. The study isolates a mechanism with one object and one wearer at about 10 sessions per model and condition; we outline the replication needed next, with multiple objects and a human benchmark. Data, code, and raw outputs are released.

World Action Models (WAMs) combine future-video prediction with robot action learning, yet improvements in task success alone do not reveal how predictive supervision manifests in execution behavior or whether its benefits persist under task and environmental shifts. We conduct controlled future-video prediction loss ablations within FastWAM and OpenWAM, keeping model architecture, initialization, robot training data, and training steps fixed within each model family. Under clean conditions on seen tasks, predictive supervision increases success rates by 24.38 and 72.91 percentage points, respectively. Trajectory clustering further reveals higher success rates within several coarse trajectory clusters, including cases where cluster frequencies change little, indicating that the gains are not solely reflected in changes in the prevalence of trajectory patterns. However, these benefits do not consistently persist under distribution shifts: improvements on unseen tasks vary across models and tasks, while both models exhibit low success rates under the evaluated environmental randomizations, without a consistent advantage from predictive supervision. We further introduce future-video prediction as an auxiliary training objective for $π_{0.5}$, where a lightweight Transformer predictor used only during training increases success from 82.94% to 89.19%. These findings support future-video prediction as effective auxiliary supervision for action learning, while distinguishing improved execution on familiar tasks from reliable transfer and showing that such gains need not rely on a large pretrained video diffusion transformer (DiT) in the evaluated setting.

An AI agent run is no longer a function call. It is a cascade of prompts, model calls, tool invocations, file and network effects and sub-agents. When such a run misbehaves, or an auditor asks what happened, logs and traces answer poorly: they are mutable, partial and cannot be re-executed. This technical report describes NovaFabric, an open-source (Apache-2.0) black-box recorder for AI agents that turns a run into a sealed, replayable, diffable and auditable evidence capsule. The design rests on two formats only. The Run Capsule is a directory of flat files and the source of truth; every database is a rebuildable index over capsules. The Evidence Bundle is the signed export for an auditor. Everything else follows existing standards: OpenTelemetry GenAI, OpenLineage, W3C PROV, in-toto/DSSE, RFC 3161 and CycloneDX. A single-node run is the smallest case of a distributed one; the schema supports a capsule hierarchy for Slurm arrays and Kubernetes jobs, though automatic parent finalization is library-only today. The report covers the architecture and the engines behind the verb chain capture, seal, replay, diff and audit: fail-closed mocked replay; a diff gate with a stable exit-code contract; DSSE signatures that bind their intent and a capsule root that commits to file names; a capsule treated as untrusted input; signer identity-trust levels with offline TSA and CRL checking; maker-checker promotion against an operator-held trust list; and a deny-by-default authorization table for every dashboard route. It presents no new experiments; the evaluation is in arXiv:2609.12582. Every count except the private ADR tally is generated by a probe script run on the public source at the v0.107.0 tag (150 top-level commands, 84 Python subpackages, 16,721 test functions), every capability carries an explicit maturity label, and honest-limits boxes state where the system stops.

Distributed vector stores increasingly serve multimodal workloads whose representations are jointly accessed but independently partitioned and placed. As a result, cross-modal physical locality remains largely unoptimized. Multimodal queries can incur remote accesses and cross-tier data movement even when each modality's ANN search remains efficient. We present Coloc, a storage-management layer that makes cross-modal access locality a first-class data-layout signal. A Cross-Modal Access Graph combines semantic affinity, co-access, and temporal behavior. A movement-aware optimizer places frequently co-accessed vectors under capacity and topology constraints. A migration manager adapts placement as workloads shift by weighing locality gains against migration cost. A confidence-gated prefetcher hides remaining slow-tier latency. Coloc operates above existing ANN indexes without modifying embeddings, search, or retrieval semantics. We deploy Coloc on a multi-tier AWS testbed spanning GPU, NUMA-DRAM, NVMe, and S3. Coloc substantially reduces data movement and query latency while leaving ANN retrieval unchanged. Under a scheduled workload shift, its migration manager matches the locality of periodic global reorganization while moving 5.9x less data and completing 3.9x faster.

Finite-size effects are ubiquitous in quantum matter, yet typically invisible in the thermodynamic limit; when system size is restricted, boundaries and confinement reveal modified spectra, correlations, and emergent phenomena. With growing access to well-controlled few-spin systems, these effects are now directly observable and offer a route to probing universal physics and enabling quantum information applications. Here, we study finite-size physics in the quasi-one-dimensional Ising-like quantum antiferromagnet Ba(Co$_{1-x}$Mg$_x$)$_2$V$_2$O$_8$ with $x = 2\%$ and $x = 5\%$, where non-magnetic Mg$^{2+}$ ions fragment the Co$^{2+}$ spin chains into finite segments. Combining inelastic neutron scattering and numerical calculations, we identify distinct regimes with fundamentally different low-energy quantum excitations: spinons confined to chain boundaries, and a cluster mode in shorter chains corresponding to a collective reversal of the Néel-ordered segment without classical analogue. Our results demonstrate how chemical substitution acts as a quantum microscope providing direct access to boundary-shaped excitations in strongly correlated spin systems.

Erasing all furniture from a single room image to generate its empty counterpart is valuable for XR applications such as diminished reality and virtual staging. The challenge is twofold: inpainting the furniture regions with realistic content, and doing so without distorting the room's 3D geometry. Prompt-driven image editors, such as FLUX.2, handle realism impressively, but their structural faithfulness is inferior to explicit layout conditioned inpainting. To improve geometric consistency, we propose a training recipe for finetuning a LoRA on 2,500 furnished-empty room pairs. FLUX.2 with our LoRA adaptor significantly improves geometric consistency while retaining the high texture fidelity. This single-photo inpainter can be an effective building block for depth-aware and 3D-consistent XR pipelines.

Despite advances in automated liver lesion segmentation, a gap remains between image-derived predictions and clinically interpretable radiology reports. Bridging this gap requires quantitative measurements that are both reproducible and traceable. We present an evidence-grounded agentic AI framework that connects liver and lesion segmentation with deterministic quantification and structured reporting. TotalSegmentator-based nnU-Net models delineate the liver, Couinaud segments, and lesions, while computational tools extract volumes, dimensions, counts, and anatomical locations. A large language model (LLM) organizes these measurements into a predefined reporting schema, with numerical consistency checks against source measurements. On 51 LiTS cases, the segmentation stage achieved a liver Dice score of 0.947, lesion sensitivity of 75.6%, and positive predictive value of 68.9%. Exploratory screening of 25,494 MERLIN reports identified 10,208 (40.0%) with liver-related abnormalities. By connecting quantitative imaging evidence with agentic report generation, this work takes a step toward human-centered medical AI that prioritizes traceability and clinical relevance.

Objective. Deformable image registration remains challenging because corresponding anatomy may exhibit different intensity relationships. Hand-crafted modality-robust descriptors such as Modality-Independent Neighborhood Descriptor with Self-Similarity Context (MIND-SSC) and features from pretrained vision encoders provide distinct representations for correspondence estimation, but how they should be combined remains unclear. We investigate whether tighter integration improves registration over a sequential, scale-separated design. Approach. We introduce FlexiMIND, a training-free and label-free two-stage framework in which frozen FlexiCT-2D encoder features establish contextual correspondence and MIND-SSC refines the deformation within ConvexAdam. Five alternative feature-coupling strategies were evaluated under a protocol across CT-CT (DIR-Lab 4DCT 4DCT, 10 cases), MR-MR (ACDC, 50 patients), and MR-CT (Learn2Reg Abdomen MR-CT, 8 pairs) registration. Performance was assessed using target registration error (TRE), Dice similarity coefficient (Dice), SDlogJ, and local folding. Main results. FlexiMIND achieved a TRE of 1.27 mm on DIR-Lab 4DCT, a DSC of 0.807 on ACDC, and an organ-averaged DSC of 0.825 on Abdomen MR-CT. Across 15 coupling-strategy dataset comparisons, only four outperformed the reference method, with a maximum absolute improvement of 0.0043 in Dice, whereas degradation reached 20.6 % in TRE and 37.9 % in Dice. Changes in registration accuracy were closely associated with changes in deformation-field regularity, and strategies that better preserved regularity generally remained closest to the reference performance. Landmark-level analysis showed that the pretrained encoder stage primarily reduced large correspondence errors rather than uniformly improving local precision. Code is available upon acceptance at https://github.com/mosaf/FlexiMIND.

Artificial intelligence (AI) is changing how data-driven research is produced. As AI tools make information and technical execution more accessible, mentorship must concentrate on judgment, ethics, and the design of end-to-end AI-augmented workflows. Disciplinary experts need mentoring to adopt AI while preserving their expertise and human agency, and AI-native research trainees need mentoring to become polymathic workflow developers. This chapter proposes Everyone's Backyard, an interdisciplinary model in which disciplinary experts, trainees, and community partners mentor one another in both directions and across disciplines through shared research practice in a convergence studio. The model centers on four capacities: statistical thinking, data ethics, collaboration, and AI for social good and society. We illustrate the model with the Spring 2026 aiX Faculty Fellows Program at Columbia University, which brought together 20 faculty fellows and 15 student interns from 14 schools and departments. Evaluation data show growth in faculty confidence, intern competence, and cross-disciplinary connection.

Vision-language anomaly detectors describe normal and abnormal appearance with text, and their gains are commonly credited to the semantic content of these descriptions. This attribution is plausible in the zero-shot setting, but few- and full-shot detectors interpose a trained visual adapter, and in that setting it has not been isolated. Changing a description changes both its meaning and its geometry, so accuracy comparisons cannot separate the two. We ask what a fixed pair of text embeddings, or anchors, contributes to such a detector: semantic content, effective scale, or joint anchor geometry. For a single anchor pair, the answer is effective scale alone. The score reads the anchors only through their difference, and a trained adapter can rotate to follow any replacement direction, leaving that direction, and with it the linguistic content, unidentifiable. We prove that replacement anchors with the same difference-vector length permit exactly the same probability maps and attainable losses. Across seven medical datasets, three vision backbones, both supervision regimes, and three adapter families, scale-matched random and orthogonal anchors track correct prompts; breaking the scale match opens a gap that restoring it closes without text. The same pattern holds in MVFA and when MadCLIP's learned prompts are replaced by a text-free learned scale. When one adapter serves many categories, the answer expands to their joint arrangement. Rotating all category axes together changes nothing, as predicted. For the tested CLIP prompts, these axes are nearly collinear, and meaning-free rotations that spread them apart improve performance on both industrial benchmarks. Even under frozen zero-shot transfer, a random anchor frame transfers as well as the prompt frame: coordinate consistency, not meaning. What these detectors read from their prompts is scale and arrangement, not semantic content.

We release a battery of 28 propensities for AI research, with expert-written rubrics, synthetic datasets, and annotated demand intervals, built with the method of Romero-Alvarado et al. (2026). We selected a wide collection of generic propensities that may influence the behavior of AI systems and humans. They are inspired by psychometric, psychological, and behavioral research, so that experimental results can be understood in the context of familiar constructs previously used also for human behavior research. The rubrics are useful for annotating existing benchmarks whose items may be relevant or not for one or more propensities. For easier profiling, however, the synthetic datasets are defined in such a way that they should be sensitive to one propensity only, allowing for a quick prototyping of propensity profiles using the battery of datasets. We also outline directions for future propensity research.

Indoor context deciphered by ambient sensing underpins many applications, from assisted living to smart buildings, yet remains weakly connected to the language-aligned paradigm of modern multimodal systems. Through billions of IoT devices, ambient WiFi Channel State Information (CSI) captures the indoor context of human activity and environmental dynamics passively via ubiquitous, always-on infrastructure. However, unlike vision or audio, CSI lacks naturally paired text like captions or transcripts, limiting its integration with language-driven AI systems. We present CSI-TextBench, a large-scale dataset and benchmark for aligning CSI data with natural language, unifying 3 sensing benchmarks into 285,790 samples across 7 tasks and pairing them with 2,291 hierarchically structured, label-derived descriptions via many-to-many assignment to construct 2.0 million CSI-text training tuples. Benchmarking 5 alignment methods from 4 paradigm families, we show that contrastive CSI-text alignment matches supervised classifiers without class labels, adapts to unseen classes with few samples, and responds to open-vocabulary natural-language prompts. A single unified model supports compositional scene understanding, answering joint queries over activity, proximity, and identity, achieving 86.9% top-1 accuracy on 140 composite scenes, outperforming task-specific classifier ensembles. CSI-TextBench enables ubiquitous ambient sensing as a language-indexed perception layer, enabling indoor contextual awareness in language-driven AI systems.

Diffusion models can sometimes reproduce examples from their training data, a phenomenon known as memorization. Existing memorization detection methods for unconditional diffusion models typically operate at a pre-selected timestep and therefore cannot adapt the detection time to the evolving denoising trajectory. Sequential monitoring enables adaptive detection but repeated testing across timesteps complicates trajectory-level false-alarm control. We study two ways of combining split conformal calibration with sequential monitoring for prompt-free memorization detection: per-step Bonferroni calibration and direct trajectory-level calibration of the maximum memorization score. The former controls repeated testing by splitting the false-alarm budget across timesteps, whereas the latter calibrates the event of ever crossing a threshold directly through the trajectory-level maximum. We evaluate this formulation on an unconditional CIFAR-10 EDM using two complementary per-step statistics based on geometry and representation spikiness. Experiments show that sequential monitoring improves the power-timing tradeoff over fixed-time detection. Compared with Bonferroni calibration, trajectory-level calibration achieves comparable detection power while using the false-alarm budget less conservatively and enabling earlier detection at higher noise levels.