论文库

The signature transform is a principled feature map for continuous-time paths, valued for its uniqueness and universality. Recovering a path from its truncated signature is, however, structurally ill-posed, because the truncated signature map is not injective. We therefore reframe truncated signature inversion as a probabilistic problem---learning the conditional distribution of a path given its truncated signature---and adopt a signature-conditioned flow matching model as a practical estimator. This formulation elucidates the fundamental difficulty of inversion: posterior-sampling reconstruction error quantifies the irreducible uncertainty remaining after conditioning on a statistic. For Gaussian process families, we derive this error from the tractable posterior under linear-statistics conditioning, obtaining a closed form for log-GBM and numerically tractable formulas for drifted fBM and OU. This oracle error upper-bounds the corresponding error under truncated-signature conditioning, since truncated signatures are more informative than linear statistics. The experimental results are consistent with the theoretical analysis: the learned sampler under linear-statistics conditioning closely matches the theoretically derived posterior in both reconstruction error and distribution, while reconstruction errors decrease under richer truncated-signature conditioning. Moreover, generated paths faithfully recover the conditioning signature and preserve key distributional and temporal structures. Together, these results establish a well-posed probabilistic framework for truncated-signature inversion, with applicability demonstrated on financial data beyond the process families covered by theory. Code is available at https://github.com/Junoh-Kang/ProbSigInv.

We introduce a mathematical framework for studying contraction of the distributional Bellman operator under Maximum Mean Discrepancy (MMD). We show that contraction reduces to conditional positive definiteness of an associated kernel constructed from the base kernel, which we call the Bellman difference kernel. Focusing on radial kernels, we use Schoenberg's theorem to connect this condition to Bernstein functions. This gives contraction criteria that hold in any dimension and can be verified analytically or tested numerically. Our framework unifies known results for the Gaussian RBF, power-distance, and multiquadric kernels. A numerical search identifies 11 new kernels that induce contraction. We also propose chaining, a general construction that produces kernels inducing contraction with any prescribed factor. To reconcile theory with practice, we show that contraction on a set only requires conditional positive definiteness on that set. This explains why the RBF kernel can remain a valid choice when rewards are bounded, despite its lack of global contraction. Finally, we identify a fundamental tradeoff between contraction rate and discriminative power, where kernels that contract faster tend to discriminate less between distributions. Code is available at https://github.com/BaptisteDebes/BellmanContractionMMD

Enforcement defenses against prompt injection, such as CaMeL, Progent, IPIGuard and DRIFT, ask the agent's own model to write a security artifact (a program, a privilege policy, a dependency graph or a constraint list) that code then enforces. We ask whether small language model (SLM) agents can be trusted to write these artifacts. Across 15 open-weight models, 13 of them between 1.7B and 12B parameters, they cannot: the policies, graphs and constraints that the agent's model writes admit attacks on 14 (Progent), 13 (IPIGuard) and 11 (DRIFT) of the models, and CaMeL's programs fail to run in up to 68% of episodes. We present CapLite, which derives its policy from the tool schemas, commits the write calls before any tool result is read, and admits a write only if every argument that decides whom or what it affects is stated in the user's request. This guarantees write integrity: injected text cannot add a write, and no write reaches a recipient, amount, object or destination that the user did not state. No attack succeeds in 13,935 attacked AgentDojo episodes. CapLite reaches utility under attack comparable to CaMeL's (29.0% vs. 27.2%) with fewer tokens than every other enforcement defense and than the undefended agent: 17.1k per episode, 18% of CaMeL's, and the highest utility per token of all enforcement defenses.

As autonomous AI agents increasingly interact in persistent populations, their collective capabilities and alignment depend not only on individual models, but also on the institutions governing their interactions. Yet AI research has largely focused on individual agents. In this Perspective, we argue that institutional design must become a distinct focus of AI research. Drawing on institutional political economy, social epistemology and organizational theory, we develop seven principles for designing AI institutions that sustain cooperation, enable reliable collective judgments and remain accountable to legitimate human purposes. These address reciprocal contributions, accountable authority, functional differentiation, epistemic pluralism, criticism and correction, human direction, and institutional adaptation. We illustrate their application through machine science, where autonomous research challenges institutions developed around human capabilities and constraints. We then propose an experimental research programme in which matched populations of AI agents operate under alternative institutional arrangements, and describe MoltJournal, an API-first journal for autonomous research agents, as an illustration of how such institutions can be made programmable and observable. Together, these contributions establish institutional design as a research agenda concerned not only with aligning autonomous agents, but with understanding how institutions can transform them into capable, reliable and accountable collectives.

Embodied foundation models hinge on diverse robot interaction data, which are costly to collect. Egocentric human videos offer a complementary source of experience, and latent action models (LAMs) provide a popular means of leveraging these videos for policy supervision. Compared with world-action models (WAMs), LAMs can offer greater training efficiency and potentially lower inference costs by avoiding explicit pixel prediction during policy learning and execution. However, most existing LAMs learn latent actions solely through video reconstruction, which can cause their representations to cluster by visual appearance rather than by the underlying actions. As a result, they struggle to align human actions with their robot counterparts. To bridge the gap, we introduce SALA, which emphasizes establishing the semantic correspondence for latent actions. Without requiring paired data, we use the language descriptions of unpaired human and robot clips to estimate semantic similarities and supervise cross-embodiment correspondence. Specifically, we translate these similarities into soft neighborhood structures that guide human latent actions toward semantically related robot latents, while robot action reconstruction grounds the latent space in control. The resulting shared latent action space provides a unified supervision signal for training an embodied foundation model on both human and robot videos. Notably, latent action supervision enables scaling along two axes: (1) pre-training on increasing amounts of general human video consistently reduces robot action prediction error on downstream tasks, and (2) post-training on increasing amounts of task-specific human video substantially improves real-world robot task success rates.

Pore-space evolution and fluid displacement influence how rocks transmit and store fluids, affecting geological carbon storage, underground hydrogen storage and groundwater contaminant transport. A single time-resolved micro-CT experiment may produce tens to hundreds of three-dimensional images, and segmentation is required to quantify physical properties and run image-based simulations. Traditional methods such as thresholding perform poorly on noisy, low-contrast images and need manual adjustment per image; 3D deep learning networks segment each image without temporal information, so their errors vary between images and could be mistaken for physical change. Here we introduce a transformer-based 4D segmentation framework combining spatial and temporal information. It uses sequential images to resolve ambiguous phase assignments and separate physical change from segmentation error. The method is tested on images of mineral dissolution: it measures pore-volume growth and rock boundaries more accurately than an equivalent 3D model that ignores temporal information. It also captures the increase in permeability verified against reference segmentations and flow simulations. The advantage transfers to another dissolution sample without retraining. On two other datasets of fluid displacement, it reduces spurious changes in predicted rock and porosity fluctuations and accurately identifies filling events. Spatiotemporal segmentation turns sequences of hundreds of three-dimensional images into more reliable quantitative measurements of pore-space evolution and fluid displacement without per-image parameter adjustment to support the analysis of time-resolved CT imaging.

Paper published at NeurIPS 2026. For data-driven PDE surrogates, generalizing across a wide range of initial conditions and physical coefficients requires a training set of numerical simulations that consistently covers the resulting dynamics. Yet uniform sampling of these configuration parameters can leave challenging regimes insufficiently covered, leading to high prediction errors and large error variance in the trained surrogate. To address this sampling imbalance, we introduce the Online Generative Active Sampling (OGAS), which continuously adapts configuration sampling during surrogate training, as an alternative to classical round-based active learning. As the surrogate learns from a stream of simulation data generated online, OGAS trains a fast diffusion model in parallel to sample configuration parameters conditioned on a training difficulty signal, such as loss or uncertainty. This conditional sampler enables OGAS to parametrize subsequent simulations to generate challenging training data by prioritizing configurations with high difficulty values. We evaluate OGAS on 2D PDEs with distinct challenging dynamics-Kuramoto--Sivashinsky, Navier--Stokes, and Gray--Scott-using multiple surrogate architectures and up to 308 configuration parameters. Across the tested PDEs and architectures, OGAS consistently reduces the 99th-percentile prediction error and overall error dispersion compared with uniform sampling, while wall-clock overhead is negligible. Code and experiments are available at https://github.com/melissa-sa/ogas.

We study contextual bandits with $K$ actions, a class of $N$ policies, and i.i.d.\ contexts from a distribution that the learner can sample. For any sequence of loss functions fixed before play, we give an oracle-efficient algorithm with expected regret $O(\sqrt{KT\log(2N)}\,\log(2KT))$ against the best policy in hindsight on the realized contexts. This improves the $T^{2/3}$ dependence on the horizon in prior oracle-efficient bounds and achieves the optimal regret rate in this setting up to logarithmic factors. Our algorithm perturbs policy scores using a Poisson sample of auxiliary contexts. At each sampled context, the perturbation assigned to an action is a Laplace noise draw multiplied by a scale specific to that context and action. We show that choosing these scales to minimize a convex objective determined by past observations yields the stated regret bound. We further approximate the minimizing scales by projected stochastic gradient descent using only an exact offline cost-sensitive optimization oracle that returns the optimum value. Since the table of scales can be large, the algorithm represents the SGD iterates implicitly by storing the random draws that determine each update and evaluates the scales only at queried contexts. Both the oracle complexity and the remaining resource bounds are polynomial in $T$, $K$, and $\log(2N)$.

Memory decides which LLMs an edge device runs, and how fast: capacity on a $4$ GB Jetson Nano, bandwidth on an $8$ GB Jetson Orin Nano Super. Deployed formats (GPTQ, AWQ, $\texttt{llama.cpp}$'s K- and I-quants) spend equal bits on every integer code of a matrix, although the codes are far from uniform. $\texttt{LazyWeights}$ keeps these formats but tunes GPTQ so the codes compress, Huffman-codes them losslessly in interleaved lanes, and decodes them on demand in a small unit between DRAM and L2, so GPU kernels run unchanged and DRAM moves only coded bytes. At $1\%$ and $3.5\%$ perplexity budgets, coded Phi-3-mini, Mistral-7B and SmolLM-1.7B are $5.7-31.4\%$ smaller than the best $\texttt{llama.cpp}$ format. A bit-exact $0.21$ mm$^2$ ASIC decoder unit ($1$ GHz, $7$ nm) cuts Orin latency and energy per token by up to $36\%$ and $38\%$ ($54\%$ and $44\%$ with prompt-lookup speculation). On the Nano, $\texttt{LazyWeights}$ needs $58-64\%$ less time and $53-57\%$ less energy per token than CPU $\texttt{llama.cpp}$, and runs a streamed Mistral-7B 6.6$\times$ faster at $3.89$ bits per weight. A Huffman decoder beats an rANS decoder in rate and area at equal throughput; the ASIC decoder unit runs bit-exact on a Zynq UltraScale+ FPGA (AMD ZCU102).

In NLP, models trained via Empirical Risk Minimization (ERM) often exploit spurious correlations, such as dialectal markers, at the expense of robust linguistic features, thereby degrading their out-of-distribution (OOD) generalization. Invariant Risk Minimization (IRM) aims to suppress such shortcuts by identifying predictive relationships that remain stable across environments, but its practical utility for NLP remains debated. We use a causality-driven framework to evaluate IRM under three shortcut-generating mechanisms: label-generated features, confounding, and selection bias. Our results show that IRM successfully rejects shortcuts across the evaluated causal and anti-causal structures, including under limited environmental variation and increasing label noise. We then extend our analysis beyond controlled synthetic artifacts to two less constrained settings: gender-profession associations in Bias in Bios and semantically loaded actor-name shortcuts in ActorCorr. These experiments show that invariant learning can mitigate more realistic textual shortcuts, while semantically meaningful features require careful calibration of the invariance penalty.

Combining vision-language models (VLMs) with parameter-efficient fine-tuning (PEFT) offers a promising approach to few-shot whole-slide image (WSI) classification in computational pathology. This study evaluates this approach for predicting ethanol drinking status from nonhuman primate liver histology. Adapters are evaluated against non-PEFT configurations on a subset of the Monkey Alcohol Tissue Research Resource (MATRR). All evaluated PEFT configurations achieve higher mean balanced accuracy than the non-PEFT baselines. For example, in the four-shot setting, attention-based multiple instance learning (ABMIL) alone achieves 43.5% mean balanced accuracy, compared with 78.1% after adding an adapter. Qualitative attention analysis shows that textual pathway adaptations produce localized attention heatmaps, while visual pathway adaptations produce more diffuse ones. A pathologist's review identified similar histological features across adaptations.

Quantifying disease-associated renal tubular remodeling is challenging because tubular appearances are heterogeneous. We introduce TuMAP (Tubular Morphotype-Aware Pathomics), a pipeline combining (1) dual-view foundation-model representations and provisional morphotype annotation, (2) compositional and within-morphotype pathomics, and (3) patient-level statistical inference. From 456,158 tubules in 358 PAS-stained kidney biopsy slides, TuMAP identified eight image-based morphotypes, seven of which showed stable subsampling assignments. Across 219 patients in six diagnostic groups, diabetic nephropathy (DN) and tubulointerstitial nephritis/acute tubular injury (TIN/ATI) each differed from minimal change disease in seven morphotype proportions, while IgA nephropathy differed in six. DN showed reduced nuclear solidity and increased eccentricity across all eight morphotypes. Area-normalized nuclear density exposed additional within-morphotype differences. TuMAP provides a framework for separating changes in tubular morphotype composition from phenotypic differences within morphotypes.

Merging independently fine-tuned checkpoints into a single multi-task model requires no data, no labels, and no gradient steps. In practice the task vectors of different tasks interfere, and the standard remedies--averaging, magnitude pruning, sign election--operate entry by entry, ignoring that each delta induces a low-dimensional update on the hidden features it acts upon. We recast merging as a subspace interference problem. For every two-dimensional weight tensor we take the top-r right-singular subspace of each task's delta--the input directions along which that task moves the representation most--and remove from each task vector the component lying in the union of the other tasks' subspaces. The resulting Joint Null-Space Projection (JNSP) is closed-form and order-independent, needs no forward pass, and is defined entirely by the checkpoint set. On eight CLIP image-classification tasks JNSP merges ViT-B/16 experts to 89.45% average accuracy without using a single image, 11.88 points above the strongest parameter-wise training-free baseline (TIES-Merging, 77.57%), 14.22 above Task Arithmetic, and 0.98 above WUDI's data-free consensus merge (88.47%). The gain holds across three backbones on the independently trained TALL release (+10.8, +12.6, +9.1 over TIES for ViT-B/16, ViT-B/32, ViT-L/14) and replicates there at 89.20%; controls confirm the source--a single shared subspace instead of per-task ones loses 2.9 points, and a sequential variant collapses to 69.6%. On RoBERTa-large the same projection underperforms plain task arithmetic, which we report rather than hide. Code is available at https://github.com.

P300-based brain-computer interfaces (BCIs) enable communication by decoding stimulus-evoked EEG responses into character selections without requiring voluntary motor output. Reliable P300 detection remains difficult because of low response amplitude and signal-to-noise ratio, while practical spellers require accurate character selection with few stimulus repetitions and low computational cost. We propose a compact deep learning architecture that combines xDAWN spatial filtering for event-related potential enhancement and dimensionality reduction, a fixed frequency-selective filter bank, and convolutional feature learning for spatio-temporal EEG decoding. Depthwise-separable convolutions and progressive average pooling reduce computational complexity while retaining discriminative temporal information. The resulting target/non-target classifier contains only 5,100 trainable parameters. We evaluated the model on two public benchmarks, BCI Competition II Dataset IIb and BCI Competition III Dataset II, and compared it with established P300 decoding methods across different numbers of stimulus repetitions. The model achieved an information transfer rate of 17.8 bits/min with two repetitions on BCI Competition III and 40.5 bits/min on BCI Competition II, demonstrating a favorable accuracy-speed trade-off. These results suggest that combining domain-informed spatial and spectral priors with compact neural networks can support efficient P300 decoding for EEG-based BCI communication.

The rapid growth of artificial intelligence is driving demand for new data centers at large scale and on short deployment timelines. To power them, firms connect to the commercial grid or contract generation directly, but interconnection and gas-turbine delays now incentivize on-site generation. We compare grid-connected and off-grid data center energy infrastructure (AC- and DC-coupled solar-plus-storage, islanded natural gas, and grid interconnection) across the continental U.S. Using an open-source technoeconomic framework built on empirically calibrated AI training loads, climate-driven cooling, stage-by-stage power conversion, and physics-based battery degradation, we model designs providing equivalent energy services. Our central contribution is a speed-adjusted cost of energy that values the compute unlocked by faster construction, making options with different deployment timelines directly comparable on one physically consistent basis. We find DC coupling reduces lifetime energy costs by 18% ($0.09/ kWh) on average versus AC counterparts by eliminating inverters and improving efficiency. Though rarely cheapest on unadjusted energy cost, DC-coupled microgrids' faster deployment makes them the lowest-cost modeled option in 85% of U.S. locations once foregone compute is valued, or 55% under accelerated natural gas timelines. For AI infrastructure, deployment speed rather than unit energy cost determines the economically preferred path to power.

Large language models (LLMs) are increasingly being used to support computer science research. To contribute reliably, these systems must be able to work with information distributed across research papers and across different aspects of the research process. However, large-scale resources that systematically organize such information into structured supervision for both model evaluation and post-training remain limited. To address this gap, we propose a systematic paper-to-QA construction pipeline that organizes information from AI research papers into structured QA pairs supported by source evidence. Using this pipeline, we construct CS-54k, a 54k-pair corpus derived from 14,474 openly licensed AI research papers. The corpus covers eight recurring paper components, including research domain, prior work, existing challenges, motivation, findings and assumptions, methods, experimental settings, and experimental results. We further derive two complementary subsets: CS-4k, a benchmark for evaluating LLMs on paper-derived research QA, and CS-50k, a companion corpus for post-training. Extensive evaluations on CS-4k reveal substantial performance differences across existing LLMs and paper components, with experimental settings and results remaining particularly challenging. Moreover, post-training on CS-50k substantially improves Qwen2.5-7B-Instruct on CS-4k, demonstrating the practical utility of structured, paper-derived supervision. Together, CS-4k and CS-50k provide a unified and scalable resource for benchmarking and improving LLMs on research paper question answering.

Provably secure linguistic steganography assumes that the receiver recovers the sender's tokens, but a text channel delivers only text, and ambiguous tokenizations break extraction. Existing fixes change the distribution, synchronize whole pools of tokens at a capacity that collapses with large vocabularies, or track several token histories. We prove that if extraction is exact and error-free across full-support language models, a single-history receiver is confined to a prefix-free candidate set at every step -- even if it reads the entire future text and the sender constrains later steps -- and must therefore give up the stop entropy, the entropy of deciding whether each prefix token ends there. Fixing these stop decisions on the prefix forest with shared randomness yields coin projection: a closed-form scheme that attains the bound, works with any distribution coder in one model call per token, preserves ordinary sampling, and refines SyncPool for every key. Across English, Chinese and Japanese, ambiguous text is rare (at most 11 in 1,000 tokens), yet the stop entropy at word and morpheme prefixes takes 7.2-9.0% of the entropy at every step; SyncPool's further loss comes from space and single-byte UTF-8 hubs that merge subtrees while carrying almost no stop uncertainty. Coin projection keeps 91-93% of the string entropy for the coder at every vocabulary size; with the full vocabulary, it turns 2.16-6.85 times as much entropy into message bits as SyncPool and recovers every completed message.

We present Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for stationary-base desktop manipulation. MR0 combines 147 million vision-language samples with 15,060 hours of curated robot trajectories spanning 12 embodiments. A three-stage training recipe aligns multimodal representations with robot behavior through discrete action-token pre-training, transfers these priors to continuous cross-embodiment control through flow-matching mid-training, and adapts the policy through real-world post-training. We introduce Rollback, which pairs replaced policy segments with human corrections to provide positive and negative supervision for CFG-DAgger without value learning or advantage labeling. A unified end-effector interface supports heterogeneous embodiments, while asynchronous action-chunk merging maintains smooth execution under variable inference latency. An event-driven agent maintains persistent task events and reassesses plans when progress or feasibility changes, enabling cross-task retrieval and conditional task resumption. MR0 achieves 93.6% success on RoboTwin 2.0 and ranks fifth in the RoboDojo VLA track. Under matched HG-DAgger post-training, MR0 achieves higher average success rate and progress score than $π_{0.5}$ across three real-robot tasks. On Ethernet insertion, CFG-DAgger trained with Rollback data reaches 70% success and a progress score of 0.90. Qualitative agent deployments demonstrate cross-task event retrieval and recovery from temporarily unsatisfied task conditions.

The Witness is a game with combinatorial puzzles that are challenging for both human players and AI solvers. Search-based AI solvers can require large amounts of time to solve such puzzles. We accelerate search by automatically learning a predicate that predicts whether a partial path to a Witness puzzle is completable to a solution path. We demonstrate that our learned predicate is human-explainable, which makes it amenable to proofs, and we prove a key property that allows us to use it for pruning successor states in search. Doing so accelerates search by about six times while maintaining search completeness. Conversely, given a fixed time budget per puzzle, our predicate-accelerated search can solve more puzzles of larger sizes than a baseline search using a hand-coded predicate. Finally, we empirically demonstrate how accelerating search using an automatically learned predicate can outperform two competitors, weighted A* and Levin tree search with neural networks, in terms of time and number of nodes expanded.

Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted approaches by a wide margin. Motivated by this observation, we address the following question: can the privacy vulnerability of individual training points be assessed without training shadow models? We show that per-sample exposure to MIA is governed not only by a point's loss, but also by a data-dependent geometric measure. In the linear setting, we derive a closed-form decomposition of individual black-box MIA vulnerability into a population leverage score and a residual loss term, making explicit how sample-dependent geometry translates into privacy exposure. Since the final layer of most modern architectures is linear, we extend this framework to deep networks and propose a surrogate score operating on last-layer representations that requires only a single trained model and no shadow models. Empirical evaluations across diverse datasets and architectures show that our score outperforms loss and gradient-norm baselines at identifying the highest-risk points under state-of-the-art attacks, providing a computationally efficient and theoretically grounded tool for per-sample privacy risk assessment.

Change detection in remote sensing conventionally relies on spatially aligned bi-temporal imagery, which may be unavailable or unreliable in practical scenarios. Recent single-temporal approaches address this limitation by learning structural evidence, such as building regions, from a labeled source dataset and transferring it to unseen target imagery using only the current image. However, adaptation to the source dataset can over-specialize pretrained features and reduce their cross-dataset generalization, a risk that this paper argues is higher when the feature adaptation is parameterized independently of the states used for prediction. To address this issue, the current study introduces SALT, a State-Aligned Low-Rank Transfer framework. SALT keeps a DINOv3 backbone frozen and learns negative and positive structural states that both score each patch and, through State-Aligned Low-Rank Adaptation (SALA), span the rank-2 subspace in which patch features are corrected. Directional State Alignment supervises these corrections to raise the evidence of positive patches and lower that of negative ones, while Geometry Preservation limits changes to the pairwise relations among pretrained patch features. Experiments on LEVIR-CD and the WHU aerial building dataset show that, at the pixel level and in both transfer directions, SALT outperforms four baselines reproduced under a common source-only protocol, improving over the strongest reproduced baselines by 9.45 and 5.79 points in pixel-level AP and by 27.69 and 14.25 points in IoU (LEVIR-CD to WHU and WHU to LEVIR-CD, respectively), with only 0.068M trainable parameters and 40.2 ms per image. In order to facilitate reproducibility and further research, the source code of SALT is available at https://github.com/gthpapadopoulos/SALT

We investigate the minimal width of deep neural networks that can approximate all continuous functions from $\mathbb{R}^n$ to $\mathbb{R}^m$ in the topology of uniform convergence on compact subsets. We show that whenever the real projective space $\mathbb{RP}^{n-1}$ admits a smooth immersion into $\mathbb{R}^n$, the minimal width is at least $n+\min\{n,m\}$, assuming that the activation function is continuous and monotone. As a consequence, the minimal width of ReLU networks is $n+m$ whenever $n$ is equal to 2, 3, 4, 7 or 8 and $1\le m \le n$, extending results of Hanin-Sellke and Hwang.

Ontology matching (OM) enables semantic interoperability between different ontologies and resolves their conceptual heterogeneity by aligning related entities. OM systems currently have two prevailing design paradigms: conventional knowledge-based expert systems and newer machine learning-based predictive systems. While large language models (LLMs) and LLM agents have revolutionised data engineering and have been applied creatively in many domains, their potential for OM remains underexplored. This study introduces a novel agent-powered LLM-based design paradigm for OM systems. With consideration of several specific challenges in leveraging LLM agents for OM, we propose a generic framework, namely Agent-OM (Agent for Ontology Matching), consisting of two Siamese agents for retrieval and matching, with a set of OM tools. Our framework is implemented in a proof-of-concept system. Evaluations of three Ontology Alignment Evaluation Initiative (OAEI) tracks over state-of-the-art OM systems show that our system can achieve results very close to the long-standing best performance on simple OM tasks and can significantly improve the performance on complex and few-shot OM tasks.

Fine-tuning foundation models on financial data has a wide range of applications, including identifying event types from news, monitoring risk and compliance language, and answering questions over filings and earnings calls. In this setting, the main challenge is to improve task performance without degrading the generalization capabilities of the model. In this paper, we present an extensive set of ablations for fine-tuning Qwen3-8B with low-rank adaptation (LoRA). We compare three training regimes: (1) response-only LoRA, where the supervised response is the label alone; (2) single-adapter reasoning, where reasoning traces from a teacher model are included alongside the labels in the training loss; and (3) dual-adapter composite training, where separate LoRA adapters are trained on traces and labels. Response-only LoRA improves in-domain performance and leaves general capabilities near those of the frozen model. The in-domain change is largest for calibration and argmax accuracy. Under single-adapter reasoning, the in-domain metrics remain behind those of the response-only regime, while MMLU-Pro can rise slightly and the other retention benchmarks stay within ordinary variation. Dual-adapter composite training remains on the same side of this comparison and yields no further gain. Finally, we compress the teacher traces by summarizing them before training, and show that shorter summaries move calibration toward the response-only regime without reaching it.

Automatic setlist identification aims to identify the songs performed in live concert recordings by matching noisy and variable-quality audio against a database of reference tracks. This task presents challenges beyond conventional music version identification, including substantial arrangement differences, background noise, and the need to process continuous recordings efficiently at large scale. In this work, we evaluate modern music version retrieval methods for setlist identification using the ASID benchmark, comparing the established Re-MOVE system with CLEWS and NAVE, an internal neural audio version embedding model. Our results show that NAVE and CLEWS substantially outperform Re-MOVE. Notably, NAVE uses 256-dimensional embeddings, compared with 1024 dimensions for CLEWS, providing a four-fold reduction in embedding storage while achieving better retrieval performance. We further evaluate music/non-music gating and find modest improvements in detection and temporal coverage, while qualitative analysis suggests that such preprocessing can improve recognition boundaries beyond what the standard ASID metrics capture. Overall, the results demonstrate that segment-level audio embeddings provide a strong basis for scalable setlist identification and that compact representations can achieve strong accuracy under realistic live-concert conditions at much lower storage and serving cost.

Program evolution provides a promising approach to discover agent memory designs and study the choices underlying their effectiveness. We introduce MAPE, a framework that evolves whole memory programs from minimal seeds through a standardized lifecycle interface and an iterative diagnosis-proposal loop. Experiments on LoCoMo and LongMemEval yield an absolute accuracy gain of up to 12% over manually designed baselines at 35% of the serving cost, with further evaluations supporting transfer across serving backbones and benchmarks. Empirical analyses and ablations identify and validate two recurring design patterns: retaining raw conversations as retrievable evidence preserves details omitted from extracted memories, while composing retrieved evidence according to query intent helps the answering model use it effectively. Transplanting the composition module into five existing memory systems improves accuracy across all five. Beyond these patterns, the search objective shapes where computation goes: optimizing serving cost alongside accuracy shifts computation from LLM-based memory construction to selective processing at query time while retaining competitive accuracy. Together, these findings offer empirical lessons for agent memory design. Code is available at https://github.com/ash-ding/MAPE.

System thermal-hydraulics codes such as the System Analysis Module (SAM) close turbulence on coarse meshes with algebraic zero-equation mixing-length models. These models cannot represent the non-equilibrium turbulence, flow separation, and large-scale recirculation of open-cavity advanced reactors. We develop an invariant neural-network eddy-viscosity closure for SAM and apply it to the Molten Salt Fast Reactor (MSFR). The closure predicts the turbulent kinetic energy and timescale of each element from the flow and geometry of its neighbors, without solving turbulence transport equations. The resulting non-negative eddy viscosity enters the implicit diffusive operator, which keeps the momentum equations well conditioned. We prove that the closure is exactly invariant to translation, Galilean boost, rotation, reflection, and neighbor ordering. A network trained on high-order Nek5000 fields sees a different feature distribution on the coarse SAM mesh. We remove this covariate shift by iteratively retraining the network on SAM flow states against fixed Nek5000 targets. For a held-out steady state, the coupled closure reproduces the single recirculation cell and eddy-viscosity plume of the Nek5000 reference. In a 120 s pump-coastdown transient, it halves the velocity error of the mixing-length model, from 37.6% to 17.7%, and matches the Nek5000 eddy viscosity with a time-averaged relative error of 12%. The remaining velocity error comes from the coarse mesh. The coupled transient takes about 0.2 core-hours, compared with about 330 core-hours for Nek5000. The results show that the closure can recover two-equation RANS turbulence behavior in a coarse-mesh system code at a small fraction of the CFD cost.

Large foundation models such as GPT-6 Astra and Claude Fable 5.1 have recently been shown to control robots directly from visual observations. They nevertheless remain brittle on long-horizon, contact-rich tasks in real-world environments. Further progress depends on two complementary resources: demonstrations of human behavior that supervise how tasks are performed, and interactive environments in which policies can be rolled out, evaluated, and improved in closed loop. Language models have advanced along well-characterized scaling laws; the corresponding question for physical AI is how capability scales with environments and behaviors, which first requires identifying which data to scale and how to produce and reuse such data continuously. To address this question, we introduce Ropedia Xperience 2, comprising 1,589 released metric-scale 3D scans and a collection of 4,230 egocentric recordings of 74 tasks (131 hours). We further show that each capture can be repurposed for robot learning: scenes are converted into physically interactive simulation environments, human motion is retargeted to whole-body robot trajectories, and additional robot behaviors are obtained through virtual teleoperation and automated long-horizon trajectory generation. We propose this joint capture of environments and behaviors as a gold standard for physical AI data collection, laying a data foundation for establishing scaling laws over environments and behaviors.

Online conformal risk control (OCRC) enables reliable uncertainty quantification in machine learning by converting model outputs into prediction sets with long-term risk guarantees. These guarantees, however, hinge on the assumption that the loss of each round is revealed immediately and losslessly. In practice, feedback may be delayed, and limited resources may prevent tracking all pending predictions, causing some feedback to be lost. To address this challenge, we develop capacity-aware OCRC (CA-OCRC), a framework that jointly determines how to allocate limited tracking feedback capacity and how to construct prediction sets. CA-OCRC is based on a randomized tracking policy that samples a proxy delay to decide whether, and for how long, feedback for the current round is tracked. CA-OCRC updates the prediction sets via inverse probability weighting, compensating for the possibility of feedback lost due to delays and limited tracking capacity. We analyze risk bounds for both arbitrary and stochastic delays, revealing a trade-off between receiving more feedback and avoiding capacity saturation. Building on these bounds, we optimize the proxy delay distribution, showing scaling laws for the tracking capacity that ensure the same long-term risk as OCRC with unlimited feedback. Experiments on medical imaging, natural language processing, computer vision, and wireless communications show the effectiveness of CA-OCRC as compared to existing OCRC mechanisms.

Large language models (LLMs) have been widely adopted for clinical question answering (QA). Current systems can attach citations to their answers, but these often point to broad texts, leaving time-pressed clinicians unable to verify them efficiently. An alternative is to ensure that responses are verifiable by construction: providing fine-grained verbatim quotes from reference material that substantiate claims, so users can verify an answer without opening other documents. In this paper, we evaluate the ability of current models to perform this task end-to-end: from providing citations for every factual claim, to producing verbatim quotes, to ensuring that those quotes fully substantiate the claims. To do so, we build a standardized harness over four clinical practice guidelines and evaluate fourteen LLMs on 222 synthetic clinical questions, measuring each of these stages separately. We find that most models can attach verbatim quotes to over 90% of their claims from prompting alone, apart from some lightweight models such as claude-haiku-4.5. Yet these quotes often fail to substantiate every detail of the claims they accompany. For instance, claude-opus-5 produces verbatim quotes for 98.0% of its claims, but fully substantiates only 37.1%. Our work provides insights into the current capability gap of LLMs in building verifiable clinical QA systems, along with artifacts for future research.