arXiv:2511.15912v2 Announce Type: replace
Abstract: The Nab (Neutron a b) experiment is designed to measure the beta-antineutrino angular correlation in free neutron $\beta$ decay with an ultimate precision goal of 0.1%, providing input for tests of Cabibbo-Kobayashi-Maskawa (CKM) matrix unitarity. This measurement is performed via detection of electrons and protons in delayed coincidence using custom large-area segmented silicon detectors. We present the characterization of one such detector system to establish the proton energy and timing response, using a dedicated proton accelerator. The detected proton peak was studied for 25 keV, 30 keV, and 35 keV incident protons on a set of detector segments and multiple cooling cycles over a one year period. Ionization losses were consistent with models of the detector dead layer with thicknesses less than 100 nm. The detected proton peak was stable within the uncertainty from energy calibration (0.25 keV). The rise times of detector pulses from $^{109}$Cd and $^{113}$Sn conversion electron sources were used to extract the impurity density profile and establish a precise model for the detector timing response. The observed impurity density profile varied from $(2 \pm 2) \times 10^9$ cm$^{-3}$ at the center to $(26 \pm 2) \times 10^9$ cm$^{-3}$ at the edge. This impurity density profile was then used to characterize systematic effects in proton time-of-flight measurements due to detector pulse-shape effects; the resultant proton timing systematic uncertainties were below 0.3 ns, which is sufficient for the Nab experiment.
Science Journals
arXiv:2607.14305v1 Announce Type: new
Abstract: In this paper we propose DCVC-Mamba (DCVC-MB), a neural video codec framework for B-frame coding. Our approach incorporates an IBP frame strategy for low-delay B-frame coding, a spatio-temporal fusion model based on state-space models for bidirectional temporal prediction, and an entropy-aware skipping mechanism that selectively omits coding certain latents to reduce entropy coding times. In addition to our model contributions we also implement two inference-time strategies that enhance compression performance. Experimental evaluation shows that DCVC-MB compares favorably to existing NVCs and traditional codecs. The method demonstrates BD-rate reductions of up to $8.98\%$ on average compared to prior neural video codecs, and improvements of up to $30.45\%$ and $1.81\%$ over the VTM-19.0-LDP and VTM-19.0-RA(Inter-GoP=16) benchmarks, respectively, contributing to advances in neural video compression.
arXiv:2607.14407v1 Announce Type: new
Abstract: Many signal processing systems ultimately exist to {act}. Whenever the state variable that determines the action to be taken by a decision maker, or agent, is uncertain, the way that uncertainty is represented decides how well the agent performs and how much its performance can be trusted. This lecture note develops, from first principles and within a single decision-theoretic setting, the link between the {objective} and the knowledge of an agent and the form of uncertainty representation that is sufficient to act optimally. To start, assuming a known environment distribution, we show that a risk-neutral agent needs the posterior distribution over the state, whereas a risk-averse agent can rely without loss of optimality on a {prediction set} and a worst-case decision rule. We then turn to the case in which the environment is unknown, and identify three complementary approaches to address the resulting epistemic uncertainty: calibration of a fixed predictor, credal (ambiguity) sets with distributionally robust optimization, and Bayesian inference over model parameters. The common thread is that reliable decisions require an uncertainty representation matched to the decision objective and to the knowledge profile of the agent, together with a guarantee that certifies the utility the agent will actually obtain.
arXiv:2607.14452v1 Announce Type: new
Abstract: Semi-structured interviews are widely used in empirical software engineering (ESE), but they are resource-intensive and difficult to coordinate across schedules, locations, and natural languages. This experience report examines a customized MyGPT used to conduct short, self-administered interviews in two ESE studies: one on refactoring practices and another on generative AI in Scrum-related activities. Participants accessed the interviewer through shared links, used voice interaction, selected a preferred natural language, and completed the interview without a researcher present. The AI followed a predefined protocol and generated a structured synthesis that participants voluntarily submitted; these artifacts were not treated as verbatim transcripts. We analyzed 66 submissions and questionnaire responses, and audited artifact format, language, length, and protocol consistency. Of the submitted artifacts, 92.4% followed the expected synthesis format, 65 were predominantly in Portuguese and one in English, and two conflicted with the reported protocol. Participants generally rated the experience positively: 90.9% reported a positive overall experience and comfort, 95.5% considered the questions clear, 97.0% rated the pace positively, and 89.4% would participate again. Reported limitations included generic questions, limited sensitivity to answers, insufficient depth, privacy concerns, and missed human interaction. The findings support the operational viability and acceptability of this workflow among analyzed respondents, but do not establish completion rates, time savings, summary fidelity, or equivalence to human-conducted interviews. AI interviewers should therefore be treated as a complementary option for short, focused, low-risk studies, with protocol design, privacy guidance, artifact validation, and human oversight.
arXiv:2607.14327v1 Announce Type: new
Abstract: Efficient long-context inference is not only about reducing memory cost, but also about keeping useful contextual evidence accessible as generation proceeds. However, existing compression-oriented approaches, such as key-value (KV) cache compression and context compression, often either make an early decision about which contextual information to keep or rely on an external compressor. Such designs make it difficult to adapt the compressed context to the evidence needed by later reasoning steps. This paper introduces PReM (Preserve and Refresh Memory), a context-compression framework that maintains the long context as the model's internal layer-wise KV memory and learns what to preserve and when to refresh it. Specifically, PReM uses a dedicated memory layer to make memory-selection decisions, and a special memory token <m> to trigger refreshes during generation. To train this behavior, PReM introduces Phase-Separated Refresh Training, aligning memory selection with memory-conditioned generation while preserving continuity across refreshes. Experiments with 32K-token contexts show that PReM outperforms strong baselines under both 16x and 32x compression, while maintaining a favorable balance between answer quality and inference efficiency.
arXiv:2511.19356v3 Announce Type: replace
Abstract: Group Relative Policy Optimization (GRPO) enables stable and preference-oriented updates via group-wise comparisons for post-training video generation. However, GRPO directly optimizes reward-induced advantages. Under sustained optimization, the reward score can lose fidelity as a proxy for true video quality, consistent with the phenomenon described by Goodhart's Law. This leads to two recurring issues: (i) shortcut-driven optimization under composite objectives and (ii) reward saturation within prompt groups. To address these issues, we introduce TaRoS, a Target-Robust Reward Signaling framework for Video generation GRPO. TaRoS leverages component level performance assessment together with intra-group sparsity to organize multi-aspect rewards towards optimization objectives. In addition, it adaptively downweights components that exhibit saturation, thereby preserving effective optimization directions and mitigating redundancy. This maintains meaningful optimization directions and preserves within-group ranking separation, thereby preventing reward hacking and leading to more reliable policy updates. Extensive experiments show consistent improvements in visual fidelity, motion coherence, and text-video alignment over strong baselines.
arXiv:2511.21352v4 Announce Type: replace
Abstract: As computational resources continue to increase, the storage and analysis of vast amounts of data will inevitably become a bottleneck in computational fluid dynamics (CFD) and related fields. Although compression algorithms and efficient data formats can mitigate this issue, they are often insufficient when post-processing large amounts of volume data. Processing such data may require additional high-performance software and resources, or it may restrict the analysis to shorter time series or smaller regions of interest. The present work proposes an improved version of the existing \emph{Sparse Spatial Sampling} algorithm ($S^3$) to reduce the data from time-dependent flow simulations. The $S^3$ algorithm iteratively generates a time-invariant octree grid based on a user-defined metric, efficiently down-sampling the data while aiming to preserve as much of the metric as possible. Using the sampled grid allows for more efficient post-processing and enables memory-intensive tasks, such as computing the modal decomposition of flow snapshots. The enhanced version of $S^3$ is tested and evaluated on the scale-resolving simulations of the flow past a tandem configuration of airfoils in the transonic regime, the incompressible turbulent flow past a circular cylinder, and the flow around an aircraft half-model at high Reynolds and Mach numbers. $S^3$ significantly reduces the number of mesh cells by $35 \%$ to $95\%$ for all test cases while accurately preserving the dominant flow dynamics, enabling post-processing of CFD data on a local workstation rather than HPC resources for many cases.
arXiv:2511.22098v2 Announce Type: replace
Abstract: Recent advances in video world models enable interactive environments with free navigation, making translation between first-person (egocentric) and third-person (exocentric) perspectives increasingly important. However, existing studies focus on unidirectional exocentric-to-egocentric translation, overlooking reference-guided exocentric perspective synthesis. This capability is crucial for gaming and embodied AI applications. Motivated by this, we present WorldWander, an in-context learning framework tailored for translating between egocentric and exocentric worlds in video generation. Building upon advanced video diffusion transformers, WorldWander integrates (i) In-Context Perspective Alignment and (ii) Collaborative Position Encoding to model cross-view synchronization and character consistency. To support our task, we curate EgoExo-8K, a dynamic and scene-rich dataset containing synchronized egocentric-exocentric triplets from both synthetic and real-world scenarios. Experiments demonstrate that WorldWander achieves superior perspective synchronization, character consistency, and generalization, setting a new benchmark for egocentric-exocentric video translation.
arXiv:2512.01208v5 Announce Type: replace
Abstract: In standard Transformer architectures, semantic importance is often conflated with activation magnitude, obscuring the geometric structure of latent representations. To disentangle these factors, we introduce PRISM, a complex-valued architecture designed to isolate the computational role of phase. By enforcing a strict unit-norm constraint ($|z| = 1$) and replacing attention with gated harmonic convolutions, the model is encouraged to utilize subtractive interference in the frequency domain to suppress noise, rather than relying on magnitude-based gating. We utilize this constrained regime to study a hybrid architecture -- fusing phase-based routing with standard attention -- which achieves improved parameter efficiency and representation quality compared to baselines in our evaluated settings. Mechanistically, interventional ablations indicate that the model carries substantial task-relevant information in phase: preserving phase largely maintains performance, whereas disrupting phase causes severe degradation. Together, these results suggest that phase-based spectral interference is a usable computational mechanism for neural sequence modeling at the evaluated scale.
arXiv:2512.03054v2 Announce Type: replace
Abstract: Federated Learning (FL) holds the potential to advance equality in health by enabling diverse institutions to collaboratively train deep learning (DL) models, even with limited data. However, the significant resource requirements of FL often exclude centres with limited computational infrastructure, further widening existing healthcare disparities. To address this issue, we propose a Green AI-oriented adaptive layer-freezing strategy designed to reduce energy consumption and computational load while maintaining model performance. We tested our approach using different federated architectures for Magnetic Resonance Imaging (MRI)-to-Computed Tomography (CT) conversion. The proposed adaptive strategy optimises the federated training by selectively freezing the encoder weights based on the monitored relative difference of the encoder weights from round to round. A patience-based mechanism ensures that freezing only occurs when updates remain consistently minimal. The energy consumption and CO2eq emissions of the federation were tracked using the CodeCarbon library. Compared to equivalent non-frozen counterparts, our approach reduced training time, total energy consumption and CO2eq emissions by up to 23%. At the same time, the MRI-to-CT conversion performance was maintained, with only small variations in the Mean Absolute Error (MAE). Notably, for three out of the five evaluated architectures, no statistically significant differences were observed, while two architectures exhibited statistically significant improvements. Our work aligns with a research paradigm that promotes DL-based frameworks meeting clinical requirements while ensuring climatic, social, and economic sustainability. It lays the groundwork for novel FL evaluation frameworks, advancing privacy, equity and, more broadly, justice in AI-driven healthcare.
arXiv:2512.06364v4 Announce Type: replace
Abstract: Current mobile health platforms are predominantly individual-centric and lack the support for coordinated, auditable multi-actor workflows. However, in many settings worldwide, health decisions are enacted through multi-actor coordination rather than individual users. We present JEEVHITAA, a cross-platform mobile system enabling role-aware sharing and verifiable information flows within permissioned care circles. JEEVHITAA ingests platform and device data, builds layered profiles from sensors and tiered onboarding, and enforces fine-grained, time-bounded access control across care graphs. Data stays secure both within the application and the cloud. Integrated retrieval-augmented Large Language Models produce structured, role-targeted summaries and action plans, offer evidence-grounded verification with provenance and confidence scores, and support advanced insights on reports. We describe the architecture, connector abstractions, and security primitives, and report robustness evaluations using synthetic, ontology-driven data and findings from a feasibility study with real-life care circles across 9-14 weeks. We outline plans for larger multi-site evaluations focusing on operational alignment, longitudinal trust & literacy impact, and relational friction & efforts to sink into the daily infrastructure.
arXiv:2512.08967v2 Announce Type: replace
Abstract: Recent advancements in Large Language Models (LLMs) have led to their widespread adoption in daily applications. Despite their impressive capabilities, they remain vulnerable to adversarial attacks, as even minor meaning-preserving changes such as synonym substitutions can lead to incorrect predictions. As a result, certifying the robustness of LLMs against such adversarial prompts is of vital importance. Existing approaches focused on word deletion or simple denoising strategies to achieve robustness certification. However, these methods face two critical limitations: (1) they yield loose robustness bounds due to the lack of semantic validation for perturbed outputs and (2) they suffer from high computational costs due to repeated sampling. To address these limitations, we propose CluCERT, a novel framework for certifying LLM robustness via clustering-guided denoising smoothing. Specifically, to achieve tighter certified bounds, we introduce a semantic clustering filter that reduces noisy samples and retains meaningful perturbations, supported by theoretical analysis. Furthermore, we enhance computational efficiency through two mechanisms: a refine module that extracts core semantics, and a fast synonym substitution strategy that accelerates the denoising process. Finally, we conduct extensive experiments on various downstream tasks and jailbreak defense scenarios. Experimental results demonstrate that our method outperforms existing certified approaches in both robustness bounds and computational efficiency.
arXiv:2512.09727v2 Announce Type: replace
Abstract: Monte Carlo Tree Search is a cornerstone algorithm for online planning, and its root-parallel variant is widely used when wall clock time is limited but best performance is desired. In environments with continuous action spaces, how to best aggregate statistics from different threads is an important yet underexplored question. In this work, we introduce a method that uses Gaussian Process Regression to obtain value estimates for promising actions that were not trialed in the environment. We perform a systematic evaluation across 6 different domains, demonstrating that our approach outperforms existing aggregation strategies while requiring a modest increase in inference time.
arXiv:2512.10473v2 Announce Type: replace
Abstract: The numerical simulation of incompressible flows is challenging due to the tight coupling of velocity and pressure. Projection methods offer an effective solution by decoupling these variables, making them suitable for large-scale computations. This work focuses on reduced-order modeling using incremental projection schemes for the Stokes equations. We present both semi-discrete and fully discrete formulations, employing BDF2 in time and finite elements in space. A proper orthogonal decomposition (POD) approach is adopted to construct a reduced-order model for the Stokes problem. The method enables explicit computation of reduced velocity and pressure while preserving accuracy. We provide a detailed stability analysis and derive error estimates, showing second-order convergence in time. Numerical experiments are conducted to validate the theoretical results and demonstrate computational efficiency.
arXiv:2512.12427v2 Announce Type: replace
Abstract: Many aerial tasks involving quadrotors demand both instant reactivity and long-horizon planning for obstacle avoidance, energy efficiency, or trajectory tracking. High-fidelity models enable accurate control but are too slow for long horizons. Low-fidelity planners scale but cannot directly control the system, necessitating cascaded architectures. Prevailing hierarchical approaches plan with a simplified model and use a high-fidelity controller for tracking, yet this decomposition is inherently suboptimal. The controller is limited by the coarse plan, and conventional MPC alternatives shorten the horizon to stay real-time feasible. We present UNIQUE, an MPC architecture that replaces this hierarchical stacking with temporal cascading. The planning problem is formulated as the second-tail horizon of a single multi-phase MPC, rather than being solved separately. We align costs across horizons, derive feasibility constraints for the point-mass planning model, and introduce transition constraints that convert high-fidelity states into meaningful low-fidelity states. Parallel point-mass and mixed-integer solvers address nonconvexities while incorporating progressive 3D obstacle smoothing over the planning horizon. In simulations and real flights, under equal computational budgets, UNIQUE improves closed-loop tracking by up to 75% compared with standard MPC and hierarchical baselines. Ablations and Pareto analyses confirm performance gains across variations in horizon, constraint approximations, and smoothing schedules.
arXiv:2512.13993v3 Announce Type: replace
Abstract: Discretized versions of optimization problems over continuous arguments are routinely solved at a single fine resolution, incurring a per-iteration cost that grows, often superlinearly, with the number of grid points. This paper analyzes a multiscale method that instead solves a hierarchy of increasingly fine dyadic discretizations. Linear interpolation of each coarse solution warm starts the next finer scale using any q-linearly convergent update rule as the inner solver. Each coarse problem is a consistent discretization of the continuous problem. Structural properties such as convexity and smoothness are preserved. For problems with Lipschitz-continuous solutions, two variants of the method converge to the fine-scale solution with explicit error bounds. The fine-scale solution in turn approximates the continuous solution once the grid is sufficiently fine, with quantified constants. The total cost to reach a fixed accuracy is provably lower than that of single-scale optimization whenever the cost of one update grows at least linearly in the problem size. Numerical experiments on probability density demixing problems, including geological survey data, show four- to sevenfold speedups while using a fraction of the memory.
arXiv:2607.14408v1 Announce Type: new
Abstract: A self-evolving agentic loop repeatedly proposes a tweaked version of an agent (its prompt template or program) and accepts or rejects the change based on a per-iteration quality signal. Designing that signal is often the costly part of the project: a reliable scalar reward requires domain expertise and labeled examples that are themselves as expensive to assemble as the agent's underlying task. We propose replacing the scalar at the accept/reject gate with a pairwise validator: a frozen LLM that, given the parent and child candidate, returns a binary verdict on which is better. Pairwise judgment is generally easier and more stable than absolute scoring, due to its contrastive nature, which mitigates the need for strict scale calibration. The validator also requires no training of its own. We integrate the validator into three published self-evolving engines (GEPA, ADRS, ShinkaEvolve) and report two flavors: Adaptive Focus, which retains the engine's existing val-set parent selection, and Soft Elo, which lets the validator's verdicts drive parent selection so that val-set rewards drop as well. Across multiple agents and two artifact substrates (prompt and code), our method matches or exceeds the full-reward baseline on the majority of settings we evaluate, and the pattern survives a cross-family validator swap. The pairwise gate is thus a drop-in replacement for per-step reward design at competitive task accuracy without the labeling cost.
arXiv:2512.14008v2 Announce Type: replace
Abstract: Masked Discrete Diffusion Models (MDMs) have achieved strong performance across a wide range of multimodal tasks, including image understanding, generation, and editing. However, their inference speed remains suboptimal due to the need to repeatedly process redundant masked tokens at every sampling step. In this work, we propose Sparse-LaViDa, a novel modeling framework that dynamically truncates unnecessary masked tokens at each inference step to accelerate MDM sampling. To preserve generation quality, we introduce specialized register tokens that serve as compact representations for the truncated tokens. Furthermore, to ensure consistency between training and inference, we design a specialized attention mask that faithfully matches the truncated sampling procedure during training. Built upon the state-of-the-art unified MDM LaViDa-O, Sparse-LaViDa achieves up to a 2x speedup across diverse tasks including text-to-image generation, image editing, and mathematical reasoning, while maintaining generation quality.
Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring
arXiv:2512.14332v2 Announce Type: replace
Abstract: The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately. However, a growing body of studies show that LRMs are still inefficient, over-generating verification and reflection steps. To address this challenge, we introduce the Step-Tagging framework, a lightweight sentence-classifier enabling real-time annotation of the type of reasoning steps that an LRM is generating. To monitor reasoning behaviors, we introduced ReasonType: a novel taxonomy of reasoning steps. Building on this framework, we demonstrated that online monitoring of the count of specific steps can produce effective interpretable early stopping criteria of LRM inferences. We evaluate the Step-tagging framework on three open-source reasoning models across standard benchmark datasets: MATH500, GSM8K, AIME and non-mathematical tasks (GPQA and MMLU-Pro). We achieve 20 to 50% token reduction while maintaining comparable accuracy to standard generation, with largest gains observed on more computation-heavy tasks. This work offers a novel way to increase control over the generation of LRMs, and a new tool to study behaviors of LRMs.
arXiv:2607.14331v1 Announce Type: new
Abstract: Long interaction histories are among the most informative inputs for click-through rate (CTR) prediction, yet in online advertising they collide with a hard serving constraint: ads must be scored within a few hundred milliseconds to enter the auction, which rules out running a large sequence encoder at request time. We describe how a production advertising system resolves this conflict by decoupling history encoding from real-time inference. A high-capacity offline transformer asynchronously encodes the user's full cross-surface interaction history into a compact representation cached in a feature store, while a lightweight runtime model combines this cached representation with the user's most recent events and the request context at serving time. The offline encoder is pre-trained autoregressively on large-scale interaction logs with a dual objective - feedback prediction and next-item prediction - and the two-stage architecture is then fine-tuned for CTR prediction on the target advertising surface. Offline, the split design recovers 72-80% of the quality of a full-history runtime transformer that would be too expensive to deploy, and the cached representation is robust enough to staleness to permit inexpensive refresh policies. In production A/B experiments, the system improves the primary ranking metric by +2.77% in search advertising and +2.1% on the Yandex Advertising Network, with revenue gains of +2.26% and +0.43% respectively - without increasing serving latency.
arXiv:2508.09769v2 Announce Type: replace
Abstract: Ongoing standardization efforts in 5G and Time-Sensitive Networking (TSN) aim to provide safety-critical applications with real-time communication. However, 5G-TSN network schedules often rely on idealistic delay models that can jeopardize the validity of their guarantees. This paper presents an $(m,k)$-firm Elevation Policy to uphold a base level of weakly hard real-time guarantees (WHRT). It augments the primary schedule with a dynamic priority-driven scheme to elevate the priority of $m$ out of $k$ consecutive frames if they experience unexpected delays. Our evaluations demonstrate the necessity of WHRT to increase fault-tolerance against 5G delay outliers and to uphold the quality of control within a 5G-TSN networked control system. Still, only a small resource overhead is imposed during epochs where the primary schedule is valid and can serve stronger QoS guarantees. The $(m,k)$-firm Elevation Policy thereby yields a robust but light-weight fallback mechanism to serve applications with dependable guarantees during unstable network conditions.
arXiv:2512.15875v2 Announce Type: replace
Abstract: We develop and employ general Tree Tensor Networks (TTNs) to compute the vibrational spectra for two model systems: a set of 64-dimensional coupled oscillators and acetonitrile. We explore various tree architectures, ranging from the simple linear structure of Matrix Product States (MPS), to trees where only the leaf nodes carry a physical leg -- as commonly seen in the underlying ansatz of the Multilayer Multiconfiguration Time-Dependent Hartree (ML-MCTDH) method -- and further to more general trees in which all nodes are allowed to possess a physical leg. In addition, we implement Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG) methods and Inverse Iteration methods as eigensolvers. Benchmarking runtime and accuracy shows that all tested topologies can reach high accuracy. For acetonitrile, inverse-iteration refinement brings all 84 computed states below 1~cm$^{-1}$ error, while the fork-4 tree, a comb-like tree with four backbone nodes, provides the best overall balance between accuracy and cost. MPS remains computationally attractive, whereas more connected trees generally improve accuracy at fixed bond dimension. All numerical simulations were performed using PyTreeNet, a Python package designed for flexible tensor network computations.
arXiv:2512.16864v2 Announce Type: replace
Abstract: Instruction-based image editing enables natural-language control over visual modifications, yet existing models falter under Instruction-Visual Complexity (IV-Complexity), where intricate instructions meet cluttered or ambiguous scenes. We introduce RePlan (Region-aligned Planning), a plan-then-execute framework that couples a vision-language planner with a diffusion editor. The planner decomposes instructions via step-by-step reasoning and explicitly grounds them to target regions; the editor then applies changes using a training-free attention-region injection mechanism, enabling precise, parallel multi-region edits without iterative inpainting. To strengthen planning, we apply GRPO-based reinforcement learning using 1K instruction-only examples, yielding substantial gains in reasoning fidelity and format reliability. We further present IV-Edit, a benchmark focused on fine-grained grounding and knowledge-intensive edits. Across IV-Complex settings, RePlan consistently outperforms strong baselines trained on far larger datasets, improving regional precision and overall consistency. Our project page: https://replan-iv-edit.github.io
arXiv:2512.18390v2 Announce Type: replace
Abstract: Organizations often have an incumbent predictive model in production when new data sources become available. Because historical training data lack the new features, a challenger model must be trained on a small but growing full-feature dataset. We study whether, and when, the organization should switch to the challenger. The decision is statistical and economic: the challenger's predictive performance improves as full-feature data accumulate, but repeated retraining is costly and delays benefits from deployment. We develop a framework linking learning-curve dynamics to model-switching economics. Under a standard power-law learning curve and finite data-collection horizon $T$, the optimal time to train and evaluate the challenger scales as $T^{1/(1+\alpha)}$: learning-curve shape (through its learning speed $\alpha$) is the primary theoretical determinant of when to stop experimenting; costs determine switching profitability. Even without knowing the learning curve, the operational problem is tractable: we show that any algorithm stopping on the $T^{2/3}$ scale and making reliable switch/discard decisions achieves $O(T^{2/3}\sqrt{\log T})$ regret relative to a full-foresight oracle. We propose a sequential evaluation algorithm that uses local learning-curve trends to anticipate improvement, and test it in a real-world credit-scoring study. Even with this local approximation, the algorithm theoretically and empirically achieves near-oracle performance. It is also more stable than greedy sequential evaluation algorithms, where noisy early estimates trigger premature discarding, or simple one-shot evaluation algorithms, which work only when their fixed evaluation time matches the (unknown in practice) theoretical timing scale. Our framework offers a step toward principled model governance when new data sources require costly collection, validation, and deployment.
arXiv:2512.20153v2 Announce Type: replace
Abstract: Low-shot object counting addresses estimating the number of previously unobserved objects in an image using only few or no annotated test-time exemplars. A considerable challenge for modern low-shot counters are dense regions with small objects. While total counts in such situations are typically well addressed by density-based counters, their usefulness is limited by poor localization capabilities. This is better addressed by point-detection-based counters, which are based on query-based detectors. However, due to limited number of pre-trained queries, they underperform on images with very large numbers of objects, and resort to ad-hoc techniques like upsampling and tiling. We propose CoDi, the first latent diffusion-based low-shot counter that produces high-quality density maps on which object locations can be determined by non-maxima suppression. Our core contribution is the new exemplar-based conditioning module that extracts and adjusts the object prototypes to the intermediate layers of the denoising network, leading to accurate object location estimation. On FSC benchmark, CoDi outperforms state-of-the-art by 15% MAE, 13% MAE and 10% MAE in the few-shot, one-shot, and reference-less scenarios, respectively, and sets a new state-of-the-art on MCAC benchmark by outperforming the top method by 38% MAE. The code is available at https://github.com/gsustar/CoDi