Recalibration

An unlearning audit reads its verdict off numbers that an unlearned model and its retrained reference each publish, and both also ship batch-normalization statistics that no gradient step wrote and no release records. Refitting them on kept data at bit-identical weights moves 47 of 221 released checkpoints past the spread their own release's seeds show, several inside a method whose average does not move: what moves is the checkpoint's property, not its method's. What does the moving is not the removed data surviving in the state: exchanging kept records for removed ones inside a fixed fitting pool moves a published cell by almost nothing, while how far a checkpoint's shipped state has drifted from any refit does track it. The consequence for a published decision is real but narrow: twelve verdicts cross, four clear a measured recalibration budget, two clear it on every replicate, and a population we trained and sited near its own criterion yields none. A release should therefore name the fitting convention beside the number, on the batch-normalized vision models where this channel exists.

Bone-selective digitally reconstructed radiograph (DRR) synthesis depends on high-resolution encoder detail, yet static skips cannot condition reuse on the evolving decoder representation. We ask whether decoder state adds useful information beyond encoder-only self-recalibration for high-resolution skip reuse. RFS-UNet uses pooled encoder and aligned decoder statistics for bounded residual channel recalibration at the 512^2 and 256^2 skips, leaving the backbone unchanged. In the matched seed-2026 comparison isolating decoder conditioning, RFS raises validation PSNR by 0.254 dB over Self-RFS. Across three seeds, locked-test PSNR rises from 33.225+/-0.048 to 33.537+/-0.128 dB; RFS lowers MAE in 179/200 held-out CT cases and reduces mean MAE by 3.91%. It adds 0.117% parameters and 1.169% counted Conv2d operations. These results support decoder state as a useful conditioning signal for high-resolution feature reuse in controlled paired projection synthesis.

Shortcut learning denotes the widespread situation in which a classifier exploits spurious correlations rather than diagnostic features. Existing mitigation strategies mostly aim to learn shortcut-invariant representations; their empirical success is limited and they cannot be applied to classifiers using frozen foundation model encoders. We propose to reframe shortcut learning as fundamentally a calibration problem: unconstrained learning implicitly calibrates each shortcut group to its training set disease prevalence, rendering the resulting classifier necessarily over-confident in one group and under-confident in the other. Building on this insight, we prevalence-equalize calibration between shortcut groups through two encoder-agnostic methods, an in-processing regularizer and a post-hoc prevalence-equalized recalibration step. Across chest-drain-pneumothorax benchmarks on CheXpert and SIIM-ACR, spanning fine-tuned CNNs and frozen foundation-model backbones, both methods substantially outperform all baselines. Post-hoc recalibration of a standard ERM-trained DenseNet raises misaligned-group AUROC from 0.23 to 0.73, indicating that shortcut reliance degrades the classification head rather than the underlying representation. Besides two new state-of-the-art shortcut mitigation approaches, our findings more fundamentally connect shortcut learning to calibration theory and algorithmic fairness.

Vision models deployed on microcontrollers (MCUs) are quantized to integer-only arithmetic and run in inference-only runtimes that do not carry the machinery backpropagation needs: the standard tool for adapting a model to the distribution shift (sensor noise, blur, lighting) it meets in the field. Existing forward-only test-time adaptation (TTA) methods either run only on server- or edge-GPU-class models (not true microcontroller integer execution), or require the batch-normalization (BN) layers that integer deployment fuses away. We present a forward-only TTA method that operates on deployed, BN-folded, integer-only convolutional networks. The key observation is that fusing BN into the preceding convolution, a mandatory step for integer inference, destroys the statistics that normalization-based adaptation relies on. We restore adaptation by re-normalizing each folded convolution's per-channel output to its clean training statistics, using only forward-pass estimates. The method (i) recovers most of gradient-based TENT's accuracy gain (+20.9 vs. +24.9 points) and matches forward-only BN adaptation, while being the only method that runs on a folded integer-only model; (ii) needs to adapt only 3 of 21 layers (selected without seeing the test corruptions) to recover 93% of the benefit; (iii) survives single-sample streaming with a batch-size-scaled momentum; and (iv) generalizes across three datasets (up to 200 classes) and two architectures. We validate bit-exact int8 convolution execution and deploy on an ESP32-S3, where, measured with a Nordic PPK2 power profiler, the forward-only adaptation (a lightweight fp32 recalibration around the int8 convolutions) costs only 8.3 mJ (6.8% of inference energy) and 21.9 ms on the deployed SIMD-optimized model: forward-only adaptation is cheap on a real microcontroller.

Large language models are powerful, but their interfaces often devolve into a type $\rightarrow$ read $\rightarrow$ retype loop, creating conversational AI fatigue, cognitive load, and eventual task abandonment. To mitigate this, we present RecalibrateGPT, a system introducing five cross-turn operators (Anchor, Replay, Delta, Scope, and Steer) that each target a distinct fatigue type, recalibrating LLM responses through a structured panel by acting on the full conversation history with a single click. Users invoke these operators through the AssistiveButton in one of three operator palette layouts: Vertical, Arc, or Tablet. We conducted two pilot studies with the same 12 advanced LLM users. An initial formative qualitative study identifies a taxonomy of four fatigue types (retyping, scanning, decision paralysis, and context drift) and derives two design objectives for RecalibrateGPT. A follow-up quantitative evaluation finds it reduces perceived cognitive workload by half (NASA-TLX = 2.7) at high perceived usability (SUS = 86.5), suggesting AI fatigue is not just a model-quality issue but an interaction-flow cost that interfaces can remove.

Referring remote sensing image segmentation (RRSIS) aims to delineate targets specified by natural language expressions in remote sensing imagery. Existing methods mainly follow joint fusion segmentation (JFS) or decoupled prompt segmentation (DPS). JFS is efficient but often suffers from limited accuracy because referent localization and mask delineation are optimized under a unified objective, whereas DPS separates localization from mask generation using spatial prompts and foundation segmenters at the cost of higher memory consumption and inference latency. To bridge this gap, we propose DiCoR, a decoupled referent disambiguation and contour recalibration framework built on an efficient JFS pipeline. DiCoR addresses two key challenges: distinguishing the correct referent from ambiguous candidates and refining coarse masks after localization. A disambiguation-aware localization guidance strategy ranks salient candidate regions with adaptive linguistic cues and injects the resulting localization prior into fused features. A lightweight contour recalibration module further predicts residual corrections to coarse logits under localized contour supervision, improving mask quality with limited computational overhead. Experiments on RefSegRS, RRSIS-D, and RISBench show that DiCoR achieves the best segmentation accuracy across all three benchmarks. On RefSegRS, it improves mIoU and gIoU by 5.28% and 2.87% over a competitive JFS method while running 4.7% faster than a representative DPS method, demonstrating a favorable accuracy-efficiency trade-off. Code is available at https://github.com/zyGao1126/DiCoR.

Vision Transformers (ViTs) are widely believed to require more labeled data than CNNs for industrial dense prediction. Through controlled experiments on four industrial datasets, we show that the data-efficiency gap stems from pretraining incoherence, which refers to the statistical mismatch between ImageNet-pretrained ViT backbones and COCO-pretrained CNN necks, rather than from inherent self-attention deficits. We characterize the cross-architecture feature gap and propose a lightweight AlignBlock family for pyramid-level feature recalibration. Our core finding empirically identifies a data-efficiency frontier: for domain-proximal scenes with >= 200 samples, Swin-Graft surpasses YOLOv11x (terminal 703-shot: 0.973 vs 0.956 mAP@50); for domain-distant scenes, CNNs retain advantage (hook 141-shot: 0.900 vs 0.600 mAP@50). Grafted neck weights yield up to 2.5x the mAP of a randomly initialized neck.

Subtype robustness asks whether a model keeps the correct coarse prediction when test examples come from fine-grained subtypes absent from training but still inside a known coarse category. Prior work studies this almost entirely through accuracy. We ask whether the model also stays calibrated. We present the first systematic study of the question across ImageNet, BREEDS, iNaturalist and CIFAR-100 with five architectures. Calibration breaks down on unseen subtypes, where accuracy drops while confidence barely follows, leaving the model systematically overconfident exactly where it has become less accurate. At matched accuracy loss, generic image corruption causes a much larger drop in confidence, so the effect is not a general consequence of losing accuracy. The model reacts to visible degradation but not to in-taxonomy novelty. Recalibration tuned on seen subtypes narrows the gap but does not close it, and out-of-distribution scores flag the affected inputs only weakly. Subtype robustness should therefore be evaluated through calibration, not accuracy alone.

We show with experiments and system-level simulations that it is possible to successfully mitigate the impact of retention loss on inference accuracy degradation by using both circuit-level compensation techniques and batch normalization recalibration at the algorithmic level. Experiments are performed on a single-poly floating-gate (FG) analog non-volatile memory array for analog in-memory computing fabricated in a standard 65 nm CMOS. We use a model of retention-loss statistics calibrated with experiments to evaluate the system-level impact on neural network models such as VGG-10/CIFAR-10 and WideResNet-28-10/CIFAR-100. We show that, after 60 days since programming, combined mitigation techniques enable to recover the baseline inference accuracy within 2-4%

Neural networks are hindered by accumulating dormant neurons and loss of expressivity throughout training, particularly in non-stationary data settings, such as continual supervised and reinforcement learning. Recently, neuron resets have been used to maintain gradient flow and restore plasticity. However, full unit reinitialization often sacrifices peak performance and can destabilize training, leading to policy collapse. To preserve plasticity without destabilizing training, we propose Calibrated Partial Resets (CPR), an optimizer that periodically pulls low-utility neurons toward their initialization, with pull strength scaled by each neuron's utility. Unlike binary reset methods, partial resets avoid brittleness; unlike uniform decay, calibrated utility-scaling concentrates adjustment on the units that need it most. Among compared methods, only CPR avoids policy collapse over 400M training steps in SlipperyAnt, and it outperforms prior decay and reset-based methods on Continual MetaWorld and Continual MinAtar benchmarks. Ablations reveal a tunable trade-off between plasticity and peak performance, highlighting utility-scaled reinitialization as a promising direction for continual learning.

We study the problem of recalibrating an online predictor [KE17, OKS24]: given an arbitrary "hint" sequence of forecasts, the learner must output new predictions that are calibrated while incurring small excess error relative to the original forecasts, under a proper loss. We give an online algorithm that achieves $(\varepsilon, \varepsilon^2)$-recalibration for Lipschitz proper losses in $T \approx \varepsilon^{-3}$ rounds, using an imbalanced extension of the recent simultaneous Blackwell approachability reduction framework of [HTY26]. We show that this tradeoff is optimal by proving a matching lower bound for recalibrating against the squared loss. We also prove a companion $\mathcal{K}_2$-recalibration theorem that obtains the same tradeoffs up to a logarithmic factor. As our main application, we show how our recalibration algorithms can be combined with the online refinement method of [FH23] to obtain simultaneous $\varepsilon$-calibration and $\varepsilon^2$-calibeating for smooth proper losses at the same asymptotic rate, improving upon prior works that achieved these properties separately or with a worse $\varepsilon$ dependence. In particular, the $\mathcal{K}_2$ variant answers a question of [CHJL26] on simultaneously achieving near-optimal calibeating and calibration rates. We also derive extensions to settings with multiple hint sequences. Finally, we empirically evaluate our algorithms on a classification dataset undergoing distribution shift.

Composed image retrieval (CIR) uses a reference image and a text modification to search for a target image. However, such queries often describe several possible images rather than one exact target, making the user's intent ambiguous. Recent methods address this by using conformal prediction to estimate ambiguity and by asking users clarifying text questions. However, these methods have two limitations: their coverage guarantee only holds at the first interaction, and text questions are often insufficient for resolving fine-grained visual differences such as appearance, attributes, or viewpoint. We propose CLARA, a clarification framework that resolves ambiguity by showing users a small panel of visual alternatives. Instead of answering text questions, the user simply selects the prototype image closest to the intended target. This provides a direct visual signal and avoids relying on a model to predict the user's answer. To maintain valid conformal guarantees across multiple interaction rounds, CLARA reweights calibration using the likelihood ratio induced by the user's selection. The displayed prototypes are also constrained to represent the current candidate set and are snapped to real corpus images, ensuring that generated images cannot artificially improve coverage. Experiments on open-domain and fashion benchmarks show that CLARA matches single-turn state-of-the-art retrieval performance, maintains nominal coverage across interaction rounds, and finds the intended target in fewer rounds than strong text-question baselines. Its advantage is especially clear when ambiguity involves viewpoint or fine-grained attributes, where visual clarification is more effective than textual questioning.

In small-batch scientific deployments, labeled target outcomes may be too scarce for reliable shift estimation even when unlabeled target inputs are available. We address the complementary setting where the practitioner has a pre-specified label-shift correction from domain knowledge and asks whether incoming labeled outcomes support it. We show that the per-observation likelihood ratio between a label-shift-corrected predictive and the source predictive is a conditional e-value, so its running product is a nonnegative martingale and Ville's inequality yields an anytime-valid confirmation rule. The log martingale equals the cumulative negative log-predictive density (NLPD) gap between the source and the corrected predictive, converting routine model monitoring into a formal sequential test. Rejection means the incoming data support the posited correction relative to the source predictive, but it is not a precise estimate of the degree of shift. Closed forms are available for GP sources with Gaussian label-shift ratios. GP regression simulations validate Type I control, finite-sample power, miscalibration sensitivity, and the small-batch advantage of a reliable prior over label-based re-estimation.

Composed Image Retrieval (CIR) constitutes a pivotal paradigm requiring models to perform joint reasoning on reference images and modification texts. However, the prevalence of Noisy Triplet Correspondence (NTC) in large-scale datasets severely constrains model performance. Existing denoising methods either target binary mismatches or rely on scalar-based point-wise estimation, neglecting rich global structural correlations among sample populations and dynamic value variations during training, thereby yielding suboptimal results. This paper identifies two critical unresolved challenges: Global Structural Inconsistency of Semantic Correlations and Hard Sample Discrimination Uncertainty. To address these, we propose RankVR, a framework designed to construct a robust CIR model via global structure consistency and dynamic value perception. Specifically, we introduce the Global Structure Consistency Perception (GSCP) module, which utilizes the Effective Rank of the Correlation Matrix to decouple clean samples from structural noise. By measuring rank difference, GSCP identifies samples disrupting macroscopic semantic symmetry. Furthermore, we develop the Adaptive Semantic Value Calibration (ASVC) module to distinguish high-value hard clean samples. By integrating training potential and reliability, it dynamically quantifies the semantic value of each triplet, ensuring effective utilization of hard samples while suppressing noise characterized by logical conflicts. Extensive experiments on the FashionIQ and CIRR benchmark datasets demonstrate that RankVR significantly outperforms existing state-of-the-art methods, validating its superior robustness in noisy environments.

Many applications require statistically valid inference across many related tasks, while using only a handful of high-quality labels per hypothesis. In AI evaluation, these tasks may correspond to model behaviors across prompts, subgroups, or hypotheses; in social science surveys, they may correspond to related questions, populations, or measurement conditions. Prediction-powered inference (PPI) uses abundant but inexpensive proxy measurements to improve inference from limited, ground-truth labels, but commonly used methods treat tasks independently and therefore fail to exploit shared structure across related tasks. This limitation is especially important in settings where only a small number of labels are available per task. To address this issue, we introduce a multi-task prediction-powered inference framework that uses labeled data from related tasks to improve power while preserving task-specific inference. Our methods exploit the shared structure in the proxy-ground-truth relationship through cross-task recalibration, while retaining within-task rectification and power tuning to construct accurate point estimates and confidence intervals. We prove that efficiency gains beyond power-tuned PPI are only possible when the proxy-ground-truth relationship contains nonlinear structure; affine cross-task recalibrations are asymptotically equivalent to using the original proxy. We complement our theoretical findings with experiments on synthetic and semi-synthetic datasets, as well as a case study auditing language models on election-related information during the 2024 U.S. presidential election. Using a large human-annotation study, we show that cross-task recalibration can substantially reduce confidence interval widths when labels are scarce.

Visual outcomes are increasingly central to multimodal large language models, making reliable and fine-grained verification essential for scaling generalist foundation models. In this work, we investigate multimodal meta-verification, which leverages verifier-generated rationales rather than decision-only signals, and explore how to effectively incorporate meta-verification feedback into multimodal verifier training. We identify two key findings. First, symbolic verifier outputs (e.g., bounding boxes) outperform textual explanations as meta-verification rationales, enabling efficient rule-based reinforcement learning rewards while avoiding reliance on model-based rewards from auxiliary judge models. Second, decoupling reinforcement learning objectives for binary judgment and meta-verification substantially outperforms joint reward optimization, due to intrinsic differences in output structure and learning dynamics. Based on these insights, we train OmniVerifier-M1, a generalist visual verifier leveraging symbolic meta-verification and decoupled reinforcement learning. OmniVerifier-M1 provides robust verification and fine-grained error localization, and further enables M1-TTS, a verifier-driven agentic generation system achieving dynamic region-level self-correction. This approach paves the way for more reliable, interpretable, and fine-grained multimodal verification, supporting safer and more controllable foundation model deployment.

Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes. Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and annotation dependency, limiting their adaptability to scene variations and unseen camouflage patterns. To overcome these, we propose the hierarchical consistency learning (HCL) framework, which integrates test-time adaptation for dynamic representation recalibration. Specifically, we design the hierarchical representation reconstruction (HRR) to alleviate feature entanglement by synergizing spatial reconstruction with dual-stream frequency-domain decomposition, enhancing robustness against appearance homogenization. The pixel and spectrum inference provide structural and contextual priors. We further introduce task affinity guidance (TAG) to propagate knowledge across branches via channel-wise affinity, aligning local discriminative cues and mitigating semantic drift. To ensure semantic invariance, we formulate the prototype consistency calibration (PCC), which aggregates region features into compact prototypes and establishes prototype-feature similarity. This imposes implicit and hierarchical constraints that bridge task and representation gaps. Extensive experiments across four camouflaged and four underwater object benchmarks, under three degradation settings, demonstrate that our method consistently outperforms state-of-the-art approaches, highlighting its robustness and generalization under distribution shifts.

Multivariate time series (MTS) classification is foundational to pervasive computing and financial analysis, yet existing multi-scale paradigms are often constrained by suboptimal representation fidelity. We identify two critical bottlenecks: temporal non-causality in standard encoders that induces temporal confounding in non-stationary dynamics, and the absence of explicit channel saliency mechanisms that allows noise to contaminate the latent space. To address these challenges, we propose the Causal Attention and Spatio-temporal Encoder Network (CASE-NET), an architecture designed for structural manifold pre-conditioning. CASE-NET synergizes a Causal Temporal Encoder, which enforces physical arrow-of-time constraints via masked self-attention and causal convolutions, with an Adaptive Channel Recalibration module functioning as an information bottleneck to suppress detrimental noise. Comprehensive evaluations across six heterogeneous domains demonstrate that CASE-NET establishes new state-of-the-art benchmarks on four tasks, achieving a peak accuracy of 98.6% on the AWR dataset and superior robustness in non-stationary regimes.

We present PicoEyes, a unified gaze estimation framework that directly predicts all key attributes of gaze, including 3D eye parameters, eye-region segmentation, optical axis, visual axis, and depth maps, from either monocular or binocular inputs. The framework simultaneously addresses calibration, gaze forecasting, and varying device postures, while also supporting 3D eye reconstruction via joint estimation of eye parameters and depth maps in an end-to-end manner. In addition, we introduce a large-scale multi-view near-eye dataset containing comprehensive 2D and 3D annotations under diverse conditions, including train, test, rewear-test, and calibration sessions. Extensive experiments demonstrate that PicoEyes achieves state-ofthe-art performance, consistently outperforming both academic and industrial gaze tracking methods across nocalibration, calibration, rewear-after-calibration, and forecasting settings. This work establishes a practical, end-toend paradigm for robust and generalizable gaze estimation in mixed reality (MR) applications.

Local temporal patterns in real-world time series continuously shift, rendering globally shared transformations suboptimal. Current deep forecasting models, despite their scale and complexity, rely on fixed weight matrices applied uniformly to all temporal tokens. This creates a static pattern response: models settle into a compromised average, unable to adapt to changing local dynamics. We introduce Dynamic Pattern Recalibration (DPR), a backbone-agnostic mechanism that resolves this via token-level recalibration. Through a lightweight "Perceive-Route-Modulate" pipeline, DPR computes a soft-routing distribution over a learned basis of adaptive response patterns, generating a time-aware modulation vector that recalibrates hidden states via a residual Hadamard product. As a backbone-agnostic adapter, DPR enhances forecasting across diverse architectures with minimal overhead, confirming it addresses a general bottleneck. As a minimalist standalone model, DPRNet achieves competitive performance across 12 benchmarks, validating dynamic recalibration against macroscopic parameter scaling.

Tunnel inspection requires outputs that can support defect localization, measurement, severity grading, and engineering documentation. Existing training-free foundation-model pipelines usually stop at coarse open-vocabulary proposals, which are difficult to use directly in interference-heavy tunnel scenes. We propose a training-free framework TunnelMIND. Specifically, language-guided defect proposals are not treated as final outputs; instead, their spatial support is recalibrated at inference time through dense visual consistency, so that coarse semantic anchors can be transformed into more reliable prompts under tunnel-specific hard negatives. The resulting masks are further reconstructed into structured defect entities with category, location, geometry, severity, and context attributes, which are then mapped to retrieval-grounded explanation and engineering-readable report generation under expert knowledge constraints. On visible, GPR, and road defect tasks, TunnelMIND achieves F1 scores of 0.68, 0.78, and 0.72, respectively. Overall, TunnelMIND shows that training-free tunnel inspection can move beyond coarse localization toward structured defect evidence for engineering assessment.

Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the reach of offline training. Despite initial gains, existing TTT methods for LRMs plateau quickly and do not benefit from additional test-time compute. Without external calibration, the self-generated reward signal increasingly drifts as the policy model evolves, leading to both performance plateaus and diversity collapse. We propose TEMPO, a TTT framework that interleaves policy refinement on unlabeled questions with periodic critic recalibration on a labeled dataset. By formalizing this alternating procedure through the Expectation-Maximization (EM) algorithm, we reveal that prior methods can be interpreted as incomplete variants that omit the crucial recalibration step. Reintroducing this step tightens the evidence lower bound (ELBO) and enables sustained improvement. Across diverse model families (Qwen3 and OLMO3) and reasoning tasks, TEMPO improves OLMO3-7B on AIME 2024 from 33.0% to 51.1% and Qwen3-14B from 42.3% to 65.8%, while maintaining high diversity.

We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images. Despite being trained on tens of millions of images, FMDEs are susceptible to the covariate shift introduced by changes in camera calibration (intrinsic, distortion) parameters, leading to erroneous depth estimates. Our method aligns the distribution of latent embeddings encoding fisheye images to those of perspective images, enabling the reuse of FMDEs for fisheye cameras without retraining or finetuning. To this end, we introduce a set of Calibration Tokens as a light-weight adaptation mechanism that modulates the latent embeddings for alignment. By exploiting the already expressive latent space of FMDEs, we posit that modulating their embeddings avoids the negative impact of artifacts and loss introduced in conventional recalibration or map projection to a canonical reference frame in the image space. Our method is self-supervised and does not require fisheye images but leverages publicly available large-scale perspective image datasets. This is done by recalibrating perspective images to fisheye images, and enforcing consistency between their estimates during training. We evaluate our approach with several FMDEs, on both indoors and outdoors, where we consistently improve over state-of-the-art methods using a single set of tokens for both. Code available at: https://github.com/JungHeeKim29/calibration-token; https://github.com/Suchisrit/CalibrationTokens.

Recent advancements in vision-language models (VLMs) have leveraged large language models (LLMs) to achieve performance on par with closed-source systems like GPT-4V. However, deploying these models in real-world scenarios, particularly on resource-constrained devices, remains challenging due to their substantial computational demands. This has spurred interest in distilling knowledge from large VLMs into smaller, more efficient counterparts. A key challenge arises here from the diversity of VLM architectures, which are built on different LLMs and employ varying token types-differing in vocabulary size, token splits, and token index ordering. To address this challenge of limitation to a specific VLM type, we present Generation after Recalibration (GenRecal), a general-purpose distillation framework for VLMs. GenRecal incorporates a Recalibrator that aligns and adapts feature representations between heterogeneous VLMs, enabling effective knowledge transfer across different types of VLMs. Through extensive experiments on multiple challenging benchmarks, we demonstrate that GenRecal significantly improves baseline performances, eventually outperforming large-scale open- and closed-source VLMs.

We establish a formal connection between the decades-old surrogate outcome model in biostatistics and economics and the emerging field of prediction-powered inference (PPI). The connection treats predictions from pre-trained models, prevalent in the age of AI, as cost-effective surrogates for expensive outcomes. Building on the surrogate outcomes literature, we develop recalibrated prediction-powered inference, a more efficient approach to statistical inference than existing PPI proposals. Our method departs from the existing proposals by using flexible machine learning techniques to learn the optimal ``imputed loss'' through a step we call recalibration. Importantly, the method always improves upon the estimator that relies solely on the data with available true outcomes, even when the optimal imputed loss is estimated imperfectly, and it achieves the smallest asymptotic variance among PPI estimators if the estimate is consistent. Computationally, our optimization objective is convex whenever the loss function that defines the target parameter is convex. We further analyze the benefits of recalibration, both theoretically and numerically, in several common scenarios where machine learning predictions systematically deviate from the outcome of interest. We demonstrate significant gains in effective sample size over existing PPI proposals via three applications leveraging state-of-the-art machine learning/AI models.