NeurIPS 2026 Papers

Latent Diffusion Models dominate generative modeling but face two-stage training complexity and the inherent reconstruction limits of pre-trained autoencoders. Pixel-space Flow Matching offers a simplified end-to-end alternative yet often encounters training instabilities when using the standard $v$-prediction objective. Recent research attributes this difficulty to the off-manifold nature of noised targets, prompting a widespread shift toward $x$-prediction. In this paper, we carefully investigate this prevailing assumption through patch-wise Principal Component Analysis (PCA), and we reveal that the failure of $v$-prediction is primarily a bandwidth issue. Specifically, the velocity field in minor components is mostly determined by the raw noisy input, which differs from the dynamics in the principal component space. Deep backbones must propagate this minor information to the final layer to predict the velocity field, which consumes significant model capacity that should be dedicated to principal components. This is particularly critical in pixel space where noise dimensionality is comparable to the hidden dimension. To resolve this, we simply incorporate a term containing the raw noisy input into the final layer. This architectural bypass enables the backbone to focus on high-level semantics while the final layer efficiently reconstructs the minor velocity field. Our method successfully revives $v$-prediction and achieves competitive performance on ImageNet $256\times256$ dataset compared to $x$-prediction baselines.

Predicting gene expression from H\&E-stained histology images offers a scalable alternative to costly spatial transcriptomics, yet most existing methods operate at the spot level, where signals from multiple cells are aggregated and critical cellular heterogeneity is obscured. Extending this paradigm to single-cell resolution is non-trivial. Naively applying pathology foundation models faces a scale mismatch: their patch-level representations mix multiple cells, whereas per-cell cropping or resizing distorts morphology and removes local context. Conversely, segmentation-based models without strong pretrained visual encoders often lack the morphological representation capacity needed for accurate molecular prediction and inherit errors from imperfect cell boundary masks. Here, we present CELLO, an efficient end-to-end framework that performs a single pathology foundation model forward pass per image and uses grid sampling to extract location-specific features for all cells simultaneously. We further introduce a distance-decay cross-attention module that refines each cell representation using spatially biased local morphological context. Using 52 paired Xenium--WSI samples spanning 12 organs and approximately 10M cells, CELLO achieves state-of-the-art performance in both in-distribution and out-of-distribution settings while delivering at least a 7$\times$ inference speedup over DeepSpot2Cell. Our work establishes a scalable foundation for single-cell gene expression prediction from H\&E images.

Transformers use the same forward computation stream to both predict the next token and store useful state for future token predictions. We formulate the \emph{state-prediction separation hypothesis}: disentangling the two roles yields better language modeling performance. We design a Transformer variant that uses separate computation streams to separate the two functions, and conduct pretraining experiments across various scales. Our experiments show that state-prediction separation consistently offers better data-- and compute--efficiency, improving validation loss and outperforming standard Transformers by 2--3 percentage points on average on downstream tasks. We also conduct extensive empirical analysis that rules out potential confounders and demonstrates the fundamental difference in the gradients our design entails.

We analyze support mismatch in language-model in-context prediction as a frozen-prior Bayes benchmark with finite discrete support. The goal is diagnostic rather than literal: we do not identify production LMs with exact Bayesian updating, but characterize a failure mode whose signatures can be checked in learned in-context predictors. Our main theorem gives the finite-sample predictor-risk bound $R_k^\pi \le C e^{-k\rho_{\min}} + 2\varepsilon_{\mathrm{approx}}^2$, so risk decomposes into an exponentially decaying transient and a nonvanishing support-mismatch floor under exponential-moment control of log-likelihood ratios. In scalar and aligned Gaussian location families, exact two-component analyses match the upper exponent up to a tight factor 2 and show a regime change at $\mu_2=3\mu_1$. Controlled learned-model experiments track the benchmark near crossover. Decoder-only LM diagnostics then test the benchmark signatures: restricted support creates a persistent high-error regime; restoring the missing support sharply lowers error; and modern size-matched distractor controls on Qwen and Llama show that adding a wrong same-cardinality candidate does not reproduce this gain. Multiple-choice, instruction-tuned, cross-family, calibration, null-control, and near-tie checks preserve the same diagnostic picture.

Protein language models (PLMs) provide valuable evolutionary priors for fitness estimation, but may be misaligned with empirical measurements due to context-dependent selective pressures, potentially leading to hallucination-like predictions under limited experimental supervision. In this study, we introduce MmProt, a structure-prompted Multimodal Protein Language Model for preference-aligned fitness prediction with limited experimentally grounded supervision. MmProt adopts a two-stage multimodal learning strategy: contrastive pre-training on 40 million sequence--structure pairs to learn informative multimodal representations, followed by structure-prompted masked language modeling on naturally occurring related variants to capture protein-specific evolutionary constraints. When limited fitness measurements are available, MmProt further calibrates its variant preferences by encouraging the model to rank high-fitness variants above low-fitness variants. Extensive experiments across multiple benchmarks show that MmProt: (i) achieves state-of-the-art average performance on fitness prediction across 11 diverse protein targets under two challenging extrapolation settings, improving over the best-performing PLM baselines by 3.2% and 13.5% on average, respectively; (ii) captures protein-specific evolutionary patterns in a case study of the SARS-CoV-2 Spike protein, where its zero-shot predictions outperform leading PLMs fine-tuned on 512 fitness-labeled variants by a relative improvement of 3.2%; and (iii) delivers competitive results on eight downstream protein representation learning tasks. Together, these results highlight MmProt's potential as a practical tool for investigating protein evolution and supporting broader applications in protein modeling. Code and data are available at https://anonymous.4open.science/r/MmProt-239E/.

Conformal prediction offers a distribution-free coverage guarantee, making it especially attractive for clinical applications. Standard conformal prediction, however, provides such guarantees only at the population level, and its prediction sets can exhibit coverage disparities across clinically important subgroups. A natural remedy is to calibrate within predefined groups. However, this can require access to sensitive subgroup attributes and is prone to a worst-group bottleneck: protecting the most difficult subgroup can inflate prediction sets for all, increasing cognitive burden on decision makers. To this end, we propose Stochastic Grouping Conformal Prediction (SGCP), a conformal framework for subgroup-reliable uncertainty quantification. It learns a stochastic grouping map that allows each sample to draw calibration information from others with similar calibration behavior, yielding a local score law that boosts reliability across subpopulations. We prove that SGCP retains the standard coverage guarantee. Experiments on synthetic and real-world benchmarks show that it consistently reduces subgroup coverage gaps while achieving smaller or comparable prediction set sizes relative to existing baselines.

Electrolyte conductivity is not a property of isolated molecules, but a response over a formulation landscape defined by solvents, salts, composition, salt mole ratio, and temperature. The same molecular component can play different effective roles as its amount and operating conditions change, while the underlying formulation state is observed only through macroscopic conductivity measurements. This makes conductivity prediction a distinctive mixture learning problem: a model must learn how molecular identities become formulation-specific states, rather than merely how molecules are represented. We introduce SolvMix, a framework for learning formulation-state landscapes for electrolyte conductivity prediction. SolvMix constructs component tokens for solvent and salt molecules, calibrates them into amount-aware component states before mixture interaction, and predicts conductivity through a temperature-formatted readout. We evaluate SolvMix on three curated electrolyte conductivity benchmarks, CALiSol-23, DiffMix, and Bamboo-mixer, covering diverse solvents, salts, compositions, salt mole ratios, and temperatures. Across standard splits on all three benchmarks and binned out-of-distribution (OOD) splits on Bamboo-mixer, SolvMix outperforms strong molecular-representation, mixture-aggregation, and geometric-interaction baselines under the reported protocols. Ablations show that the best-performing formulation-state construction combines amount-and-type-aware component tokens, multiplicative amount calibration, token-level interaction followed by mean pooling, and late-concat temperature formatting. OOD results further show clear gains under formulation-level shifts, where static component descriptors and local interaction patterns are least aligned with the required generalization. These results suggest that electrolyte conductivity prediction benefits from treating formulation-state construction as a first-class modeling problem, beyond molecular representation learning or explicit local interaction modeling.

A fundamental open question in self-supervised learning (SSL) is the explicit characterization of the optimal geometry of the learned representations. Recently, LeJEPA identified isotropic Gaussian embeddings as optimal for minimizing downstream prediction risk in Euclidean spaces. However, the corresponding problem for distributions supported on lower-dimensional manifolds, such as the hypersphere, remains unexplored. In this work, we demonstrate that extending this minimax analysis to smooth distributions on Riemannian manifolds fundamentally changes the optimal solution. We show that, under a worst-case formulation, both \(k\)-nearest neighbors and kernel ridge regression induce hyperspherical uniformity. More precisely, we show that uniform distributions on manifolds are optimal for \(k\)-nearest neighbors, and that the uniform distribution on the sphere is optimal for kernel ridge regression with both the exponential dot-product kernel and the linear kernel. This theoretical insight reveals a fundamental limitation of Gaussian embeddings: their non-uniform density induces anisotropic $k$-NN neighborhoods, severely biasing the estimator. To correct this, we introduce \textbf{SPHERE-JEPA}, a theoretically grounded SSL framework. We adapt LeJEPA's Cramér--Wold projection mechanism to enforce hyperspherical uniformity rather than a Gaussian prior. Empirically, SPHERE-JEPA yields significant improvements, boosting texture retrieval mAP by over 6\%, while consistently matching or outperforming LeJEPA on standard benchmarks—including a $+1.8\%$ linear probing gain on ImageNet-1K (ViT-B/14).

Conformal prediction (CP) constructs prediction sets with marginal coverage guarantees under the assumption that the calibration and test distributions are identical. However, under distribution shift, existing approaches primarily align marginal conformal score distributions, which is sufficient to preserve marginal coverage but does not control the conditional coverage error at individual test inputs. As a consequence, CP can remain unreliable in regions where the conditional score distributions are mismatched. In this work, we bound the conditional invalidity of CP under distribution shift in terms of the Wasserstein distance between the calibration and test distributions. This result highlights the role of invertible transport in mitigating conditional coverage degradation. Motivated by this insight, we introduce Branched Normalizing Flow (BNF), a two-branch architecture that normalizes a test input to the calibration distribution and transforms the prediction set of the normalized input back to the test distribution while preserving conditional guarantees. Empirically, BNF consistently improves conditional coverage robustness on nine datasets across a wide range of confidence levels.

Predicting future clinical events from longitudinal electronic health records (EHRs) requires selecting plausible outcomes from a large and structured event space under sparse observations. While clinical coding systems provide hierarchical organization of events, cross-modal and temporal relationships are not explicitly specified and must instead be inferred from data, making prediction difficult for weakly observed longitudinal transitions. We introduce Risk Horizons, a geometry-aware framework for constructing patient-specific candidate spaces for multi-modal next-visit prediction. Risk Horizons combines deterministic coding hierarchies with data-driven lagged cross-modal associations, embeds the resulting clinical graph in hyperbolic space, and retrieves candidate futures using directional risk cones. This reframes longitudinal prediction as ranking within a compact, clinically coherent hypothesis space rather than scoring an unconstrained vocabulary. Experiments on MIMIC-IV and eICU demonstrate competitive next-visit prediction performance, with consistently improved hierarchy consistency across diagnoses, procedures, and medications. Further analysis suggests that hyperbolic structured candidate retrieval is the primary driver of performance, while LLMs are effective as constrained inference-time rerankers operating over clinically grounded candidate sets.

Fast weight architectures offer a promising alternative to standard transformers for long-context modeling by replacing the KV-cache with a recurrently updated fixed-size memory. Despite this architectural shift, they are typically trained with the same next-token prediction (NTP) objective as standard transformers. This creates a mismatch: fast weight models rely on an evolving memory state to support future predictions, while NTP provides only token-level supervision for the immediate next token. We address this mismatch with next-sequence prediction (NSP), a sequence-level extension of NTP that trains models to produce coherent multi-token continuations from their recurrent memory state. To optimize this sequence-level objective, we propose ReFINE ($\textbf{Re}$inforced $\textbf{F}$ast we$\textbf{I}$ghts via $\textbf{N}$ext s$\textbf{E}$quence prediction). ReFINE selects informative token positions based on prediction entropy, generates multi-token rollouts, assigns sequence-level rewards, and optimizes the model with Group Relative Policy Optimization (GRPO). ReFINE is applicable throughout the training lifecycle of pre-trained language models: mid-training, post-training, and test-time training. Experiments on LaCT-760M and DeltaNet-1.3B show that ReFINE consistently outperforms NTP-based supervised fine-tuning in needle-in-a-haystack retrieval, long-context question answering, and diverse tasks in LongBench. ReFINE provides an effective and versatile framework for improving long-context modeling in fast weight architectures.

Graph representation learning has become a standard approach for analyzing networked data, with latent embeddings widely used for link prediction, community detection, and related tasks. Yet a basic design choice, the latent dimension, is still treated as a brittle hyperparameter, fixed before training and tuned by held-out performance. Learned factors are also identifiable only up to rotation and rescaling, so the nominal rank rarely coincides with the quantity that governs model behavior. We propose Spectral Prefix Extraction and Capacity-Targeted Representation Analysis (Spectra), which replaces rank as the unit of analysis with the spectrum of a learned positive semidefinite kernel, trace-normalized so that spectra are comparable across fits. The normalized eigenvalues form a distribution on the simplex, and their Shannon effective rank acts both as a summary of learned capacity and as a controllable training-time coordinate: a single scalar shapes this realized dimension during training, and bisection targets any desired value within the rank cap. To theoretically support that, we show local regularity and monotonicity of the realized-dimension profile. Across collaboration, social, biological, and infrastructure networks, Spectra traces performance--capacity frontiers that make the trade-off between predictive accuracy and realized dimension visible. It performs competitively with strong link-prediction baselines, yields aligned lower-capacity views of the same fitted model through spectral prefixes, and provides a principled handle on capacity in the overparameterized regime. Capacity thus becomes a property of the fitted model rather than a hyperparameter of the training.

Bird's-eye-view (BEV) perception has emerged as a cornerstone of autonomous driving systems, providing a structured, ego-centric representation critical for downstream planning and control. However, real-world deployment faces challenges from sensor degradation and adversarial attacks, which can cause severe perceptual anomalies and ultimately compromise the safety of autonomous driving systems. To address this, we propose a resilient and plug-and-play BEV perception method (RESBev), which can be easily applied to existing BEV perception methods to enhance their robustness to diverse disturbances. Specifically, we reframe perception robustness as a latent semantic prediction problem. A latent dynamic predictor is constructed to extract spatiotemporal correlations across sequential BEV observations, thereby learning the underlying BEV state transitions to predict clean BEV features for reconstructing corrupted observations. The proposed framework operates at the semantic feature level of the BEV perception pipeline, enabling recovery that generalizes across both natural disturbances and adversarial attacks without modifying the underlying backbone. Extensive nuScenes experiments show RESBev notably enhances BEV perception robustness against natural disturbances and adversarial attacks, with latency, parameter and memory analyses verifying its excellent robustness-efficiency trade-off.

Crystal Structure Prediction (CSP) aims to predict a material's 3D structure from its chemical composition, with applications from energy storage to pharmaceuticals. Despite its importance, existing evaluation frameworks suffer from key limitations: they rely on threshold-sensitive or incomparable metrics, focus predominantly on geometric performance while overlooking physical plausibility, and fail to account for polymorphism, where a chemical composition can crystallize into multiple stable structures. In parallel, recent Symmetry-Informed CSP (SICSP) methods often report results alongside standard CSP baselines while receiving crystallographic templates at inference, which constrain the search space and make SICSP a fundamentally different task. To address these limitations, we introduce an Orientation-invariant, Polymorph-Aware, Large Benchmark (OPAL-Bench) that evaluates CSP and SICSP as separate tasks. We evaluate 7 CSP and 2 SICSP methods under OPAL-Bench across 4 datasets using threshold-free geometric and physical distance metrics. Our results show that no method dominates across all metrics, and that geometric performance is not strongly correlated with physical plausibility. Motivated by this gap, we provide OPAL-CSP, an SE(3)-equivariant flow-matching baseline that performs competitively on geometric metrics and consistently ranks among the best on physical ones. By unifying geometric and physical metrics under a polymorph-aware protocol, OPAL-Bench enables a more comprehensive assessment of generative quality in CSP.

Evaluating modern machine learning models often requires labels on large test pools, yet obtaining these labels can be expensive. Active testing reduces this cost by adaptively selecting which test points to label, but existing unbiased estimators do not fully exploit cheap black--box predictions that are often available for the entire pool. We introduce \textbf{Prediction--Powered Active Testing (PPAT)}, a label--efficient risk estimation framework that combines the unbiased LURE estimator with a prediction--powered control variate. Rather than using proxy predictions as biased pseudo--labels, PPAT uses them to residualise the loss, preserving unbiasedness while reducing variance. This control--variate perspective also changes the optimal acquisition problem: we derive residualised oracle proposals and practical surrogate--based acquisition rules tailored to the PPAT estimator. We further establish asymptotic normality for LURE and PPAT, enabling asymptotically valid confidence intervals. Across tabular regression and image classification tasks, PPAT consistently improves over existing active testing baselines, remains unbiased, and reaches the desired coverage level with substantially fewer labels.

Machine learning (ML) is increasingly central to scientific discovery, but translating ML predictions into rigorous scientific claims still requires statistical inference on gold-standard labeled data. A setting that has emerged across the sciences provides the analyst with a small labeled sample, a much larger unlabeled sample, and a pre-trained predictor, with the goal of constructing a confidence interval for a quantity of interest, as was formalized in Angelopoulos et al. (2023). In this ML-driven scientific discovery literature, labeled data is typically the binding constraint on precision while computation is comparatively unconstrained, motivating the design question of how additional computation can extract more inferential value from a fixed labeled set, a fixed unlabeled set, and a fixed predictor. To address this question, we propose the *Prediction-Augmented Residual Tree* (PART) estimator. PART takes the same inputs as the original PPI estimator and replaces their single global rectifier with locally computed rectifiers obtained from an adaptive partition of the feature space. We show that PART outperforms existing methods by producing tighter confidence intervals across real-world datasets from ecology, astronomy, and census reports, among other domains. We then describe and analyze PAQ, an estimator that arises when considering the limit of PART when the depth of its tree grows to infinity. Under appropriate assumptions in the input data, we show that the variance of PAQ shrinks at a rate of $O(N^{-1} + n^{-4})$, showing that there are settings where the rate of $O(N^{-1}+n^{-1})$ of existing methods can be provably broken.

Bayesian persuasion, a central model in information design, studies how a sender, who privately observes a state drawn from a prior distribution, strategically sends a signal to influence a receiver's action. A key assumption is that both sender and receiver share the precise knowledge of the prior. Although this prior can be estimated from past data, such assumptions break down in high-dimensional or infinite state spaces, where learning an accurate prior may require a prohibitive amount of data. In this paper, we study a learning-based variant of persuasion, which we term persuasive prediction. This setting mirrors Bayesian persuasion with large state spaces, but crucially does not assume a common prior: the sender observes covariates $X$, learns to predict a payoff-relevant outcome $Y$ from past data, and releases a prediction to influence a population of receivers. To model rational receiver behavior without a common prior, we adopt a learnable proxy: *decision calibration*, which requires the prediction to be unbiased conditioned on the receiver's best response to the prediction. This condition guarantees that myopically responding to the prediction yields no swap regret. Assuming the receivers best respond to decision-calibrated predictors, we design a provably efficient algorithm that learns a decision-calibrated predictor within a randomized predictor class that optimizes the sender's utility. In the commonly studied single-receiver case, our method matches the utility of a Bayesian sender who has full knowledge of the underlying prior distribution. Finally, we extend our algorithmic result to a setting where receivers respond stochastically to predictions and the sender may randomize over an infinite predictor class.

Predicting mutation-induced changes in peptide--protein binding affinity ($\Delta\Delta G$) is central to therapeutic peptide optimization, but peptide-specific predictors remain limited by scarce labels, target overlap in supervised benchmarks, and costly molecular simulations. We introduce PepDDG, a zero-shot, training-free predictor that ranks peptide mutations by decomposing binding perturbations into three complementary information channels: energetic perturbation, geometric environment, and evolutionary compatibility. Each channel is computed from a wild-type complex structure, transformed into rank space, and combined by non-parametric Borda aggregation, without fitting fusion weights or fine-tuning neural predictors. PepDDG is motivated by rank-covariance analysis showing cross-channel fusion can improve rank correlation when channels retain complementary signal, whereas increasingly expensive refinement of a single energetic channel has diminishing returns. Empirically, the channels are individually moderate but capture distinct mutation regimes, and rank fusion consistently outperforms single-channel variants and training-free baselines. On our curated benchmark of 332 peptide-chain mutations across 33 targets, PepDDG reaches Spearman $\rho = 0.619$; the calibrated PepDDG-Cal variant reaches $\rho = 0.691$. Performance remains strong on short and cyclic peptide subsets, with $\rho = 0.813$ and $0.872$, respectively. These results support complementary evidence fusion on PDB-derived complex structures as a practical alternative to costly same-channel physical refinement for peptide $\Delta\Delta G$ ranking; a separate diagnostic shows that predicted structures can be used when no crystal structure is provided at inference time.

Predicting spatial gene expression from histopathology images enables transcriptomic analysis on archival H\&E samples where matched spatial transcriptomics data is unavailable. Gene expression is organized through cyclic regulatory circuits: transcription factor complexes are themselves products of regulated genes, aggregating upstream gene activity and modulating co-expressed downstream programs (e.g., the ISGF3 complex coordinating hundreds of interferon-stimulated genes through shared cis-regulatory elements). Existing approaches to histology-to-expression prediction, both deterministic and generative, employ generic architectures that ignore this structure. We introduce regulator attention, a mechanism that encodes this cycle by pooling gene representations into a small set of content-dependent tokens via a learned selector and routing them back through cross-attention to modulate gene-level features, in contrast to learnable token arrays whose identity is independent of the input. Within a flow matching framework conditioned on pathology foundation model embeddings, regulator attention consistently outperforms deterministic and generative baselines on correlation-based metrics across four tissue types spanning human cancer, normal tissue, and cross-species samples, with substantial gains on highly variable genes. Beyond predictive accuracy, 87.5\% of regulator tokens align with known biological pathways without supervision. Replacing them with content-independent learned queries eliminates this specialization and degrades predictive performance, isolating content-dependent token generation as the causal mechanism.