NeurIPS 2026 Papers

Domain Generalization (DG) aims to leverage multiple source domains to train models that can generalize to unseen target domains, thereby mitigating the performance degradation caused by domain shifts. Most existing approaches impose unified alignment or suppression constraints in the global feature space, overlooking the heterogeneity of feature channels in terms of class discriminativeness and domain stability. Such coarse-grained constraints may lead to the loss of discriminative information or the retention of domain-sensitive features. To address this issue, we propose a novel DG framework consisting of two core modules: Channel Sensitivity Decomposition (CSD), which employs channel-wise response variances along the class and domain dimensions as empirical proxy signals to partition feature channels into four functional subspaces via a continuous and differentiable soft decomposition mechanism; and Subspace-Specific Feature Augmentation (SSA), which implements tailored augmentation and regularization strategies for different subspaces to suppress environment-related spurious correlations while preserving cross-domain stable discriminative features. Additionally, a KL-divergence-based prediction consistency constraint is introduced to stabilize the training process and enhance model robustness. Extensive experiments on multiple standard DG benchmarks demonstrate that our framework consistently outperforms state-of-the-art methods.

Cross-Domain Recommendation is essential for enabling cross-sell in multi-service platforms; however, limited user overlap and strict cross-service data-sharing constraints often result in little to no ground-truth supervision for cross-domain learning. To bridge this gap, we propose an LLM-based framework for cross-domain recommendation in the non-overlapping user scenario. First, we propose an agentic pipeline that constructs cross-domain pseudo supervision, which is unavailable in the non-overlapping user scenario, by leveraging a user’s source-domain history to generate a target-domain item recommendation. Using this dataset, we further propose \underline{C}oupled \underline{U}ser-G\underline{R}ouped R\underline{E}inforcement Learning (CURE), which induces coupling between in- and cross-domain gradient updates via user-level joint normalization, thereby calibrating synthetic cross-domain updates against reliable in-domain signals. We provide a theoretical analysis showing that user-level coupling stabilizes policy updates under imperfect pseudo supervision and improves cross-domain generalization. Experiments on Amazon Reviews and MovieLens show consistent gains over baselines in cross-domain recommendation, while also improving in-domain performance. An online A/B test demonstrates a statistically significant 56\% lift in click-through rate over existing ML methods.

Parameter-Efficient Fine-Tuning (PEFT) commonly adapts pretrained weights through low-rank updates, and recent methods further exploit the singular value decomposition (SVD) of the base weight for initialization or subspace selection. However, these methods do not explicitly preserve the coupled geometry between the pretrained left and right singular bases. Motivated by recent minimum-perturbation theory, which shows that stable finetuning admits a coherent SVD rotation in which a single orthogonal $Q$ acts on both the left singular basis $U_0$ and the right singular basis $V_0$, we prove a per-slice analogue: each row slice of $W_0$ can be adapted by a shared orthogonal rotation $Q_i$ on its left basis $U_i$ and right basis $V_i$ together with a diagonal spectrum shift. We instantiate this form as **CORA** (*Coherent Orthogonal Rotation Adaptation*), which applies per-slice orthogonal rotations and a per-layer diagonal scale to the rank-$r$ SVD truncation of $W_0$. CORA uses $\tfrac{1}{2}m(r{-}1)$ trainable parameters per linear layer, about $4{\times}$ fewer than LoRA at the same rank. CORA outperforms LoRA, DoRA, PiSSA, and MiLoRA on commonsense reasoning and code generation while using $\sim 8{\times}$ fewer parameters.

Convolutional neural networks (CNNs) are widely used for time-series classification, but their deployment in critical domains requires understanding the temporal and spectral patterns that drive their predictions. Concept extraction (CE) methods identify such patterns by analyzing representations within the models' latent space. However, existing time-series CE methods have three limitations: they operate only in the time domain and overlook frequency features, predefine the number of concepts, and produce localizations misaligned with the regions the model uses. We address these limitations by proposing CENDRe, a concept extraction method for CNNs. It first discovers concepts by clustering per-timestep latent representations in two stages, where silhouette-guided aggregation selects the number of concepts automatically. Then, it localizes each concept through gradients of a presence score that contrasts the latent representations with their prototypes, producing masks that concentrate on the regions driving the concept. These gradients, propagated through a differentiable invertible mapping of the input such as a Fourier transform, yield localizations for the same concepts in the frequency domain. Finally, each concept receives a relevance score that quantifies its contribution to each class. On synthetic benchmarks, CENDRe achieves representation correctness comparable to state-of-the-art CE methods and substantially higher importance correctness. On real bearing-fault data, CENDRe extracts the frequency bands driving the model's predictions, located in regions commonly inspected for fault diagnosis, producing evidence to assess the model that time-domain CE methods cannot.

Drug-target interaction (DTI) prediction is pivotal for accelerating drug discovery, yet existing methods struggle with generalization under cross-domain distribution shifts. Conventional approaches typically rely on static protein representations and assume distributional consistency between source and target domains, often resulting in poor calibration when encountering novel protein families or scaffolds. To address this issue, we present $\textbf{Bi}$-view $\textbf{Fold}$-aware prediction (BiFold), a novel unified interaction-adaptive framework that enhances generalization via dual-view representation learning and calibration-aware adaptation. BiFold synergistically models sequence and structural evidence, introducing a routing module to dynamically fuse the two views at the feature-channel level and exploit complementary information. Furthermore, we design a calibration-aware training principle that aligns domain statistics and encourages flatter source solutions. Crucially, target supervision is introduced only after a forward-only warm-up phase to prevent reinforcement of miscalibrated early predictions, effectively mitigating confirmation bias in pseudo-label learning. Extensive experiments demonstrate that BiFold consistently outperforms the state-of-the-art methods across diverse datasets in both in-domain and cross-domain settings. Additionally, interpretability analysis reveals that the routing module partitions the feature space into view-dominant and view-neutral subspaces, providing concrete evidence of adaptive multi-modal complementarity.

Vision-language models such as CLIP enable zero-shot classification from arbitrary class names, but under test-time corruptions, their visual encoder projects distorted features onto incorrect textual anchors with high confidence—a phenomenon we term \textbf{modality bias}. Standard entropy minimization reinforces these overconfident errors, triggering a destructive confirmation-bias loop that collapses the predicted label distribution. We propose \textbf{CDIM} (Cross-Modal Information Maximization), an online test-time adaptation method that breaks this loop at three levels. At the \textit{representation level}, a frozen self-supervised DINO backbone is combined with CLIP via a cross-covariance logit ensemble; by projecting text prototypes into DINO's geometric space—rather than the reverse—the classifier operates free of text bias. At the \textit{optimization level}, a gated information-maximization objective (GT-IM) pairs per-sample sharpening with batch-level diversity, while an adaptive gate excludes unreliable samples from the gradient. At the \textit{prediction level}, an online logit adjustment corrects the residual class-distribution skew. Ultimately, \textbf{CDIM} validates its broad effectiveness by delivering robust, competitive performance across demanding setups, including continual TTA, mixed-domain shifts, and diverse domain generalization benchmarks.

Recently, reinforcement learning (RL) has been widely applied during post-training for diffusion large language models (dLLMs) to enhance reasoning with block-wise semi-autoregressive generation. Block size has therefore become a vital factor in dLLMs, since it determines the parallel decoding granularity and affects the rollout trajectories during RL optimisation, e.g., GRPO. Instead of investigating the effect of block size during inference on individual domains, this paper studies block size from a domain conflict perspective for dLLM RL post-training in multi-domain scenarios. The main contributions are: (1) a formulation of domain block size conflict in multi-domain RL for dLLMs, which will largely affect the post-training effectiveness for rollout-based RL methods; (2) a novel dataset, \textbf{Block-R1-41K} is constructed with a best-improved training block size for each sample, which also induces a Block Size Conflict Score to quantitatively measure the domain conflict; (3) a new benchmark, Block-R1, for flexible RL post-training for dLLMs in both single and cross domain; and (4) a simple yet powerful cross-domain post-training method with sample-level best-improved training block sizes. Extensive experiments on 13 distinct datasets, 7 latest RL algorithms, and various different dLLM backbones are covered in Block-R1. The benchmark is open-sourced at https://anonymous.4open.science/r/Block-R1-2026, with the dataset released at https://huggingface.co/datasets/dLLM-R1/Block-R1-41K.

Sharpness-Aware Minimization (SAM) is widely used in domain generalization to promote flat minima that generalize to unseen distributions. Existing SAM-based methods typically penalize the sharpness of the *average* loss across domains. We show that this prevailing formulation—termed AvSAM—has a fundamental geometric limitation: it can favor solutions with misaligned domain-wise dominant Hessian eigenvectors. As a result, such solutions may appear flat on average while remaining sharp within individual domains. To address this limitation, we propose an alternative objective that penalizes the average *domain-wise* sharpness. We show that this objective decomposes into the AvSAM objective plus a non-negative residual term, which we call the *Cancellation Gap*. This gap is minimized if and only if the domain-wise dominant eigenvectors are aligned up to sign, indicating that it mitigates AvSAM's tendency to favor misaligned solutions. However, we further uncover a degeneracy: the Cancellation Gap can become small without improving alignment when sharpness is highly imbalanced across domains. To mitigate this failure mode, we propose Cancellation Gap Minimization (CGM), which augments the objective with a squared coefficient-of-variation ($\mathrm{CV}^2$) regularizer to discourage sharpness imbalance. Experiments show that CGM achieves the best average performance across standard domain generalization benchmarks among strong baselines. Diagnostic analyses further confirm reduced domain-wise sharpness and improved alignment of dominant Hessian eigenvectors.

Language models (LMs) obtain much of their capability from the diversity of their training data. This is possible because neural architectures like transformers are remarkably flexible and can handle a variety of domains such as natural language, code, and mathematics. This raises the question: are transformers optimal for any specific domain? In this position paper, we present empirical evidence that the inductive biases of transformer-based LLMs should be re-examined, since, while broadly useful, they are often suboptimal on subsets of their training data. **Methods.** To support this position, we use a method that learns new activation functions within a transformer as a tool to explore the space of inductive biases. We train the resulting modified architectures on various data subsets. A large-scale evaluation shows that vanilla transformers are relatively easy to improve, but mostly on a per-domain basis. For example, an architecture optimized for a natural language dataset like FineWeb performs well on another such dataset like TinyStories, whereas architectures optimized for mathematics perform poorly on natural language. We also identify the mechanisms responsible for these improvements. **Implications.** These results call for re-evaluating core design choices in language models. We do not advocate a return to handcrafted, domain-specific models. Instead, we emphasize that different domains can benefit from different learning mechanisms. This will require new designs that preserve cross-domain interactions, analogous to how reasoning in the brain arises from the interaction of multiple specialized networks. We argue that this perspective may be key to improving reliability and data efficiency.

Link prediction (LP) is a widely applied task in graph learning. Conventional LP approaches typically follow a dataset-specific paradigm, requiring independent training for each graph and incurring high computational and maintenance costs in large-scale applications. Motivated by these limitations, recent work explores Universal Link Prediction (ULP), aiming to enable training-free inference on arbitrary unseen graphs. However, existing methods primarily rely on subgraph sampling strategies to construct universal representations, which are unable to capture higher-order information due to the exponential growth of higher-order neighborhoods. As a result, they often under-perform on graphs where long-range signals are essential, such as biological networks. Moreover, their prediction models are typically domain-agnostic and lack the ability to adapt to different graph domains, leading to limited generalization. To address these challenges, we propose an Atlas-based Universal Link Prediction framework (AtlasULP), which introduces the relation atlas to capture structural associations between node pairs from both global and local perspectives, enabling a comprehensive characterization of connectivity signals across diverse graph domains. Building upon this representation, we develop a domain-guided prompting ULP model, which generates domain-aware prompt tokens from contextual structures and performs prompt-guided in-context prediction for adaptive link inference. Extensive experiments demonstrate that AtlasULP consistently outperforms state-of-the-art methods across diverse graph domains.

Despite the growing popularity of Multimodal Domain Generalization (MMDG) for enhancing model robustness, it remains unclear whether reported performance gains reflect genuine algorithmic progress or are artifacts of inconsistent evaluation protocols. Current research is fragmented, with studies varying significantly across datasets, modality configurations, and experimental settings. Furthermore, existing benchmarks focus predominantly on action recognition, often neglecting critical real-world challenges such as input corruptions, missing modalities, and model trustworthiness. This lack of standardization obscures a reliable assessment of the field's advancement. To address this issue, we introduce MMDG-Bench, the first unified and comprehensive benchmark for MMDG, which standardizes evaluation across six datasets spanning three diverse tasks: action recognition, mechanical fault diagnosis, and sentiment analysis. MMDG-Bench encompasses six modality combinations, nine representative methods, and multiple evaluation settings. Beyond standard accuracy, it systematically assesses corruption robustness, missing-modality generalization, misclassification detection, and out-of-distribution detection. With $7, 402$ neural networks trained in total across $95$ unique cross-domain tasks, MMDG-Bench yields five key findings: (1) under fair comparisons, recent specialized MMDG methods offer only marginal improvements over ERM baseline; (2) no single method consistently outperforms others across datasets or modality combinations; (3) a substantial gap to upper-bound performance persists, indicating that MMDG remains far from solved; (4) trimodal fusion does not consistently outperform the strongest bimodal configurations; and (5) all evaluated methods exhibit significant degradation under corruption and missing-modality scenarios, with some methods further compromising model trustworthiness. We release MMDG-Bench to enable more rigorous, reproducible, and directly comparable evaluation, addressing current limitations in evaluation practices and providing a stronger foundation for future progress in multimodal domain generalization.

Remote photoplethysmography (rPPG) enables non-contact physiological measurement from facial videos, but performance often degrades under unseen environments due to severe domain shifts. Continual learning offers a practical paradigm for updating rPPG models over sequential domains. However, it is challenged by two coupled issues: First, adapting to new domains may overwrite previously acquired physiological representations, resulting in the degradation of physiological consistency across domains. Second, drastic environmental variations induce heterogeneous facial video distributions, making the adaptation process unstable and prone to suboptimal convergence. To address these challenges, we propose ApexPhys, a continual rPPG framework that simultaneously anchors physiological invariance and expands domain plasticity. Specifically, we introduce a Backbone Consistency Representation Preservation (BCRP) mechanism, which leverages the Fisher Information Matrix to identify and preserve parameters critical to physiological consistency. To enhance adaptation flexibility under diverse environmental shifts, we further propose a Hierarchical Expansion Strategy (HES) that autonomously perceives layer-wise distribution discrepancies and dynamically expands hierarchical adaptation branches. Additionally, we develop a Prior-Guided Pathfinding (PGP) strategy, which leverages parameter inheritance to guide the adaptation along a stable trajectory. Experiments on five public datasets demonstrate that ApexPhys achieves strong anti-forgetting performance and robust adaptation under continual learning.

Continual pre-training (CPT) enables injecting domain-specific knowledge into large language models during the learning rate annealing phase. However, this compute-efficient paradigm forces practitioners to navigate a challenging optimization space: simultaneously choosing the injection fraction $\lambda$, the data mixture ratio $r$, and the re-warmup peak learning rate $\eta$. Because existing scaling laws have yet to comprehensively integrate and couple these interacting variables, they cannot reliably forecast the resulting trade-offs and final convergence outcomes across unseen injection configurations. To bridge this gap, we introduce the Annealing-phase Domain Injection Scaling Law (ADIS-Law), a parametric framework that explicitly models late-stage distribution shifts as physical perturbations applied to the base pre-training trajectory. ADIS-Law formalizes two opposing macroscopic behaviors: general-domain performance follows a linear forgetting-recovery process, whereas target-domain adaptation adheres to a power-law adaptation trend. Across data-budget and model-scale extrapolation, ADIS-Law predicts target-domain trajectories with an average Spearman correlation of $0.947$ and forecasts tail losses with relative error below $5\\%$. We further show that ADIS-Law can predict optimal injection strategies at extrapolated scales: it ranks target-scale candidate policies with a mean Spearman correlation of $0.936$. By replacing blind grid search over $(\lambda, r, \eta)$ with a single fitted law, ADIS-Law offers a data-driven approach for strategy selection in annealing-phase domain injection.

Graph domain adaptation (GDA) has emerged as an important problem in graph machine learning when the distribution of the source graph used for training differs from that of the target graph used for testing. While much of the prior work on GDA has focused on aligning node representations across source and target domains, recent studies show that such approaches can be suboptimal in the presence of graph structure shift, where the underlying connection patterns between nodes change across domains. In this work, we develop a unified pairwise distribution matching framework for mitigating conditional structure shift (CSS), a specific form of graph structure shift in which conditional edge distributions vary across domains. The framework recovers existing GDA methods as instances of moment matching and motivates PLSA, a new likelihood-based method that uses calibrated probabilistic predictors on connected target node pairs. Theoretically, we establish finite-sample guarantees for both the likelihood-based and moment-matching estimators under the contextual stochastic block model. Our analysis uses Bernstein-type concentration bounds for edge-weighted U-statistics, leading to error bounds that reflect both the effective number of observed edges and the conditioning of the corresponding likelihood or moment-matching problem. We complement our theoretical results with empirical studies that demonstrate the effectiveness of the proposed framework.

Self-play, a type of training algorithm that enables a model to self-improve, has recently shown promising empirical results in the context of formal theorem proving using Large Language Models (LLMs). (Dong & Ma, 2025) instantiate self-play with two cooperating agents: a prover, which proves theorems, and a conjecturer, which generates new theorems as a curriculum to the prover. In this paper, we provide a theoretical framework for understanding the self-improvement capabilities of self-play algorithms for theorem proving. First, we formalize the set of theorems as a graph, with nodes as theorems and edges between pairs of theorems with similar semantics. We introduce a set of primitive assumptions that characterize the guarantees of a trained prover and how a conjecturer can access the structure of the graph. Second, we show that if the underlying graph of theorems is well-connected, then a prover-conjecturer system, where the conjecturing algorithm is based on a reversible random walk, is sufficient to grow the set of proved theorems exponentially. Third, we formulate an issue of diversity encountered empirically by self-play algorithms in our framework, where the conjecturer tends to generate artificially complex and non-fundamental theorems. We propose a diversity measure for a training distribution of theorems generated by a conjecturer and an improved conjecturing algorithm that locally maximizes this diversity measure, by computing the diffusion similarity between neighboring theorems in the theorem graph. Finally, we describe a method to compute the diffusion similarity by first using contrastive learning to embed nodes into Euclidean space and second computing the inner-product between the embeddings.

How much of zero-shot benchmark accuracy is captured by word-level alignment between a pre-training corpus and the benchmark target? We study this question through word-level unigram cross-entropy (UCE), a tokenizer-agnostic, model-free measure of lexical alignment between a reference corpus and a target benchmark. Likelihood training allocates probability mass according to the pre-training corpus, and likelihood-based zero-shot evaluation partly reads out the lexical alignment between this mass and the benchmark target. Cleanly tracing how the lexical imprint of pre-training data scales with corpus--benchmark alignment requires controlled from-scratch pre-training that varies corpus identity while holding the training recipe fixed. Across this controlled sweep, spanning $11$ zero-shot benchmarks, $4$ pre-training corpora, and $3$ model scales, we find that corpus--benchmark lexical alignment, UCE, consistently tracks zero-shot accuracy on every benchmark, with corpora more aligned with the benchmark (lower UCE) achieving higher accuracy. The same signal extends from measurement to control at finer scopes. At the document level, strengthening the imprint by selecting training documents to maximize lexical alignment with the benchmark yields a data-selection rule that improves accuracy over same-size random sampling and an importance-resampling baseline across sources and scales. At the prompt level, matching the imprint per prompt by routing each prompt to the drafter whose domain corpus is most lexically aligned with it gives a training-free routing rule for speculative decoding and improves throughput over a generalist-drafter baseline. Taken together, pre-training corpora leave a measurable lexical imprint on zero-shot behavior, and UCE provides a model-free probe of lexical alignment between reference and target data.

Positional encoding in Vision Transformers presents a recurring trade-off: spatial relative-position tables (Swin) carry thousands of parameters per block and require ad-hoc interpolation to transfer across resolutions, while no-bias designs leave the attention logits geometry-agnostic. We propose a relative positional bias parameterized directly in the frequency domain. This parameterization yields three benefits over the standard spatial-table position encoding: (i) it expresses the same translation-equivariant bias with $3.25\times$ fewer parameters than Swin's spatial table at the same head count; (ii) it admits a closed-form, structurally exact transfer to a different patch grid, in contrast to bilinear interpolation of spatial tables which smooths the learned structure; and (iii) it shares the same parameterization style as a frequency-domain spectral mixer, enabling co-design of positional encoding and token mixing in a common substrate. We demonstrate the bias inside our **Dual-Domain Residual (DDR)** framework, in which a spectral mixer and a gated attention head act as parallel residuals within each block. Head-to-head, the frequency-domain bias recovers $+1.98$ pp over Swin RelPos and $+2.74$ pp over no positional bias; removing the entire attention branch (which carries the bias) drops accuracy by $5.35$ pp, while removing the spectral branch drops it by $2.22$ pp. On ImageNet-1K from scratch, DDR outperforms SpectFormer at every comparable parameter budget, by $+2.0$ pp at Tiny (DDR-Ti-SF, 10.7M, 78.9\%) and $+0.4$ pp at Base (DDR-B-Deep, 63.1M, 82.5\%); at sub-parity parameters, DDR-Ti+ (8.9M, 77.9\%) exceeds SpectFormer-Ti (9.0M, 76.9\%) by $+1.0$ pp. The learned per-layer gates concentrate spectral processing in early blocks and attention in late blocks, qualitatively matching the schedules that are hand-coded in the previous hybrid models.