NeurIPS 2026 Papers

Palmprint modality offers a privacy-preserving biometric solution, yet its deployment is hindered by the domain gap between controlled enrollment and unconstrained authentication. Existing datasets are largely restricted to controlled setups and fail to capture the compound variability of real-world environments. In this paper, we introduce X-Palm, a cross-domain dataset comprising 6,006 palm images from 103 individuals (206 hands). To the best of our knowledge, X-Palm is the first palmprint dataset providing novel paired-identity acquisition specifically designed to bridge the gap between reliably controlled multispectral enrollment and unconstrained mobile authentication while encompassing a broad spectrum of in-the-wild variability. Unlike existing datasets that focus on single to a few variations, X-Palm addresses the massive modality and environmental shifts encountered in practical deployments by capturing paired data for identities across two distinct domains: (1) a controlled Multispectral Palmprint setting using our custom-developed scanner, and (2) an unconstrained smartphone palmprint setting that is participant-driven, incorporating simultaneous variations in hardware, hand pose, illumination, background, camera-to-hand distance, perspective, and palm surface conditions (e.g., moisture and occlusions). Our extensive benchmarks of 12 SOTA models reveal that while existing methods achieve high performance on controlled data, they experience severe performance collapse on X-Palm. Conversely, models trained on X-Palm demonstrate consistent robustness across domains, positioning X-Palm as a valuable resource for training a model towards real-world, cross-domain generalization. Data access instructions and the related benchmarking codes are publicly available at: https://github.com/X-Palm/X-Palm-2026

Rehearsal-free continual learning with parameter-efficient adapters can be cast as a sequence of task-vector write-in operations: for each new task, a low-rank adapter is learned and merged into a running model. We propose Proximity Regularized Merging (PRM), a minimal modification to sequential LoRA merging that adds a proximal penalty during task-vector training without changing the subsequent write-in rule. PRM acts as a robust task-vector regularizer: in the reported Base$\rightarrow$+Prox diagnostics, it improves AAA across multiple write-in rules, backbones, and class-incremental settings, while its fixed-coefficient variant remains competitive with strong coefficient-based baselines. Mechanistically, matched-prefix norm controls and proximal-strength sweeps show that proximal training shrinks the task-vector radius, lowers Fisher-weighted interference, broadens the coefficient plateau, and exposes a stability--plasticity trade-off. Together, these results suggest that the effectiveness of sequential LoRA merging depends not only on how much of a task vector is written in, but also on whether the task vector itself has been trained to be mergeable.

Pretraining noise in foundation models has been shown to significantly impair the generalization performance of downstream tasks, leading to catastrophic inheritance. However, when downstream tasks arrive sequentially, how pretraining noise affects continual adaptation, which involves the forgetting of previously learned knowledge, remains underexplored. This paper is the first to study this problem. Using asymmetric label noise as a realistic setting, we find that pretraining noise persistently degrades performance on new tasks during continual adaptation and may further exacerbate forgetting of previously adapted tasks. Further analysis shows that the persistent effect of pretraining noise mainly manifests as inherited output contraction, where the logit gap between the true class and competing classes is compressed. To mitigate this issue, we propose Ambiguous Boundary Correction (ABC), a method that performs anchor-guided neighborhood reweighting to correct ambiguous regions induced by inherited output contraction. Experiments on synthetic and real-world noisy pretrained models show that ABC improves robustness to pretraining noise under both domain shifts and class shifts.

Unsupervised domain adaptation has become an important paradigm for mitigating distribution shift in time series classification. However, existing time series domain adaptation methods typically align source and target data at a fixed time scale and simply fuse time-frequency features before uniform alignment. Furthermore, they do not consider the impact of noisy samples on distribution alignment. To address these limitations, we propose CSPAN (Time-Frequency Decoupled \textbf{C}ross-\textbf{S}cale \textbf{P}artial Optimal Transport \textbf{A}lignment \textbf{N}etwork) for time series domain adaptation. CSPAN first constructs segment-scale time-frequency candidates, and then uses Segment-Scale Aware Top-k Fusion to select the most suitable segment-scale feature representation. It then performs cross-domain alignment after decoupling time and frequency through Temporal Partial Optimal Transport and Frequency Partial Optimal Transport, where temporal domain alignment is guided by the transferability estimated from a probing transport plan, and frequency domain alignment is guided by the discriminability estimated by an auxiliary frequency classifier. By combining segment-scale representation selection, time-frequency decoupling, and partial distribution alignment, CSPAN enables more flexible cross-domain matching. Extensive experiments on six datasets demonstrate CSPAN’s consistent superiority, achieving an average accuracy improvement of 3.16\% in cross-domain scenarios. Code is available at the anonymous link: \url{https://anonymous.4open.science/r/CSPAN-35FB/}.

Convolutional neural networks trained on ImageNet are known to rely heavily on local high-frequency texture, an inductive bias that translates into fragile robustness against distribution shifts in real-world environments. Event cameras, in contrast, record only changes in scene brightness and are therefore well suited to capturing contour information; however, due to the absence of diagnostic benchmarks in the event domain, the inductive bias that event-camera data instills in vision models has remained unexplored. In this work, we use knowledge distillation from the event domain to the RGB domain so as to exploit the rich evaluation toolkit available in the RGB domain and systematically dissect this inductive bias. Our experiments show that distillation from the event domain induces, in the RGB domain, notable color invariance, shape bias, and robustness to high-frequency noise. We identify the underlying mechanism as the model suppressing its dependence on high-frequency texture while simultaneously acquiring a strong dependence on edge-based object shape. This hypothesis is supported by changes in how color and spatial information are processed at the early layers, together with a "spectral trade-off" in which robustness to the absence of high-frequency components coexists with vulnerability to contamination of the relied-upon frequency bands and to disruption of geometric structure. We further show that this inductive bias differs markedly from existing robustification methods and that it functions as a strong prior for diverse downstream tasks that demand shape-based reasoning, such as medical imaging. The code and experimental configurations for reproducing our experiments are submitted alongside this paper as supplementary material.

We introduce and analyze Target-Induced Loss Tilting (TILT) for unsupervised domain adaptation under covariate shift. It is based on a novel objective function that decomposes the source predictor as $f+b$, fits $f+b$ on labeled source data while simultaneously penalizing the auxiliary component $b$ on unlabeled target inputs. The resulting fit $f$ is deployed as the final target predictor. At the population level, we show that this target-side penalty implicitly induces relative importance weighting at the population level, but in terms of an estimand $b^*_f$ that is *self-localized* to the current error, and remains *uniformly bounded* for any source-target pair (even those with disjoint supports). We prove a general finite-sample oracle inequality on the excess risk, and use it to give an end-to-end guarantee for training with sparse ReLU networks. Experiments on controlled regression problems and shifted CIFAR-100 distillation show that \tilt improves target-domain performance over source-only training, exact importance weighting, and relative density-ratio baselines, with a stable dependence on the regularization parameter.

Medical visual question answering (VQA) and federated learning (FL) have gained prominence as critical methods for clinical artificial intelligence, with VQA supporting image-based diagnostic reasoning and FL allowing institutions to train models jointly without sharing sensitive patient data. However, existing approaches face substantial challenges in cross-modal vertical FL settings, where each participating institution possesses unimodal, modality-specific textual data without access to paired multimodal samples. To address this limitation, we introduce SynTeX-FL, a federated framework designed to enable cross-modal text transfer for medical VQA without sharing raw data. Moreover, SynTeX-FL applies a reconstruction-based text synthesis model that extracts clinically relevant semantics from medical images to generate cross-modal textual representations. Furthermore, the proposed method incorporates modality-specialized low-rank adaptation (LoRA) modules to enhance modality-aware representations for each imaging domain. During aggregation, the central server employs discriminator-based quality scores and source-aware weighting strategies to integrate heterogeneous client contributions. Extensive experiments on multimodal medical VQA benchmarks demonstrate that SynTeX-FL significantly outperforms current FL baselines, providing a robust and efficient solution for cross-modal reasoning in decentralized clinical environments.

Multi-modal large language models (MLLMs) achieve strong modality understanding by pairing a large language model (LLM) with an encoder for a target modality such as vision, video, or audio. However, improving an MLLM's capability for a given modality typically requires additional training on large modality-specific datasets, incurring substantial data collection and compute costs. Model merging offers an alternative, but it is often infeasible for data-scarce, large per-sample size, or domain-specific modalities (e.g., audio and video), where same-modality model variants are rarely available. In this work, we characterize an intriguing asymmetric phenomenon: merging a well-aligned, data-rich source-modality MLLM into a data-scarce target-modality MLLM substantially improves the target on its own benchmarks. Our theoretical and empirical analyses show that this gain stems from enhanced alignment between modality-specific and textual tokens, induced by the stronger donor modality. Specifically, we derive a mutual-information lower bound that is monotonic in alignment-related quantities and strongly correlated with downstream MLLM performance. Building on this principle, we propose Directional Cross-Modal Alignment Transfer (DCAT), a novel framework that transfers textual alignment from a strong, well-aligned source (donor) modality to a weak target (recipient) modality, boosting target-modality performance without further fine-tuning. We further show that the alignment-enhancing objective admits a closed-form weight-space solution computed from only a small calibration set. DCAT outperforms existing model-merging methods, offering an efficient path toward cross-modal alignment transfer.

The performance of *Graph Domain Adaptation* (*GDA*) is fundamentally limited by *covariate-driven* discrepancies between source and target graphs, captured by *Covariate Shift* (*CS*) in the joint feature-structure space beyond label-related formulations. We show that CS induces bias at two non-interchangeable stages of *Graph Neural Network* (*GNN*) computation: *Feature Shift* (*FS*) distorts representations before message passing, while *Feature-Conditional Structure Shift* (*FCSS*) biases propagation, rendering single-stage alignment intrinsically insufficient. Based on this, we propose *Dual Alignment for Covariate Shift* (*DACS*), a stage-aware GDA framework that aligns discrepancies at their source. DACS mitigates FS via adversarial feature alignment and addresses FCSS through layer-wise reweighting to correct propagation bias, followed by final adversarial alignment for residual mismatch. This design follows directly from the stage-wise structure of CS rather than heuristic combinations of alignment modules. We further show that representation and propagation biases correspond to distinct components of target-domain error that cannot be eliminated in isolation. Experiments on synthetic and real-world benchmarks demonstrate that DACS consistently outperforms prior methods, especially under complex and coupled distribution shifts.

Source-free domain adaptation (SFDA) adapts a pre-trained source model to an unlabeled target domain without access to source data. However, existing SFDA studies have predominantly focused on classification tasks, leaving time series forecasting (TSF), a fundamentally different problem with continuous outputs and complex temporal dependencies, largely unexplored. In this work, we identify unique characteristics and key challenges of SFDA in TSF: 1) forecasting labels correspond to future temporal segments of the same underlying signal, enabling us to split target input and construct a self-supervised learning task, thereby training an accurate short-term forecasting model to provide high-quality pseudo-labels; 2) however, such supervision remains inherently *local* rather than *global* for long-horizon source model adaptation. To fill this gap, we propose the notion of Spectral Energy Allocation (SEA) pattern, defined over a short-long signal pair. The SEA pattern provides a structured correspondence that bridges signals across different temporal horizons, enabling reliable short-horizon pseudo-labels to guide long-horizon adaptation. Extensive experiments demonstrate that our method substantially outperforms baselines across different forecasting backbones.

Domain generalised semantic segmentation (DGSS) has recently benefited from combining multiple foundation models, such as vision-language and vision foundation models, to leverage their diverse representations for generalisation. Existing multi-model approaches share a common design choice: cross-model fusion is restricted to depth-aligned layers, implicitly assuming that mutually beneficial information resides at the same depth across models. However, foundation models pretrained under different objectives may develop distinct representation hierarchies, making the optimality of depth-aligned fusion questionable. Moreover, we observe that the foundation models have different depth-wise domain sensitivity. Motivated by these observations, we propose a Sparse All-Layer Connector (SALC) that enables each layer to access information from preceding layers of another model. As the number of accessible layers grows with depth, dense aggregation may hurt generalisation. SALC therefore learns to adaptively select a sparse subset of informative layers. We further introduce a candidate dropout regularisation that strengthens sparsity and encourages SALC to explore diverse layers, leading to more robust selection. Across four foundation model combinations and three DGSS evaluation settings, the proposed design demonstrates stronger generalisation than conventional depth-aligned fusion. Code will be public upon acceptance.

Scientific communication increasingly relies on slide-based narrated videos rather than static PDFs. However, transforming a paper into a presentation video is not a conventional text-to-video task. It requires preserving technical rigor, rendering dense multimodal assets faithfully, and synchronizing narration, subtitles, and cursor motion over long horizons. Current research faces two critical bottlenecks: (1) Benchmark Gap: existing evaluations are restricted to narrow domains or structured LaTex inputs with limited long-range supervision; (2) Evaluation Gap: current protocols often overlook the joint measurement of content fidelity, channel alignment, and actual knowledge transfer. To bridge these gaps, we introduce SLIDE P2V-BENCH, a cross-domain bench mark comprising 108 high-quality paper-video pairs spanning four domains and various durations, coupled with an auditable multi-dimensional evaluation suite. Furthermore, we propose PAPER2MEDIA, a slide-grounded agentic pipeline that produces editable presentations by synchronizing decoupled media channels via a shared semantic clock. Extensive experiments demonstrate that PAPER2MEDIA significantly outperforms existing automated baselines and, notably, achieves performance comparable to human-authored presentations in terms of narrative coherence, visual quality, and knowledge conveyance efficiency.

Hyperspectral single-source domain generalization aims to train a robust model capable of overcoming domain shifts using only one available source domain for cross-scene hyperspectral image (HSI) analysis. Existing methods typically adopt data augmentation to broaden decision boundaries or utilize style transfer techniques for test-time alignment. However, these studies either fail to completely bridge the domain gap or inadvertently disrupt the discriminative spectral information, leading to suboptimal generalization and degraded classification performance on the target domain. To overcome these limitations, we propose a novel method, termed the domain memory retention framework, which optimizes domain memory during training to explicitly encode the semantic structure of the source domain. During inference, the target features are projected to the source distribution by leveraging this memory, thereby skipping domain shifts and improving generalization performance across unseen scenes. Specifically, the memory is formulated as a codebook, consisting of multiple semantic codewords. We further develop a semantic richness constraint and a perturbation robustness constraint to enhance representation diversity while empowering domain invariance for the memory. Extensive experiments conducted on three remote sensing datasets demonstrate that the proposed method outperforms state-of-the-art methods.

Multimodal face anti-spoofing (FAS) improves spoof detection by combining complementary RGB, infrared, and depth cues, yet its generalization to unseen domains remains fragile. We revisit multimodal domain-generalized FAS from the perspective of representation freedom. In a controlled CLIP-based post-fusion baseline, increasing visual encoder depth does not monotonically improve cross-domain performance, suggesting that higher-capacity representations may introduce additional degrees of freedom that are not necessarily aligned with real-vs-spoof semantics. To inspect this effect, we introduce the Semantic Dominance Ratio (SDR), a diagnostic statistic that measures the relative proportion of feature variation along the text-defined real-vs-spoof semantic axis versus off-axis residual directions. Motivated by this perspective, we propose Semantic Freedom Bottleneck (SFB), which reparameterizes multimodal features around CLIP text geometry. SFB decomposes each representation into a semantic component along the real-vs-spoof axis and a bounded low-rank residual component for modality-specific evidence. The residual basis is regularized to be orthogonal to the semantic axis, encouraging the residual space to retain complementary modality-specific cues without duplicating the task-semantic direction. This yields a conservative multimodal constraint that preserves discriminative real/spoof semantics while limiting unconstrained non-semantic variation. Experiments on WMCA, CASIA-CeFA, PADISI, and CASIA-SURF under fixed-modality, missing-modality, and limited-source protocols demonstrate consistently strong cross-domain performance.

Source-Free Domain Adaptation (SFDA) aims to adapt a source-pretrained model to an unlabeled target domain without access to the original source domain. While early single-model approaches rely on self-refinement, they are inherently susceptible to confirmation bias and struggle to correct their own systematic errors. To overcome this limitation, recent methods introduce Vision-Language (ViL) models as external knowledge sources. However, these approaches operate in a largely unidirectional paradigm, using the ViL model primarily to supervise the source-pretrained model. This overlooks a key structural property: the two models exhibit distinct failure modes -- where one produces an incorrect prediction, the other may produce a correct one, creating a natural opportunity for mutual correction within the target domain. Yet, without ground-truth labels, identifying which model is correct on any given sample is non-trivial, and naively exchanging predictions risks propagating errors across models. To address this challenge, we propose SafeCut, a novel approach that leverages the cut statistic as a label-free measure of prediction reliability to gate cross-model supervision. Our approach dynamically controls both the direction and strength of supervision based on relative reliability, selectively amplifying true corrections while suppressing miscorrections on a per-sample basis. We further provide theoretical justification showing that this reliability-gated mechanism guarantees a net-positive correction signal. Extensive experiments across diverse SFDA benchmarks demonstrate that SafeCut achieves state-of-the-art performance, highlighting the effectiveness of safeguarding mutual correction in SFDA via cut statistics. Codes are available https://anonymous.4open.science/r/SafeCut_Source_Free_Domain_Adaptation-65D0/

Low-rank adaptation (LoRA) has attracted significant attention in the parameter-efficient fine-tuning (PEFT) landscape. However, its design suffers from two fundamental limitations. First, its invariance manifold induces flat directions in the loss landscape, creating an optimization bottleneck for adaptive optimizers. Second, its effective rank scales only linearly with the parameter budget. In this paper, we propose Scalable Morpho Adaptation (SaMA), a PEFT method grounded in a principled generalization of the Kronecker product. By relaxing the shared-block constraint in the perfect-shuffle factorization, SaMA spans from low to full rank and achieves effective rank that scales \quadratically in parameters. Furthermore, we show that its invariance manifold collapses to a diagonal group, making it structurally more optimizer-friendly. Empirically, SaMA consistently outperforms strong PEFT baselines on commonsense and arithmetic reasoning benchmarks while being more parameter-efficient.

We present SS3D, a web-scale SfM-based self-supervision pretraining pipeline for feed-forward 3D estimation from monocular video. Our model jointly predicts depth, ego-motion, and intrinsics in a single forward pass and is trained/evaluated as a coherent end-to-end 3D estimator. To stabilize joint learning, we use an intrinsics-first two-stage schedule and a unified single-checkpoint evaluation protocol. Scaling SfM self-supervision to unconstrained web video is challenging due to weak multi-view observability and strong corpus heterogeneity; we address these with a multi-view signal proxy (MVS) used for filtering and curriculum sampling, and with expert training distilled into a single student. Pretraining on YouTube-8M (~ 100M frames after filtering) yields strong cross-domain zero-shot transfer and improved fine-tuning performance over prior self-supervised baselines. We release the pretrained checkpoint and code.

Neural networks are known to be susceptible to over-reliance on spurious correlations. However, the precise mechanism by which models exploit shortcut features is not fully understood, and algorithms to mitigate this behavior rely on as yet unjustified assumptions about the learned representations. In this work, we provide the first end-to-end theoretical characterization of spurious feature learning for two-layer ReLU neural networks trained by online minibatch SGD on the logistic loss. We consider data drawn from the high-dimensional Boolean hypercube with a quadratic signal function (namely XOR) and a linear spurious correlation. We show that SGD learns the spurious feature first, and exponentially fast. Moreover, the optimization dynamics couple the spurious and signal features, with a stronger spurious component inhibiting signal feature learning. Our analysis reveals precise phase transitions in the learning dynamics. In the first phase, alignment between the signs of the spurious feature and second-layer weight drives rapid growth of the spurious feature. When the spurious correlation is maximally strong, we show theoretically that the spurious feature dominates even at the sample complexity threshold where XOR would be learned in isolation (i.e., if the spurious feature was absent). In contrast, when the correlation strength is constant, we provide preliminary empirical evidence that the model can eventually learn the XOR signal, although the spurious feature is not forgotten.

Adapting language models on long-form corpora can improve domain behavior while also making protected passages easier to reproduce verbatim from short prefixes. We study this tension through \emph{relative energy gain}, the token-level log-density ratio between an adapted model and its pre-adaptation anchor on an exact protected continuation. This quantity separates ordinary predictability from update-induced copying pressure and accumulates over suffixes as a likelihood-ratio advantage for extractable memorization. Building on this view, we introduce Energy-Gated Copyright Regularization (EGCR), a training objective that augments maximum likelihood with a soft relative-energy budget on protected tokens. EGCR uses a differentiable gate combining local persistence of relative gain with anchor surprisal, so regularization is concentrated on distinctive spans whose probabilities rise in a memorization-like way while ordinary next-token supervision is retained elsewhere. Across BookMIA adaptation stress tests, training-prefix extraction, CopyBench transfer, and gate ablations, EGCR reduces exact-match and overlap-based reproduction while preserving held-out language-modeling and book-related utility. Token-level visualizations further show that the gate focuses on a small set of expressive positions associated with verbatim recovery. These results suggest that relative-energy barriers offer an effective and inspectable mechanism for copyright-aware language model adaptation.