NeurIPS 2026 论文列表

Discovery of novel materials for physical memory is essential for superior memory systems enabling AI hardware scaling. Among them, ferroelectrics hold promise for highly scalable DRAM. Yet their discovery remains driven largely by human intuition and exhaustive database screening. We present Ferrogen, a generative pipeline for the targeted discovery of novel ferroelectric materials for memory by fine-tuning the diffusion-based crystal structure generator Mattergen on ferroelectric-relevant properties. To enable property-conditioned generation, we construct a ML-labeled dataset using a suite of fast machine learning estimators, including a novel two-stage ensemble polarization predictor, dramatically reducing reliance on high-throughput Density Field Theory (DFT) during training and screening. The base Mattergen model is fine-tuned via lightweight adapter layers conditioned on polarization, switching energy, and metal-probability embeddings, with classifier-free guidance enabling targeted generation of candidates with high polarization, low but finite switching barriers, and insulating character. Generated candidates are screened by the same ML estimators and validated through rigorous DFT calculations, including structural relaxation, band gap verification, and Berry phase polarization computation. Against the ML screens, Ferrogen achieves a roughly $80 \times$ improvement in search efficiency over exhaustive database search. The screened candidates are then finally validated using DFT and made publicly available as a database of theoretically confirmed novel ferroelectrics. The pipeline is readily extensible to other functional material classes, establishing generative models as a powerful paradigm for accelerating electronic materials discovery for high performance memory.

In real-world deployment, large language models (LLMs) are frequently updated through post-training techniques to maintain up-to-date knowledge. Yet their reliability depends not only on what the LLM knows, but also on whether it knows what it knows—a self-assessment known as the feeling of knowing (FoK). FoK is the signal behind selective generation, retrieval triggering, and model routing; when miscalibrated, it leads systems to overconfidence on unknown questions or to refuse ones they could have answered. As LLMs are updated through posttraining, however, we discover that what an LLM knows can change without a corresponding update to its FoK. This creates a knowledge–FoK desynchronization challenge, where FoK estimators calibrated to the pre-trained LLM become unreliable as the model’s knowledge state evolves. To address this challenge, we propose a two-channel design: a knowledge channel that changes what the LLM knows and a FoK channel that judges whether the current knowledge state supports answering. We train these channels with a three-stage procedure: onpolicy supervised fine-tuning (OP-SFT) updates the knowledge channel from corrected on-policy answers, knowledge-delta FoK training (K∆-FT) trains the FoK channel over intermediate knowledge states, and FoK-guided policy optimization (FGPO) uses the judgment to generate the corresponding answer or explanation. Experiments on three datasets show that explicit FoK alignment substantially improves judgment quality on updated knowledge. The code is available at https: //anonymous.4open.science/status/Know-thyself-code-8D65.

Feed-forward novel view synthesis has recently shown promising results from sparse posed images, but most existing methods assume that context and target views share a fixed camera family. This homogeneous-camera assumption breaks in practical multi-sensor systems, where perspective, fisheye, and panoramic cameras may coexist and where the target projection may be unseen during training. We study feed-forward NVS across heterogeneous central cameras and identify a key ambiguity introduced by tokenization: a visual token aggregates a projection-dependent bundle of pixel rays, while existing camera encodings mainly expose absolute rays or token-center relations. To address this, we combine token-center relative Camera Positional Encodings and proposed local raymaps, a token-level representation that explicitly describes the intra-patch ray distribution summarized by each token. We further propose projection-aware 2D RoPE, which replaces raw image-grid coordinates with ray-induced angular coordinates so that relative positional reasoning is aligned across camera projections. Together, these components treat diverse cameras as calibrated samplings of a shared ray space rather than separate visual domains. On ScanNet++ with heterogeneous-camera system, our method improves over camera-conditioned baselines under mixed-camera evaluation and demonstrates zero-shot generalization to panoramic views.

World models aim to improve robotic decision making by predicting the consequences of actions. However, in practice, their predictions often become unreliable once the robot encounters states outside the training distribution, limiting their effectiveness at deployment. We observe that execution itself provides a natural but underutilized signal: after each action, the robot directly observes the true next state, revealing the mismatch between predicted and actual outcomes. Building on this insight, we propose $\textbf{feedback world model}$, a new paradigm that closes the loop between prediction and observation at inference time. Instead of treating the world model as a static open-loop predictor, our method maintains a lightweight feedback state that is updated online to iteratively correct future predictions, compensating for model errors using real-time observations without additional training data or parameter updates. We show that this process can be interpreted as a latent-space observer and admits convergence guarantees under mild conditions. We further introduce action-aware guidance to better translate corrected predictions into control by emphasizing action-controllable components while suppressing irrelevant variations. Experiments on LIBERO-Plus, Robomimic, and real-world manipulation tasks demonstrate that our method substantially improves both prediction accuracy and policy performance under distribution shift. In particular, it reduces world model prediction error by up to 76.4\% and improves out-of-distribution (OOD) success rate by 30\%. These results show that incorporating real-time feedback at inference time provides a simple yet powerful alternative to static world modeling.

Recent hand avatar reconstruction methods achieve high-quality results through multi-view observations or per-subject optimization, limiting scalability and practical applicability. We present \emph{FF3DGS-Hand}, a feed-forward framework that reconstructs animatable hand avatars from a single monocular image using 3D Gaussian Splatting. Our method establishes a stable canonical geometry for thin and articulated hand structures, then reconstructs appearance by leveraging source image evidence instead of relying solely on global latent features. We further introduce a rendering-aware, source-conditioned appearance framework that selectively updates Gaussians according to their rendering contribution, recovering input-specific details while suppressing artifacts in unobserved regions. The resulting representation is animatable via standard hand pose parameters and supports efficient rendering. Experiments demonstrate strong visual quality and quantitative performance in the single-image setting.

Federating a LGN is challenging because each gate is parameterised by a distribution over 16 Boolean operations, so averaging parameters across clients does not correspond to averaging the underlying functions. Under non-IID data, such parameter-space merging collapses to near-chance accuracy. Boolean Feature Selection (BFS) avoids this issue by selecting discrete Boolean functions rather than averaging parameters. We propose Federated Boolean Feature Selection (FBFS), which extends BFS to LGNs by treating hardened last-layer gates as candidate Boolean features and aggregating per-class, per-gate sufficient statistics across clients. Clients share only firing aggregates computed on a held-out split, allowing the server to reconstruct discriminative scores, defined as the gap between a gate's mean firing for a class and for the remaining classes, without accessing raw data. This procedure is equivalent to centralized BFS on the union of client data. We further introduce a diversity-regularized variant of FBFS that encourages complementary feature selection across gates. Empirically, FBFS is the only data-free method we evaluate whose performance remains stable under extreme non-IID settings, outperforming parameter-space merging and other baselines by large margins. It maintains high accuracy across a wide range of heterogeneity levels and scales to large architectures. In addition, FBFS enables efficient deployment: the resulting models compile to hardware-efficient logic representations with substantially fewer post-synthesis cells than ensemble-based alternatives while remaining bit-exact with their software counterparts.

Federated Learning (FL) algorithms implicitly assume that clients passively comply with server-side orchestration by sharing local model updates upon server request. However, this overlooks an important aspect in real-world cross-silo environments: clients are often rational agents who may prioritize their utilities such as local model performance over that of the global model. In settings with significant statistical heterogeneity, rational clients may opt out of the federation if the perceived benefits of collaboration fail to meet their local utility thresholds. Such attrition degrades the global model performance and can lead to the collapse of the federated training process. In this work, we introduce FedUCA: Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation, a framework that formalizes the server's role as an optimizer seeking to maximize global model performance by sustaining client participation. We substantiate our framework through extensive experiments on standard datasets demonstrating that by prioritizing participation feasibility, FedUCA achieves significantly higher client retention and, consequently, a superior global model performance.

Federated Graph Learning (FGL) aims to collaboratively train Graph Neural Networks (GNNs) across distributed subgraphs with a primary challenge of missing cross-client connections. Existing approaches predominantly rely on a retrieval-based paradigm, which reconstructs missing context by accessing external information across clients. However, such cross-client transmissions inevitably expand the attack surface for privacy inference and incur significant communication overhead. In this work, we propose \textbf{FedLMC}, a novel framework that eliminates the necessity of any node information sharing and prior global adjacency knowledge. FedLMC exploits a dual-stage message compensation mechanism to generate informative and expressive node representations. For the semantic information loss of external neighbors, we propose Local Semantic Compensation, which exploits semantic expansion via semantic surrogates to compensate for missing semantic context. For the structural information loss induced by semantic expansion, we propose Community Structural Compensation, which exploits structural anchoring via community anchors to compensate for underlying structural context. Extensive experiments on twelve datasets (both homophilic and heterophilic) demonstrate that FedLMC establishes a new state-of-the-art performance with superior generalization and robustness to highly fragmented graph data.

Neural combinatorial optimization (NCO) solvers generalize poorly under distribution shift, yet robustness across heterogeneous problem distributions is essential for real-world deployment where no single client should be left behind. Group distributionally robust optimization (Group DRO) offers a principled remedy, but requires pooling data that often cannot be shared due to confidentiality or regulatory constraints. Federated learning removes data-sharing requirements; however, existing federated DRO methods cannot accommodate the policy-gradient estimators used in modern NCO. Specifically, prior analyses rely on Lipschitz losses with bounded variance. In contrast, the REINFORCE policy-gradient estimator multiplies stochastic costs by score functions, causing variance to scale with cost magnitude and violating these standard assumptions. We close this gap by replacing Lipschitz-loss conditions with a bounded-cost assumption. This allows us to control cost-dependent variance and establish the first federated Group DRO framework with $O(1/\sqrt{T})$ convergence guarantees. Our analysis applies to any REINFORCE-trained model under bounded costs, including NCO solvers as a special case. Experiments on capacitated vehicle routing---one of many applicable domains including scheduling and packing---demonstrate the necessity of federated training for minority-distribution clients. We show that while na\"ive Group DRO suffers from catastrophic weight collapse, our KL-regularized formulation avoids this collapse. Furthermore, it provides a formal worst-group robustness certificate with no empirical performance penalty compared to standard federated averaging.

Concept-based Models (CMs) enhance interpretability in deep learning by grounding predictions in human-understandable concepts. However, concept annotations are costly and rarely available at scale within a single data source. Federated Learning (FL) could alleviate this limitation by enabling cross-institutional training over concept annotations distributed across multiple data owners. Yet, FL lacks interpretable modeling paradigms. Integrating CMs with FL is non-trivial: although FL supports heterogeneous and non-stationary client participation, it typically assumes a fixed shared architecture, whereas CMs may require architectural adaptation as the available concept set evolves. We propose _Federated Concept-based Models_ (F-CMs), a new methodology for deploying CMs in evolving FL settings. F-CMs aggregate concept-level information across institutions and efficiently adapt the model architecture to changes in concept supervision while preserving privacy. Empirically, F-CMs maintain accuracy and intervention effectiveness comparable to training settings with full concept supervision, while outperforming on average non-adaptive federated baselines. Notably, F-CMs enable interpretable inference on concepts unavailable to a given institution, a key novelty over existing approaches.

Large language models (LLMs) are increasingly accessed as remotely hosted services by edge and enterprise clients that cannot run frontier models locally. Since models vary widely in capability and price, routing queries to models that balance quality and inference cost is essential. Existing router approaches assume access to centralized query-model evaluation data. However, these data are often fragmented across clients, such as end users and organizations, and are privacy-sensitive, which makes centralizing data infeasible. Additionally, per-client router training is ineffective since local evaluation data is limited and covers only a restricted query distribution and a biased subset of model evaluations. We introduce the first federated framework for LLM routing, enabling clients to learn a shared routing policy from local offline query-model evaluation data. Our framework supports both parametric multilayer perceptron router and nonparametric K-means router under heterogeneous client query distributions and non-uniform model coverage. Across two benchmarks, federated collaboration improves the accuracy-cost frontier over client-local routers, both via increased effective model coverage and better query generalization. Our theoretical results also validate that federated training reduces routing suboptimality.

Federated Continual Learning (FCL) suffers from spatial-temporal catastrophic forgetting caused by sequential task learning on individual clients and the aggregation of heterogeneous client knowledge. However, most existing methods either overemphasize preserving old knowledge, which restricts model plasticity for new tasks, or rely on training complex generative models for replay, incurring substantial computational overhead. In the human immune system, immune memory is preserved implicitly and can be reactivated through vaccination even after long periods of dormancy. Motivated by this, we propose ***FedVaccine***, a novel framework that explicitly permits forgetting to preserve high plasticity for new tasks, while efficiently recovering past knowledge through re-learning a compact vaccine set. Specifically, the vaccine set for each task is synthesized by compress task gradient information under the guidance of the fine-tuned local model, capturing representative data characteristics and task-specific discriminative patterns. Two novel components are also introduced: ***Priming & Boosting***, which encodes task-specific knowledge in a compact spectral form, priming the model with essential information and enabling efficient memory boosting via vaccine set replay after forgetting; and ***Vaccination Aggregation***, which aggregates vaccine sets from all clients to train a globally generalized model without accessing any raw private data. Extensive experiments on three benchmarks demonstrate that FedVaccine achieves competitive performance, enables rapid knowledge recovery after forgetting, and incurs no additional overhead from training generative models.

As large generative models become widely deployed and customized, federated learning is increasingly used to adapt them while keeping user data local. Because clients repeatedly receive up-to-date adapters, a malicious client can copy a dispatched adapter, use it offline, and monetize generated images without exposing the stolen weights or a queryable service. Existing federated watermarking and traitor-tracing methods usually assume white-box access to suspect weights or black-box query access to the deployed model. In realistic generative-model theft, however, the defender may only observe images that have already circulated. We propose \emph{FedTrace}, a generated-content-based watermark verification framework that attributes leaked federated models from suspicious generated images alone. FedTrace couples three designs: a round-wise watermark lifecycle that separates client identity distribution from global utility aggregation, a low-drift reliable-bit carrier that embeds identity in watermark positions stable under local adaptation, and anti-collision coding with soft subset verification for distinguishing singleton and collusive leakage. These components enable post-local, collusion-aware attribution from generated outputs alone, without suspect weights or online query interfaces. Extensive experiments across customized diffusion datasets, base models, and federated settings show that FedTrace preserves detectable client identities under local adaptation and strengthens subset-aware tracing against collusive leakage.

Federated Multiple Instance Learning (MIFL) has emerged as a promising paradigm for privacy-preserving weakly supervised learning, particularly in medical image analysis where instance-level annotations are expensive or unavailable. Existing federated MIL methods mainly rely on parameter aggregation to learn a global model across clients. However, in MIL, the key challenge is not only client-level data heterogeneity, but also the ambiguity of instance-level evidence. Since supervision is only provided at the bag level, each client must independently infer discriminative instances through local attention mechanisms. Under heterogeneous data distributions, different clients may focus on inconsistent or even misleading instances, resulting in cross-client critical evidence drift. To address this problem, we propose FedSEM, a Federated Shared Evidence Memory framework that introduces an evidence-level communication pathway in addition to standard model aggregation. Specifically, each client identifies high-confidence evidence instances using local attention scores and compresses them into compact prototypes with importance scores. The server then refines these prototypes through redundancy removal, diversity selection, and score normalization to construct a shared evidence memory. Importantly, FedSEM does not require transmitting raw patches or dense instance embeddings; it only exchanges a small number of evidence prototypes and periodically broadcasts the refined memory, thereby introducing limited additional communication overhead compared with standard federated training. The shared memory serves as cross-client evidence anchors to guide local attention learning and instance-level representation optimization. By explicitly aligning critical evidence patterns across clients, FedSEM mitigates evidence drift while maintaining communication efficiency and privacy preservation. Extensive experiments under heterogeneous federated settings demonstrate that FedSEM consistently improves MIL performance and generalization over existing federated learning baselines.

Low-rank adaptation (LoRA) enables communication-efficient federated fine-tuning of large language models, but standard FedLoRA averages the factors $A$ and $B$ separately even though the model update is determined by their product $\Delta W=sBA$. Under task heterogeneity, factor-wise aggregation can further dilute directions that are locally useful but not strongly shared across clients; we call this phenomenon \emph{directional dilution}. We analyze this effect through the singular directions of client LoRA updates and find that low-strength directions are most vulnerable to dilution. Their repeated owner-specific recovery suggests client-specific adaptation signals rather than random noise. We propose \textsc{FedReCall}, a client-private plug-in that captures observable dilution gaps, selects reliable diluted directions into a private frozen cache, and recalls them through a low-rank bypass guarded by a single-batch loss probe when the client next participates. As a plug-in, \textsc{FedReCall} can be seamlessly integrated into existing FedLoRA methods without changing their aggregation rules, communication payloads, or trainable-parameter sets, consistently improving personalized adaptation and improving global evaluation metrics on most aggregators.

Federated Graph Learning (FGL) on Text-Attributed Graphs often encounters the missing neighbor issue. This problem arises from structural fragmentation across dispersed clients, which restricts the effective message passing of Graph Neural Networks. Current completion methods frequently struggle in cross-domain, non-IID scenarios because they lack access to external knowledge. To address these limitations, we propose FedProG, an asymmetric framework that utilizes a frozen server-side LLM to reconstruct missing structural contexts. Furthermore, deploying Large Language Models locally to augment these graphs incurs prohibitive computational costs for edge devices. We introduce a split architecture where a lightweight client-side generator maps graph features into the LLM’s embedding space. This allows the server to produce virtual neighbors via uploaded soft prompts. To ensure system reliability and privacy, we implement a dual-guard mechanism: a server-side uncertainty filter rejects low-confidence generations through multi-path sampling, while a client-side semantic consistency projector maintains utility under differential privacy. Experiments show that FedProG improves robustness and generalization over baselines while drastically reducing client computational overhead.

Proxy model-based heterogeneous federated learning enables clients with diverse architectures to collaborate through a shared lightweight intermediary. However, current methods aggregate and distill proxy knowledge in a structure-agnostic manner, ignoring layer-wise convergence dynamics, conflating shared and client-specific information, and transferring knowledge without assessing its reliability. These oversights jointly cause model oscillation, drift, and negative transfer. We propose FedPeel, a framework that makes the aggregation pipeline aware of the internal structure of model parameters. Rather than updating the proxy monolithically, FedPeel selectively aggregates only the layers that have stabilized, decouples their frequency-domain representations to separate generalizable patterns from personalized details, and modulates knowledge transfer intensity on a per-sample basis according to teacher confidence. Theoretical analysis establishes an O(1/T ) convergence rate. Experiments on image, text, and audio benchmarks show that FedPeel consistently outperforms state-of-the-art methods in both accuracy and communication efficiency.

Low-Rank Adaptation (LoRA) is a popular parameter-efficient fine-tuning (PEFT) method for fine-tuning of large language models (LLMs), especially in federated learning, due to its strong performance and communication efficiency. In practice, LoRA is applied to the query and value projections of transformer layers without considering the distinct roles of these components. In this work, we analyze the impact of these projections in federated fine-tuning of LLMs using LoRA and observe that the value projection converges significantly faster than the query projection. Motivated by this finding, we propose FedLoVA, a federated fine-tuning framework that trains LoRA adapters on both query and value projections locally while sharing only the value projection with the server. This approach reduces communication overhead while improving performance and convergence efficiency. Experiments on natural language understanding, multilingual sentiment analysis, and generation tasks show that FedLoVA reduces the communication cost by up to $7.8\times$ compared to existing federated LLM fine-tuning baselines while achieving comparable performance.

Federated adaptation of large vision-language models (VLMs) is appealing for privacy-sensitive applications but must contend with client data heterogeneity, strict communication budgets, and on-device inference constraints. Recent methods predominantly introduce additive adaptation interfaces, such as learnable prompts or adapter modules, which attach extra trainable components to the frozen backbone, inflating both parameter counts and inference latency. We challenge this additive paradigm and ask: can robust federated VLM adaptation be achieved through a compact intrinsic interface alone? We answer this question with \textbf{FedIBS} (Federated Intrinsic Bias Selection), a module-free framework that fine-tunes only the biases in feed-forward network projections. FedIBS operates on existing backbone parameters and introduces zero additional inference cost. To make such compact intrinsic adaptation viable under heterogeneous clients, we further propose a Fisher-guided progressive masking mechanism that disentangles shareable and personalized bias coordinates. Each client retains personalized coordinates locally and communicates only the shareable subset for aggregation, enabling sparse communication while preserving client-specific adaptation. Extensive experiments on diverse datasets and heterogeneity settings demonstrate that FedIBS consistently outperforms recent federated prompt- and adapter-based baselines in both personalization and generalization, all while achieving substantially lower communication cost.