NeurIPS 2026 论文列表

We present a novel theoretical analysis of Federated SARSA (FedSARSA) with linear function approximation and local training. We establish convergence guarantees for FedSARSA in the presence of heterogeneity, both in local transitions and rewards, providing the first sample and communication complexity bounds in this setting. At the core of our analysis is a new, exact multi-step error expansion for single-agent SARSA, which is of independent interest. Our analysis precisely quantifies the impact of heterogeneity, demonstrating the convergence of FedSARSA with multiple local updates. Crucially, we show that FedSARSA achieves linear speed-up with respect to the number of agents, up to higher-order terms due to Markovian sampling. Numerical experiments support our theoretical findings.

Traditional recommendation systems rely on latent (dense) representations, making them difficult to interpret and control. We propose the Controllable and Content-Based Recommendations (CCBR) framework, which builds its recommendations from textual user profile representations. CCBR plugs into collaborative filtering models and introduces controllability via text bottlenecks. We show that CCBR enables text-based and multimodal interventions, allowing users to steer the model towards the directions they prefer. Different from existing controllable recommendation systems, CCBR infers the text summaries directly from item contents (images, audio or video). Across image-, audio-, and video-based datasets, we demonstrate that the proposed framework obtains competitive model performance with standard (latent-representation) models while providing controllable model summaries via text. The model also outperforms TEARS, a recent baseline for controllable recommendation systems. Through systematic interventions, we demonstrate the efficacy of the user steering mechanism.

Next-token prediction leaves hidden-state trajectories largely unconstrained, motivating recent geometric regularization methods based on angular penalties. However, these approaches control only the direction of motion and provide no explicit bound on trajectory deviation. We introduce the Controlled Joint Embedding Predictive Architecture (ControlJEPA), a trajectory regularization framework grounded in discrete-time Input-to-State Stability theory. Our novel Lyapunov Tube Loss enforces a contraction condition on a normalized measure of transversal deviation, yielding a provable guarantee that confines hidden states within a tube of explicit width determined by two interpretable hyperparameters. ControlJEPA integrates seamlessly with standard training and requires no architectural changes. Across six benchmarks and seven model families, it consistently outperforms standard fine-tuning and prior trajectory regularizers, improving accuracy and data efficiency while preserving output diversity. Notably, the induced geometric structure persists at inference time, indicating that the method reshapes the representation space rather than memorizing training trajectories.

Missing data is pervasive in real-world datasets, arising from sensor failures, image occlusions, and incomplete reporting. Imputation is a conditional generation problem that must preserve observed entries exactly while producing plausible values for missing ones. Yet most diffusion-based imputers adopt Gaussian noising whose global perturbations are structurally misaligned with this local hard constraint, so consistency is typically enforced through conditional training, clamping, projection, or repainting-style corrections. We address this mismatch with Continuously-Augmented Hybrid Masked Diffusion (CAHMD), a masked diffusion framework whose conditional sampler leaves observed coordinates unchanged by construction. To extend masked diffusion beyond purely discrete data, CAHMD attaches coordinate-wise auxiliary continuous latents to masked entries, providing a denoising channel before values are revealed in continuous and hybrid data. For incomplete training data, we introduce observed-mask gating, an observed-data masked reconstruction principle that uses available entries as pseudo-missing targets and avoids repeated EM-style imputation steps. Across tabular, image, and image--caption benchmarks, CAHMD gives a strong reconstruction--perception--efficiency trade-off while reducing the training overhead of EM-style self-imputation and the inference overhead of repainting-style inner loops.

Concept-bottleneck models (CBMs) are neural classifiers that compute predictions from high-level concepts extracted from the input. CBMs ensure stakeholders can understand the concepts — and the predictions they entail — by learning these from concept-level annotations, which are however seldom available. Recent CBM architectures work around this issue by obtaining annotations from Vision-Language Models (VLMs). While greatly broadening applicability, doing so can yield lower quality concepts and therefore less interpretable models. We strike for a middle ground by introducing **Vision-plus-Human-guided CBM** (VH-CBM), a *hybrid* approach that exploits both VLMs and a small amount of dense annotations. VH-CBM employs a Gaussian Process in the VLM's embedding space, which captures useful global information about the target domain, to propagate the expert's supervision to any target data point. Our empirical evaluation on four datasets showcases how **VH-CBM** predicts substantially more accurate concepts than VLM-guided CBMs even when annotating as little as **1%** of the data, while sporting better concept-level calibration.

Large-scale verifiable prompts underpin the success of Reinforcement Learning with Verifiable Rewards (RLVR), but they contain many uninformative examples and are costly to expand further. Recent studies focus on better exploiting limited training data by prioritizing hard prompts whose rollout pass rate is 0. However, easy prompts with a pass rate of 1 also become increasingly prevalent as training progresses, thereby reducing the effective data size. To mitigate this, we propose Composition-RL, a simple yet useful approach for better utilizing limited verifiable prompts targeting pass-rate-1 prompts. More specifically, Composition-RL automatically composes multiple problems into a new verifiable question and uses these compositional prompts for RL training. Extensive experiments across model sizes from 4B to 30B show that Composition-RL consistently improves reasoning capability over RL trained on the original dataset. Performance can be further boosted with a curriculum variant of Composition-RL that gradually increases compositional depth over training. Additionally, Composition-RL enables more effective cross-domain RL by composing prompts drawn from different domains. All our codes, compositional datasets, and models will be released to facilitate future research.

Chemical reaction datasets such as USPTO suffer from substantial incompleteness, frequently missing byproducts, co-reactants, and stoichiometric coefficients. This limits their applicability and reliability in downstream applications. Here, we introduce CompleteRXN, a large-scale supervised benchmark for reaction completion under realistic missing-data conditions. We construct a dataset of aligned incomplete and atom-balanced reactions by mapping USPTO records to curated mechanistic reactions. We evaluate representative baselines, including a novel encoder-decoder reaction completion model with constrained decoding, the Constrained Reaction Balancer (CRB), and a recent algorithmic method, SynRBL. On our CompleteRXN benchmark, the CRB achieves high performance across splits of increasing difficulty, reaching 99.20% equivalence accuracy on the random split and 91.12% on the extreme out-of-distribution split. SynRBL produces many balanced and chemically plausible completions, but with lower accuracy on the benchmark test splits. Across all methods, performance degrades with increasing incompleteness. We observe a substantial drop when evaluating on reactions outside the benchmark (full uncurated USPTO), highlighting the gap between benchmark performance and practical robustness and motivating future work.

Swapping two LLM post-training stages can change the final model, but an aggregate loss or benchmark delta only says that something moved, not where the order-dependent residue landed. We ask whether this residue leaves a memory trace: a structured signal that is localized in output space, changes held-out order-gap NLL under targeted interventions, and is assignable from paired endpoint weights. For a specified two-stage path $(A,B)$, we define commutator memory by projecting the Lie bracket $b_{AB} := H_B g_A - H_A g_B$ at the base model through the logits into token scores $\tau_k=\mathbb{E}[e_k\,\delta z_k]$, whose sum is the leading bracket-predicted order effect. The token readout is localized: endpoint and batch-resampled checks preserve bracket top-token supports far more than norm-matched random directions (82--99% vs. 35--49% top-20 overlap), and a separate endpoint-support prediction check recovers 53--57% of Qwen top-1% active-token supports. It has intervention leverage in the tested protocols: top-positive-$\tau_k$ token interventions close 32% (median) of the held-out Qwen-3-4B SFT ordering gap with tau-neutral controls near zero, with the same bracket-vs-control separation on a pre-specified above-floor Qwen-2.5-1.5B fp32 subset. It is assignable from paired endpoints: given a base model, candidate stages, and paired alternate-order endpoints, the statistic $\langle\theta_{AB}-\theta_{BA},\,b_{AB}\rangle$ distinguishes $k=1$ SGD training order in 66/72 pair-seed units across four LLMs. Matched-batch DPO and frozen-rollout reward-surrogate experiments are matched-path stress tests; AdamW is reported as an analogous lifted-state pilot. Commutator memory turns training order from a scalar nuisance into a localized, intervention-tested, and paired-endpoint-readable residue.

Money laundering detection on financial transaction graphs is critical but challenging. Laundering activities often conceal illicit fund flows within dense legitimate transaction neighborhoods and disperse suspicious behaviors over extended time spans. These patterns cause weak illicit signals to be spatially diluted and temporally forgotten, limiting the effectiveness of standard graph learning methods in AML scenarios. In this paper, we propose a spatio-temporal dual denoising framework for money laundering detection on evolving graphs, named EvoDen. For spatial denoising, instead of relying on passive neighborhood aggregation, we design a risk-potential guided walk mechanism to extract denoised and suspicion-biased transaction sequences, enabling the model to isolate anomalous fund flows from noisy local neighborhoods. For temporal denoising, we propose a continual Transformer-based sequence learning method driven by a reconstruction objective, which learns denoised sequence representations while enabling latent-space replay of historical knowledge to mitigate representation drift. We conduct experiments on three transaction datasets, and the results show that EvoDen outperforms state-of-the-art baselines in accurately identifying concealed money laundering entities.

Stellarators are fusion energy devices that confine hot plasma using a carefully shaped magnetic field, and they are one of the most promising candidates in the race towards commercial fusion. Among the many systems that make up a stellarator, the electromagnetic coils generate the confining magnetic field. Their design is the key factor in deciding whether a stellarator can be practically engineered and cost‑effectively realized. Coilset design is an intrinsically complex problem: it does not admit either a closed or a unique solution, making it suitable for optimization. Coilset optimization is therefore at the heart of stellarator design: a coilset must accurately reproduce a target magnetic field while satisfying stringent engineering constraints on coil spacing, curvature, and length. Although recent datasets have accelerated progress on stellarator equilibria optimization, data-driven coilset design is limited by the lack of standardized datasets that pair target plasma configurations with engineering-aware coilsets. Here, we release a dataset (https://huggingface.co/datasets/proxima-fusion/coilstellaration) of 177,000 optimized stellarator coilsets targeting plasma configurations sampled from the publicly available ConStellaration dataset. For each configuration, we optimized coilsets to reproduce the magnetic field while satisfying a diverse set of engineering constraints. Alongside the dataset, we introduce a benchmark for conditional coilset generation: given a target plasma boundary and a set of engineering requirements, a model should produce a coilset that satisfies the engineering constraints while reproducing the target field. We provide reference code, evaluation scripts and baselines models trained on a subset of the provided data (https://github.com/proximafusion/coilstellaration). Beyond enabling better optimization initializations and one-shot coil design, our dataset provides a testbed for data-driven constrained optimization and for studying which plasma geometry features predict simpler, more engineerable coils. By releasing data, and code for benchmarks and baselines, we aim to lower the barrier for machine learning and optimization researchers to engage with stellarator coilset design and accelerate progress toward engineerable and cost-effective stellarators power plants.

Streaming video understanding with large vision-language models (VLMs) requires a compact memory that can support future reasoning over an ever-growing visual history. A common solution is to compress the key-value (KV) cache, but existing streaming methods typically rely on local token-wise heuristics, such as recency, temporal redundancy, or saliency, which do not explicitly optimize whether the retained cache is representative of the accumulated history. We propose to view KV-cache compression as a *coreset selection* problem: rather than scoring tokens independently for retention, we select a small subset that covers the geometry of the accumulated visual cache. Our method operates in a joint KV representation and introduces a bicriteria objective that balances coverage in key and value spaces, preserving both retrieval structure and output-relevant information. To encourage a more diverse retained subset, we further introduce an orthogonality-driven diversity criterion that favors candidates contributing new directions beyond the current selection, and connect this criterion to log-determinant subset selection. Across four open-source VLMs and five long-video and streaming-video benchmarks, our method improves over heuristic streaming compression baselines under a fixed cache budget. These results highlight that representative coreset selection offers a more effective principle than token-wise pruning for memory-constrained streaming video understanding.

We introduce CoLa3D, a simple and effective model for composable 3D scene decomposition that, given a single whole-scene latent from either a single image or an existing scene mesh as input, directly outputs a set of object meshes with consistent spatial layout that can be assembled back into a coherent scene. CoLa3D introduces a novel paradigm for 3D scene decomposition within a shared \emph{whole}-scene latent, unlike alternatives that perform per-object generation in canonical spaces and then glue the objects back together with fragile pose and scale estimation. The network is a lightweight, flexible, and scalable query-based transformer that accepts various types of queries, including 2D masks, 3D points, and learnable queries, and learns to decompose the scene into objects in a compact latent space. On both synthetic and real-world datasets, CoLa3D achieves state-of-the-art performance on composable 3D scene decomposition, substantially improving global scene-level consistency and object-level quality while running $2\times$ faster and using less than 1% of SAM 3D's training data. Visible depth on par with MoGe2 further confirms that latent decomposition preserves accurate visible scene geometry while producing physically complete, decomposable object meshes.

Despite impressive progress, existing feed-forward stereo 3D reconstruction models produce a single, irrevocable prediction. When these models fail, there is no mechanism to correct their mistakes. We introduce Click3R, a framework for interactive geometric correction of feed-forward models using sparse human correspondence clicks. Given an image pair and a small set of cross-view point correspondences provided by a user, Click3R injects geometric constraints into the 3D reconstruction networks through a lightweight point correspondence adapter, enabling the model to resolve ambiguities in challenging scenarios such as repetitive textures, symmetric structures, large viewpoint changes, or textureless regions. To evaluate interactive reconstruction, we curate a challenging benchmark specifically designed to expose failure modes of existing feed-forward stereo 3D reconstruction methods. Experiments show that Click3R dramatically reduces reconstruction error with as few as a single correspondence click, improving performance on both standard benchmarks and our curated dataset. Our results demonstrate that sparse human interaction provides an effective and practical mechanism for correcting geometric reconstruction errors.

Deep neural networks have achieved remarkable success across a variety of tasks, yet they often suffer from unreliable probability estimates, leading to overconfident predictions. Conformal Prediction (CP) offers a principled framework for uncertainty quantification, yielding prediction sets with rigorous coverage guarantees. Recent work has proposed integrating conformal objectives into training, optimizing for overall set size. Nevertheless, shaping the prediction sets in a class-conditional manner is not straightforward and typically requires prior knowledge of the data distribution. While class-conditional efficiency has been studied at the post-hoc calibration level (e.g., via class-conditional scoring or calibration partitioning), no prior conformal training method explicitly addresses it. To fill this gap, we introduce Class Adaptive Conformal Training (CaCT), which formulates conformal training as an augmented Lagrangian optimization problem that adaptively shapes prediction sets class-conditionally without relying on parametric distributional assumptions, beyond a user-specified global coverage constraint. Experiments on multiple benchmark datasets, including standard and long-tailed image recognition as well as text classification, demonstrate that CaCT consistently outperforms prior conformal training methods, reducing prediction set size while maintaining the desired coverage guarantees.

Large Language Models (LLMs) struggle with temporal alignment, often producing outdated time-sensitive facts as real-world knowledge evolves. Yet the field's ability to measure this misalignment is itself fragile. Existing benchmarks are static snapshots, rely on rigid templates, are small, lack provenance, conflate willingness-to-answer with recall, and use phrasings that newer models have likely memorised. We argue that progress on temporal alignment is bottlenecked less by data scarcity than by evaluation design, and we contribute on both fronts. We present ChronosAlign, a natural language, programmatically updatable dataset and evaluation framework for temporal alignment in LLMs; generated from a Wikidata and Wikipedia corpus of ~500,000 question-answer pairs covering ~27,000 unique questions across sport, politics, and culture from 2000 to 2025. Each question carries a Wikipedia URL and a documented update procedure, so the same evaluative claim can be re-tested against future models without re-authoring the benchmark. We couple ChronosAlign with a framework focussed on three prompting modalities, explicit (year-anchored), relative ("current" anchored), and invariant (untimed control), whose disagreement isolates which component of temporal alignment a model fails. We benchmark sixteen LLMs surfacing three findings: (i) a sharp post-2022 decay in explicit recall even for models with later training cutoffs, (ii) systematic misalignment between explicit and relative recall, with some models better aligned to explicit year prompts and others to relative anchors, and (iii) a confounding effect of refusal behaviour. Our generation and update code can be found at: https://github.com/sg-sy/ChronosAlign. Our dataset can be found at: https://huggingface.co/datasets/sg-sy/ChronosAlign.

Large perturbation models require training data encompassing chemical, cellular, and assay diversity. Current transcriptomic resources for small-molecule modeling, however, are fragmented across technologies, metadata conventions, controls, doses, and preprocessing pipelines. We introduce Chem-PerturBridge, a harmonized multi-dataset resource comprising over 37k compounds, 136 cellular contexts, and 1.25M transcriptomic samples across eight assay types, with standardized identifiers, metadata, and replicate-aware condition-level effects. We use the resource to evaluate matched-condition agreement across datasets and replicate agreement within datasets. Matched same-compound conditions generally show weak agreement in fine-grained logFC rankings and magnitudes across most dataset pairs, often falling below same-context different-compound baselines. In contrast, logFC direction agreement is substantially more stable and usually exceeds these baselines. We further evaluate Chem-PerturBridge as a pretraining resource for compound representation learning. Under a compound-held-out OP3 evaluation split, embeddings pretrained on Chem-PerturBridge improve over L1000-only embeddings, Morgan fingerprints, and the descriptor-free OP3 baseline across metrics. Chem-PerturBridge therefore supports both diagnostic evaluation of cross-dataset signature agreement and model-oriented reuse of heterogeneous perturbation transcriptomic data.

We investigate the use of formal methods to provide tight and sound generalization bounds for learning algorithms. By casting the traditional notion of algorithmic stability as a specification to be verified, we demonstrate that recent advances in reachability analysis can yield provable bounds on the generalization of a given model and algorithm on a sample dataset. As sample-specific algorithmic stability is insufficient to bound the usual distributional notion of generalization, we develop a novel concentration inequality to connect the sample-specific results of formal certification algorithms to the required distributional analysis.The resulting framework enables the theoretical analysis of prior generalization bounds to extend far beyond their original restrictive analytical assumptions while achieving a provably sound bound on the generalization gap. In practice, we demonstrate that our framework provide formal generalization guarantees that are orders of magnitude tighter than alternative computational approaches at scales ranging from toy datasets to fine-tuning of modern large language models. While we implement certification-enhanced versions of several well-known stability results, future extensions of our approach will enable tighter bounds and enhanced practical adoption across the spectrum of modern generalization bounds.

We introduce *causal pieces*, a novel concept for analysing spiking neural networks (SNNs), inspired by *linear pieces* used to study expressivity and trainability in artificial neural networks (ANNs). Causal pieces partition the input and parameter space of a feedforward SNN with single-spike coding into distinct regions where the same subnetwork causes the output spikes. For networks of current-based leaky integrate-and-fire (LIF) neurons with large membrane time constants, we show that within each causal piece, output spike times are locally Lipschitz continuous with respect to inputs and network parameters. We further prove a lower bound on the approximation error that depends on the number of causal pieces. Thus, the number of causal pieces is a measure of the approximation capabilities of SNNs, which is valid despite spike-time discontinuities and applies to networks with both excitatory and inhibitory synapses. Empirically, we find that parameter initialisations yielding more causal pieces on the training set strongly correlate with SNN training success across multiple benchmarks, including Yin-Yang, Fashion-MNIST, and EuroSAT. Moreover, simulations with standard single-spike LIF neurons indicate that our findings extend beyond the theoretically analysed regime. These results establish causal pieces as a powerful and principled tool for analysing and improving the computational capabilities of SNNs.

This position paper argues that causal benchmarks for multimodal AI should measure categorical difference, not capability gap. The field reports machine causal performance against human performance and interprets progress as gap-closing along a shared scale. The shared-scale assumption rests on a flattened reading of Hume's regularity theory in which causation reduces to constant conjunction across instances and the temporal experience of the observer has no role. When understood in terms of its presuppositions, Hume's regularity is inseparable from a temporally extended subject who undergoes the conjunctions over time. Human and machine causal cognition therefore have different temporal architectures. The two are grounded in time as substrate and time as dimension, a categorical difference that scale or additional intervention machinery cannot close. Evaluation paradigms that treat the two as commensurable produce inflated assessments of machine causal competence that independently scored probes cannot capture. We propose \textit{Anthropomorphic Competence Inflation} as a construct the field can develop into a broader measurement instrument and formalize it through the \textit{Inflation Score}. Preliminary observations on two recent vision-language models match the pattern predicted by the categorical claim. The implications affect evaluation practice, deployment in causal-decision domains, and the next phase of AI causality research.