NeurIPS 2026 Papers

Multivariate time-series anomaly detection aims to identify abnormal temporal patterns in complex real-world systems. However, robust unsupervised time-series anomaly detection remains challenging because anomalies can manifest over different temporal ranges and emerge from interactions among variables, while distribution shifts can cause normal patterns to drift over time. To address these challenges, we propose Codebook-based Online-adaptive Multi-scale Embedding for Time-series anomaly detection (COMET), a unified framework with three tightly coupled components. First, Multi-scale Patch Encoder learns correlation-aware patch embeddings by combining variable-specific temporal dynamics with shared inter-variable structure across multiple patch scales. Second, Vector-Quantized Coreset quantizes these embeddings into representative normal prototypes, which are used to detect anomalies through a dual score combining quantization error and density-aware memory distance. Third, Online Codebook Adaptation leverages the same codebook structure to identify reliable normal samples from training-activated codebook entries, and then updates the prototypes through contrastive learning at inference time. Experiments on five benchmark datasets demonstrate that COMET achieves the best performance on 39 out of 45 evaluation metrics compared to seven baselines, showing robust performance across diverse evaluation protocols.

While Speculative Decoding (SD) has become an essential lossless acceleration technique for Large Language Models, its direct application to Multimodal Large Language Models (MLLMs) is hindered by the intricate visual dependencies present in cross-modal generation. Existing SD methods enforce a uniform global alignment between the draft and target models, which proves ineffective in multimodal settings due to a structured distribution bias: deviations of the draft model are systematically concentrated on a sparse subset of tokens that demand fine-grained visual comprehension. To overcome this limitation, we reformulate the training of multimodal draft models as an acceptance-oriented critical-token alignment problem and introduce CATS, a novel two-stage training framework. CATS employs two complementary selection mechanisms to pinpoint critical tokens:hard tokens that exhibit high rejection probabilities, and vision-critical tokens whose prediction fundamentally depends on visual semantics. Following an initial global alignment phase, CATS performs sparse, targeted refinement exclusively on the union of these identified token sets. Extensive experiments across three representative benchmarks using multiple LLaVA and Qwen2.5-VL target models demonstrate that our approach consistently improves the token acceptance rate over strong baselines such as EAGLE-2 and supervised fine-tuning. Ultimately, CATS substantially accelerates MLLM inference, achieving speedups of up to 3.05×.

Memory facilitates question answering over long videos by extracting and retrieving facts to fit within the limited context windows of multimodal LLMs (MLLMs). Existing solutions typically extract independent memory entries from fixed-length video clips and thus cannot capture high-level semantics that need to be summarized over extended time periods, such as character traits and relations. Moreover, they rely solely on similarity-based retrieval and may fail to retrieve the fine-grained details required for question answering. To tackle these problems, we propose CAM, featuring continuous extraction for high-level semantics and \textit{adaptive querying} for fine-grained details. In particular, CAM stores the entities and relations extracted from video clips in a knowledge graph. To capture the high-level semantics of each entity or relation, CAM summarizes the local subgraph of the target entity or relation once the subgraph reaches a predefined size. To retrieve the fine-grained details required for question answering, CAM supports multiple search methods, such as knowledge graph traversal, video re-watching, and audio listening, and utilizes a planner-executor-verifier pipeline to adaptively compose these search methods according to question intent. Evaluations on three benchmarks show that CAM outperforms SOTA baselines and improves their accuracy by up to 23 percentage points.

This work proposes the Adaptive Federated Hamiltonian Monte Carlo (AFHMC) for Bayesian federated learning (FL) tasks. The prior work on HMC applications for FL achieves $O(\sqrt{d}/\epsilon)$ communication cost under log-convex distributions, already demonstrating its advantage over the Langevin dynamic-based counterpart. Based on a refined analysis, this paper further reveals the benefit of HMC for the FL regime by incorporating a control mechanism for local node shifts. We prove that AFHMC at most requires $O((d/\epsilon^2)^{1/3})$ communication cost up to a logarithmic term, which is significantly better than the existing results. Moreover, the proposed method adapts to client heterogeneity. Under low-heterogeneity settings (i.e., the target sampling precision $\epsilon^2$ is higher than the heterogeneity level), the communication rate of AFHMC can be as good as $O(\log(d/\epsilon^2))$, resembling the communication costs for FL optimization tools. To the best of our knowledge, this provides the first logarithmic communication complexity result for federated sampling. Our code is available at https://anonymous.4open.science/r/Adaptive-Federated-HMC.

Existing hallucination detectors for retrieval-augmented generation (RAG), whether based on model outputs (e.g., likelihood) or internal representations, typically apply a uniform detection strategy across responses. However, we find that different detection signals are informative in different response regimes, making a uniform strategy insufficient for both short- and long-form generation. In short-form tasks such as factoid QA, hallucination typically appears as selecting an incorrect final answer among multiple context-relevant candidates. In this regime, model-output-based signals that discriminate among plausible answers are particularly important. We therefore propose a bidirectional likelihood measure that evaluates logical consistency based on the retrieved evidence and a reasoning step generated after the response. In contrast, long-form descriptive responses are more prone to gradual drift: as generation proceeds, the model increasingly relies on its own prior generations and parametric knowledge, while unsupported continuations may remain locally plausible, making output-based cues less informative. For this regime, we measure context--knowledge conflict by tracking the directional alignment of context-grounding versus internal-knowledge contributions in the hidden states. Building on these regime-specific signals, we introduce ARGUS, an adaptive hallucination detector that emphasizes the more effective signal according to the response regime. Experiments on multiple RAG benchmarks show that our method achieves strong performance across both short- and long-form settings.

Conformal prediction (CP) provides a distribution-free framework for uncertainty quantification with finite-sample marginal coverage guarantees. Yet, missing values introduce distributional heterogeneity, where marginal coverage can hide systematic undercoverage for certain missingness patterns. At the same time, existing methods for conditional guarantees often fail when missing values are present, as they rely on geometric continuity of the covariate space, which is broken by missingness. Although imputation restores continuity, it obscures the missingness patterns and introduces task-dependent overhead. We develop a new CP framework that is \emph{adaptive to missingness patterns}, without imputing covariates. We rely on data augmentation by feature embedding that accounts for missingness. Our framework represents each input with missing values by a tree embedding together with its raw missingness mask, and then learns a regularized quantile score function. Varying the choices for the penalty function and the augmentation enables us to characterize three practically relevant validity levels: exact coordinate-wise validity, exact validity on observed masks, and approximate missingness-conditional guarantees for general mechanisms (MCAR, MAR, MNAR). Experiments on synthetic and real datasets support these guarantees and show that the proposed method reduces miscoverage risk while maintaining informative intervals, especially in non-MCAR settings. These results highlight the practical value of uncertainty quantification that adapts to missingness.

As Large Language Model (LLM) datasets scale to trillions of tokens, data selection has emerged as a critical frontier to filter out uninformative noise and construct adaptive learning trajectories. Beyond static heuristic filtering, advanced data selection methods for LLM training largely follow two paradigms, each with fundamental limitations. Influence-based methods provide principled bi-level objectives but require intractable inverse-Hessian computations, while excess-loss methods are computationally efficient but rely on a static reference model that becomes misaligned with the evolving proxy model during training. We propose BLADE (Bi-Level Adaptive Data sElection), a Hessian-free framework for data selection. BLADE reformulates the bi-level optimization problem underlying influence-based methods as a penalized single-level objective via Lagrange multipliers, avoiding inverse-Hessian computation while revealing a principled connection to excess-loss based data selection. The resulting objective recovers an excess-loss form but replaces the static reference model with a dynamic one that stays synchronized with training. Theoretically, we prove that this penalized formulation guarantees first-order convergence. For efficient online batch selection, we instantiate BLADE as a memoryless randomized block-coordinate Frank-Wolfe algorithm. Extensive experiments show that BLADE consistently outperforms state-of-the-art data selection baselines, providing a practical recipe for LLM training.

Feed-forward transformer models have driven remarkable progress in 3D vision, yet their quadratic complexity renders them impractical for long video sequences. Streaming 3D reconstruction addresses this bottleneck by processing frames sequentially with constant memory. However, existing recurrent architectures inevitably suffer from progressive degradation over long sequences, as they fail to account for the intrinsic reliability of observations and the accumulated confidence of the historical state, leading to severe error accumulation. To address these issues, we introduce BAT3R, a training-free Bayesian adaptation framework comprising two synergistic modules: State Innovation Gating (SIG) and Bayesian-guided Adaptive State Updating (BASU). SIG acts as a distributional regularizer that anchors state evolution to its geometric initialization, effectively arresting representational drift during long-term inference. Building on this, BASU reformulates state update as a recursive Bayesian inference process within a Kalman filtering framework. By jointly modeling the temporal reliability of observations via information-theoretic gain and spatial relevance via cross-attention maps, BASU achieves an asymmetric spatio-temporal state fusion: well-consolidated historical regions are protected from redundant updates, while genuinely novel scene content is aggressively incorporated. Extensive experiments on standard benchmarks (7-Scenes, TUM, ScanNet, KITTI, etc.) demonstrate that BAT3R consistently outperforms state-of-the-art online 3D reconstruction methods, with the most significant gains observed on long sequences and complex scenes.

Understanding how distributed brain regions coordinate during behavior requires models that are both predictive and interpretable. We introduce Behavior-Adaptive Connectivity Estimation (BACE), an end-to-end framework for learning behavior-conditioned directed effective connectivity from multi-region intracranial local field potentials (LFPs). BACE first encodes within-region dynamics with region-specific temporal encoders, then applies a learned adjacency matrix selected for each behavioral context, and finally forecasts future neural activity through a graph-conditioned autoregressive decoder. This design yields explicit region-level connectivity matrices whose edges are tied to predictive dynamics rather than post-hoc explanation. On controlled synthetic time series with known directed graphs, BACE recovers the ground-truth edge structure from forecasting alone. We then evaluate BACE on human deep-brain LFP recordings from three participants performing structured motor tasks. Across participants, BACE achieves strong neural forecasting while producing compact, behavior-specific directed graphs that can be inspected across task segments. Reliability analyses further support the stability of the inferred connectivity patterns. Together, these results position BACE as a practical framework for estimating behavior-adaptive effective connectivity from high-dimensional intracranial recordings, enabling interpretable hypotheses about how deep-brain networks reorganize during behavior.

Masked diffusion language models can reduce inference steps by revealing multiple tokens per denoising iteration, but this parallelism is fragile: positions that are individually confident may be unsafe to commit together when their predictions are coupled. Existing training-free samplers such as Top-\(k\), Fast-dLLM, and EB-Sampler mainly control how many tokens to reveal, while often ranking candidates by token-wise scores that ignore interactions within the selected set. We propose ADAS, a training-free reranking rule for parallel masked diffusion decoding. ADAS leaves the base sampler's stopping rule unchanged and modifies only subset construction: it greedily discounts a candidate when it attends strongly to already selected positions whose predictions remain uncertain. Unlike graph-constrained methods that turn attention into hard compatibility constraints, ADAS keeps attention continuous and uses it as a soft marginal penalty. Across LLaDA-8B-Base and Dream-7B-Base on GSM8K, MATH500, HumanEval, and MBPP, plugging ADAS into Top-\(k\), Fast-dLLM, and EB-Sampler improves low-NFE performance at matched denoiser evaluations by \(9.11\) and \(10.46\) percentage points on average, respectively, with \(3.1\%\) per-forward runtime overhead. These results show that soft attention-discounted reranking is a simple and modular way to improve quality in highly parallel decoding for masked diffusion language models.

Test-time scaling systems often choose how much to sample, which prompt to use, and which verifier or aggregation rule to trust after repeatedly inspecting a calibration set. Standard validation error bars are not valid after this adaptive selection. We model a test-time scaling recipe as a randomized predictor with a random cost and prove a time-uniform PAC-Bayes certificate that holds simultaneously over all calibration times, all posterior mixtures over recipes, and all data-dependent stopping rules. Thus the same event covers the recipe search that precedes deployment, not merely the fixed recipe finally reported. For a finite grid of budgets and verifiers, the penalty is the familiar $\log M/n$, while non-uniform priors and localized posterior mixtures give sharper certificates for structured searches. We specialize the result to self-consistency and show a complementary margin law: plurality voting improves exponentially in the sample budget only on examples where the correct answer is the generator's unique mode; otherwise more compute can provably amplify errors. The same margin analysis yields an oracle water-filling law for compute allocation. A synthetic audit quantifies the optimism caused by adaptive budget selection, and a 192-example GSM8K audit using gpt-4.1-mini generations illustrates risk-cost reporting for a real inference pipeline. The results give a lightweight, distribution-free way to report risk and compute claims for adaptive inference systems.

Real-world tasks rely on information from multiple sensory sources, motivating multimodal learning as a core paradigm in modern machine learning. However, multimodal learning suffers from modality laziness, where one modality suppresses the contribution of the other modalities by dominating the training process. Recent studies of proposing various metrics to identify lazy modalities and manipulate optimizations to mitigate this imbalance, facing two main problems: 1) The identification of lazy modality is incomplete and overly sharp; 2) The dominated modality can be lagged by under-optimized lazy modalities. To address these issues, we propose Adaptive-Margin Masking and Restoration (AMRe), which introduces adaptive-margin modality identification and restoration optimization to balance dominated and lazy modalities. Experimental results show that AMRe consistently outperforms competitive baselines and several state-of-the-art methods by achieving significant improvement on standard multimodal benchmarks. The codes are released in https://anonymous.4open.science/r/AMRe-5E69.

A major bottleneck in characterizing the failure modes of generative AI systems is the cost and time of annotation and evaluation. Consequently, adaptive testing paradigms have gained popularity, where one opportunistically decides which cases and how many to annotate based on past results. While this framework is highly practical, its extreme flexibility makes it difficult to draw statistically rigorous conclusions, as it violates classical assumptions: the number of observations is typically limited (often 10 to 50 cases) and decisions regarding sampling and stopping are made in the midst of data collection rather than based a pre-specified rule. To characterize what statistical inferences can be drawn from highly adaptive audits, we introduce a hypothesis testing framework from two 'dueling' perspectives: (i) the model's null that asserts there is no failure mode with performance below a target threshold versus (ii) the auditor's null that asserts they have a sampling strategy that will uncover a failure mode. Leveraging Safe Anytime-Valid Inference (SAVI), we formalize the auditor as conducting 'testing by betting', which translates into simultaneous e-processes for testing the dueling null hypotheses. Furthermore, *if* the auditor is sufficiently powerful, we prove that these two hypotheses are asymptotically inverses of each other, in that passage of a stringent audit does in fact certify the AI system as being globally robust. Empirically, we demonstrate that our proposed testing procedures maintain anytime-valid type-I error control, outperform pre-specified testing methods, and can reach statistically rigorous conclusions sometimes with as few as 20 observations.

Evolution strategies (ES) have recently emerged as a promising alternative to gradient-based reinforcement learning for fine-tuning large language models, but classical zeroth-order optimization theory does not systematically account for the empirical observations driving this success. We formulate the continuous-time limit of Z-score-normalized ES as a unified stochastic differential equation and identify three sequential dynamical regimes characterized by the dominant gradient contribution to the population reward variance; under a basin-local low-rank Hessian assumption, this framework systematically explains (1) the information-geometric optimality of the Z-score heuristic, (2) the dimensionality paradox of sample-efficient ES with populations far smaller than the parameter dimension, (3) the same-task rise-then-decay of the training reward, and (4) catastrophic forgetting of pre-training capabilities. Synthetic experiments and direct verification on Qwen2.5-{0.5B,3B,7B}-Instruct confirm these predictions, matching the parameter drift reported by Abdi et al. (2026) within $\sim 1.5\\%$.

The target-charging technique (TCT), a generalization of the sparse vector technique, monitors whether query answers deviate beyond acceptable bounds while incurring privacy costs only upon significant deviations. We develop a more mature theory of TCT through three contributions. First, we generalize TCT and replace prior simulation-based analyses with a direct stochastic domination argument, yielding a tighter bound and a modular proof structure that affords flexibility in the choice of privacy representation for the base mechanism as well as the composition accountant. Second, we provide an anytime-valid TCT guarantee that integrates with approximate Rényi DP filters. Third, we enable individual-level privacy filters. Together, these provide the first end-to-end TCT construction compatible with privacy filters and individual-level accounting, with practical relevance demonstrated through benchmarks inspired by the impending world-scale deployment of the W3C Attribution standard, which is fundamentally rooted in individual filters.

Modern deep reinforcement learning algorithms often store past sensory observations in a buffer for later replay and learning. However, this process is biologically implausible; animals do not store raw sensory observations. Instead, they store their imperfect understanding of the world and the events in it. An alternative to storing all past sensory observations is to learn directly from the observations as they come in and store the seemingly important parts of the incoming data. Eligibility trace algorithms in reinforcement learning (RL) sweep back updates for multiple steps, improving efficiency and providing update rules that do not rely on storing large data buffers. These algorithms were common and effectively used in the linear setting, but have not been widely adopted in the deep RL setting. Many questions remain open to make these algorithms more effective, even as basic as how to incorporate vector step-sizes. We first highlight how adaptive vector step-sizes need to be incorporated into the eligibility trace and then introduce a new vector step-size algorithm that is more amenable to the forward-backward view equivalence needed to derive an update with eligibility traces. We show that our new algorithms improve over other streaming algorithms across Mujoco and MinAtar environments, and are comparable to methods with replay buffers such as PPO.

We present the Adaptive Scheduling Pipeline (ASP), a bounded-lag asynchronous reinforcement learning (RL) architecture for post-training large language models (LLMs). Rather than only disaggregating generation and training, the ASP combines two design ideas. First, a queue-aware scheduling policy that jointly reduces three sources of rollout underutilization —padding bubbles from intra-minibatch length heterogeneity, skewness bubbles from long-tail outputs, and sorting bubbles from queue instability induced by length-sorted dispatching—through a single offline preprocessing pass. This enables efficient multi-instance rollout that overcomes the early scaling plateau of single-instance inference while maintaining stable queue dynamics. Second, a bounded-lag asynchronous architecture decouples rollout from training while keeping policy lag observable and small enough to preserve stable learning in our experiments. We also provide an explicit weight-flow path that converts trainer snapshots into inference-ready weights without re-coupling generation and training. Experiments show that ASP improves end-to-end throughput by up to $3.22\times$, reduces iteration time by up to 76\%, scales more robustly with additional generation resources than the MindSpeed-RL and verl baselines, and shows no visible convergence degradation. ASP has also been used in an internal telecom-domain RL post-training workflow, reducing the reported training period from more than three months to about two months and producing a domain-enhanced model for knowledge answering and tool calling.

Adaptive Random Forests (ARF) are among the most effective ensemble methods for learning from non-stationary data streams, yet their success relies on heuristic drift detectors and reset rules that lack formal guarantees and require careful tuning. We revisit ARF from an online learning perspective and show that its design decomposes into two fundamental questions: how to aggregate a dynamically evolving set of trees, and how to update the pool of trees over time. We address aggregation using parameter-free online learning methods with strongly adaptive regret, enabling the ensemble to track the best tree mixture. For pool updates, we replace detector-driven resets with deterministic multi-scale scheduling based on geometric lifetimes, combined with incumbent--challenger replacement governed by anytime-valid statistical tests. This design yields theoretical guarantees: global control of false replacements, bounds on promotion delay under post-change advantage, and adaptivity under piece-wise stationary environment. Empirically, the resulting Online RF consistently outperforms ARF and is competitive with broader streaming baselines across several classification and regression benchmarks.

Gaussian process (GP) bandits provide a powerful framework for performing blackbox optimization of unknown functions. The characteristics of the unknown function depend heavily on the assumed GP prior. Most work in the literature assume that this prior is known but in practice this seldom holds. Instead, practitioners often rely on maximum likelihood estimation to select the hyperparameters of the prior - which lacks theoretical guarantees. In this work, we study two algorithms for joint prior selection and regret minimization in GP bandits based on GP Thompson sampling (GP-TS): Prior-Elimination GP-TS (PE-GP-TS) that disqualifies priors with poor predictive performance, and HyperPrior GP-TS (HP-GP-TS) that utilizes a bi-level Thompson sampling scheme. We theoretically analyze the algorithms and establish a sublinear regret bound for HP-GP-TS. In addition, we demonstrate the effectiveness of these algorithms compared to the alternatives through extensive experiments with synthetic and real-world data.