NeurIPS 2026 Papers

Identifying root cause of an anomaly among hundreds of sensors is critical for preventing safety incidents and costly downtime in complex monitored systems. Existing studies evaluate root cause analysis (RCA) methods using top-k accuracy. We show that this metric has a fundamental blind spot: it conflates two failure modes: *retrieval failure*, where the true cause is never considered, and *reranking failure*, where it is considered but ranked too low. In this work, we introduce a retrieval-reranking decomposition and audit four well-known benchmarks to expose this blind spot. Our experiments show that, on benchmarks with complex faults, statistical baselines mis-rank the true cause 78-100\% of the time, and graph-based methods perform poorly because of unreliable causal graphs constructed using short fault windows. Meanwhile, on simple benchmarks where faults manifest significantly at their origin, retrieval is trivially solved at 100\%. Guided by the decomposition, we build a two-stage pipeline combining a multi-signal retriever with an LLM reranker that lifts top-1 accuracy by $+$2 to $+$26 points over the best baseline on complex-fault benchmarks and $+$9 to $+$13 points on simple benchmarks, with no causal graph or labeled data required.

Spatiotemporal forecasting plays an important role in real-world applications, where probabilistic approaches provide uncertainty estimates for decision-making. Real-world systems are inherently non-stationary, leading to distribution shifts between training and test data. However, existing probabilistic methods mainly focus on modeling data distributions under standard settings, while distribution shift methods often handle such shifts in a coarse manner, failing to characterize shift degree and adapt prediction strategy accordingly. As a result, they often produce miscalibrated and unreliable forecasts. To address this issue, we propose REMIND, a retrieval-guided probabilistic framework for spatiotemporal forecasting under distribution shift. REMIND leverages retrieval to estimate how well current observation are supported by historical patterns, enabling adaptive prediction under different shift regimes. It employs spatiotemporal retrieval to construct a memory bank and introduces a dual branch architecture, combining a memory-calibrated probabilistic branch for mild shifts with a deviation-aware probabilistic branch for severe shifts. A shift-adaptive gate, guided by retrieval similarity and memory dispersion, balances the two branches according to shift degree. We further design a hierarchical Gaussian mixture to capture heterogeneous uncertainty over the dual branch predictions, and introduce a memory perturbation training scheme to improve generalization. Experiments on real-world datasets with distribution shifts demonstrate that REMIND consistently outperforms state-of-the-art methods in both forecasting accuracy and probabilistic prediction quality. Code is available at https://anonymous.4open.science/r/REMIND-A46E/.

Graph retrieval-augmented generation (GraphRAG) is motivated by the idea that relational structure can help a language model find evidence that flat retrieval may miss. Yet retrieval scores and final-answer scores often compress a multi-stage pipeline into a single method row. We study the missing middle of this pipeline through an evidence-to-answer audit that follows each system from candidate availability, through evidence selection and context construction, to generated answers and cost. Across GraphRAG-Benchmark Medical and Novel tasks, we find a consistent conversion gap. Strong reranking, learned evidence scoring, and graph-based retrieval can improve evidence-side signals, but these gains do not yield significant answer-correctness improvements under the same generator and evaluator. Matched attribution controls show that some apparent graph-side gains are driven by reranking rather than graph expansion alone. Gold-evidence and bridge-aware interventions further show that evidence completeness is insufficient on its own; answerability also depends on salience, organization, and support in the generator-facing context. We therefore argue that GraphRAG evaluation should report the full evidence-to-answer conversion chain, including candidate source, selected context, generated answer, metrics, and cost, rather than relying on retrieval or answer leaderboards alone.

Recent studies have adapted generative Multimodal Large Language Models (MLLMs) into embedding extractors for text--vision tasks, typically by fine-tuning them to produce universal representations. However, their performance on video--text retrieval often remains below that of dedicated Video Foundation Models (VFMs). In this paper, we revisit the video--text retrieval capabilities of MLLMs. We first analyze the zero-shot retrieval capabilities of pretrained MLLMs and show that they already encode substantial retrieval-relevant information: combining intermediate-layer embeddings with a calibrated MLLM head yields strong performance without any training. To further exploit these capabilities, we introduce a lightweight text-based optimization strategy that requires no paired multimodal data. Our method uses dense video captions as rich textual surrogates for video semantics and short summaries as compact, query-like views, showing that a carefully designed text-alignment objective can improve multimodal alignment through the shared MLLM backbone. We backup these findings through in-depth analysis. Without visual supervision our method outperforms existing approaches, often by a substantial margin, and achieves state-of-the-art performance across common video--text retrieval benchmarks. More broadly, our results offer a new perspective on retrieval with pretrained MLLMs, suggesting that textual descriptions of visual content can serve as an effective substitute for large-scale visual supervision.

Vector databases are increasingly deployed as retrieval pipelines in which representation, indexing, and query-time execution jointly determine accuracy, throughput, and cost. Existing vector database evaluations primarily focus on indexing while treating embeddings as fixed inputs and ignoring the role of query-time execution, making it difficult to decide whether a bottleneck should be addressed by changing the embedding model, the index, or the query-processing stages. To address the above limitation, we introduce \textbf{VecDBLens}, a modular attribution framework that treats the component under diagnosis as an \emph{evaluated object} and all remaining dataset, workload, parameter, and runtime factors as matched \emph{evaluation conditions}. VecDBLens reports stratified marginal effects, paired matched-condition differences, Flat-relative retention, and monotonicity audits, thereby turning vector database benchmarking from leaderboard ranking into a reproducible diagnostic procedure. VecDBLens reveals two key insights. First, retrieval performance is fundamentally upper-bounded by embedding quality, revealing that many apparent indexing failures are therefore representation-side limitations. Second, stronger index parameterization is not always beneficial: overly aggressive configurations can reshape neighborhood topology and cause recall regression. These results challenge the common practice of evaluating vector databases primarily through indexing and show that real-world limitations emerge from stage-wise constraints rather than any single module alone. VecDBLens provides a principled basis for identifying the true performance drivers of vector databases and for guiding their design in practical applications. The code is available at \url{https://anonymous.4open.science/r/VecDBLens-83A4}.

Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motion in this geometry remains challenging and benefits from strong motion priors learned from real-world videos. Existing 3D trackers either follow iterative paradigms trained from scratch on synthetic data or fine-tune 3D reconstruction models learned from static multi-view images, both lacking real-world motion priors. Pre-trained video diffusion transformers (video DiTs) offer rich spatio-temporal priors from internet-scale videos, making them a promising foundation for 3D tracking. However, their frame-anchored formulation, which generates each frame's content, is fundamentally mismatched with reference-anchored dense 3D tracking, which must follow the same physical points from a reference frame across time. We present TrackCraft3R, the first method to repurpose a video DiT as a feed-forward dense 3D tracker. Given a monocular video and its frame-anchored reconstruction pointmap, TrackCraft3R predicts a reference-anchored tracking pointmap that follows every pixel of the first frame across time in a single forward pass, along with its visibility. We achieve this through two designs: (i) a dual-latent representation that uses per-frame geometry latents and reference-anchored track latents as dense queries, and (ii) temporal RoPE alignment, which specifies the target timestamp of each track latent. Together, these designs convert the per-frame generative paradigm of video DiTs into a reference-anchored tracking formulation with LoRA fine-tuning. TrackCraft3R achieves state-of-the-art performance on standard sparse and dense 3D tracking benchmarks, while running 1.3x faster and using 4.6x less peak memory than the strongest prior method. We further demonstrate robustness to large motions and long videos. Our code and weights will be publicly released.

We introduce Track4D, a method that formulates dense 3D tracking as conditional video generation. Repurposing large-scale pretrained video generators for 3D tracking is non-trivial: 3D point tracking in world space produces signals far from natural video, making it difficult for the video diffusion model (VDM) to learn. We systematically study two representations for encoding 3D tracking in the VDM latent space: a Residual 3D Tracking Video (RTV) that directly encodes metric 3D offsets, and a Normalized Coordinate Map Video (NCMV) that implicitly encodes the underlying geometric correspondences as canonical 2D coordinate maps. We further condition the VDM on point maps from an off-the-shelf 3D reconstructor to provide an explicit geometric scaffold for tracking. Trained exclusively on limited synthetic data with LoRA adaptation, Track4D achieves competitive zero-shot tracking performance across five benchmarks, demonstrating the potential of leveraging video generation priors for dense 3D tracking.

Most theories of in-context learning (ICL) treat the prompt as fixed. This fixed-prompt view misses the key difficulty in memory-updated retrieval systems such as Memory Mosaics. An inference-time write can help later queries, but it can also shift softmax weights and create interference. The question is when the benefit exceeds the later cost. We introduce TRIM (Theory of Retrieval with Incremental Memory), a theorem-level theory of append-only softmax retrieval under a write-independence abstraction. The five-theorem spine links retrieval-weight concentration, local write-induced defect, recurrence-level accumulation, ideal squared-loss benefit, and a benefit-cost comparison with critical-horizon regimes. TRIM places helpful memory and harmful interference within a single frame, so the harmful length scale is derived rather than tuned. We record a first-order dynamic correction for state-dependent writes separately, and it is not part of this spine. We give a theorem-facing empirical protocol. Exact synthetic checks test the spine identities and inequalities. Learned base-MM analyses measure calibrated analogues of concentration, local defect, horizon worsening, and realized benefit. These analyses test whether TRIM observables organize learned systems along the same routes.

E-commerce image search often takes a cropped image as the query, while each candidate is represented by full item images and structured text. This image-to-multimodal retrieval setting presents two asymmetries: a modality disparity -- a visual query must match image--text items, and a granularity disparity -- a cropped query must be compared with full images containing background context and possible distractors. Detection-based pipelines handle the granularity disparity through explicit localization but incur extra cost and error propagation, whereas CLIP-style encoders avoid detection, but are vulnerable to backgrounds or irrelevant items. To address these limitations, we propose TIGER-FG, a text-guided implicit fine-grained grounding framework for image-to-multimodal e-commerce retrieval. TIGER-FG uses item text as semantic guidance to produce target-focused item representations without object detection for retrieval. We further introduce dual distillation objectives that preserve target-region spatial consistency and query--item similarity structure, yielding more stable and discriminative multimodal representations. In addition, we construct ECom-RF-IMMR, a realistic benchmark suite with a 10M-pair training set and two evaluation benchmarks covering standard and cluttered item layouts. TIGER-FG improves Recall@1 over the strongest baseline by 6.1 and 34.4 percentage points on the two evaluation benchmarks, respectively, with only 85.7M query-side parameters and 256-dim embeddings. Results on public e-commerce benchmarks further demonstrate its generalization to noisy and one-to-many retrieval scenarios. Code and data will be released.

We propose a dense associative memory for empirical measures (weighted point clouds). Stored patterns and queries are finitely supported probability measures, and retrieval is defined by minimizing a Hopfield-style log-sum-exp energy built from the debiased Sinkhorn divergence. We derive retrieval dynamics as a spherical Hellinger Kantorovich (SHK) gradient flow, which updates both support locations and weights. Discretizing the flow yields a deterministic algorithm that uses Sinkhorn potentials to compute barycentric transport steps and a multiplicative simplex reweighting. Under local separation and PL-type conditions we prove basin invariance, geometric convergence to a local minimizer, and a bound showing the minimizer remains close to the corresponding stored pattern. Under a random pattern model, we further show that these Sinkhorn basins are disjoint with high probability, implying exponential capacity in the ambient dimension. Experiments on synthetic Gaussian point-cloud memories demonstrate robust recovery from perturbed queries versus a Euclidean Hopfield-type baseline.

We investigate a general-purpose layer for deep learning that, instead of compressing arbitrary-size training data into fixed-size weight matrices, stores a new pair of key-value representations for every data point during training, and retrieves and recombines these representations through an attention mechanism at inference time---resulting in a growing neural net (NN). We derive such a "retrieval-centric deep learning" (RCDL) paradigm from the classic duality of a linear layer trained by gradient descent as a type of linear attention (LA) over the training data points---which motivates us to replace the corresponding LA by a more powerful form of attention from recent work on sequence models, namely, kernelized attention using radial basis function (RBF) and softmax-like kernels, as well as more advanced linear attention variants such as MesaNet and DeltaNet. We theoretically derive learning algorithms for the growing layers with kernelized attention, and empirically demonstrate their promising performance and sample-efficiency on classic image classification tasks and synthetic teacher-student learning datasets. In the MesaNet/DeltaNet-inspired extensions, we show a formal connection to a recently proposed optimizer and derive highly sample-efficient optimizers for conventional fixed-size NNs. Despite open challenges, RCDL represents a promising paradigm for nonparametric machine learning.

Anomaly detection is a fundamental task for time-series analytics, with important implications for the downstream performance of many applications. Despite the large number of anomaly detection methods proposed in the literature, recent benchmark studies have shown that no single detector performs best across highly heterogeneous time series. Therefore, a practical and scalable solution is to develop a model-selection method that, for a given time series, selects the anomaly detector most likely to perform well. Nevertheless, the model selection approach proposed in the literature suffers from a significant drop in accuracy when applied in Out-of-Distribution (OOD) settings. In this paper, we tackle the aforementioned limitation and propose \textbf{\textsc{RAMSAD}}, a train-free, retrieval-based framework for model selection in time-series anomaly detection. Given a new time series, our method queries a knowledge base of previously observed instances, retrieves the top-${k}$ most similar series, and transfers detector recommendations from their performance profiles. The framework can operate with standard similarity measures as well as embedding-based representations. Overall, we demonstrate that similarity-based retrieval constitutes a strong and efficient foundation for model selection in time-series anomaly detection.

Gradient Boosted Decision Trees (GBDTs) remain a leading approach for tabular learning, offering strong predictive performance, computational efficiency, and robustness to heterogeneous feature types. Yet their standard second-order leaf updates suffer from a node-level statistical limitation: as trees grow deeper, sparse leaves provide increasingly unreliable gradient estimates, while global regularization cannot adapt to local uncertainty or residual structure. We propose RAGBoost, a retrieval-augmented and ancillary-guided boosting framework for robust tabular learning. RAGBoost augments standard GBDT optimization with a two-layer node-adaptive correction mechanism. First, it retrieves historically observed leaves with similar gradient-state configurations to form node-conditional gradient priors, stabilizing variance-dominated sparse-leaf updates through empirical shrinkage. Second, it uses ancillary residual correction to detect and mitigate bias-dominated within-leaf residual structure that remains unresolved by the main tree. These corrections modify only leaf values, preserving the original tree structure and inference pipeline. Empirically, RAGBoost achieves the best overall average rank across 40 heterogeneous tabular benchmarks in our evaluation, while remaining strongly competitive with recent deep tabular and tabular foundation model baselines. On TabReD, an industrial-scale temporal-shift benchmark, RAGBoost outperforms XGBoost and the base TabM variant overall, suggesting improved robustness under realistic distribution drift.

Highlight detection in content-dense untrimmed videos, such as livestreams, is particularly challenging due to the prevalence of semantically similar moments and the application-driven demand of fitting a target duration budget. Existing methods typically rank segments independently based on semantic relevance, struggling to discriminate fine-grained quality among similar moments and allocating the budget to redundant selections. We therefore reformulate highlight detection as jointly selecting high-quality and complementary segments under a duration budget. To study this formulation, we introduce QB-Highlights, a large-scale benchmark of 50,000 e-commerce livestream videos with densely occurring query-relevant events and subtle quality variations. QB-Highlights is organized around two complementary dimensions: Segment Qualification, which assesses fine-grained per-segment quality; and Budgeted Composition, which evaluates set-level complementarity under a duration budget. It provides MLLM-assisted pseudo labels for training, dense human annotations for testing, and an evaluation protocol jointly measuring quality and diversity. We further propose a Qualification-then-Composition Reasoning (QCR) framework that performs structured deliberative reasoning to produce a highlight set matching the target duration. Extensive experiments show that QCR outperforms strong MLLM, moment retrieval, and highlight detection baselines on both segment quality and compositional diversity.

Large EEG foundation models are pretrained on heterogeneous corpora, but two challenges remain underexplored: (1) experimental protocols provide mental-process cues that are rarely used in masked pretraining, and (2) electrode montages vary across datasets, making spatial representations montage-dependent. Existing methods typically learn a single general-purpose representation and model spatial structure implicitly, limiting their ability to exploit process-related information under montage heterogeneity. We introduce BrainPro, a process-conditioned self-supervised pretraining framework that couples topographic spatial retrieval with shared and process-associated representation learning. BrainPro maps dataset-specific montages to a universal channel-region template and retrieves channel- and region-level spatial filters to form a topographically aligned spatial basis. Over this basis, BrainPro learns a shared encoder for general EEG structure and additional affective, motor-related, and auxiliary residual branches for process-associated variation. Protocol-derived mental-process cues condition branch activation and region-weighted masked reconstruction, incorporating topographic spatial priors and process information without using downstream class labels. Across nine public BCI benchmarks, BrainPro achieves strong performance among evaluated baselines. Ablations, channel-drop analysis, encoder-configuration studies, and spatial-filter visualizations suggest that topographic spatial retrieval and process-conditioned representation learning jointly improve EEG decoding.

In real-world AI for Science scenarios, retrieval systems are increasingly expected to support experimental workflows such as experimental design and method reproduction. These workflows require retrieving protocols that satisfy a set of interdependent constraints, such as specific materials and operating conditions. However, systematic evaluation of retrievers in such multi-constraint scenarios remains lacking. To address this gap, we introduce ProSearch, a scientific retrieval benchmark for multi-constraint experimental protocol retrieval. ProSearch has three key features: (1) realism, as queries are instantiated from real method paragraphs using expert-defined experimental fields, query templates, and filtering rules; (2) complexity, involving 60 distinct fields, such as experimental subjects, materials, and operating conditions, together with dependencies among these fields; and (3) diagnosticity, as each query contains 3 to 5 explicit hard constraints and covers challenging cases such as numeric constraints and negation constraints. We construct ProSearch through LLM-based extraction, data-driven constraint selection, controlled query generation, and evidence-based relevance validation. The final benchmark contains 1,551 high-quality queries across six experimental science domains. We use ProSearch to systematically evaluate 19 representative retrievers, spanning lexical matching, general dense retrieval, scientific retrieval, and reasoning-oriented retrieval. The results reveal that current retrievers generally struggle with multi-constraint protocol retrieval, with the best-performing model achieving an average nDCG@10 of 0.290. Further constraint-wise and error analyses reveal key failure modes of existing retrievers.

Matrix multiplications dominate the inference cost of modern transformer-based vision models, yet existing efficiency techniques such as post-training quantization and mixed-precision inference are largely limited to the small set of fixed-width formats—INT4, INT8, BF16, and FP16—supported by conventional accelerators. We revisit stochastic computing (SC) as a way to lift this constraint: viewed as a dense adaptive quantizer, SC controls precision by bit-stream length L rather than a fixed datapath, while each multiplication reduces to a single AND/XNOR gate. We build a GPU library that emulates SC matrix multiplication at scale, exposes stream lengths as first-class kernel arguments, and evaluates SC end-to-end on image classification, object detection and instance segmentation, class-conditional image generation, and visual world-model planning. On top of this substrate, we develop a dynamic per-row mixed-precision policy that assigns stream length per token or group at matched average budget, requires no retraining, and uses the same SC hardware across schedules. Across tasks, SC remains competitive with fixed-format INT quantization at matched bit budgets, while per-row mixed precision helps maintain accuracy at lower average stream lengths. These results provide software-level feasibility evidence that SC can serve as a dense-precision substrate for fine-grained mixed-precision inference on modern vision transformers.

Learning expressive and transferable representations from unstructured 3D data remains a fundamental challenge. Existing backbones mirror the design of image-based networks by relying on symmetric U-Net architectures with large parametric decoders and feature skip connections. While successful in 2D, these designs are ill-suited for 3D domain where point coordinates, that define the underlying geometric manifold on which feature representations are learned, are sensitive to sensor-specific sampling patterns. In such architectures, skip connections allow low-level coordinate cues to bypass the semantic bottleneck, leading the model to overfit to local spatial patterns rather than learning robust, transferable semantic abstractions. We re-think this design and introduce Point Clustering Encoders (PCE), a minimal, decoder-free network that treats point cloud processing as a hierarchy of end-to-end learned spatial supertokens. At the core of PCE is our Time-Reversible Attention Pooling (TRAP) layer, which formalizes hierarchical downsampling as a time-reversible Markov chain. By coupling upsampling to the reverse chain, we eliminate the need for traditional decoders; the task of representation learning is fully delegated to the encoder. PCE not only surpasses state-of-the-art w.r.t. segmentation accuracy in indoor/outdoor datasets across a variety of tasks, but also reduces the number of trainable parameters, and can process scenes consisting of up to 6.5M points.

Representation alignment (REPA) accelerates diffusion transformer training, but its alignment targets are almost exclusively semantic encoders such as DINOv2 and CLIP. Recent analysis points to spatial structure, not global semantics, as the carrier of the alignment effect, yet dense-prediction foundation models trained to predict that structure remain overlooked as REPA targets. In pixel-space diffusion, SAM2, Depth Anything v2, and Metric3D v2 each outperform the DINOv2-only GenEval baseline, with the two geometric teachers leading the segmentation teacher. A flat sum of all four teachers, however, lands below the best single geometric teacher, semantic teachers reward viewpoint invariance and instance identity while geometric teachers reward metric layout and surface orientation, and forcing both kinds of gradients through one denoiser projection collapses them into a shared subspace. We introduce PixelDense, which routes DINOv2 and SAM2 through a semantic projection stream, routes Depth Anything v2 and Metric3D v2 through a geometric projection stream, and adds a weight-space orthogonality penalty that keeps the two streams in disjoint subspaces. All four teachers are frozen during training and dropped at inference. Applied to PixelGen and DeCo with a single recipe, PixelDense improves GenEval, DPG-Bench, and HPS v2.1, raises PixelGen-XXL's GenEval Overall from $0.7927$ to $0.8093$, and beats every single-teacher and unfactored multi-teacher variant. In partial-noise reconstruction, independent panoptic, depth, and surface-normal probes show up to 53.1% PQ gain and 36.0% depth AbsRel reduction at $\tau=0.5$ across COCO and Flickr30K. From random initialization, PixelDense also reaches the baseline's peak GenEval $1.23\times$ faster.