NeurIPS 2026 Papers

Risk assessment and anomaly detection in financial interaction networks often fail under regime shifts triggered by external events such as policy changes or enforcement actions—models may retain high AUC yet suffer sharp drops in average precision and calibration. Although news and regulatory filings contain actionable signals, naïvely injecting raw text or off-the-shelf LLM embeddings into temporal GNNs can introduce temporal leakage, misalignment, and unstable out-of-time ranking. We propose REGATE, a time-causal framework that integrates exogenous documents into dynamic graphs through three coupled components: (1) a schema-guided extractor that converts unstructured documents into auditable, time- and entity-aligned policy tokens with explicit confidence scores; (2) a bounded gating mechanism that fuses these tokens into temporal GNN states as a residual update, downweighting uncertain or stale evidence with a stability guarantee under direction consistency; and (3) a closed-loop retrieval adaptation module that distills the model's own routing attention into a lightweight document scorer without manual relevance labels. On established dynamic-graph benchmarks with documented regime shifts and six backbone architectures (TGN, TGAT, DyGFormer, GraphMixer, CTAN, GeneralDyG), REGATE yields up to +0.16 AP and up to 90% ECE reduction in post-shift windows on Elliptic; cross-domain pilots on credit and equity networks confirm consistent gains. Ablations show improvements stem from time-aligned semantic content rather than timestamps alone, and we report quality–cost trade-offs across open-source and commercial extractors.

RNA molecules often function through multiple experimentally observed conformational states. A central challenge is to capture ensemble diversity without sacrificing structural fidelity: samples may collapse toward averaged representative structures or drift into unsupported conformational regions. We introduce $\texttt{REFLEX}$ (\underline{R}NA \underline{E}nsemble generation calibrated by \underline{FLEX}ibility), a sequence-conditioned generator for RNA backbone-frame ensembles based on a heteroscedastic stochastic bridge on $\mathrm{SE}(3)$. During training, experimental $\mathrm{B}$-factors calibrate residue-wise bridge widths, exposing each observed conformer through local perturbation neighborhoods with residue-specific scales while keeping constrained regions sharper. A learned flexibility condition guides the bridge-field network to recover target conformer-specific frames from these calibrated noisy states. At inference, $\texttt{REFLEX}$ uses only the input sequence, requiring no MSA-subsampling heuristics. On held-out multi-conformer RNA clusters, $\texttt{REFLEX}$ achieves the best precision--recall trade-off for ensemble coverage across evaluation thresholds, while ablations indicate that the learned bridge field recovers conformer-specific basins more reliably.

Visual planning asks a model to generate the remaining steps of a procedure in natural language given a partial video context and a goal. Progress on this task is bottlenecked by annotation: clean labeled datasets are small, domain-narrow, and encode a single execution trajectory per example, even though many valid orderings often exist. Large-scale instructional video corpora such as HowTo100M offer orders of magnitude more procedural content, but supervised fine-tuning on pseudo-labels extracted from their noisy ASR narrations fails: segmentation and alignment errors propagate into training, and the resulting supervision is still single-trajectory. We identify a key asymmetry. Extracting clean step labels from noisy video is hard, but verifying whether a generated step sequence is temporally grounded in ASR transcripts is comparatively cheap and scales to millions of videos via precomputed text embeddings. We exploit this asymmetry in RECIPE, which uses grounding quality as a reward signal for Group Relative Policy Optimization (GRPO), turning the noisy corpus into a verification signal rather than a labeling source. The framework applies uniformly to two input configurations of the planner: a Socratic pipeline in which a frozen vision-language model rewrites the video into a textual history fed to the planner, and a Video configuration in which the planner consumes video tokens directly. It applies equally to annotated and weakly supervised training regimes. We evaluate on seven procedural benchmarks using a reference-based LLM-as-judge protocol that scores generated plans across six procedural-quality criteria. RECIPE-RL improves over the base checkpoint at every scale we test (0.5B, 3B, 7B) and on every benchmark, with macro-accuracy gains of +7 to +8 points in-domain at every scale and up to +16 points zero-shot. It substantially outperforms supervised fine-tuning on both annotated and pseudo-labeled continuations (the latter actually *degrades* the base checkpoint), and is robust to fully replacing human annotations with VLM-derived pseudo-traces. Plugging RECIPE-RL into the proposal stage of VidAssist [14] improves over the strongest zero-shot baseline in our comparison at every horizon on the Visual Planning for Assistance benchmark, and a diversity analysis on COIN shows that RECIPE-RL preserves the generation variety that supervised fine-tuning collapses.

Single-step inorganic retrosynthesis is evaluated by whether a complete precursor set is recovered, yet many data-driven systems first rank individual precursors and then rely on threshold or count heuristics to assemble sets. This mismatch is especially severe when the true set size is unknown: individually plausible precursors can combine into incomplete, over-complete, or otherwise wrong near-miss sets. We reformalize the task as variable-size set-level ranking and introduce RECIPE, a target-conditioned framework that separates precursor recall from final set-level scoring. The Precursor Candidate Generator learns formula-level compatibility to build a high-recall precursor pool, while the Complete-Set Reranker compares variable-size candidate precursor sets directly. On the Retrieval-Retro year-split benchmark, the generator improves Combo@20 from 69.00 to 72.75. Compared with Retrieval-Retro, the reranker improves Combo@1 by 11.30 points to 71.70, Combo@20 by 20.82 points to 89.82, and Combo MRR by 14.14 points to 77.43. A preliminary 20-case out-of-distribution evaluation shows the same direction of improvement. These results suggest that set-level prioritization remains important after strong precursor recall, and that optimizing ranked complete precursor sets can reduce the inspection burden in inorganic synthesis planning.

Long chain-of-thought reasoning improves vision-language models (VLMs), but it also exposes a temporal grounding failure: as generation unfolds, models may drift from image evidence while reinforcement learning still provides only a final-answer reward. We study this gap through visual revisit, a temporally localized reactivation of image evidence during reasoning. Across three VLM backbones, revisit peaks are predictive of correctness and causally linked to performance: masking them degrades accuracy more than masking non-peaks, while injecting revisit-like peaks into failed rollouts partially restores correct answers. Control analyses show that this signal is not explained by raw attention strength, uncertainty, logit margin, or hidden-state norm. We propose RECAP, a GRPO-compatible training method that turns detached revisit traces into a credit-assignment signal. RECAP uses revisit-conditioned advantage estimation, dynamic discounting, and gated value prediction to propagate final rewards through visually important reasoning steps, without extra rewards, additional rollouts, or inference-time changes. Across Qwen2.5-VL-7B, InternVL3-8B, and LLaVA-OV-7B, RECAP consistently improves over GRPO and VPPO, yielding $+6.1$--$+6.5$ HallusionBench gains over the SFT base while preserving reasoning and text-only performance. Results on larger LoRA-tuned models, Chinese zero-shot benchmarks, visual perturbations, and human evaluation further demonstrate robust improvements in image-grounded reasoning.

Latent diffusion models (LDMs) achieve high-fidelity generation by moving diffusion from pixels to a compact latent space, but standard tokenizers are optimized for compression, not robustness under diffusion-time corruption. We formulate latent tokenization as diffusion-aware joint source--channel coding and diagnose standard LDM pipelines as missing an explicit channel-coding step. A diffusion-aware rate--robustness functional admits an explicit spectral characterization in $G^\top G$, yielding the Redundancy-Balance Principle: optimal redundancy is not uniform, but aligns with semantic sensitivity and equalizes marginal integrated-risk reduction across active directions. The resulting optima take weighted tight-frame and water-filling forms; isotropic bottlenecks are minimax-suboptimal under heterogeneous sensitivity, and a group-conditioned extension identifies rare groups as capacity-limiting under a fixed latent budget. We instantiate the theory as RB-LDC (Redundancy-Balanced Latent-Diffusion Coding), a lightweight tokenizer modification that inserts a learned coding layer before diffusion. Six controlled experiments validate the theorem sequence up to $k{=}1024$, with a $53.5\times$ alignment gap, $659\times$ minimax gap, and real-image VAE learnability via Adam recovery of the KKT spectrum with relative error below 0.5 percent. On SD-VAE and VA-VAE at ImageNet-256, RB-LDC outperforms isotropic uniform redundancy in all 20 perturbed metric cells over a 15-SNR grid; VA-VAE block-local obtains $-15.40$ average pFID and $-105.79$ peak pFID at $\log_{10}\rho{=}+1$, while preserving clean rFID parity (gap $-0.0001$). RB-LDC turns latent tokenizer design into a reliability problem for diffusion models.

Camera sensor RAW data offers intrinsic advantages for object detection, including richer bit depth, preserved physical information, and freedom from image signal processor (ISP) distortions. However, varying exposure conditions, spectral sensitivities, and bit depths across devices introduce substantially larger domain gaps than sRGB, making sensor-agnostic generalization a fundamental challenge. In this study, we present a physics-guided global-local tone mapping framework for sensor-agnostic RAW object detection. By factoring sensor-induced variations into a global tonal correction and a spatially adaptive local color adjustment, both driven by RAW distribution priors, our framework enables a single network to train jointly across heterogeneous sensors. To further support cross-sensor generalization, we construct a physics-based RAW simulation pipeline that synthesizes realistic sensor outputs spanning diverse spectral sensitivities, illuminants, and sensor non-idealities. Extensive experiments across multiple RAW benchmarks, covering bit depths from 12 to 24, demonstrate state-of-the-art (SOTA) performance in single-dataset, mixed-dataset, and challenging robustness settings.

Multimodal large language models (MLLMs) have advanced rapidly on image and video understanding, but their ability to reason over paired aerial electro-optical and infrared (EO-IR) videos remains underexplored. Such videos contain small targets, sparse temporal evidence, changing viewpoints, and modality-dependent cues that are poorly captured by RGB-centric benchmarks. We introduce RAVEN-Bench (Reasoning over Aerial Videos with EO-IR aligNment), a paired EO-IR video QA benchmark for low-altitude aerial multimodal understanding. RAVEN-Bench contains 48 temporally aligned EO-IR video pairs and 576 human-verified four-way multiple-choice questions. It supports EO-only, IR-only, and paired EO+IR evaluation, and uses hierarchical capability levels and structured question groups to diagnose cross-modal gain, modality reliance, consistency, and reasoning coherence. We evaluate representative frontier and open-weight MLLMs, showing that aggregate performance can overestimate reliable EO-IR reasoning. RAVEN-Bench provides a focused testbed for assessing whether progress on RGB video benchmarks transfers to aerial cross-spectral understanding.

Despite rapid advances in text-to-image (T2I) generation, current models often struggle with rare, compositional, and culturally grounded concepts where training data is sparse and visual priors are weak or absent. Increasing model capacity or prompt detail alone does not consistently resolve these challenges, particularly in long-tail settings where attribute grounding remains unstable due to attention skew, semantic collapse, and needle-in-a-haystack retrieval dynamics. We introduce RAVEL, a training-free framework that improves rare concept generation, context-driven image editing, and self-correction by integrating graph-based retrieval-augmented generation (RAG) into T2I pipelines. Unlike prior RAG and LLM-enhanced approaches that rely on visual exemplars, static captions, or implicit model knowledge, RAVEL leverages structured knowledge graphs to retrieve targeted compositional, symbolic, and relational context, enabling more precise grounding even in the absence of visual priors. To further refine generation quality, we propose SRD, a self-correction module that iteratively updates prompts using multi-aspect alignment feedback, improving attribute accuracy, narrative coherence, and semantic fidelity. Our framework is model-agnostic and is compatible with leading diffusion and autoregressive models, including Stable Diffusion XL, Flux, DALL-E 3, GLM-Image, and Janus-Pro. We conduct extensive evaluations across three newly proposed benchmarks: MythoBench, Rare-Concept-1K, and NovelBench, and show consistent improvements over SOTA baselines across perceptual, alignment, and LLM-as-a-Judge metrics, while also demonstrating stable and interpretable refinement trajectories for rare concepts across diverse model families. These results position RAVEL as a simple and robust approach for controllable and interpretable T2I generation in long-tail domains. Our code is available at: https://anonymous.4open.science/r/ravel-54E5/

When humans see a bird, they recognize far more than just ``bird'' --- they see a head, wings, and talons, a structured assembly of reusable parts that can be identified across every bird they have ever seen. We ask whether a self-supervised visual model can discover the same compositional structure on its own. To this end, we propose $RATS$ ($R$egister $A$ttention $T$ransformer$s$), which decomposes the classification token into $N$ learnable register tokens that route patch information through an $L{\to}N{\to}N{\to}L$ bottleneck. The $N$ registers are hard-partitioned across $H$ attention heads, structurally isolating each subset in an independent projection subspace. Without auxiliary losses or part annotations, each register spontaneously specializes into a semantically coherent visual part. RATS surpasses all baselines by an average of +12 mIoU on five segmentation benchmarks, and demonstrates stronger dense prediction on ADE20K (+1.11 mIoU) and COCO (+0.2 AP$^{\text{m}}$). The visual dictionary extracted from the trained registers also shows signs of part-level consistency and semantic proximity across related categories. Our results suggest that RATS may provide a useful architectural prior for structured and interpretable visual representation learning.

Full-dataset NeRF evaluation can require training and evaluating thousands of scenes, making exhaustive comparison expensive even when the benchmark is fixed. We introduce RASS, a risk-audited protocol for constructing compact NeRF benchmark subsets with explicit fidelity criteria. Given full-dataset per-scene logs, RASS repeatedly samples candidate subsets, checks whether their global metric means and score distributions match the full benchmark within user-defined tolerances, and recommends the smallest evaluated subset size whose Wilson lower confidence bound exceeds a target pass probability. We instantiate RASS on 3,522 Nutrition5k-derived food scenes using Zip-NeRF logs for the formal audit and PSNR, SSIM, LPIPS, and Kolmogorov-Smirnov (KS) distributional tests as fidelity criteria. The released 48-scene balanced operating point, RASS-48, is the lowest-cost evaluated screening subset that passes our declared global-fidelity audit and is intended for low-cost early ablations and rapid screening. A stricter target pass probability, $p_{\min}=0.20$, selects RASS-96, which we recommend as the compact reporting subset: it also passes joint fidelity audits over three and four view-synthesis methods. We also evaluate alternative subset generators, including uniform random sampling, farthest-first selection, and facility-location diversity sampling, and find that the RASS audit can validate different generators under the same fidelity contract. On DL3DV, a re-declared contract certifies 64 of 140 scenes for four methods under proportional allocation. We release the RASS-48 and RASS-96 scenes, configurations, descriptors, regime labels, seeds, audit scripts, and permitted logs to enable reproducible, compact NeRF evaluation. Project page: https://amughrabi.github.io/RASS/.

Probing studies what information is encoded in a frozen LLM's layer representations by training a lightweight predictor on top of them. Beyond analysis, probes are often used operationally in probe-then-steer pipelines: a learned concept vector is extracted from a probe and then injected via additive activation steering by adding it to a layer representation during the forward pass. The effectiveness of this pipeline hinges on estimating concept vectors that are accurate, directionally stable under ablation, and inexpensive to obtain. Motivated by these desiderata, we propose RAPTOR (Ridge-Adaptive Logistic Probe), a simple $\ell_2$-regularized logistic probe whose validation-tuned ridge strength yields concept vectors from normalized weights. Across extensive experiments on instruction-tuned LLMs and human-written concept datasets, RAPTOR matches or exceeds strong baselines in accuracy while achieving competitive directional stability and substantially lower training cost; these quantitative results are supported by qualitative downstream steering demonstrations. Finally, using the Convex Gaussian Min-max Theorem (CGMT), we provide a mechanistic characterization of ridge logistic regression in an idealized Gaussian teacher-student model in the high-dimensional few-shot regime, explaining how penalty strength $\lambda$ mediates probe accuracy and concept-vector stability, yielding structural predictions that qualitatively align with trends observed on real LLM embeddings.

LLM agents do not present a fixed inference job to an edge and cloud system. At each step, a placement decision chooses where to generate the next message, where to execute any resulting tool call, which prefix must be replayed, which cache state is updated, and whether the episode continues. As a result, the workload to be scheduled is partly produced by the scheduling decisions themselves. We formalize this problem as an *endogenous, sequentially revealed workload* (ESRW) controlled trajectory MDP. We then introduce **Resource Aware Orchestration Policy** (RAOP), a step level orchestration policy that first places language generation and then, after observing any tool call, places tool execution. RAOP predicts candidate action workloads from prefix replay, prefill, KV cache residency, queue, network, and tool payload features, and is trained with GRPO to optimize measured full trajectory success and latency rather than a one step latency surrogate. To make controlled evaluation auditable, the main simulator replays language and tool continuations produced by real model and tool execution while recomputing physical timing under the sampled placement sequence. As an analytical lens, we derive a Bellman regret decomposition showing that myopic placement policies incur error from workload prediction, success priors, and a controlled endogeneity term. On GSM8K, HotpotQA, WebShop, and a calibrated three tier deployment, RAOP matches the strong cloud only success reference while reducing P99 latency by about 53\% and communication by about 73\%. Against the strongest learned step level baseline, RAOP improves average success by 2.5 points, indicating that full trajectory optimization is central for agent orchestration.

We explore whether Omni-Language Models (OLMs) can be directly applied to zero-shot Semantic Audio-Visual Navigation (SAVN). Recent work demonstrates that even state-of-the-art specialized models still struggle to achieve generalist multimodal navigation, despite extensive task-specific training. In this paper, we introduce **RAO-Nav**, short for Reasoning All-in-One OLM, a deployment pipeline for zero-shot SAVN. By leveraging the rich implicit audio-visual knowledge encoded in OLMs, the embodied agent is enabled to hear, see, reason, and act in the environment. To further elicit the built-in thinking ability of OLMs, we propose a test-time Latent Navigation Reasoning (LNR) module that can be seamlessly integrated into the decoding space. LNR encourages the model to retrieve more target-relevant observations and make effective navigation decisions. Through comprehensive experiments, we show that our framework surpasses existing state-of-the-art baselines on public SAVN benchmarks without using any training data. Moreover, we introduce a new Global Navigation Instruction setting to further evaluate the ability of OLMs to serve as embodied navigation agents. Results under this setting posit that applying OLMs to real-world natural-language-guided audio-visual navigation remains challenging.

The most widely used RANSAC variants score candidate models by counting inliers or summing truncated likelihoods; every such score requires a user-supplied parameter that is a function of the inlier scale, which must itself be estimated from contaminated data. We remove this dependence by reversing the usual order of inference: for a fixed inlier partition we marginalize $\sigma$ analytically in closed form under a conjugate Inverse-Gamma prior, then optimize over partitions. A single closed-form expression spans the non-informative Jeffreys limit (which requires no validation data to fit the prior) and informative empirical-Bayes priors fit from a small validation set, so the same score adapts across data-rich and data-scarce regimes without any change to the algorithm. To our knowledge this is the first RANSAC score in which the inlier scale is genuinely absent from the score formula. The score admits $O(N \log N)$ computation via sort-and-sweep. On a benchmark of nearly $70\,000$ image pairs spanning different two-view estimation problems and both engineered and learned feature pipelines, the proposed score matches or exceeds the state of the art (RANSAC, MSAC, GaU, MAGSAC++), excelling in robustness to hyperparameter miscalibration, sample efficiency at small validation budgets, and adaptive regularization across data-rich and data-scarce regimes.

Fraudulent behaviors in Ethereum, such as Ponzi schemes and phishing attacks, pose persistent threats to blockchain security. Classifying high-risk accounts is crucial for mitigating these threats. Given the graph-structured nature of Ethereum transactions, Graph Neural Networks (GNNs) are widely adopted for this task. However, conventional GNNs rely on local aggregation and treat all edges equally, which amplifies structural noise and limits the ability to capture weak but semantically meaningful connections. This limitation arises from the inability to distinguish informative links from spurious ones during message passing, especially in noisy and long-range transaction graphs. To address this, we propose RAMA, a Resistance-Aware Multi-hop Aggregation framework that reweights edges using resistance distance to reduce the influence of noisy links while preserving important topological information. It also employs attention-based multi-hop aggregation to effectively integrate both local and global transaction patterns. Experiments on real-world Ethereum datasets show that RAMA consistently outperforms strong baselines in Macro-F1 and remains robust under edge perturbations, demonstrating its effectiveness for practical account classification in blockchain environments.

Rheumatoid arthritis (RA) assessment from hand radiographs requires multi-level analysis and modeling of anatomical structures and fine-grained local pathological changes. However, existing public resources do not support such multi-level analysis, often lacking full-hand coverage, fine-grained annotations, and consistent integration with clinical scoring systems. In particular, annotations that enable quantitative analysis of bone erosion (BE) remain scarce. RAM-H1200 contains 1,200 hand radiographs from a regional, multi-institutional Japanese cohort collected across six medical centers in the Sapporo region, with multi-level annotations including (i) whole-hand bone structure instance segmentation, (ii) pixel-level BE masks, (iii) Sharp/van der Heijde (SvdH)-defined joint regions of interest, and (iv) joint-level SvdH scores for both BE and joint space narrowing (JSN). It provides a common evaluation resource covering anatomical structure modeling, localized erosive pathology analysis, and clinically standardized RA severity assessment from the same radiographs. The proposed BE masks enable, for the first time, quantitative BE analysis beyond coarse categorical grading by providing explicit spatial supervision for lesion extent and morphology. To our knowledge, RAM-H1200 is the first public benchmark resource providing whole-hand bone structure instance segmentation, pixel-level BE delineation, and clinically grounded joint-level SvdH scoring for both BE and JSN. Results across benchmark tasks show that anatomical modeling is substantially more mature than quantitative BE analysis: whole-hand bone segmentation achieves strong performance, whereas BE segmentation remains a major open challenge. By providing multi-level annotations spanning anatomical structure modeling, quantitative lesion analysis, and clinically grounded SvdH scoring, RAM-H1200 provides a comprehensive benchmark resource for RA analysis on hand radiographs. Benchmark \& Code: https://github.com/YSongxiao/RAM-H1200 Dataset Repository: https://huggingface.co/datasets/TokyoTechMagicYang/RAM-H1200-v1

Humans process rich auditory environments through tightly integrated cognitive capabilities such as audio perception, audio reasoning, and memory. Despite recent progress in large audio-language models (LALMs) across speech understanding and multimodal audio reasoning, current evaluation paradigms remain largely task- or modality-centric, focusing on end performance while overlooking underlying auditory cognitive behaviours. This reveals a fundamental gap between how auditory cognition is understood in humans and how it is evaluated in LALMs, particularly in the lack of frameworks that operationalise cognitive principles beyond task-level metrics to systematically capture model behaviour. In this work, we introduce RAIL, a human-centric evaluation paradigm grounded in the Cattell-Horn-Carroll (CHC) cognitive framework. RAIL formalises auditory cognition into five core capabilities and develop them into structured evaluation tasks that probe how models process, retain, and integrate auditory information. We further construct a cognitively grounded benchmark with principled data curation and human-aligned evaluation protocols. Evaluating 26 state-of-the-art LALMs, we find that current models exhibit highly uneven performance across cognitive abilities. RAIL establishes a new evaluation paradigm that moves beyond task-centric benchmarking toward cognitively grounded assessment of auditory intelligence.

Policies trained on offline logs can perform well in open-loop evaluation but fail in closed-loop deployment, because they never learn to recover from their own mistakes. Fine-tuning these policies typically requires either many human demonstrations or large-scale reinforcement learning rollouts, both of which are expensive. We propose RAHF, a two-stage closed-loop fine-tuning framework that reduces human effort by amplifying a small number of human corrections with a cheap verifiable reward. In Stage 1, a human operator monitors the policy during closed-loop rollout and intervenes at dangerous states, producing a small but targeted correction dataset that also keeps the training process safe. In Stage 2, the improved policy runs without any human involvement. At each step, the verifiable reward scores the policy's candidate proposals. We use these reward scores to construct group-normalized advantages and fine-tune the policy toward the higher-advantage proposals. To prevent the policy from forgetting its pretrained knowledge, we propose a Policy Adaptation Module (PAM) that freezes the pretrained weights and learns closed-loop corrections through a separate trainable branch. On BridgeSim-NavHard, RAHF with a human teacher reaches a driving score of 78.90, surpassing all baselines including DAgger, HG-DAgger, GRPO, and AWR. In addition, PAM reduces forgetting and enables zero-shot transfer to HUGSIM without any additional fine-tuning.