NeurIPS 2026 Papers

Traditional differential privacy assumes each training example affects only one user's privacy, but many real-world datasets contain examples attributed to multiple users. We study \emph{fixed-graph differential privacy}, a framework for learning from such multi-attribution data where the attribution structure is public but example contents are private. We establish fundamental limits and optimal algorithms for this setting. First, we develop approximation algorithms for the NP-hard contribution bounding problem: a sampling-based LP-rounding algorithm achieving $O(|V|^{1/(k+1)})$-approximation and a greedy algorithm achieving $O(r)$-approximation, where $r$ is the maximum number of users per example. We prove matching hardness results showing the greedy bound is tight up to $O(\log r)$ factors. Second, we introduce a \emph{network density parameter} $c$ that measures how concentrated the attribution network is, and establish information-theoretic error lower bounds scaling as $\tilde\Omega(c^2d/\varepsilon^2)$ for learning $d$-dimensional models from $n$ examples. We provide matching upper bounds using contribution bounding combined with DP-SGD, demonstrating our algorithms are optimal. We further characterize when contribution bounding introduces selection bias and provide conditions under which bias vanishes. Finally, we extend our analysis to the i.i.d. setting where examples are sampled from a distribution, obtaining improved bounds scaling as $\tilde{O}(\sqrt{c/n})$ for hypothesis testing and providing matching algorithm for clustered networks.

Retrieval-augmented generation (RAG) is bottlenecked by the token budget of large language models: feeding long documents into the context window is expensive, while aggressive textual compression discards fine-grained information that is irreversibly lost in a one-dimensional token sequence. We argue that this bottleneck is not fundamental to information density but to the choice of compression \emph{modality}. Modern visual encoders can pack the contents of a rendered text page into roughly a hundred visual tokens with little semantic loss, opening a new compression-fidelity tradeoff that purely textual methods cannot reach. We present \textbf{OpticalRAG}, a framework that renders documents as page images, encodes them with a frozen vision encoder, and distills the retrieved visual tokens into as few as $16$ injected tokens before passing them to the LLM. Two ingredients make this work without expensive cross-modal training: (i) \emph{Encoder-Bridged Retrieval}, which reuses the shared representation space of a pretrained vision-language model to retrieve visual chunks from a text query, with no contrastive training; and (ii) \emph{Query-Driven Distillation}, a lightweight cross-attention compressor that condenses thousands of visual tokens into a small set of query-conditioned prefix tokens. On LongBench-v2, BAMBOO, and LooGLE-v2, OpticalRAG achieves the best compression-aware accuracy (CAP) on all three benchmarks while injecting only $16$ tokens, and improves the closed-book Qwen2.5-7B-Instruct backbone by $5.17$ points on LongBench-v2.

Video generation models are becoming a scalable form of world models, but they mainly generate plausible motion rather than proactively control or optimize the underlying dynamics. As a result, an object in the generated video may follow trajectories that are unsafe, not smooth, inefficient, or physically inconsistent. In this work, we propose OptiWorld, a framework that brings classical optimal control into video generation at inference time. OptiWorld first extracts a compact, task-relevant world state, then plans an optimal trajectory under physical constraints, and finally renders the video conditioned on this trajectory. We formulate planning as a geometric problem on a continuous manifold, which converts 3D geometry and task-dependent physical constraints into a unified planning geometry. By adding this optimal-control layer, OptiWorld generates videos with preferable dynamics, demonstrating strong potential in multiple tasks including goal-conditioned image-to-video generation, video dynamics editing, and counterfactual generation.

Understanding model predictions is essential for physical applications, where outputs often inform safety-critical decisions, such as structural load assessment, weather warnings, and clinical diagnosis. Shapley values satisfy many desirable properties as an attribution method, but their computational cost during inference hinders their practical use. Current amortized explainers, such as FastSHAP, are limited to homogeneous inputs, which is problematic for physical applications where data often comes from irregular grids and geometries. We introduce OperatorSHAP, a grid-agnostic attribution method and training procedure that allows us to train FastSHAP-like explainers for neural operators. We establish a theoretical framework for attributions in function space, connecting to Aumann–Shapley values. We further show that OperatorSHAP's explanations are consistent with state-of-the-art discrete Shapley values across resolutions and transfer across grid sizes without retraining.

Detecting LLM reasoning failures at inference time without ground-truth labels motivates a family of confidence baselines, including self-consistency, semantic entropy, and $P(\text{True})$, built on within-question sampling and self-evaluation. Operad theory, the formalism for systems built by iterated substitution, suggests a complementary diagnostic: a model's direct answer to a compositional query should agree with the answer it produces by composing a stated decomposition of the same query. We instantiate this idea as *operadic consistency* (OC), a per-question signal. Across twelve instruction-tuned LLMs (4B--671B parameters, open-weights and closed-source) on four multi-hop QA datasets, OC is strongly correlated with accuracy on every dataset (Pearson $r \in [{+}0.86, {+}0.94]$, all $p \leq 0.0004$), making it a substantially stronger population-level accuracy proxy at roughly one-third the inference cost of the strongest sample-based baseline (whose own cross-model rates never exceed $r{=}{+}0.80$ on any dataset). At the per-question level, OC contributes information beyond self-consistency, semantic entropy, $P(\text{True})$, and constructed decomposition-aware baselines on every dataset (cluster-robust $p \leq 10^{-19}$). We translate the regression coefficients into deployment-ready selective-prediction lifts ($\Delta_{\text{AUARC}}$ up to $+0.088$, $\Delta_{\text{AUROC}}$ up to $+0.167$ over a tuned $\text{SC}_{K=3}$ baseline). On five frontier thinking models, where the decomposition is extracted from the model's own chain of thought, the same equal-cost comparison gives positive selective-prediction lift on all $16$ (dataset, budget, metric) cells tested.

Classifier-free guidance (CFG) is a standard technique for improving conditional generation in diffusion models, yet its activation schedule is usually selected heuristically. In practice, most existing CFG-based methods rely on a pre-defined activation policy throughout inference, while recent dynamic variants often depend on hand-designed schedules without a principled theoretical explanation of when conditional information is most useful. In order to understand how the informational relevance between conditioning inputs and the score function evolves over the course of generation, we explore when guidance should be activated from an information-theoretic perspective. In this work, we formulate the diffusion trajectory as a time-dependent information bottleneck and show that the effectiveness of conditional information is not uniform throughout sampling, but becomes significantly stronger after a critical stage characterized by a Fisher-information balance condition. Motivated by this insight, we propose a training-free dynamic CFG strategy for inference. Rather than prescribing a fixed schedule in advance, our method constructs a stochastic process from conditional and unconditional score statistics and activates guidance when the estimated guidance gain crosses a prescribed threshold. This yields an adaptive activation rule that aligns condition injection with the underlying generation dynamics, while also recovering interval-based guidance as a limiting special case. Extensive experiments across diverse architectures and tasks, demonstrate that our method is effective, robust, and broadly applicable. Beyond empirical improvements, our framework provides an interpretation of dynamic guidance methods and a principled foundation for inference-time control in conditional diffusion models.

Building capable visual web agents demands precise grounding, long-horizon reasoning, and robust interaction with dynamic, real-world websites. Despite rapid progress, the strongest systems remain largely proprietary, while open agents still depend heavily on supervised post-training over large collections of curated web trajectories. This dependence creates a major scalability bottleneck: high-quality demonstrations are expensive to collect, and static datasets offer limited coverage of the diverse, ever-changing open web. Although online reinforcement learning (RL) has shown promise for text-based agents, its potential for training visual web agents directly on live websites remains largely unexplored. In this paper, we introduce OpenWebRL, an open framework for training visual web agents with online multi-turn RL on real websites. OpenWebRL covers the full training pipeline, including task selection, supervised warm-starting, live-browser execution, multimodal context management, trajectory success judging, and efficient multi-turn policy optimization. Using this framework, we train OpenWebRL-4B, which establishes a new open-source state of the art on challenging live-web benchmarks. With only 0.4K initialization trajectories and 2.2K open-ended training tasks, OpenWebRL-4B achieves 67.0% success on Online-Mind2Web and 64.0% on DeepShop, outperforming prior open agents of similar or larger scale and remaining competitive with proprietary systems including OpenAI and Gemini CUA. Beyond strong benchmark performance, OpenWebRL systematically identifies the key design choices that make online RL effective for visual web agents. Overall, our work offers a practical path toward building more capable, reproducible, and cost-efficient open web agents. We will release our training data, models, and code to support future research.

Recent multimodal large language models (MLLMs) show great potential in natural image understanding. Yet, they perform well, mainly on reasoning in-view contents within the image frame. This paper presents the first study on out-of-view (OOV) understanding, i.e., the ability to reason about objects, activities, and scenes beyond the visible frame of a perspective view. Our technical contributions are threefold. First, we design OpenView, a four-stage pipeline that leverages panoramic imagery for large-scale and diverse multi-choice VQA synthesis, where full-scene coverage enables flexible view framing while preserving global scene awareness. Second, we curate OpenView-Dataset, a high-quality synthetic dataset from diverse real-world panoramas to empower MLLMs upon supervised fine-tuning. Third, we build OpenView-Bench, a benchmark that jointly measures choice and rationale accuracy for interpretable and diagnosable evaluation. Experimental results show that despite having a large gap from human performance in OOV VQA answer selection, multiple MLLMs, upon empowered by OpenView, can consistently boost their performance, uplifted from 48.3% to 62.3% on average. Code, benchmark, and data will be released.

Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remains a persistent bottleneck. Traditional metrics struggle to quantify fine-grained texture details and semantic consistency, while existing datasets fail to meet commercial standards in scale and diversity. We present OpenVTON-Bench, a large-scale benchmark comprising approximately 100K high-resolution image pairs (up to $1536\times1536$). The dataset combines Gemini-powered dense captioning with stratified sampling across 20 visual clusters obtained by DINOv3 K-Means. To support reliable evaluation, we propose a multi-modal protocol that measures VTON quality along five interpretable dimensions: background consistency, identity fidelity, texture fidelity, shape plausibility, and overall realism. The protocol integrates VLM-based semantic reasoning with a novel Multi-Scale Representation Metric based on SAM3 segmentation and morphological erosion, enabling the separation of boundary alignment errors from internal texture artifacts. Under the specified evaluation rubric, our representation metric shows strong agreement with human model rankings (Kendall's $\tau$ of 0.833 vs. 0.611 for SSIM). Code and dataset are available at https://github.com/RenxingIntelligence/OpenVTON-Bench.

Deep search capabilities have become an indispensable competency for frontier large language model (LLM) agents, yet training high-performance deep search agents remains constrained by three key challenges: as synthesized reasoning graphs grow in complexity, verifying answer correctness and uniqueness becomes increasingly difficult to scale; heavy dependence on online search APIs makes data synthesis costly and hard to scale; and the lack of fully open synthesis pipelines severely hinders reproducibility.To bridge this gap, we introduce OpenSearcher, the first deep search agent training pipeline with zero online API dependency throughout the entire data synthesis and model training process, built upon two core technical innovations: (1) \textit{Distinguishing Set-grounded QA synthesis with programmatic verification}: we compute minimal Distinguishing Sets on Wikidata to uniquely identify target entities, recursively expand them into reasoning DAGs, and transform the structured graphs into natural language questions via progressive generation and fuzzification. Answer uniqueness is deterministically verified through SPARQL conjunctive queries, complemented by lightweight LLM filtering for linguistic quality. (2) \textit{Fully offline training pipeline}, which builds an offline corpus of tens of millions of documents from publicly downloadable Wikidata, Wikipedia, and Web Crawl Dumps, and completes trajectory synthesis, SFT cold start, and reinforcement learning entirely offline. Experimental results demonstrate that OpenSearcher achieves strong performance across deep search benchmarks, establishing a new state of the art among fully offline methods, for example, achieving 32.3\% on BrowseComp and 72.8\% on GAIA. We fully open-source the complete data synthesis pipeline to democratize offline deep search agent research and foster a more transparent, collaborative ecosystem.

Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step reasoning. Despite rapid progress, top-tier multimodal search agents remain difficult to reproduce, largely due to the absence of open high-quality training data, transparent trajectory synthesis pipelines, or detailed training recipes. To this end, we introduce **OpenSearch-VL**, a fully open-source recipe for training frontier multimodal deep search agents with agentic reinforcement learning. First, we curate a dedicated pipeline to construct high-quality training data through Wikipedia path sampling, fuzzy entity rewriting, and source-anchor visual grounding, which jointly reduce shortcuts and one-step retrieval collapse. Based on this pipeline, we curate two training datasets, *SearchVL-SFT-36k* for SFT and *SearchVL-RL-8k* for RL. Besides, we design a diverse tool environment that unifies text search, image search, OCR, cropping, sharpening, super-resolution, and perspective correction, enabling agents to combine active perception with external knowledge acquisition. Finally, we propose a multi-turn fatal-aware GRPO training algorithm that handles cascading tool failures by masking post-failure tokens while preserving useful pre-failure reasoning through one-sided advantage clamping. Built on this recipe, OpenSearch-VL delivers substantial performance gains, with over 10-point average improvements across seven benchmarks, and achieves results comparable to proprietary commercial models on several tasks. We will release all data, code, and models to support open research on multimodal deep search agents.

We release OpenSanctions Pairs, the first large-scale public benchmark for entity matching on sanctions and OSINT data. The dataset includes 755,540 expert-labeled pairs over 1 million entities, aggregated from 293 source datasets across 45 jurisdictions. It captures real-world diversity in compliance data, spanning multiple languages and writing systems (e.g., Latin, Cyrillic, Arabic), inconsistent structure, and time-varying provenance, and is substantially more heterogeneous than prior entity matching benchmarks. As baselines, we evaluate the production rule-based matcher (nomenklatura RegressionV1) alongside open- and closed-source LLMs in both zero- and few-shot settings, each tested with and without MIPROv2 prompt optimization to control for prompt sensitivity. The rule-based baseline reaches 91.3\% F1; GPT-4o achieves the best result at 99.0\% F1, and a locally deployable open-source model (DeepSeek-R1-Distill-Qwen-14B) achieves 98.2\% F1. The rule-based baseline and LLMs fail in complementary ways: rules over-match, while LLMs struggle with cross-script transliteration. These results suggest that pairwise matching performance is approaching a practical ceiling and shift attention toward pipeline components such as blocking, clustering, and uncertainty-aware review.

High-stakes clinical use of large vision–language models (LVLMs) requires reasoning that is grounded in visual evidence and clinical knowledge, not just correct final answers. We introduce OpenMedReason, a large-scale, open multimodal medical reasoning corpus comprising approximately 450K image–question–answer instances whose reasoning traces are primarily derived from curated biomedical, human-authored scientific articles. OpenMedReason provides high-fidelity supervision beyond synthetic chains of thought, covering diverse medical domain vision modalities such as radiological scans, microscopic images, visible light photographs, charts, and others. We complement it with OpenMedReason Bench, a held-out benchmark that allows fine-grained evaluation of LVLMs along three complementary axes of capability, including perception, medical knowledge, and rationale, enabling diagnostic evaluation beyond final answer accuracy. OpenMedReason is a rich training resource that exhibits its effectiveness in both supervised fine-tuning (SFT) and reinforcement-based alignment. Training with OpenMedReason yields a 20\% average improvement in VQA accuracy over the base model and achieves 4.2\% the strongest performance among comparable-scale medical LVLMs. Fine-grained performance analysis confirms that the gains are not concentrated in any single axis: OpenMedReason improves perception, medical knowledge, and rationale jointly, and its reasoning traces are preferred over those of the base model in 86.1\% of pairwise comparisons. We release the dataset and code.

Mobile and wearable devices offer an unprecedented opportunity for continuous, passive health monitoring and active health coaching. However, the largest wearable datasets are not publicly available for research, and leading wearable foundation models trained on such datasets are rarely open-weight or come with reproducible training code. To accelerate open science in wearable health, we release **OpenMyHeartCounts (OpenMHC)**, the largest and most comprehensive open-access wearable health dataset to-date, alongside open-source implementations of recent wearable foundation models. \openmhc{}, derived from over a decade of data collected through the My Heart Counts study app, includes >60 million hours of wearable data across 19 sensor channels (e.g., step count, heart rate, sleep, workouts) and up to 169 linked variables, including health, lifestyle, mood, and behavior from 11,894 consenting participants. Furthermore, we introduce a unified, open benchmark that enables standardized comparison of wearable health models across three tracks: health and behavior downstream prediction, multivariate data imputation, and time-series forecasting. We benchmark classical methods alongside recent wearable and multivariate time series foundation models. By open-sourcing data, code, and model weights at this unprecedented scale, we aim to democratize wearable health AI research and enable the community to drive open progress in this domain.

Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences. Recent video generation models offer a reasoning path distinct from previous Chain-of-Thought (CoT): reasoning can unfold through temporally connected frames, known as Chain-of-Frame (CoF) reasoning. However, existing video generators are primarily trained on general video corpora, still lacking diverse supervision and dedicated designs for CoF reasoning. To address this gap, we introduce OpenCoF, a framework comprising the OpenCoF-17K Dataset, a reasoning video dataset spanning 11 task families, and Wan-CoF, a fine-tuned video model for studying whether diverse temporal supervision improves CoF behavior. Across four video reasoning benchmarks, Wan-CoF achieves considerable gains over the Wan2.2-I2V-A14B baseline. Building on this, we empirically explore more advanced designs for CoF capabilities, i.e., equipping the model with visual and textual reasoning tokens. This mechanism respectively captures low-level visual cues and high-level semantic priors for spatial and temporal reasoning. Through performance comparisons and attention analysis, we examine how these tokens contribute across model depth, denoising steps, space, and time. Our results suggest that stronger video reasoning requires both broad temporal supervision and explicit mechanisms for organizing intermediate reasoning state. We will open-source the dataset, model, and code to facilitate future research on reasoning-oriented video generation.

Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or capability-boundary overcommitment. We study this mismatch as the Outcome-Process Gap and introduce OpenClawBench, a large-scale dataset for measuring and supervising process-side anomalies in real agent execution processes. OpenClawBench is built from BFCL-driven OpenClaw sessions produced by 6 source models and contains 31,264 annotated trajectories. It aligns task-oracle outcomes with structured process evidence. FullTax converts the aligned trajectories into structured anomaly supervision: binary labels, supporting evidence, onset/span localization, severity, recoverability, and a 5-class anomaly taxonomy. Using OpenClawBench, we make the Outcome-Process Gap measurable. Among 31,135 oracle-passing executions, 2,904 (9.33%) are still labeled process-anomalous under FullTax. Within oracle-passing executions that contain high-risk process evidence, 1,765 of 1,904 (92.70%) are labeled anomalous. These results show that success-only evaluation misses a concrete class of process-side failures in real agent executions. FullTax silver labels match human audit on 96.0% of a 300-trajectory human-audited pilot. A LoRA-fine-tuned Gemma 3 12B detector trained on the high-confidence FullTax supervised pool reaches binary F1=0.729 on the cleaner-labels held-out test split (n=2,646). It outperforms the GPT-5.4 frontier reference by +0.302 absolute, the no-fine-tuning base by +0.357, and wins on all six source-model agent slices. The gain comes from calibration rather than higher recall: zero-shot detectors over-flag at 42–50% against a 14.7% label rate, while the fine-tuned detector predicts anomalies 17.7% of the time. Together, OpenClawBench turns real agent execution logs into auditable and reusable supervision for studying, diagnosing, and operationally monitoring runtime agent reliability.

Scientific discovery is fundamentally open-ended, characterized by epistemic uncertainty, and requiring endogenous goal-setting and recursive knowledge accumulation. While current agentic systems have demonstrated success in addressing goal-based discovery tasks, they struggle to sustain discovery in open-ended settings. In this work, we posit that open-ended discovery is an emergent network-level property of a socially driven system. We introduce $\texttt{ASCollab}$, which translates four key algorithmic conditions: (1) population heterogeneity in research behaviors, (2) endogenous interaction networks where collaborations and attention routing emerge organically, and (3) socially driven peer evaluations, which are enabled by (4) a global, shared memory that reflects evolving research states. Specifically, social memory is implemented to capture time-varying expertise and reputational signals, and shifting attention paid to historical artifacts produced by the system. Through experiments on large-scale discovery problems in genomics, cell biology, and epidemiology, we demonstrate that $\texttt{ASCollab}$ produces discoveries judged by domain experts to be both sound and significant. Crucially, the system independently recovers real-world scientific findings. Furthermore, systematic investigations show that social dynamics fostered by each of the four conditions are vital, where heterogeneous agents operating within self-organizing networks significantly outperform both fixed-workflow baselines and homogeneous networks.

Vision-Language Models (VLMs) exhibit remarkable zero-shot generalization, yet they often encode unwanted or hazardous stylistic domains such as idealized textbook diagrams in medical AI or cartoon vehicles in autonomous driving. Approximate Domain Unlearning (ADU) aims to selectively erase a model's recognition of a target visual domain while preserving accuracy on the remaining domains. However, existing ADU methods operate under a flawed closed-vocabulary assumption: they evaluate unlearning solely on the specific object classes seen during the unlearning fine-tuning phase. Consequently, these methods do not unlearn the domain itself; they merely overfit to seen class-domain pairs, leaving the domain easily recognizable for unseen classes and providing a false sense of removal. We argue that true domain erasure must be class-agnostic. To address this, we formalize Open-Vocabulary Domain Unlearning (OVDU), a rigorous protocol that mandates domain forgetting must transfer to held-out classes. To solve the OVDU challenge, we propose a surgical parameter-editing framework. First, a Fisher Information mask isolates domain-sensitive weights, mathematically protecting foundational zero-shot generalization. Second, our Targeted Manifold Scattering (TMS) objective uses preference-based mining to locally scatter the forget domain's stylistic geometry. Evaluated across PACS, OfficeHome, and DomainNet, our method vastly improves open-vocabulary generalization over existing baselines. Crucially, it delivers exceptional sample efficiency, outperforming peak 8-shot baseline results with only 4 shots.

We study seamless world generation, where a model must update a persistent visual world according to online user operations rather than full next-scene descriptions. To make this task well-defined, we introduce an operation-centric taxonomy that represents each scene with a global-local schema and each boundary with a typed operator program specifying change and preservation. This taxonomy enables SeamlessWorld, a synthetic data and benchmark pipeline with 8 operation families, 23 atomic operators, dual prompt surfaces, and schema-derived evaluation probes. We then develop OopsWorld, a causal video generator that learns from SeamlessWorld using operation-conditioned decoupled distillation: the student is driven by operation prompts and visual history, while scene-conditioned teachers provide target-state supervision. We further apply dynamics curriculum learning to progressively compose simple edits into high-dynamic world transitions. OopsWorld substantially improves dynamic responsiveness and long-video quality, achieving 91.67 VBench Dynamics and 80.42 Long-Quality with 100K samples. A systematic explicit--implicit study further reveals a persistent operation-prompting gap in current systems, especially for preserving visual anchors, calling for operation-driven world models beyond next-scene prompt switching.