paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

NeurIPS 2026

Offline Constrained Reinforcement Learning under Partial Data Coverage

Seokmin Ko, Ambuj Tewari, Kihyuk Hong

We study offline constrained reinforcement learning with general function approximation in discounted constrained Markov decision processes. Existing methods either require full data coverage for evaluating unsupported intermediate policies, are not oracle efficient, or requires the knowledge of data-generating distribution for policy extraction. We propose PDOCRL, an oracle-efficient primal-dual algorithm based on a decomposed linear-programming formulation. The decomposition makes the policy an explicit optimization variable, avoiding policy extraction through the unknown distribution $\mu_D$. We show that naive restricted saddle-point formulations may have spurious saddle points, so realizability of an optimal solution alone is insufficient. We then show that, under a stronger but explicit realizability assumption, every restricted saddle point is optimal, avoiding the regularization and auxiliary function classes used in prior LP-based analyses. These ingredients yield PDOCRL, an oracle-efficient primal-dual algorithm that computes a near saddle point of the empirical decomposed LP Lagrangian and returns a near-optimal, near-feasible policy with a $\widetilde{\mathcal O}(\epsilon^{-2})$ sample guarantee under partial coverage, without access to $\mu_D$ or a reference policy. Empirically, PDOCRL is competitive with strong baselines on standard offline constrained RL benchmarks.

NeurIPS 2026

OfficeInstruct: A Dataset for Tool-Augmented Office Agents on Long-Trajectory Generative Tasks

Weikai Xu, Zhizheng Jiang, Lushuo Jiang, Kun Huang, Yuxuan Liu, Pengzhi Gao, Wei Liu, Jian Luan, Xiaolin Hu, Bo An

The recent trend of integrating autonomous agents into operating systems, supported by the Model Context Protocol (MCP) tools and Deep Searching, has driven research on efficient assistants for daily office tasks like document writing, spreadsheet analysis, and presentation generation. However, training these agents still faces several challenges: the overemphasis on question-answering tasks at the expense of multi-turn generative tasks; the absence of a training paradigm that jointly enhances coding and tool-calling capabilities; the difficulty of evaluating tool efficiency and artifact quality in the presence of drifting user intents. To address these problems, we deploy a unified multi-turn agent framework to collect real-world user interactions, creating \textit{OfficeInstruct}: a comprehensive dataset of 199k high-quality trajectories across Doc, Spreadsheet, and PPT, with an average of 56.2 steps. To ensure data quality, we propose a graph-based evidence evaluation method that models interaction histories as directed graphs, filtering out redundant tool cycles, execution errors, and hallucinations. Experiments demonstrate that our \textit{OfficeAgent} 8B and 14B models surpass open-source baselines on in-domain and out-of-distribution benchmarks, with the 32B variant attaining a 96.19\% success rate on the newly proposed \textit{OfficeAgentBench}, surpassing proprietary models like Claude-4.5-Sonnet and Gemini-3-Pro.

NeurIPS 2026

Off-policy Learning with Excursion Policies

Jiamin He, Mark Rowland, Daniel (Zhaohan) Guo, Hado Van Hasselt, Diana Borsa

Off-policy reinforcement learning (RL) tries to learn the value of a target policy while data comes from a different behavior policy. This often requires trading off bias for variance or stability. One way to trade these off is to linearly interpolate between the behavior and target policies, but this represents only one point in a broader space of interpolation mechanisms. We introduce \emph{excursion policies}--a structured alternative where the agent follows the target policy for a multi-step ``excursion'' before reverting to the behavior policy. We derive dynamic programming results for these policies, establishing the theoretical basis for their use in RL. We further develop provably sound off-policy temporal-difference (TD) algorithms for excursion value estimation. We find that excursion policies provide an efficiency-stability trade-off comparable to mixture policies in continuous control benchmarks, and our analysis illustrates conceptual differences in their behavior.

NeurIPS 2026

Off-Policy Evaluation of Large Language Models via Learned Semantic Bottleneck Embeddings

Younwoo Choi, Hadi Sheikhi, Leo Feng, Haanvid Lee

Evaluating large language models (LLMs) via online human feedback is prohibitively expensive and time-consuming. Off-policy evaluation (OPE) addresses this by estimating LLM policy performance from offline data. However, traditional OPE estimators such as Inverse Propensity Score (IPS) suffer from high variance. Marginalized IPS (MIPS) addresses this variance issue by reweighting the IPS weights via condensed semantic embeddings. However, MIPS assumes embeddings contain sufficient reward-predictive information, an assumption that off-the-shelf embeddings often fail to satisfy. To address this, in this paper, we propose Semantic Bottleneck Embedding (SBE), which learns representations for marginalized reweighting via a conditional information bottleneck, compressing reward-irrelevant information while preserving reward-predictive content to achieve both bias and variance reduction. Our objective targets minimizing the derived mean squared error upper bound of the resulting MIPS estimator. Empirically, evaluation on the HelpSteer2 and UltraFeedback datasets across Qwen, Gemma, and Llama policies show SBE-MIPS reduces MSE over prior baselines.

NeurIPS 2026

OdysSim: Building Foundation Models for Human Behavior Simulation

Xuhui Zhou, Weiwei Sun, Weihua Du, Jiarui Liu, Haojia Sun, Qianou Ma, Sherry Wu, Yiming Yang, Maarten Sap

Large language models are increasingly used as human simulators for interactive evaluation and social simulation, yet current post-training often produces homogeneous, overly helpful systems unlike real people, creating a behavioral Sim2Real gap that prompting alone cannot close. We present Odyssim, a large-scale open study of behavioral foundation models organized around SOUL, whose five capability Axes (CONV, SS, COG, ROLE, EVAL) jointly guide data curation and evaluation. We release three artifacts: (1) SOULIndex, a 23-task evaluation suite for human-behavior simulation; (2) OdysSim, a corpus of 21.4M interactions, approximately 10B tokens, from 63 public sources, unified into a conversational format and retrofitted with back-generated social contexts; and (3) an end-to-end recipe combining midtraining, task-specific RL with VFRL, and expert distillation into a single deployable model. On SOULIndex, OdysSim-8B achieves an average score of 62.4, comparable to frontier models such as GPT-5.5 (62.6), ranks first on 8 of 23 tasks, and outperforms prior open behavioral-simulation baselines by 14.2 points on average. We also identify and mitigate reward-hacking failures in judge-based behavioral RL, including judge manipulation and short-response collapse. We release the corpus, benchmark, recipes, and checkpoints.

NeurIPS 2026

OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting

Sanah Suri, Kieran Ringel, Maike Sonnewald

Extreme ocean phenomena are challenging not only to predict but to diagnose, as accurate forecasts alone do not reveal the underlying physical drivers. While recent machine learning approaches achieve strong predictive skill, they remain largely opaque and provide limited guarantees of fidelity to ground-truth physics. We introduce OceanCBM, the first concept bottleneck model (CBM) for spatiotemporal prediction and mechanistic interrogation of ocean dynamics. OceanCBM uses mixed supervision to predict mixed layer heat content, a key precursor of marine heatwaves, while routing information through an intermediate layer of prescribed concepts derived from geophysical fluid dynamics and a 'free' concept. This design imposes soft physical structure without over-constraining the model, and the free concept both regularizes concept predictions and captures residual physical processes. Across ensemble initializations, we show that mixed supervision yields consistent mechanistic representations, whereas prediction-only and prescription-only baselines learn highly variable latent structures despite similar predictive performance. OceanCBM achieves interpretable, physically grounded representations without sacrificing skill, explicitly characterizing the interpretability-performance trade-off.

NeurIPS 2026

Occupancy-based Quantile Risk Control

Zihao Shi, HuaJun Xi, Bingyi Jing, Hongxin Wei

Conformal risk control is an emerging framework for the safe deployment of machine learning models with finite-sample guarantees. To accommodate a broader class of risk notions, quantile risk control extends this framework to quantile-based risk measures. However, existing methods either suffer from excessive conservatism or lack rigorous finite-sample guarantees. To address these limitations, we introduce Occupancy-based Quantile Risk Control (OQRC), a novel method that provides tight risk control bounds with finite-sample validity. Our key idea is to formulate risk control as a finite-occupancy problem by partitioning the loss space with the ordered calibration losses. Specifically, we estimate the distribution of test losses across the resulting bins and upper-bound the risk by the maximum loss attained within each bin. We then select the parameter $\lambda$ such that this upper bound does not exceed a predefined threshold $\alpha$ with high probability $1-\delta$. Theoretically, we establish a finite-sample guarantee showing that OQRC yields tight risk control bounds that converge to the optimal bounds at a provable rate of $\mathcal{O}_p(n^{-1/2})$. Extensive experiments demonstrate the effectiveness of our method, reducing the risk gap by up to 78.64\% on common benchmarks.

NeurIPS 2026

OccStress: Stress-Testing the 4D Occupancy Forecasting Chain

Yu Zheng, Jie Hu, Jiaqi Xiong, Ruiping Liu, Junwei Zheng, Kailun Yang, Jiaming Zhang

Occupancy world models use historical occupancy states to forecast future 3D scenes, but their robustness under corrupted temporal inputs remains poorly understood. Existing evaluations primarily emphasize clean forecasting accuracy and provide limited evidence about how errors enter, persist, and propagate through the occupancy perception-forecasting chain. This paper introduces OccStress, a robustness stress-testing benchmark for the occupancy forecasting chain. OccStress contains 61 corruption categories and 80k+ anchors. OccStress covers both 3D occupancy perception and 4D occupancy forecasting through two complementary tracks. This design separates realistic pipeline errors from the intrinsic sensitivity of 4D forecasting models to corrupted occupancy states. OccStress further defines temporal injection protocols to test whether errors in the current state, recent history, or earlier history affect future forecasts differently. OccStress provides aggregate metrics to evaluating robustness along occupancy forecasting chain. Experiments on OccStress reveal that current occupancy models are substantially affected by both upstream prediction errors and direct state corruptions, and that clean performance alone is an insufficient indicator of temporal robustness. Dataset: https://hf.co/datasets/OccStress/OccStress. Code: https://anonymous.4open.science/r/OccStress.

NeurIPS 2026

Observations Drift, Structures Remain: Structural Pretraining with Time Alignment for Electromagnetic Signals

Wenjin Gui, Junyu Shen, Haibo Xu, Yuchuang Sun, Luqing Luo, Wupeng Xie, Qian Huang, Fengxiang Wang, Yangang Sun, Maosong Sun

Electromagnetic signal modeling is increasingly moving toward self-supervised pretraining on heterogeneous I/Q observations. However, an observed waveform is jointly shaped by signal generation, propagation environments, and acquisition processes, which mix reusable structural regularities with observation-specific variations. Existing methods usually pursue unified pretraining with reconstruction objectives on mixed observations. This heterogeneity creates two key mismatches for reconstruction pretraining: (1) appearance mismatch, induced by propagation-dependent waveform variations; and (2) temporal mismatch, induced by acquisition-dependent sampling coordinates. These mismatches make observation-specific appearances and sampling coordinates easier to reconstruct than stable signal structures, inducing observational shortcuts. We identify this failure mode as observation-biased pretraining. To address this, we propose Structural Pretraining with Time Alignment for heterogeneous EM signals. It mitigates temporal mismatch with RoPE-fs, which maps token positions to sampling-rate-normalized physical-time positions, and reduces reliance on appearance shortcuts by replacing waveform reconstruction with masked prediction of discrete structural units. These units are organized into atomic structural units and emergent units that capture variable-length compositional patterns beyond fixed patch boundaries. Across diverse EM benchmarks, our method improves both full-supervision and few-shot adaptation over existing EM pretraining baselines, showing that the learned representations better preserve structural consistency when observations drift in waveform appearance and temporal scale.

NeurIPS 2026

Observable Neural ODEs for Identifiable Causal Forecasting in Continuous Time

Jennifer Wendland, Nicolas Freitag, Maik Kschischo

Causal inference in continuous-time sequential decision problems is challenged by hidden confounders. We show that, in latent state-space models with time-varying interventions, observability of the latent dynamics from observed data is necessary for identifying dynamic treatment effects, linking control-theoretic observability to causal identifiability, even when hidden confounders affect both treatments and outcomes. We derive a continuous-time adjustment formula expressing potential outcome dis- tributions under treatment trajectories via the measurement model, latent dynamics, and the filtering distribution over latent states given observed histories. We propose Observable Neural ODEs (ObsNODEs), Neural ODE models in ob- servable normal form for causal forecasting. ObsNODEs learn continuous-time dynamics with states reconstructible from observations, enabling outcome predic- tion under alternative treatment paths. Experiments on synthetic cancer data, semi-synthetic data based on MIMIC-IV, and real-world sepsis data show strong performance over recent sequence models.

NeurIPS 2026

ObsConDA: Observability-Constrained Data Assimilation with Control-Space Inference

He Fang, Jiaqi Fan, Dan Wang

Irregular data assimilation is difficult because sparse, off-grid observations do not constrain the same state corrections from one cycle to the next. As the observation geometry changes, the set of supported correction directions changes as well. Many learning-based DA methods infer updates in a fixed latent or control space, even when the current observation layout supports a different set of correction directions. To address this mismatch, we introduce Observability-Constrained DataAssimilation with Control-Space Inference (ObsConDA), which determines those supported correction directions from the current background and observation geometry and infers only their control coefficients. On real surface-station assimilation, ObsConDA gives the best held-out station accuracy and the best full-field reconstruction among the tested classical and learned baselines. The same advantage carries to matched synthetic observations, explicit geometry shifts, and synthetic dynamical systems, supporting the view that the usable correction directions must change from cycle to cycle. Ablations show that the gain comes from adapting those directions themselves rather than from adding a latent corrector alone.

NeurIPS 2026

Objective-Aligned Amortized Inference for Offline Bayes-Adaptive MDP Model Learning

Toru Hishinuma, Kei Senda

Learning latent environment representations from offline datasets is an important challenge for Bayes-adaptive Markov decision process model learning. A key difficulty is that offline datasets collected under heterogeneous protocols can differ in state--action visitation even when the underlying dynamics are identical. Visitation-decoupled objectives address this by evaluating transition predictive fit under a protocol-independent reference distribution via a change of measure. We show, however, that the resulting objective-induced invariances need not be inherited by amortized inference. An unconstrained encoder can depend on protocol-induced visitation variations that are invisible to the objective, a structural failure mode we term \emph{amortization mismatch}. To address this issue, we formalize an \emph{objective-aligned} design principle as an objective--inference compatibility condition: the encoder should factor through the objective-induced dataset signature. We instantiate this principle in multiple set-encoder families and, through targeted experiments, provide evidence that objective-aligned encoders improve posterior consistency and can mitigate downstream planning discrepancy across protocols.

NeurIPS 2026

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders

Wentao Shi, Qifan Wang, Chen Chen, Fei Liu, Dongfang Liu, Xu Liu, Wanli Ma, Junfeng Pan, Linhong Zhu, Fuli Feng

Reinforcement learning (RL) effectively optimizes Large Language Model (LLM)-based recommenders by contrasting positive and negative items. Empirically, training with beam-search negatives consistently outperforms random negatives, yet the mechanism is not well understood. We address this gap by analyzing the induced optimization objective and show that: (i) Under binary reward feedback, optimizing LLM recommenders with Group Relative Policy Optimization (GRPO) is theoretically equivalent to maximizing the Area Under the ROC Curve (AUC), which is often misaligned with Top-$K$ recommendation; and (ii) Replacing random negatives with beam-search negatives reshapes the objective toward partial AUC, improving alignment with Top-$K$ metrics. Motivated by this perspective, we introduce **W**indowed **P**artial **AUC** (**WPAUC**), which constrains the false positive rate (FPR) to a window [$\alpha,\alpha+d$] to more directly align with Top-$K$ metrics. We further propose an efficient **T**hreshold-**A**djusted **Win**dowed reweighting (**TAWin**) RL method for its optimization, enabling explicit control over the targeted Top-$K$ performance. Experiments on four real-world datasets validate the theory and deliver consistent state-of-the-art performance.

NeurIPS 2026

Object Hallucination Mitigation in Large Vision-Language Models via Self-Vision Dual Masking and Uncertainty-Triggered Assembly

Ziji Sheng, Guiyao Tie, Weidong Wang, Jiawen Shi, Junhao Dong, Xiaoye Qu, Shanshan Ye, Daizong Liu, Dengpan Ye, Pan Zhou, Jing Zhang

Large vision-language models (LVLMs) achieve strong multimodal reasoning performance but remain prone to object hallucination, where generated objects or existence judgments are not faithfully grounded in the image. Existing mitigation methods either require additional training or rely on external visual experts, which limits plug-and-play usability and increases inference overhead. In this paper, we propose SIGMA, a training-free framework for hallucination mitigation based on Self-vision Information-theoretic Gating and dual-Mask Assembly. SIGMA operates directly on the LVLM's own vision encoder, constructing complementary support and complement masks from image-driven concept relevance, question-aware entity cues, and CLS--patch shortcut suppression. These masks form global, support-masked, and complement-masked visual streams for query-conditioned evidence separation. During decoding, SIGMA activates correction only under high uncertainty, using full-vocabulary and candidate-answer entropy to perform support-first refinement and complement-on-demand suppression. The resulting streams are combined through logit-level assembly with lightweight positive calibration and a plausibility constraint. Experiments across multiple LVLM backbones and hallucination-oriented benchmarks show that SIGMA effectively reduces object hallucination while maintaining competitive perception performance and a selective low-overhead inference path.

NeurIPS 2026

Object Detection Benchmarks are Incomplete: The Role of Label Errors and Annotation Uncertainty

Sarina Penquitt, Jonathan Klees, Antonia van Betteray, Parssa Jashnieh, Peter Stehr, Matthias Rottmann, Lars Schmarje

While object detection has advanced through improved architectures and open-vocabulary models, we provide strong evidence that benchmark quality is limited by annotation incompleteness. Across four widely used datasets (COCO, Pascal VOC, Cityscapes, KITTI), re-annotation reveals substantial increases in annotated objects (e.g., up to +60% on KITTI and +40% on COCO), driven primarily by previously unlabeled small, occluded, or densely packed instances. While some differences arise from dataset-specific annotation conventions, we consistently find that missing annotations are the main source of label errors across all datasets. To achieve high data quality, we introduce a scalable annotation pipeline that emphasizes high recall and captures ambiguity through soft labels aggregated from at least 11 annotators per object. The resulting annotations improve coverage and align well with human calibration. We show that benchmark performance is highly sensitive to annotation quality, although model rankings remain largely stable. We introduce two large-scale benchmarks: (i) an uncertainty-aware object detection benchmark, and (ii) a label error detection benchmark grounded in real label errors. We show that current detectors are strongly depended on annotation quality and are misaligned with human perception. Current label error detection methods, which have been shown to perform well on synthetic noise, struggle to achieve high recall and precision on real label errors. Our results highlight the need for future object detection benchmarks to move beyond deterministic annotations toward high-recall, uncertainty-aware evaluation that maximizes valid instances and better reflects real-world ambiguity.

NeurIPS 2026

ObjView-Bench: Rethinking Difficulty and Deployment for Object-Centric View Planning

Sicong Pan, Hao Hu, Xuying Huang, Benno Wingender, Maren Bennewitz

Object-centric view planning is a core component of active geometric 3D reconstruction in robotics, yet existing evaluations often conflate object complexity, planning difficulty, budget assumptions, and physical reachability constraints. As a result, conclusions drawn from idealized view-planning evaluations may not reliably predict performance under realistic reconstruction settings. We introduce ObjView-Bench, an evaluation framework for rethinking difficulty and deployment in object-centric view planning. First, we disentangle three quantities underlying view-planning evaluation: omnidirectional self-occlusion as an object-side attribute, observation saturation difficulty, and protocol-dependent planning difficulty defined through a set-cover formulation. This separation supports controlled dataset construction, analysis of slow-saturation objects, and a case study showing that planning difficulty-aware sampling can improve learned view planners. Second, we design deployment-oriented evaluation protocols that reveal how budget regimes and reachable-view constraints alter method behavior. Across classical, learned, and hybrid planners, ObjView-Bench shows that difficulty, budget, and reachability constraints substantially change method rankings and failure modes.

NeurIPS 2026

OWCE: Revealing Language Model Complementarity via Online Weakness-Conditioned Evaluation

Hankyul Baek, Jaewon Noh, Sang Seo, Sungpil Shin, Yongsu Kim

While modern applications of large language models (LLMs) rarely rely on a single model, evaluation still collapses each model into a single benchmark score. This simplification obscures each model's specific weaknesses and how those weaknesses are shared or unique across models. To address this, this paper presents Online Weakness-Conditioned Evaluation (OWCE), an evaluation framework that diagnoses each model's recurring weaknesses, generates weakness-conditioned follow-up items at increasing difficulty, and cross-evaluates the resulting items on all models. Beyond a scalar score, OWCE produces per-model weakness profiles, enabling direct comparison of where models fail and which others recover those weaknesses. These profiles expose pairwise structure that scalar scores leave invisible. This paper finds that each model has a best-matched counterpart that reduces its failure rate by up to $25$ percentage points. This counterpart is determined by weakness profiles rather than overall benchmark ranking, indicating that the highest-scoring model is not always the most effective partner for a given target. This paper evaluates OWCE empirically across seven benchmarks and seven models, and conducts a mathematical analysis showing that the generated items can provide more discriminative information under benchmark saturation. Code is available at https://anonymous.4open.science/r/OWCE-57E7

NeurIPS 2026

OTROPE: Optimal Transport-based Robust Off-policy Evaluation for Large Language Models

Liner Xiang, Wenbo Zhang, Hengrui Cai

Reliable evaluation of large language models (LLMs) is essential for their development and deployment, yet is often costly, risky, and difficult to perform safely online. We study *off-policy evaluation* for LLMs, where limited human-labeled data from a behavior model are used to evaluate a newer target LLM. This setting is challenging because labels are scarce, behavior--target distribution shift is common, and response likelihoods are often unavailable for black-box LLMs. We propose the **O**ptimal **T**ransport-based **R**obust **O**ff-**P**olicy **E**valuation (**OTROPE**), a likelihood-free evaluation that performs *distributional correction* in a *semantic space* via optimal transport to align labeled behavior-policy samples with unlabeled target-policy samples. OTROPE combines corrected human-labeled residuals with proxy predictors, yielding a stable *doubly robust*-style evaluation without behavior-policy modeling or density-ratio estimation. We theoretically characterize why baseline evaluators fail under LLM distribution shift, and establish consistency and convergence rates for OTROPE when either the reweighted behavior distribution or the proxy predictor converges. Experiments on synthetic and real LLM evaluation tasks show that OTROPE consistently outperforms baselines while enabling ensembles of weaker LLM evaluators to approach and sometimes surpass stronger evaluators.

NeurIPS 2026

OTEdit: Entropic Transport Corrected Trajectory for Inversion-Free Flow-Based Image Editing

Rameshwar Mishra, Akshay Modi, A. Subramanyam

Inversion-free methods for text-driven image editing construct direct ODE paths between source and target distributions using pre-trained flow models, but operate on single trajectories vulnerable to noise-induced drift with no mechanism to exploit the geometry of plausible edits. We propose Transport-Guided Flow Editing, which recasts the editing problem in distributional terms: we construct source and target particle clouds in latent space, solve entropic optimal transport between them with an edit-direction-aware cost, and use the resulting barycentric map to define a time-varying correction field for the editing ODE. The transport plan adapts online at each integration step, and the correction strength is governed by a variational co-state derived from the OT anchor, responding to accumulated trajectory deviation rather than following a fixed schedule. The output is a single edited image, but one whose trajectory has been steered by distributional information inaccessible to single-trajectory methods. Extensive experiments demonstrate state-of-the-art structure preservation with superior semantic alignment and consistent human preference over existing baselines.

NeurIPS 2026

OT-Robust3DVLA: A Wasserstein Barycenter is the Right Inductive Bias for Robust Multi-View 3D Vision-Language-Action Policies

Pawan Kumar

Multi-view 3D vision-language-action (VLA) policies are brittle to small sensor perturbations: depth jitter, partial occlusion, calibration drift and per-view dropout can move the predicted action chunk by far more than the perturbation itself. We trace the brittleness to the *fusion stage*: concatenating per-view tokens lets a small geometric shift flip arbitrary token indices, turning a continuous-mass-transport problem into a discrete indexing problem. We propose **a single substitution**: replace concat-then-attention fusion with a *differentiable Wasserstein barycentric tokenizer* that fuses $K$ view measures into $M$ barycentric tokens by transport. We prove a chain of Lipschitz-style stability bounds that hold conditional on a declared OT perturbation set, calibrated Lipschitz constants, and bounded Sinkhorn-solver residuals. Empirically, the barycenter is the single dominant mechanism behind the gain: (i) the proposed model has the lowest mean clean $\ell_2$ on synthetic, LIBERO, RLBench and CALVIN ABC→D (3-of-4 with non-overlapping 95% CIs); (ii) a controlled ablation on synthetic regresses by $46\times$ on the corruption-stability metric when the barycenter is removed and by $<1.5\times$ when any other component is; (iii) the same mechanism transfers to LIBERO with a $+37\%$ clean $\ell_2$ regression and $+62\%$ action-OT regression on real data; (iv) in synthetic closed-loop the concat-fusion baseline collapses from 85% clean to 0% under per-view dropout while the barycenter keeps a 92% worst-case across all five conditions (3 seeds, narrowest CI of all four methods).

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.