NeurIPS 2026 论文列表

AI agents combine a learned neural component, such as a language model, with symbolic components, such as memory, tools, and environments. Existing safety alignment work improves both sides independently: neural alignment reduces unsafe model behavior, while symbolic alignment constrains memory, tool use, permissions, and action. This position paper argues that safe neural and symbolic components do not necessarily compose into a safe agent. Agent safety is often contextual: whether an answer, retrieval, or tool call is safe can depend on broader safety context, e.g., prior interactions, provenance, user boundaries, and authorization. For example, a biosafety AI research assistant might answer separate, benign-looking questions about viral delivery systems, protocol troubleshooting, and relevant literature, while the accumulated interaction begins to support the design of a dangerous pathogen. We propose contextual agent alignment as a research agenda for identifying safety-relevant context, designing safer agents that use this context, and evaluating contextual safety. Several documented agent safety failures, including cumulative dual-use risk in research assistants, peer-preservation in oversight settings, and contextual privacy violations, can be viewed as instances of contextual safety failure. This agenda is important for the broader AI safety community because frontier systems are increasingly deployed as agents in real-world settings.

Transformer predictions depend on positional embeddings, which are known to produce biases such as first- and last-token dominance. However, feature attribution methods implicitly entangle influence from positions with features into a single opaque importance score per feature. To uncover these positional effects, we propose Position-aware eXplanation (PaX), a model-agnostic framework that transforms standard attribution methods to jointly produce feature and position attributions. PaX additionally produces counterfactual positional explanations: actionable scores quantifying how the prediction changes when a feature is relocated. We use PaX to generalize perturbation-, gradient-, and boundary-based attribution methods across vision, language, and clinical time-series benchmarks with no architectural changes. We demonstrate that separating positional effects improves both feature and position attribution faithfulness by 17.5% / 55% and 16.8% / 43%, respectively (insertion / deletion). In a case study on sepsis forecasting, we find that PaX recovers clinically validated bedside signals that standard attributions miss.

Autoregressive transformers with no positional embeddings (NoPE) can recover absolute position. A common explanation is that causal attention creates a position-dependent variance signal, but this account is incomplete because LayerNorm removes per-token scale, so a viable mechanism must encode position in *direction*, not magnitude. We describe the most compact mechanism with two-layer NoPE transformers that accurately extract position. In Layer1, prefix averaging creates a shared beginning of sequence (BOS)-direction component. In Layer2, the attention's output-value matrix maps the \bos{} and \nbos{} contributions into two distinct directions, and a position-dependent \bos{} attention weight acts as a mixing coefficient that interpolates between them. The resulting directional trajectory is linearly decodable for position. Interestingly, we show two transformer variants that converge to the same theoretical mechanism and instantiate it when trained to predict position.

Recent multi-view Transformers (e.g., DUSt3R and VGGT) have advanced 3D reconstruction by scaling training data and model capacity from two views to many views and long sequences, subsuming the classical SfM/SLAM pipeline of feature extraction, matching, and pose estimation in a single feedforward pass. Yet this subsumption hides the interfaces between pipeline stages---correspondences, geometry, and pose are entangled in a single forward pass, **leaving supervised fine-tuning as the major path** to improvement and offering no mechanism to correct predictions from geometric evidence at test time. We propose PosePlaner to close this gap by reviving the classical coupling between correspondences and pose via flow matching, treating pose refinement as a conditional generation problem that takes coarse geometric matches and initial pose as input condition and fuses the resulting pose hypotheses into a single refined estimate, providing a continuous, data-driven analogue of RANSAC voting. Our method is trained efficiently on two-view data, yet serves as a periodic refiner for streaming n-view pose estimators with no retraining. Empirically, it corrects failures of feedforward predictors, substantially improves correspondence-based solvers, and reduces accumulated drift in long streaming sequences.

Zero-shot skeleton-based action recognition (ZSSAR) is typically treated as a skeleton-text alignment problem: encode joint-coordinate sequences, align them with language, and classify unseen actions. We argue that this alignment is often too late. Skeletons are not complete action observations, but compressed outputs of human pose estimation (HPE); by the time alignment begins, human-object interactions and pose-relative visual cues may no longer be explicit. We call this upstream semantic loss. To address it, we propose PoseBridge, an HPE-aware ZSSAR framework that bridges intermediate HPE representations to skeleton-text alignment. Rather than adding an RGB action branch or object detector, PoseBridge extracts pose-anchored semantic cues from the same HPE process that produces skeletons, then transfers them through skeleton-conditioned bridging and semantic prototype adaptation. Across NTU-RGB+D 60/120, PKU-MMD, and Kinetics-200/400, PoseBridge improves ZSSAR performance under the evaluated protocols. On the Kinetics-200/400 PURLS benchmark, which contains in-the-wild videos with diverse scenes and action contexts, PoseBridge shows the clearest separation, improving the strongest compared baseline by 13.3-17.4 points across all eight splits. Our code will be publicly released.

Vision-language-action (VLA) policies have shown strong potential for general-purpose manipulation, yet they often fail on novel, out-of-distribution objects whose appearance or geometry deviates from the training distribution. The standard remedy is to collect multi-view teleoperation data for every failure case, but this scales poorly in both cost and time. We introduce Pose6DAug, a failure-driven data augmentation framework that turns a policy’s own successful episodes into targeted demonstrations for its failure modes, without any new data collection. Our key insight is that each successful episode already encodes a physically valid action trajectory together with calibrated multi-view observations. By swapping only the manipulated object while preserving this trajectory, we obtain new and physically grounded demonstrations. However, the challenge lies in synthesizing object swaps, e.g., naive 2D video editing breaks multi-view consistency and physical plausibility, particularly under heavy occlusion and egocentric viewpoints. Our method instead operates directly in 3D, anchoring the target object with an explicit mesh driven by a temporally coherent 6D pose trajectory. This ensures geometrically consistent renderings across all camera views. Fine-tuning a VLA on data augmented by our method improves success rates by 16.5% relative to the state-of-the-art baseline on novel objects, while preserving in-distribution performance. These results show that multi-view and physically consistent augmentation is a practical path to scalable VLA generalization.

3D scene inpainting aims to recover missing or occluded regions in edited 3D scenes, while ensuring geometric and textural consistency. Existing approaches, however, typically require accurately calibrated camera poses, which restricts their applicability in casual, in-the-wild scenarios and introduces additional preprocessing overhead. To overcome this limitation, we present FreeInpaint, a novel feed-forward framework that generates complete and 3D-consistent scenes directly from unposed multi-view images with masked regions. At its core, FreeInpaint extends a 3D foundation model to propagate masked regions from a reference view to other unposed views, bridging 3D reconstruction and scene inpainting while preserving the model's native ability to recover camera poses and scene geometry. Our method addresses two key challenges in adapting feed-forward 3D foundation models to masked inputs. First, masked regions can corrupt cross-view correspondence reasoning, degrading pose estimation and geometry recovery. To address this, we introduce a Learnable Mask Attention mechanism that preserves the spatial anchoring of reliable observations while allowing masked regions to progressively absorb useful context in deeper layers. Second, under severe occlusions, a single forward pass often lacks sufficient appearance evidence for high-fidelity completion. Therefore, we propose a Support Token Refinement strategy, which injects diffusion-generated support evidence as confidence-weighted auxiliary tokens to refine under-observed regions while preserving the original spatial anchor. Extensive experiments across diverse datasets demonstrate that FreeInpaint achieves superior inpainting quality, eliminating the reliance on pre-computed camera poses while keeping a fast inference speed.

External beam radiotherapy is a cornerstone of cancer treatment, used in more than half of all cancer patients. It delivers high-energy radiation beams to destroy tumors while minimizing radiation dose to surrounding healthy tissues. Treatment planning requires optimizing machine parameters, including the shapes and intensities of radiation beams, based on each patient’s unique anatomy. This gives rise to large-scale, multi-criteria, and often combinatorial optimization problems that must be solved separately for each patient under strict clinical time constraints. Although recent advances in AI/ML show promise for improving many planning and decision-making tasks, progress in this area has been limited by the lack of standardized, publicly available benchmark datasets and baseline algorithms. To address this gap, we introduce PortPy (Planning and Optimization for Radiation Therapy in Python), an open-source benchmark dataset derived from real patient data, together with baseline algorithms and a Python-based framework for data processing, simulation, and standardized evaluation. Several of the provided baseline methods have been clinically validated and deployed at our institution to support automated radiotherapy planning for cancer patients. By providing a common benchmark and open research platform, PortPy aims to accelerate progress in radiotherapy treatment planning and promote collaboration across the AI/ML, mathematical optimization, medical physics, and radiation oncology communities. Toolkit: https://github.com/PortPy-Project/PortPy Dataset: https://huggingface.co/datasets/PortPy-Project/PortPy_Dataset

Recent advances in large language models (LLMs) have enabled large-scale, high-fidelity social simulations, creating new opportunities for computational social science. However, constructing persona sets that faithfully reflect real-world population diversity remains a key challenge. Existing studies often emphasize agentic frameworks and simulation environments, while paying less attention to persona generation and the biases introduced by unrepresentative persona sets. In this paper, we propose a systematic framework for synthesizing high-quality, population-aligned persona sets for LLM-driven social simulation. Our approach begins by leveraging LLMs to generate narrative personas from long-term social media data, followed by rigorous quality assessment to filter out low-fidelity profiles. We then apply importance sampling to achieve global alignment with reference psychometric distributions, such as the Big Five personality traits. To address the needs of specific simulation contexts, we further introduce a task-specific module that adapts the globally aligned persona set to targeted subpopulations. Extensive experiments demonstrate that our method significantly reduces population-level bias and enables accurate, flexible social simulation for a wide range of research and policy applications. Code is available at https://anonymous.4open.science/r/K5CQ.

Datasets in many settings naturally partition into clusters arising from sub-populations, batch effects, or aggregation across multiple sources. A common response to such heterogeneity is to ensemble learners trained on each cluster rather than fit a single model to the pooled data. Prior work motivating such approaches has typically considered settings in which both the covariate distribution and the conditional outcome model differ across clusters; the role of cluster-aware partitioning and ensembling based solely on the covariate distribution remains to be explored. We address this case for ridge-regularized least-squares regression under a linear outcome model and consider all ridge penalty values $\lambda \geq 0$, including the special case of the ridgeless predictor at $\lambda = 0$. By considering both fixed-effects and random-effects models, we argue that under random effects, an optimally tuned pooled ridge predictor always outperforms ensembles of individually optimally tuned predictors. For fixed effects, we derive a general formula for the pooled and ensembled predictors to characterize the role of both regression coefficients as well as the predictor distribution shifts. Together, these results generalize prior risk analyses of bagging and random-partition estimation using ridge and ridgeless regression predictors from the i.i.d. setting to encompass covariate shift and heterogeneity-aware partition structure.

Multimodal large language models have achieved remarkable progress, yet their language-dominant designs constrain visual perception and reasoning. Vision-centric multimodal large language models aim to restore visual understanding as the structural foundation, but existing systems rely on static visual expert fusion, leading to redundant computation, weak adaptivity, and limited multimodal transferability. Prior VC-MLLMs scale visual capacity by adding experts, whereas $\mathtt{PolyVision}$ scales visual capacity by allocating experts. We introduce $\mathtt{PolyVision}$, a vision-centric framework for conditional visual scaling in which dynamic visual expert routing assigns image patches to heterogeneous visual encoders. An \textbf{Attentive Router} selectively activates relevant experts for each patch, while a compact \textbf{VisPack} module executes routed representations efficiently and preserves example independence. Together with additional visual pre-alignment, this design turns heterogeneous visual scaling into a practical conditional-computation process. Built on the \texttt{Qwen3} backbone, $\mathtt{PolyVision}$ achieves superior efficiency and scalability on multimodal benchmarks. Experiments show that adaptive expert routing strengthens visual specialization, clarifies practical properties of visual scaling, and improves visual understanding at a favorable trade-off between efficiency and performance.

Vector polygon generation converts visual inputs, e.g., remote sensing (RS) images, into vectorized polygonal geometries, supporting applications such as autonomous driving, vector map construction, and remote sensing. Early pipelines predict raster masks and post-process them into polygons, which prevents end-to-end optimization and may miss small objects or introduce inaccurate vertices. Recent methods directly generate vector polygons, but most focus on simple exterior contours, while they either cannot represent complex polygons with holes or fail to preserve their topology. In this paper, we propose PolyTopoBench, a unified evaluation framework for vector polygon generation from RS images with explicit emphasis on complex polygons. PolyTopoBench evaluates both exterior and interior rings, and benchmarks representative methods, including segmentation-based polygonization pipelines, vision foundation model baselines, and specialized vector polygon generators, on two RS-image datasets covering buildings, roads, vegetation, and unvegetated regions. Experiments show that existing methods often recover simple exterior boundaries but degrade substantially on polygons with holes or multiple rings. These results reveal complex polygon generation as an unresolved challenge and motivate topology-aware benchmarks and model designs.

Rasterization dictates the interactive budget of 3D Gaussian Splatting (3DGS). However, the comparative speed of modern CUDA rasterizers is typically evaluated on a narrow canonical benchmark, masking severe regime-dependent performance reversals. This limited scope hides three critical kernel-level bottlenecks: warp lane underutilization, exposed global-memory latency during pixel shading, and terminal-tail penalties from hardware thread scheduling. In this paper, we present PolySplat, a workload-regime-aware 3DGS rasterizer designed to overcome these inefficiencies. PolySplat introduces a warp-saturating tile-key emitter with adaptive three-way dispatch, asynchronous shared-memory staging in the render kernel, and a persistent kernel architecture with centralized atomic dispatch to strictly bound tail latency. To rigorously validate our system, we introduce an extended 76-target benchmark that achieves comprehensive workload-regime coverage by stratifying targets across extreme Gaussian counts (up to 56.5M), high resolutions (up to 9K), and six diverse scene categories. Evaluated on this comprehensive suite, PolySplat achieves dataset-balanced geometric-mean speedups of 1.26x to 6.48x over state-of-the-art rasterizers at lossless visual quality. Notably, under sustained 60Hz interaction at extreme resolutions, PolySplat strictly meets 1-vsync display deadlines where existing renderers suffer from massive queue divergence and input-to-photon lag.

In multi-agent reinforcement learning (MARL), agents must not only discover high-reward behaviours but also reliably reproduce coordinated behaviours over time. A fundamental challenge arises from a mismatch between action-level stochastic exploration and temporally extended coordination. To address this issue, we propose a policy-level exploration framework with Deterministic Action Execution (DAE) for MARL, which shifts locally random action exploration to temporally extended policy selection via an option-based exploration mechanism. Specifically, at each time step, each agent selects a policy from a shared policy set\textemdash comprising one exploitation policy and multiple exploration policies\textemdash using a learned option policy, and actions are executed deterministically conditioned on the selected policy. By maintaining deterministic execution under temporally extended policy selection, DAE facilitates temporally coordinated behaviours across multiple time steps. Comprehensive experiments on four multi-agent tasks\textemdash Predator Prey, StarCraft II micro management challenge (SMAC), SMACv2, Google Research Football, and Multi-Agent Coordination benchmark (MACO)\textemdash demonstrate that DAE outperforms mainstream baselines, achieving superior sample efficiency and final learning performance.

Skin-friction drag induced by wall-bounded turbulent flows accounts for a substantial fraction of energy consumption across commercial aerospace, wind energy, and marine transport. Its active reduction is one of the highest-value targets in engineering fluid dynamics. Deep reinforcement learning (DRL) has emerged as the leading approach for real-time flow control, yet its performance ceiling is set not by algorithmic capability but by reward structure, the naive scalar objective does not optimally reflect the underlying physics. Policy-DRIFT bypasses this ceiling by relocating reward information from policy gradients to generative model inference: a conditional flow matching model (CFM) constructs a physically-grounded manifold of realisable flow states spanning multiple control regimes, Terminal Reward Guidance (TRG) steers samples toward reward-maximising targets at inference, and a lightweight DRL policy, structurally decoupled from reward quality, tracks these full-field targets via root-mean-squared error (RMSE) minimisation. The test case is turbulent channel flow simulated using direct numerical simulation (DNS) at friction Reynolds number of $\mathrm{Re}_\\tau = 180$, which is the canonical benchmark for wall-bounded turbulence. Policy-DRIFT achieves $49\\%$ drag reduction approaching the theoretical upper bound, which is $\\approx 16\\%$ higher than the DRL benchmark, while consuming 37$\\times$ less actuation energy. Our approach combines generative methods with active flow control, marking a paradigm shift towards controlling complex physical systems efficiently.

We study policy regret minimization in partially observable Markov games (POMGs) between a learner and a strategic adaptive adversary who adapts to the learner's past strategies. We develop a model-based optimistic framework that operates on the learner-observable process using *joint* MLE confidence set and introduce an Observable Operator Model-based causal decomposition that disentangles the coupling between the world and the adversary model. Under multi-step weakly revealing observations and a bounded-memory, stationary and posterior-lipschitz adversary and planner stability, we prove an $\mathcal{O}(\sqrt{T})$ policy regret bound. This work advances regret analysis from Markov games to POMGs and provides the first policy regret guarantee under imperfect information against an adaptive opponent.

We study policy optimization for online episodic tabular Markov decision processes with unknown transition kernels, aiming for best-of-both-worlds guarantees and multiple data-dependent regret bounds. Recent work (Dann et al., 2023; Li et al., 2026) has shown that policy optimization can adapt to both adversarial and stochastic losses with data-dependent bounds, including first-order, second-order, and path-length bounds, but only under known transitions. We resolve the open problem raised by Dann et al. (2023) by developing optimistic follow-the-regularized-leader algorithms that extend such guarantees to unknown transitions. The key ingredient is a new design of optimistic $Q$-function estimators together with a data-dependent transition bonus that controls estimator bias through the loss-prediction error. Our analysis further identifies an unavoidable transition-dependent complexity term that captures the intrinsic cost of estimating the transition kernel. As a result, we obtain first-order, second-order, and path-length bounds with this transition-dependent complexity term while simultaneously achieving gap-dependent $\mathrm{polylog}(T)$ regret in the stochastic regime.

While there is an extensive body of research analyzing policy gradient methods for discounted cumulative-reward MDPs, prior work on policy gradient methods for average-reward MDPs has been limited, with most existing results restricted to ergodic or unichain settings. In this work, we first establish a policy gradient theorem for average-reward multichain MDPs based on the invariance of the classification of recurrent and transient states. Building on this foundation, we develop refined analyses and obtain a collection of convergence and sample-complexity results that advance the understanding of this setting. In particular, we show that the proposed $\alpha$-clipped policy mirror ascent algorithm attains an $\epsilon$-optimal policy with respect to positive policies.

The inference efficiency of diffusion large language models (dLLMs) is constrained by two challenges: bidirectional attention precludes efficient KV-cache reuse, while increasing decoding parallelism with static confidence thresholds can compromise generation quality. We observe that both challenges arise from a shared phenomenon: as tokens are decoded, their contextual integration through bidirectional attention causes token representations to drift (evolve) across decoding steps. This insight motivates Polestar, a training-free inference framework that uses token representation drift as a unified signal to jointly address both challenges. Polestar comprises two components: Polestar-Cache, which identifies stale KV-cache positions via drift and performs sparse KV-cache refreshes to enable efficient reuse, and Polestar-Commit, which detects sharp drift events to reliably identify commit-ready tokens. Across mathematics and coding benchmarks on several dLLM families, Polestar sets a new state of the art on the accuracy-throughput Pareto frontier, achieving up to 10.73% accuracy improvement, up to 3.7x higher throughput, and high decoding parallelism of 3.67 tokens per forward pass over existing baselines.