NeurIPS 2026 论文列表

Vision-Language-Action (VLA) models have emerged as a promising paradigm for building embodied agents that ground perception and language into action. However, most existing approaches rely on direct action prediction, lacking the ability to reason over long-horizon trajectories and evaluate their consequences, which limits performance in complex decision-making tasks. In this work, we introduce $\textbf{World-Value-Action (WAV)} $ model, a unified framework that enables implicit planning in VLA systems. Rather than performing explicit trajectory optimization, WAV model learn a structured latent representation of future trajectories conditioned on visual observations and language instructions. A learned world model predicts future states, while a trajectory value function evaluates their long-horizon utility. Action generation is then formulated as inference in this latent space, where the model progressively concentrates probability mass on high-value and dynamically feasible trajectories. We provide a theoretical perspective showing that planning directly in action space suffers from an exponential decay in the probability of feasible trajectories as the horizon increases. In contrast, latent-space inference reshapes the search distribution toward feasible regions, enabling efficient long-horizon decision making. Extensive simulations and real-world experiments demonstrate that the WAV model consistently outperforms state-of-the-art methods, achieving significant improvements in task success rate, generalization ability, and robustness, especially in long-horizon and compositional scenarios.

Learning robust robot policies in real-world environments requires diverse data augmentation, yet scaling real-world data collection is costly due to the need for acquiring physical assets and reconfiguring environments. Therefore, augmenting real-world scenes into simulation has become a practical augmentation for efficient learning and evaluation. We present WorldComposer, an automated generative Real2Sim2Real framework that maps real-world panoramas into high-fidelity, task-ready simulation environments and further synthesizes diverse Digital Cousins through scene and object variations. Combined with high-quality physics engines and realistic assets, WorldComposer supports interactive manipulation across rigid, articulated, and deformable objects. Additionally, we incorporate multi-room stitching to construct consistent large-scale environments for long-horizon tasks. Experiments demonstrate a strong sim-to-real correlation validating our platform's fidelity, and show that extensively scaling up data generation leads to significantly better generalization to unseen scene and object variations, demonstrating the effectiveness of Digital Cousins for generalizable robot learning and evaluation.

Robust motion planning in dense traffic requires autonomous vehicles to interact in rare and safety-critical scenarios that are underrepresented in naturalistic driving data. Although adversarial training offers a feasible solution, existing methods often rely on external scenario generators, heuristic perturbations, or simulator-heavy rollouts, which makes them difficult to integrate with modern autoregressive planners. Here, we cast adversarially robust planner learning as a constrained min-max game and propose Adversarial World Modeling (AWM), a theoretically grounded multi-agent self-play fine-tuning framework. Since solving the exact game is intractable, AWM introduces a principled decoupled solver. In the inner minimization, the planner's predictive world model is converted into a role-conditioned adversary that learns sparse, scene-adaptive attack coalitions via counterfactual credit assignment. In the outer maximization, the ego planner optimizes a regret-aware robust best response against the frozen AWM, utilizing tail-risk weighting and reference-anchored trust regions to improve hard-case recovery while preserving nominal driving behavior. Experiments on the nuPlan and InterPlan benchmarks demonstrate that our method generates transferable adversarial interactions and yields a robust planner that achieves competitive closed-loop performance in both nominal and highly interactive long-tail scenarios. Theoretical analysis justifies the decoupled solver and the main optimization components.

Cross-skeleton motion generation trains generative models to carry action structure and motion intention from one body to another. Yet an action-consistent target motion admits two observationally compatible explanations: source-preserving transfer and target-action recovery. We show that this ambiguity is structural rather than incidental: under standard generative objectives, the source-conditioned retargeting map is non-identifiable in sparse heterogeneous motion domains. Unpaired marginal matching yields \emph{gauge non-identifiability}: a relative gauge between skeleton-specific latent spaces allows different source-conditioned maps to induce the same training evidence. Sparse paired supervision admits the complementary failure mode, \emph{conditional-mean degeneration}: ambiguous action-level pairings drive squared-error objectives toward a target-action prototype that is independent of the source clip's motion intention. To make the missing evidence observable, we introduce \emph{Source-Instance Fidelity} (SIF), a diagnostic that tests whether the source-side geometry remains visible in the generated target motions after the target skeleton and action are fixed. Under this diagnostic, standard action-level success across animal motion domains recurrently coincides with behavior at the \emph{source-blind floor}, while positive cases localize source-instance information to auxiliary motion-space constraints that narrow the observational equivalence class. The implication is that retargeting requires objectives and evaluations capable of identifying the source-conditioned map that a retargeting claim asserts. [Project page](https://keen-semolina-09811d.netlify.app/).

Visual token pruning is an effective way to accelerate vision-language models and is especially useful for vision-language-action (VLA) inference, where many visual tokens must be processed before predicting robot actions. Existing pruning methods usually estimate which tokens can be pruned based on attention scores or feature diversity, retaining tokens that are either highly attended or visually different from others. However, most of them use fixed pruning schedules, such as pruning once at a preset layer or pruning at uniformly spaced layers. Such schedules can be risky for VLA models, because the model may not know which visual regions matter for the action in early layers. Tokens that look unimportant at first may become useful after the model combines visual observations with the language instruction. In this work, we propose SAPrune, a training-free visual token pruning framework for efficient VLA inference. Instead of pruning at fixed layers, SAPrune uses a small calibration set to observe how action-to-visual attention changes across layers, and chooses pruning layers only after the attention pattern becomes more reliable. At each selected layer, SAPrune applies a dual-path pruning rule: one path protects strongly attended visual tokens from pruning, while the other prevents useful surrounding context from being discarded. Experiments on LIBERO, SIMPLER, and real-world robotic tasks show that SAPrune prunes 87.5% of visual tokens and achieves up to 1.718× inference speedup while maintaining competitive task success rates.

Imitation learning (IL)—training an agent to replicate expert behavior from demonstrations—underpins applications from robotics to language model training. Standard approaches such as Behavior Cloning (BC) are known to suffer from compounding errors and performance plateaus, particularly when the learner cannot perfectly represent the expert’s policy (e.g., as is typical in distillation). Two interventions are widely understood empirically to improve performance: querying the expert interactively along the learner’s own trajectories, and using value function estimation en route to generating a policy. We investigate the nature of these improvements and their potentially surprising interplay. Our main finding is that expert interaction relaxes the representational demands on the learner: one only needs a model capable of realizing the expert’s value function, bypassing the (often stricter) requirement of realizing the expert’s policy itself. Concretely, we introduce OVI, an interactive IL algorithm that is statistically and computationally efficient whenever the learner can represent the expert’s value function. We complement this with a negative result showing that interaction is necessary: without significantly stronger representational assumptions than expert-value realizability alone, a broad class of value-based IL algorithms cannot succeed in the offline setting. These findings bear out empirically: OVI outperforms offline policy-based (BC), interactive policy-based (DAgger), and offline value-based IL methods, with the largest gains when the learner network is substantially less expressive than the expert’s.

World Action Models have recently emerged as a promising paradigm for improving action generalization in autonomous driving by leveraging future video prediction as dense supervision for scene dynamics and temporal causality. However, it remains unclear how video modeling should be integrated with action generation to maximally transfer these benefits. Existing cascaded or dual-Diffusion Transformer architectures decouple video imagination from trajectory prediction, limiting knowledge transfer: the action model may still overfit dataset-specific driving priors, while the video model only indirectly regularizes planning. In this paper, we propose UNIVERSE, a unified video-action model built upon a single mask-modulated Diffusion Transformer. By co-training future video latents and ego-trajectory tokens within shared generative parameters, UNIVERSE allows dense video supervision to directly shape trajectory denoising, leading to stronger cross-domain action generalization. To ensure causal validity and efficient deployment, we introduce a Modality-Decoupling Visibility Mask, which shares historical context across modalities while blocking mutual attention between future video and trajectory tokens. This prevents future-modality dependency and enables trajectory-only inference by removing future-video denoising at test time, achieving a $4.3\times$ speedup over joint video--trajectory rollout while maintaining comparable planning accuracy. The same model also supports video-only and joint video--trajectory rollouts. Experiments show that UNIVERSE achieves 91.0 PDMS on NAVSIM and strong zero-shot transfer to nuScenes and Bench2Drive without fine-tuning, while ablations confirm the importance of single-DiT unification, video co-training, and mask-based modality decoupling.

End-to-end autonomous driving systems are known to suffer from shortcut learning and causal confusion, limiting robust generalization under distribution shift. To address this, recent Vision-Language Model (VLM) approaches introduce intermediate linguistic reasoning steps including chain-of-thought, chain-of-causation, and counterfactual (CF) reasoning, and report consistent improvements in closed-loop driving. Among these, CF reasoning has been emphasized as enabling self-reflective, high-level causal understanding, yet whether these gains reflect genuine causal reasoning or language-induced distributional bias remains unclear. In this work, we examine what CF reasoning actually induces in VLM-based autonomous driving using accident scenarios with explicit causal structure and a discrete meta-action space. We observe that CF reasoning consistently shifts the action distribution toward more conservative behaviors, accompanied by increased perplexity and policy entropy, and that this effect persists under reinforcement fine-tuning, suggesting a structural rather than transient artifact. However, visual attention analysis and causal intervention experiments show that CF reasoning does not meaningfully alter visual grounding, and VLMs respond similarly to causal and non-causal perturbations, unlike humans who selectively react to causal factors. Overall, these results suggest that CF reasoning does not induce genuine causal reasoning grounded in visual structure. Instead, it acts as a linguistic mechanism that reshapes the action distribution, teaching models what to say but not how to reason, highlighting a fundamental gap between language-based reasoning and causal understanding in VLMs.

Urban uncrewed aerial vehicle (UAV) vision-language navigation (VLN) requires agents to follow instructions across extended urban spaces, inherently demanding long-term memory and geospatial grounding. However, scaling existing benchmarks remains difficult because of their reliance on costly reconstructed 3D assets, limiting geographic diversity and episode scale. To address this, we introduce SatNav, a scalable, long-horizon UAV VLN benchmark built from high-resolution satellite imagery. SatNav targets city-level navigation missions and uses satellite crops as approximations of UAV nadir views for visual observations. Through an automated cue-to-episode pipeline, SatNav constructs 118K episodes from 59 scenes across 18 cities, with an average trajectory length of 379 m. To stress-test long-horizon memory and geospatial reasoning, SatNav defines three task families: Boundary, Landmark, and Route, targeting loop progress tracking, landmark-based spatial grounding, and route following with counting cues. Benchmarking classical and recent large vision language model (LVLM) based VLN agents on SatNav shows that city-scale navigation remains challenging. We further introduce SwiftVLN, a modular framework with switchable memory components, and conduct systematic memory-design ablations. Finally, satellite-to-UAV transfer experiments show that satellite-trained navigation models can operate on real-flight UAV observations, showing the practical relevance of SatNav.

Linear Temporal Logic (LTL) provides a rigorous framework for specifying long-horizon robotic tasks, yet existing approaches face a trade-off: model-based synthesis relies on accurate labeled transition systems, whereas learning-based methods often require online interaction, task-specific rewards, or specification-conditioned training. We study LTL-specified robotic planning and execution in a stricter offline, model-free setting, where the agent is given only fixed, task-agnostic trajectory fragments, with no dynamics model, task demonstrations, or online data collection. To address this setting, we propose SAGAS, a framework that combines the compositionality of symbolic synthesis with the data-driven reachability structure learned from offline trajectories. SAGAS first learns a reusable latent reachability graph and a frozen goal-conditioned executor from fragmented offline data. For each new LTL formula, it performs task-time semantic graph augmentation to ground state-defined propositions on the learned graph, and applies B\"uchi product search to synthesize a cost-aware accepting prefix--suffix waypoint plan executed by the frozen executor. By shifting formula-specific reasoning from policy learning to test-time graph augmentation and symbolic search, SAGAS enables zero-shot generalization to unseen, data-supported LTL specifications without task-specific reward design, policy retraining, or online interaction. Experiments on LTL task suites constructed from OGBench locomotion domains show that this design produces executable and cost-efficient prefix--suffix behaviors for diverse unseen LTL tasks from fragmented offline data.

The ability to reason, adapt, and creatively solve problems under unexpected challenges is essential for robots operating in real-world environments. However, current robotic benchmarks primarily emphasize skill-level execution and provide limited insight into such cognitive reasoning capabilities. We introduce RoboWits, a bi-manual robotic benchmark designed to systematically evaluate cognitive reasoning, creative tool use, and robustness to unexpected conditions. To enable scalable construction of high-quality reasoning-centric unexpected scenarios, we propose an automated task generation pipeline formulated as a multi-agent cooperative framework, comprising agents for seed task generation and verification, metric generation, scene generation, and task mutation. Using the pipeline, we curated 30 diverse seed tasks and 208 tasks with mutations and graded difficulty across geometry, material, and assembly-based reasoning. We benchmark popular robot policies, pre-trained VLAs, and oracle-state planners. Our results reveal a significant performance gap: while pre-trained VLAs exhibit preliminary success on seed tasks after single-task fine-tuning, they struggle to perform on mutated tasks, implying their brittleness in manipulation tasks requiring reasoning, strategy adaptation, and robustness to deceptive or constrained environments.

Long-horizon robot operation requires spatio-temporal memory to record the environment state and recall it for downstream reasoning. Scene graphs and retrieval-augmented systems ground VLM descriptions to persistent 3D entities with rich semantic descriptions. However, VLM captions are noisy and viewpoint-inconsistent, and existing systems treat them as an oracle with no mechanism to detect unreliable stored descriptions. We introduce object-level semantic uncertainty for multi-view VLM memory: a score that measures object-centric cross-view semantic scatter of captions and identifies semantically unresolved objects. Then, we include our uncertainty scores in an advanced spatial-semantic memory system, that we dub UQ-DAAAM. UQ-DAAAM uses this score to actively refine uncertain objects under a fixed query budget by selecting high-quality views and fusing the resulting multi-view captions into a single object description. We also derive probabilistic guarantees showing that higher-quality candidate views (as selected by our approach) are more likely to reduce uncertainty. Our experiments show that uncertainty quantification can make embodied 4D memory systems more reliable and more effective. In particular, on the OC-NaVQA benchmark, UQ-DAAAM achieves substantially larger uncertainty reduction and better spatio-temporal question answering performance than baselines.

Diffusion-based vision-language-action models (dVLAs) are promising for embodied intelligence but are fundamentally limited in real-time deployment by the high latency of full inference. We propose Realtime-VLA FLASH, a speculative inference framework that eliminates most full inference calls during replanning by introducing a lightweight draft model with parallel verification via the main model's Action Expert and a phase-aware fallback mechanism that reverts to the full inference pipeline when needed. This design enables low-latency, high-frequency replanning without sacrificing reliability. Experiments show that on LIBERO, FLASH largely preserves task performance by replacing many 58.0\,ms full-inference rounds with speculative rounds as fast as 7.8\,ms, lowering task-level average inference latency to 19.1\,ms (3.04$\times$ speedup). We additionally demonstrate effectiveness on real-world conveyor-belt sorting, highlighting its practical impact for latency-critical embodied tasks.

Deploying autonomous driving systems requires robustness against long-tail scenarios that are rare but safety-critical. While adversarial training offers a promising solution, existing methods typically decouple scenario generation from policy optimization and rely on heuristic surrogates. This leads to objective misalignment and fails to capture the shifting failure modes of evolving policies. This paper presents ADV-0, a closed-loop min-max optimization framework that treats the interaction between driving policy (defender) and adversarial agent (attacker) as a zero-sum Markov game. By aligning the attacker's utility directly with the defender's objective, we reveal the optimal adversary distribution. To make this tractable, we cast dynamic adversary evolution as iterative preference learning, efficiently approximating this optimum and offering an algorithm-agnostic solution to the game. Theoretically, our analysis characterizes the idealized regularized game and derives a lower bound that connects adversarial training performance with real-world long-tail generalization. Experiments indicate that ADV-0 effectively exposes diverse safety-critical failures and greatly enhances the generalizability of both learned policies and motion planners against unseen long-tail risks.

Safe robot learning often involves multiple heterogeneous safety constraints that cannot always be satisfied simultaneously. Existing neural safety layers typically treat multi-constraint safety as a numerical optimization problem, enforcing all constraints through a single QP-based projection or relaxing conflicts with slack variables. This hides the semantic question of which constraints may be sacrificed under conflict inside solver geometry, penalty weights, or a fixed total hierarchy. We propose PoSafeNet, a poset-structured composable safety layer that makes these conflict semantics explicit. PoSafeNet encodes admissible safety override relations as a partial order and realizes each admissible execution by composing closed-form projections onto CBF-induced halfspaces. Across multi-obstacle navigation, constrained manipulation, and vision-based autonomous driving, PoSafeNet improves operational feasibility, computational efficiency, and task performance over dQP-based, slack-based, and hierarchical safety layers.

Real-world robot task planning must operate under both stochastic action execution and partial observability, yet constructing Partially Observable Markov Decision Process (POMDP) models for real robotics domains remains difficult and labor-intensive. We introduce PO-PDDL, a symbolic formulation of POMDPs that preserves the relational structure and LLM-friendly syntax of the Planning Domain Definition Language (PDDL), while explicitly modeling partial observability, stochasticity, and beliefs. Building on this formulation, we propose a demonstration-driven pipeline for learning PO-PDDL models. The proposed method reconstructs latent symbolic state trajectories from real-robot execution videos, identifies partial observability via inconsistencies between inferred states and visual observations, and learns stochastic transition and observation models accordingly. The resulting PO-PDDL domains are reusable across tasks and enable online belief-space planning under both perception and execution uncertainty. Experiments on real-world long-horizon manipulation tasks show that our method consistently outperforms existing PDDL and POMDP model-learning approaches, achieving robust task planning under uncertainty with significantly lower planning cost.

Vision-Language-Action (VLA) models show promising ability in language-guided robotic tasks. However, making VLA policies reliable remains challenging, because a manipulation task is completed through closed-loop interaction, where each action affects subsequent execution. To analyze this problem, we revisit VLA policy during execution and argue that a VLA policy acts both as a planner, which makes task-oriented decisions that change the direction of execution, and as an executor, which realizes these decisions through dense continuous actions. This view suggests that improving VLA reliability requires particular attention to planning actions. Existing optimization methods can imitate actions or improve complete trajectories, but they usually do not explicitly identify planning actions or measure their importance for task success. To address this issue, we propose Planning-Aware Policy Optimization for VLA models (PAPO-VLA). PAPO-VLA first identifies planning actions by jointly considering action variation and trajectory outcome, then estimates their importance through causal sufficiency and causal necessity, and finally incorporates this importance into GRPO advantage estimation. In this way, more important planning actions receive stronger optimization emphasis, while the whole trajectory is still optimized by trajectory-level feedback. Experiments on multiple benchmarks demonstrate the effectiveness of PAPO-VLA.

Embodied AI agents increasingly require parallel execution of multiple tasks, such as manipulation, conversation, and memory construction, from shared observations under distinct time constraints. Recent Mixture-of-Transformers (MoT) Vision-Language-Action Models (VLAs) architecturally support such heterogeneous outputs, yet existing inference systems fail to achieve efficient multi-task parallelism for on-device deployment due to redundant computation and resource contention. We identify isolated KV cache management as the root cause. To address this, we propose *unified KV cache management*, an inference design that treats KV cache as a first-class shared resource across tasks and over time. This abstraction enables two key optimizations: *cross-task KV sharing* eliminates redundant prefill of shared observations, while *cross-frame continuous batching* decouples variable-length language decoding from fixed-rate action generation across control cycles. We implement this design for $\pi_{0.5}$, the most popular MoT VLA, and evaluate on both NVIDIA GeForce RTX 4090 and Jetson AGX Thor, two representative platforms for on-device VLA inference. \nickname achieves up to 3.7$\times$ speedup over isolated execution, delivering over 200 tokens/s language throughput and 70 Hz action frequency simultaneously without action quality degradation, and we further validate the gains on a real humanoid robot with on-board Jetson AGX Thor.

Deploying a language-guided navigation policy in a new building usually means watching it fail. Public-benchmark VLAs degrade scene by scene as layout, appearance, and language drift, and the standard fix of teleoperating fresh trajectories on site does not scale. We replace human demonstration with a single brief iPhone scan. Scan2Instruction compiles that scan into a complete training environment, automatically synthesizing executable navigation episodes with grounded instructions. PRPT-KS then adapts the policy through a closed-form Pareto utility read directly off the reconstructed scene, with no learned critic and no human labels. Across five real environments, the two designs together drive our RealNav to an 89% real-robot success rate, almost doubling the strongest VLA baseline at 48%, and still achieve 87% in unscanned regions of the same buildings. Our work turns demonstration-free scene adaptation for language-guided navigation from an aspiration into a working reality. All code and model will be released open-source upon acceptance.