NeurIPS 2026 Papers

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.

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.

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.

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

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.

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.

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).

Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks through Chain-of-Thought (CoT) prompting. However, these models often exhibit "computational overthinking," generating redundant reasoning steps that increase latency and cost without improving accuracy. Recent studies suggest that CoT trajectories can be significantly pruned, yet existing methods often rely on forcing a static thinking budget, heuristic filtering, sub-optimal early exit via classification, or expensive re-training. In this paper, we introduce OS-Pruner, a lightweight plug-in framework that formulates chain-of-thought pruning as an optimal stopping problem. Given a reasoning prefix, OS-Pruner learns whether further reasoning is worth its token cost by optimizing an explicit utility that trades off final-answer accuracy against generated length. Our novel formulation enables the model to dynamically assess the sufficient point of termination for a reasoning chain. OS-Pruner is designed to be lightweight during both training and inference, and to provide users with fine-grained control over the reasoning-effort vs. accuracy trade-off. On diverse reasoning benchmarks and base models, OS-Pruner achieves 20-60\% reduction in generation length with minimal accuracy sacrifice.

Computer-using agents are increasingly expected to complete realistic user goals rather than isolated GUI actions. However, existing evaluations are fragmented across web, mobile, and desktop settings, making it difficult to measure whether the same agent can sustain long-horizon workflows across heterogeneous software platforms while preserving final-state correctness. We introduce OS-Omni, a 1,200-task cross-platform benchmark and execution environment for evaluating computer-using agents across Windows, Ubuntu, macOS, iOS, Android, and Web environments. OS-Omni provides reproducible initialization, platform-specific adapters, trajectory logging, and executable final-state evaluators, and includes controlled service-backed applications for workflows involving account, cart, budget, calendar, message, and other persistent state. Human studies show that OS-Omni tasks require 67.54 interaction steps, substantially exceeding OSWorld references of 15.0 steps. Throughout our experiments, the strongest evaluated agent, GPT-5.5, reaches 47.1% average success, trailing the 88.1% human reference by 41.0 points; on hard workflows, it drops from 77.8% success on easy tasks to 16.4%, while humans remain at 76.3%. These results indicate that current agents remain far from platform-robust, long-horizon computer use, especially when success requires sustained state tracking and durable final-state changes.

Deep multi-view clustering often struggles with inter-view feature redundancy and dimensionality collapse during iterative representation fusion. To address these limitations, we propose Orthogonal Residual Consensus Alignment (ORCA). First, a Semantic Incremental Recurrent Fusion (SIRF) module explicitly separates shared redundancy from complementary residuals via geometric projection. By employing an adaptive halting mechanism, SIRF autonomously maximizes information gain while avoiding structural collapse. Second, a Consensus-Calibrated Hierarchical Contrastive Alignment (CCHA) module is introduced to preserve multi-scale semantics. It adaptively aligns view-level, local, and recurrent representations using the global consensus as a semantic anchor. Consequently, ORCA learns latent representations with robust structural integrity and highly discriminative semantics. Extensive experiments on multiple benchmarks demonstrate that ORCA consistently outperforms state-of-the-art methods, with comprehensive ablations verifying its robustness.

Text-to-image diffusion models fail predictably on compositional prompts: attributes bind to the wrong objects, spatial relations invert, and multi-object scenes lose count. Recent architectures already augment CLIP with a T5 encoder precisely because CLIP's contrastive embedding loses compositional structure, yet these failures persist. We argue the binding problem is therefore not one of missing information but of misaligned information: a text encoder preserves compositional structure, but in a representation space shaped by language modelling rather than vision, and the denoising objective does not directly reward aligning the two. We show this correspondence can be supplied as an explicit training signal, that the relevant cross-modal information is concentrated in a low-rank subspace of self-supervised visual features, and that supplying it can be folded into diffusion training as a single auxiliary loss. Our method, ORCA, Orthogonal Residual Compositional Alignment, aligns the latent of a diffusion transformer with a low-rank target derived from a frozen visual encoder, through a predictor whose orthogonal basis is parameterised by a learned residual between T5 and CLIP embeddings, which provides a prompt-dependent signal for selecting the visual readout subspace. We prove that the cross-modal information recoverable at a given rank is bounded by the spectral mass of the visual encoder's covariance in the top components. Across three diffusion-transformer backbones, DiT-B/2, DiT-L/2, and U-ViT-L, ORCA improves FID and GenEval over both vanilla and REPA baselines at zero inference-time cost; on DiT-L/2 it reaches FID 16.65 and GenEval 0.291 at 200K steps, exceeding the strongest 400K baseline at half the training cost, with the largest gains concentrated on attribute binding, spatial relations, and multi-object prompts.

Recent advances in Video Foundation Models (VFMs) have revolutionized human-centric video synthesis, yet fine-grained and independent control of subjects and scenes remains a critical challenge. Recent attempts to achieve joint human-environment control often rely on explicit human-scene 3D alignment, improving geometric control but sacrificing generative flexibility and long-horizon consistency while requiring heavy 3D pre-processing. We present ONE-SHOT, a parameter-efficient framework for compositional human-environment video generation. Our key insight is to factorize the generative process into disentangled signals, separating human dynamics from scene cues. Specifically, our canonical-space motion injection and Dynamic-Grounded-RoPE map canonical human motion to the target video region, enabling accurate motion and placement control without heuristic human-scene 3D alignment. Hybrid Context Integration further maintains subject and scene consistency for minute-level synthesis. Experiments show that ONE-SHOT consistently outperforms state-of-the-art methods in structural control, flexible composition, text-guided semantic control, and long-horizon consistency.

Cross-modal place recognition aims to retrieve a target 3D location from a spatial map using a natural language description. Most existing methods follow a global-descriptor matching paradigm, in which the text query and each 3D scene cell are independently compressed into single vectors and compared by global similarity. Although simple and widely adopted, this paradigm tends to discard the fine-grained object correspondences that are essential for language-guided localization. In this paper, we challenge the necessity of global descriptors and propose OLA-Place, an Object-Level Alignment framework for cross-modal place recognition without global descriptors. Instead of representing a query or a scene cell as a single holistic embedding, OLA-Place formulates place recognition as set-to-set semantic alignment between textual object mentions and 3D object instances. The framework contains three key modules: ObjectSet Encoder (OSE), which extracts object-level representations from both language descriptions and 3D scene cells; Object Message Encoder (OME), which injects intra-set object-context information while preserving object-level granularity; and Masked Max Alignment (MMA), which computes the query-cell matching score by aligning each textual object mention with its most similar valid 3D object. This formulation is permutation-invariant, naturally handles variable-size object sets, and requires no object-level correspondence annotations. Extensive experiments show that object-level alignment alone significantly outperforms global-descriptor-based methods, demonstrating that cross-modal place recognition is better understood as an object-level semantic correspondence problem rather than a global-embedding retrieval problem. Our code is available at: https://github.com/Anonymous09871745/OLA-Place.

Contrastive Learning (CL) has been widely used for Graph Anomaly Detection (GAD). However, existing augmentation techniques in such CL frameworks usually rely on random masking or structural alterations, which obliterates the irregularities that define anomalies and leads to *anomaly distortion*. Even improved methods using *multi-scale sampling* usually suffer from *blind contextual extraction*, which risks disrupting critical topological structures or introducing irrelevant information in the learned representations, thereby hardly capturing complex anomalies. In this paper, we propose Orthogonal-Hyperspherical Augmentation and Topology Perception (**OHATP**), a novel method that leverages the synergies at both the *feature* and *structure* levels to mitigate anomaly distortion and *blind sampling defects*. Specifically, during *feature-level* augmentation, we adapt projections and noise based on node *message-passing* influence to strengthen *feature diversity*, while utilizing projection orthogonality and hyperspherical noise constraints to preserve *feature discriminability*. To complement this feature-level augmentation, we design a *structure-level* topology perception module that leverages the high-quality representations learned from augmentation to screen abnormal dense substructures. Extensive experiments on benchmark datasets demonstrate that OHATP substantially outperforms state-of-the-art methods, achieving improvements of over 6\% in AUROC and 29\% in AUPRC. Code is available at [https://anonymous.4open.science/r/OHATP-83D7](https://anonymous.4open.science/r/OHATP-83D7).

Vision-language-action (VLA) models have shown strong promise in robotic manipulation, yet their post-training still predominantly relies on trajectory-level supervised imitation over robot demonstrations. While effective for learning feasible actions, this paradigm supervises policies to reproduce expert actions at each step, biasing them toward demonstration-specific action paths and providing limited guidance for recovering toward task-progress states once execution deviates from demonstrated trajectories. To address this limitation, we propose OGPO, an Offline Goal-conditioned Policy Optimization framework for recoverable VLA post-training. Instead of treating offline demonstrations merely as step-wise action labels, OGPO adaptively relabels trajectories with semantic key states and constructs goal-conditioned process rewards to optimize the policy for reaching these task-progress states. In this way, OGPO shifts VLA post-training from trajectory-level action imitation to key-state reachability learning, enabling policies to acquire a more robust ability to complete goal states from feasible off-demonstration states without requiring additional online interaction. Experiments on LIBERO and MetaWorld show that OGPO consistently improves VLA policy performance over standard supervised fine-tuning. Moreover, evaluations on LIBERO-Plus and our proposed LIBERO-ReAct, a mid-execution perturbation benchmark, further demonstrate that OGPO achieves stronger robustness and goal-directed recoverability under distribution shifts and recoverable off-demonstration states.

In the physical world we inhabit, space and time are fundamentally continuous. However, existing machine learning paradigms for world modeling are largely confined to discrete-time prediction and inference, thereby exhibiting significant inefficiency in capturing the fundamental dynamics of the physical world. To bridge this gap, we introduce Physical-Time Flow (**PT-Flow**), a novel approach that learns a continuous latent velocity field operating in physical time. Crucially, the underlying dynamics of sequential data are parameterized by an ordinary differential equation (ODE) embedded in a well-structured dynamical representation space. Under this paradigm, the prediction of the future can be recast as temporal integration via an ODE solver in the compressed latent space. Building upon PT-Flow, we construct **ODEWorld**, a physics-grounded, continuous-time latent world model that is both efficient and versatile. By extracting time-variant features and enforcing ODE properties on both the dynamical representation space and the latent velocity field, ODEWorld effectively addresses the long-standing representation collapse issue in latent world model literature. This also enables high-quality image reconstruction with ODEWorld even after long-horizon prediction. Moreover, its continuous nature allows for arbitrary temporal resolution and even backward prediction, which is impossible for most discrete-time models. Lastly, benefiting from the learned dynamics-centric latent space, ODEWorld can provide rich planning-oriented information to facilitate downstream policy learning. Comprehensive experiments across multiple simulation and real-world datasets demonstrate that ODEWorld successfully reconciles planning-conducive dynamics abstraction with visual realism, excelling in both video generation and robotic control. More qualitative results can be found at [Project Website](https://anonymous-submission-16982.github.io/ODEWorld).

Recent advances in deep learning for shadow removal have significantly enhanced image quality and realism. However, most approaches rely on real-world paired datasets, which are costly to collect and often limited in scene diversity, leading to limited generalization. To address these limitations, we propose One-step Deshadow Diffusion via Reward guidance (ODDR), a new framework that achieves efficient and high-fidelity shadow removal without relying on real-world paired supervision. Our method begins with One-step Deshadow Diffusion (ODD), a baseline model trained on synthetic shadow data for efficient one-step shadow-free reconstruction. We further adapt ODD into ODDR using ShadowReward. In contrast to traditional, annotation-heavy approaches, ShadowReward is the first reward model for shadow removal trained entirely without human annotation. It learns to mimic human perceptual judgments by ranking synthetically generated images with controlled degradations, such as texture distortion and boundary artifacts. This reward-guided fine-tuning enables ODDR to close the synthetic-to-real domain gap. Extensive experiments show that ODD achieves strong performance without relying on real-world paired supervision, and ODDR further improves the results and achieves performance competitive with methods trained on real-world paired data, while maintaining higher computational efficiency as a single step model.

The key-value (KV) cache dominates memory bandwidth and footprint in long-context autoregressive inference. Recent rotation-preconditioned codecs (TurboQuant, PolarQuant) show that a structured random rotation followed by a per-coordinate scalar quantizer matched to an analytically tractable marginal is a near-optimal recipe for KV compression. OCTOPUS advances this paradigm through joint quantization of rotated coordinate triplets. Each triplet's direction is mapped to a square via an octahedral parameterization, and the two resulting coordinates and the triplet norm are Lloyd-Max quantized against implementation-matched marginals. Optimizing the per-triplet squared error gives a strictly non-uniform bit allocation depending only on the total dimensionality of the keys. We find the finite-dimensional quality optimum with sweeps to be constant on every real decoder we test. The codec is data-oblivious, online, and deterministic given a seed. Across text, video, and audio, OCTOPUS matches or beats every prior rotation codec at every reported bit width and metric, with a lead that grows as bits drop for extreme compression. Furthermore, a fused Triton implementation reconstructs keys on the fly without materializing the uncompressed key, so the codec adds no decode-time bandwidth or latency over the existing dequantization.

Retrieval benchmarks are increasingly saturating, but we argue that efficient search is far from a solved problem. We identify a class of queries we call *oblique*, which seek documents that *instantiate a latent pattern*, like finding all tweets that express an implicit stance, chat logs that demonstrate a particular failure mode, or transcripts that match an abstract scenario. We study three mechanisms through which obliqueness may arise and introduce OBLIQ-Bench, a suite of five oblique search problems over real long-tail corpora. OBLIQ-Bench exposes an overlooked asymmetry between retrieval and verification, where reasoning LLMs reliably recognize latent relevance whenever relevant documents are surfaced, but even sophisticated retrieval pipelines fail to surface most relevant documents in the first place. We hope that OBLIQ-Bench will drive research into retrieval architectures that efficiently capture latent patterns and implicit signals in large corpora.