NeurIPS 2026 论文列表

Accurately matching human intentions in 3D space is an important goal of artificial intelligence. Recently, 3D Intention Grounding (3D-IG) has emerged, aiming to localize target 3D objects given a natural-language intent. Unlike conventional visual grounding with descriptive referring expressions, 3D-IG intents are abstract and non-descriptive, making object localization substantially more challenging. This requires inferring latent functional requirements from non-descriptive intents and aligning them with object-level 3D representations. However, existing methods largely rely on implicit intent–object matching, leading to logical gaps and limited interpretability, robustness, and generalization. To address these challenges, we propose Chain-of-Causal Reasoning (CoCR), a causality-inspired functional dependency reasoning framework that explicitly bridges abstract intentions and candidate objects through intermediate functional requirements. Specifically, CoCR progressively decomposes complex intents into ordered functional requirements, thereby forming an explicit intent–function–object reasoning chain that links abstract intentions to object suitability. Building on this chain, we construct a causality-inspired functional dependency graph to model requirement--attribute relationships and introduce a causal-visual alignment module that aligns function-aware representations with the geometric-semantic features of 3D point clouds, enabling bidirectional verification between structured functional reasoning and visual evidence. Extensive experiments on 3D Intention Grounding and 3D Visual Grounding demonstrate that our method enhances intent-aware object localization.

Graphic designs, such as posters, advertisements, and infographics, are an important medium for communicating information and shaping understanding. Unlike natural images, they consist of layered elements with explicit compositional order. However, existing object detection models treat these elements as an unordered set, leaving compositional order unexploited. To address this limitation, we present **D**etect **A**nything in Graphic **D**esign (DAD), a model that formulates graphic design detection as compositional deconstruction. It decodes elements in compositional order, using lower-layer elements to better detect higher-layer ones. The key feature of DAD is amodal detection, which predicts the full bounding box of each element, including regions occluded by elements placed above it. Building on this formulation, we propose **Ele**ment **R**elative **P**olicy **O**ptimization (EleRPO), which extends GRPO from sequence-level supervision to element-level optimization. EleRPO provides fine-grained training signals that capture how each detected element contributes to overall detection quality, and works synergistically with compositional order to improve detection performance. To support training and evaluation, we build a dataset of 10 million graphic designs. Experiments show that DAD outperforms all baselines and achieves human-level performance in amodal detection, supporting effective image-to-layer decomposition. EleRPO consistently improves over GRPO across nine detection benchmarks.

Vision-Language Models (VLMs) excel at open-world 2D perception but struggle with precise metric spatial reasoning, a key requirement for applications like autonomous driving, navigation, and embodied intelligence. We identify this as a structural limitation: images are 2D projections of the 3D world, inherently suffering from projective ambiguity, while VLM components favor semantic understanding and rely on 2D positional bias, leading to Spatial Collapse. To address this, we propose Despa, a Depth-grounded spatial VLMs that injects depth-based geometric information via Geometric Positional Embedding (GPE) and Depth-aware Rotational Positional Embedding (DoPE). To expose masked limitations in current benchmarks, we construct SpaDataset (1.7M QA pairs) and SpaBench (2,051 QAs), to our knowledge the largest fine-grained training corpus and benchmark suite for metric spatial reasoning. They cover three difficulty levels and ten sub-tasks across diverse settings. The fine-tuned Despa-4B model consistently outperforms general-purpose, closed-source, and specialized VLMs on SpaBench by 27.9% over Qwen3-VL-235B-A22B and 31.1% over GPT-5.2, generalizes to MSMU (66.3%), RefSpatial-U (42.4%), and the multi-frame VSI-Bench (66.0%), and consistently lifts LLaVA-1.5, Qwen2.5-VL, and Qwen3-VL backbones, achieving the performance with only a 4B model. The code will be publicly released.

Reinforcement learning (RL) post-training provides a direct way to align diffusion and flow-matching generators with human preferences and task-specific rewards, but current RL algorithms for diffusion models remain fragmented: reverse-trajectory methods rely on discretized likelihood ratios, whereas forward-matching methods train on reward-labeled noising pairs. This paper shows that these seemingly different losses arise from a single path-space principle. Starting from the regularized diffusion-RL objective, we use importance sampling between sampling SDEs to obtain an explicit policy-gradient estimator on trajectory space. The estimator contains the stochastic It\^o integral underlying Flow-GRPO-type updates; we derive an equivalent variance-reduced value-gradient form that recovers the forward-matching structure of AWM and DiffusionNFT. This identifies the empirical gap between these method families as a variance-reduction effect rather than a difference in RL principle. The derivation yields a unified design space organized by value-gradient estimation, weight functions, and sampling choices. Within this space, we propose a multi-sample KDE value-gradient estimator that reuses rollout groups, together with scale-bounded weight families that retain stable existing recipes while excluding singular ones. Experiments on SD3.5-M and Qwen-Image models validate the variance-reduction explanation and show that the resulting recipe matches or improves over prior diffusion-RL baselines.

We study cross-sample modality attribution in multimodal learning: how a modality in one training sample affects learning from other samples. This problem is central to interpretation because a modality may be redundant for some samples, uniquely informative for others, or useful only through synergy with other modalities. However, existing data attribution methods are insufficient for this setting because they typically estimate sample-level contributions using additive or linear approximations, and therefore cannot capture nonlinear interactions across samples and modalities. We propose a structured kernel surrogate (SKS) framework for multimodal attribution. SKS learns a mapping from sample-and-modality selections to the final loss. To approximate this mapping, SKS uses kernel ridge regression with a structured radial basis function kernel that captures nonlinear effects across samples and modalities. The kernel also preserves the natural hierarchy of multimodal perturbations by modeling sample participation separately from within-sample modality composition. Across diverse environments and benchmarks, SKS achieves $60.3$% higher linear datamodeling score than the strongest baseline. For downstream data selection, SKS improves the average accuracy by $2.24$% over the strongest baseline. Sharpness analysis further shows that models trained on data selected by SKS have lower Hessian trace values, indicating a flatter loss surface and better generalization. Beyond these quantitative gains, SKS also provides interpretable modality-level selections in spatiotemporal traffic accident prediction, preferentially retaining satellite tiles with visible road infrastructure over vegetation-dominated tiles.

Hyperparameter transfer has become an important component of modern large-scale training recipes. Existing methods, such as muP, primarily focus on transfer between model sizes, with transfer across batch sizes and training horizons often relying on empirical scaling rules informed by insights from timescale preservation, quadratic proxies, and continuous-time approximations. We study hyperparameter scaling laws for modern first-order optimizers through the lens of recent convergence bounds for methods based on the Linear Minimization Oracle (LMO), a framework that includes normalized SGD, signSGD (approximating Adam), and Muon. Treating bounds in recent literature as a proxy and minimizing them across different tuning regimes yields closed-form power-law schedules for learning rate, momentum, and batch size as functions of the iteration or token budget. Our analysis, holding model size fixed, recovers most insights and observations from the literature under a unified and principled perspective, with clear directions open for future research. Our results draw particular attention to the interaction between momentum and batch-size scaling, suggesting that optimal performance may be achieved with several scaling strategies.

Fine-scale-faithful neural simulation under fixed storage budgets remains challenging. Many existing methods reduce high-frequency error by improving architectures, training objectives, or rollout strategies. However, under budgeted coarsen-quantize-decode pipelines, fine detail can already be lost when the carried state is constructed. In the canonical periodic incompressible Navier--Stokes setting, we show that primitive and derived fields undergo systematically different retained-band distortions under the same operator. Motivated by this observation, we formulate **Derived-Field Optimization (DerivOpt)**, a general state-design framework that chooses which physical fields are carried and how storage budget is allocated across them under a calibrated channel model. Across the full time-dependent forward subset of PDEBench, DerivOpt not only improves pooled mean rollout nRMSE, but also delivers a decisive advantage in fine-scale fidelity over a broad set of strong baselines. More importantly, the gains are already visible at input time, before rollout learning begins. This indicates that the carried state is often the dominant bottleneck under tight storage budgets. These results suggest a broader conclusion: in budgeted neural simulation, carried-state design should be treated as a first-class design axis alongside architecture, loss, and rollout strategy.

Derivative-informed training improves neural operators by directly supervising their input--output sensitivities, but existing methods rely on offline tangent solves and stored derivative labels. We propose sketched tangent consistency loss (sTCL), an on-the-fly drop-in derivative regularizer for neural-operator training that improves learned Jacobians without changing the architecture or generating offline sensitivity data. At each training step, sTCL samples a small number of perturbation directions in the input function space, computes the corresponding surrogate Jacobian--vector products using forward-mode automatic differentiation, and penalizes the residual of the forward sensitivity equation. This equation is obtained by differentiating the governing PDE with respect to the input perturbation direction, so derivative supervision is obtained directly from the physics rather than from stored tangent labels. We further show that sketching makes online derivative-informed training computationally feasible, while conditioning is the key to making it effective. Random directional sketching keeps the derivative penalty at the same order of cost as the standard data-fitting loss, making sTCL compatible with stochastic neural-network training as a lightweight loss term. However, raw forward-sensitivity residual penalties can fail for stiff, ill-conditioned, or indefinite tangent operators. To address this, we introduce lightweight operator-aware preconditioners selected by a simple tangent-operator decision rule. Across four PDE benchmarks---Helmholtz, nonlinear diffusion--reaction, Burgers, and two-dimensional Navier--Stokes---operator-conditioned sTCL achieves accuracy comparable to offline DIFNO while eliminating the offline derivative-data generation stage. These results show that on-the-fly derivative-informed training need not merely amortize offline tangent-solve cost into training; with appropriate sketching and conditioning, sTCL provides an attractive drop-in path to derivative-informed neural operators.

Monocular depth estimation has improved significantly in recent years, driven by increasingly powerful models and large-scale training data. Predicted depth is increasingly used as an input signal for downstream tasks such as Structure-from-Motion (SfM), visual localization, and SLAM. However, monocular depth estimators (MDEs) are still primarily evaluated in terms of depth accuracy. Standard metrics aggregate errors globally and may not reflect the usefulness of depth for downstream geometric tasks. We therefore propose Depth2Pose, a framework for evaluating MDEs in the context of downstream tasks. By combining depth predictions with feature correspondences in depth-aware geometric solvers, we use relative camera pose estimation accuracy as a task-driven proxy for depth quality. Traditional benchmarks require dense ground truth in the form of per-pixel depth, which is expensive to obtain. In contrast, our formulation requires only camera poses, which can be estimated efficiently, e.g., using Structure-from-Motion pipelines. As a result, our framework can be applied to scenes where ground-truth depth is difficult to obtain, for example due to large scene scale or heavy occlusions (e.g., vegetated environments). Leveraging this, we introduce the D2P dataset, which contains challenging scenes outside the distribution of commonly used training data. We show that methods performing well under standard depth error metrics on existing benchmarks also perform well under our pose-based metric when evaluated on the same datasets, but do not necessarily generalize to our more challenging dataset. Finally, we provide a simple and extensible evaluation framework. The dataset and code are available at kocurvik.github.io/depth2pose.

Depth-recurrence promises improved latent reasoning by sharing parameters across depths. However, prior work still relies on partially fixed layer stacks and overlooks the bottleneck of constant hidden-size; moreover, it largely lacks rigorously resource-matched ablations. To address this, we introduce depth-recurrent attention mixtures (Dreamer), a modular architecture with a single recurring layer. Concretely, we mix sequence attention, depth attention, and sparse expert attention. This alleviates the hidden-size bottleneck, decouples scaling dimensions, and achieves effective yet efficient depth-recurrence. Across natural language reasoning benchmarks at up to ~2B parameters, Dreamer requires on average ~3x fewer training tokens for the same accuracy as FLOP-, parameter-, and memory-matched modern Transformers, and outperforms ~2x larger Transformers given same training tokens. Analysis further reveals 2-11x greater expert selection diversity than conventional MoEs, highlighting the flexible knowledge sharing across depths.

Modern automatic speech recognition (ASR) systems have achieved remarkable accuracy by scaling model depth and capacity, but at the cost of substantial memory and computation. On edge devices where ASR is often most needed, such as watches and glasses, deploying such large models is infeasible due to extremely constrained resources. This raises a fundamental question: can we achieve high representational power in deep ASR models without scaling up parameterization? In this work, we revisit the role of depth and identify layer-wise representational dynamics, in which most layers learn functionally similar transformations. Motivated by this insight, we propose a block-recurrent ASR architecture that replaces parameterized depth with a small set of recurrent blocks, each consisting of weight-shared layers, thereby preserving effective depth while drastically reducing model size. Through representation-guided grouping and knowledge distillation, block-recurrent models retain the accuracy of large reference models while using an order of magnitude fewer parameters. Across Open ASR Leaderboard benchmarks, a model with only two shared blocks recovers $97.4$% of the accuracy of large models on average. The compact backbone further enables efficient on-device personalization through lightweight MoE-LoRA adaptation, allowing user-specific models to match or surpass the accuracy of general-purpose ASR systems with significantly lower inference cost. Together, these results show that high-quality ASR can be achieved without large parameterization, and that structured recurrence provides a principled path towards ultra-compressed, high-efficiency, and personalized speech recognition on the edge.

Behavioral cloning (BC) is a powerful paradigm for learning robotic policies from demonstrations. However, most existing approaches operate in an offline setting and do not address a critical requirement for real-world deployment: the ability to continually improve policies after deployment. While interactive imitation learning methods such as DAgger enable improvement by collecting additional data, they rely on repeated retraining over an ever-growing dataset, leading to increasing computational cost and limited scalability. In practice, robotic systems must adapt continuously during deployment while remaining operational, making retraining on all accumulated data impractical. In this work, we introduce an online formulation of interactive BC, where the policy is updated in real time with expert corrections to address failure cases, with no access to past data. This setting presents a fundamental challenge due to catastrophic forgetting, which degrades previously acquired behaviors when learning from new data. To address this, we propose a novel method based on online ridge regression and random projections, enabling efficient policy updates without gradient-based retraining. We evaluate our approach on a range of manipulation tasks and show that it enables continuous and stable improvement after deployment, outperforming state-of-the-art BC baselines.

Large language model test-time training (TTT) is often evaluated through local proxy metrics: models are updated on recent tokens, retrieved context, target-domain data, or verifiable task attempts, and then judged by perplexity, future-token loss, long-context performance, or reward. These metrics are well matched to claims about stream adaptation, domain adaptation, context compression, and reward-backed test-time improvement. This position paper argues that TTT has a distinct claim-calibration problem: proxy evidence for local adaptation can migrate into stronger claims about deployed assistant memory, personalization, or sparse post-deployment learning. Such claims require behavioral evidence: later recall, paraphrase robustness, retention, locality, conflict handling, and use in downstream actions after the original support context is removed. We propose a claim-calibrated evidence ladder for LLM TTT, audit recent work through this lens, and provide a diagnostic counterexample in which proxy losses improve without behavioral recall. Our goal is to give authors and reviewers a standard for aligning TTT memory claims with the evidence actually reported.

Discrete diffusion language models (dLLMs) accelerate text generation by unmasking multiple tokens in parallel. However, parallel decoding introduces a distributional mismatch: it approximates the joint conditional using a fully factorized product of per-token marginals, which degrades output quality when selected tokens are strongly dependent. We propose DEMASK (DEpendency-guided unMASKing), a lightweight dependency predictor that attaches to the final hidden states of a dLLM. In a single forward pass, it estimates pairwise conditional influences between masked positions. Using these predictions, a greedy selection algorithm identifies positions with bounded cumulative dependency for simultaneous unmasking. Under a sub-additivity assumption, we prove this bounds the total variation distance between our parallel sampling and the model's joint. Empirically, DEMASK achieves 1.7--2.2$\times$ speedup on Dream-7B while matching or improving accuracy compared to confidence-based and KL-based baselines. When applied to dParallel, a block diffusion model, DEMASK also produces Pareto-optimal accuracy-step trade-offs across math and code benchmarks.

We study post-hoc Learning to Defer (L2D) through the lens of ideal distributions: divergence-regularized reweightings of the data distribution under which a model attains low loss. We define deferral via the density-ratio between a model's and an expert's ideals. Using the reduction from density-ratio estimation to class-probability estimation, we derive the DR CPE losses for post-hoc L2D scorers. Deferral decisions are then made by thresholding the scorer, allowing deferral rates to be adjusted without retraining. For KL-based ideal distributions, our deferral rules recovers Chow's rule under the original distribution and a connection to an expert-tilted Bayes posterior—which incorporates the expert's performance—depending on if the ideal distributions are joint or marginal distributions. Experimentally, our approach is competitive compared to common baselines and more robust across dataset settings. More broadly, our results cast post-hoc L2D as density-ratio learning between ideal distributions, bridging Chow-style rules, expert comparison, and elucidating connections to related learning settings including anomaly detection.

Cross-tokenizer knowledge distillation lacks a shared coordinatesystem between teacher and student vocabularies, and existingmethods each drop one of the two ingredients comparison needs:shape-based objectives preserve density but discard token identity,lexical alignment restores identity but uses surface form as a proxyfor meaning, and text-space matching compresses the teacher signalinto chunk-level events. We introduce SOLA (Semantic Optimal LocalAlignment), which reconstructs the missing coordinate systemexplicitly: it partitions inputs into decoded-text blocks viaMinimal Complete Correspondence, estimates a cross-vocabularycorrespondence cost from calibration text, and runs entropicoptimal transport on a bidirectional local support retrieved aroundeach teacher prediction. Under matched training and decodingprotocols, SOLA outperforms direct cross-tokenizer baselines onDolly instruction following, an UltraChat general-instructionbenchmark, and code and math domain transfer; a coverage--scorecorrelation and component ablations attribute the gain to theconstructed support.

Diffusion language models (Diffusion-LMs) generate text through iterative denoising, exposing a temporal structure that is largely absent from autoregressive decoding. In this paper, we show that this temporal structure provides a useful control axis for generation diversity: early denoising steps mainly determine high-level semantic trajectories, while later steps refine lexical realization. Motivated by this observation, we propose Time-Annealed Perturbation Sampling (TAPS), a training-free inference strategy that samples nearby conditioning trajectories through time-aware, manifold-constrained perturbations. TAPS encourages semantic branching during early denoising and anneals the perturbation away before refinement, improving exploration while preserving prompt alignment, generation quality, and reasoning ability. Experiments on multiple Diffusion-LM backbones, including non-autoregressive and semi-autoregressive models, show that TAPS consistently improves semantic and lexical diversity across open-ended and instruction-following generation tasks, while preserving reasoning ability on verifiable reasoning benchmarks with negligible overhead.

Semi-implicit variational inference (SIVI) expands the representational capacity of variational families, but optimizing the Evidence Lower Bound (ELBO) remains challenging because the marginal score of the semi-implicit distribution is generally intractable. Unbiased Implicit Variational Inference (UIVI) and related methods address this difficulty through reparameterized ELBO gradients, but existing approaches estimate the required score indirectly through reverse-conditional sampling or approximation, which can be computationally costly and unstable. We propose Denoising Implicit Variational Inference (DIVI), which learns the marginal score directly via denoising score matching. The learned score is used as a plug-in estimator in the pathwise ELBO gradient, replacing inner reverse-conditional sampling with a score-network evaluation. We analyze DIVI as inexact stochastic gradient ascent and show, under stated assumptions, that the averaged stationarity measure is controlled by the usual optimization term and the average score-matching error. Empirically, we evaluate DIVI on both synthetic distributions and a variety of real-data Bayesian inference tasks. The results show that DIVI improves over the current UIVI baselines while reducing the cost of ELBO-gradient estimation.

Muon has recently demonstrated strong empirical performance in large language model training, but the theoretical role of momentum in Muon remains unclear. Existing analyses of Muon either remove momentum to study spectral updates in isolation, or retain momentum without explaining why it improves empirical performance. Our work bridges this gap by showing momentum in Muon acts as a spectral filter. Under a structured signal-plus-perturbation gradient model, we prove that momentum suppresses perturbations while preserving the dominant signal, thereby enlarging the spectral gap between them. This enlarged gap stabilizes the singular subspaces of the matrix passed to Muon's orthogonalization step, making the resulting update more reliable. We further show that applying momentum before orthogonalization achieves provably stronger alignment with the signal component of the gradient than either reversing this order or simply removing momentum. Experiments across diverse tasks, including LLM training, support our theoretical analysis. More broadly, our theory offers a starting point for understanding the benefits of momentum in other matrix-based optimizers.