NeurIPS 2026 Papers

Multi-view transformers for feed-forward 3D reconstruction must jointly solve two tasks. They need to extract precise per-view features and reason about cross-view geometric correspondences. Existing architectures apply cross-view attention throughout the network, leaving each layer to handle both objectives together. We revisit this design through a layer-wise probing analysis of feed-forward geometry transformers and observe that trained models tend to divide these two roles across layers. Early layers tend to specialize in per-frame feature extraction, while spatial cognition and cross-view reasoning emerge predominantly in later layers. This suggests that separating the two roles across the network can allocate compute more effectively. Building on this observation, we propose U-MVP, a U-shaped multi-view transformer for feed-forward 3D Gaussian Splatting that reflects this structure in the architecture itself. The encoder applies frame-wise attention to preserve per-view detail, the decoder introduces multi-view attention for cross-view geometric reasoning, and skip connections fuse the two streams so that appearance and geometry are recombined at decoding time. To scale to dense view regimes, we replace several global interaction blocks at the bottleneck with a grouping and swapping scheme that preserves cross-view information flow at lower cost. U-MVP performs competitively with feed-forward and optimization-based baselines from 16 to 256 views, generalizes to unseen datasets, and achieves strong results on 3D reconstruction and novel-view synthesis in posed and unposed settings.

We study fixed-confidence best-action identification (BAI) in stochastic minimax trees. This problem is increasingly relevant in modern AI planning, where deep minimax search and Monte Carlo Tree Search (MCTS) with language model long rollouts face a fundamental tradeoff: heuristic evaluations are cheap but biased, while accurate rollouts are reliable but prohibitively expensive. We propose 2FFS, a two-fidelity tree-search algorithm that brings multi-fidelity flat bandit ideas into trees. The algorithm combines minimax-style fast expansion with MCTS-style stochastic sampling, adaptively deciding when to exploit cheap biased evaluations and when to invoke expensive accurate evaluations for local certification. We prove fixed-confidence correctness, establish finite stopping for exact identification, and give a polynomial-depth cost upper bound for general-depth trees. Across numerical stochastic-tree experiments, 2FFS uses substantially fewer samples and computational operations comparing to existing BAI-MCTS baseline.

We introduce Rapid Simulation Based Inference (RSBI), a diffusion-based variational approach to likelihood-free Bayesian inference that achieves high posterior sample efficiency under large and multi-dimensional prior-to-posterior volumes. RSBI builds on recent advances in Schrödinger Bridge (SB) diffusion sampling to handle multi-modal posteriors, with the likelihood supplied either by a neural ratio estimator or kernal surrogate via a differentiable simulator. Furthermore, a key observation is that an appropriate surrogate likelihood gives a proposal distribution covering most of the generally multi-modal posterior mass, replacing the sequential rounds of standard methods with a one-shot proposal step. Subsequent NRE refinement recovers exact inference under the simulator and original model prior. As a variational method, RSBI does not suffer from prior leakage and implicit target drift commonly observed in standard sequential posterior estimation methods. To improve mode coverage we optionally utilize the well-tempered meta-dynamics framework, which also provides a mechanism through which to encourage exploration of the prior volume. We observe strong performance not only on standard SBI benchmarks, but also as prior volume is scaled up to 2500 times the original, achieving a performance degradation of only $\sim$5% on the two moons benchmark under a highly constrained simulation budget. Additionally, we evaluate RSBI's potential for gravitational wave ring-down posterior estimation, highlighting a real-world use-case where our method excels.

End-to-end autonomous driving planning requires trajectories that are multimodal, scene-compliant, and efficient to generate. Deterministic regression is fast but often collapses to a single future, while trajectory-vocabulary methods depend on predefined candidate coverage and iterative generative planners incur multi-step inference cost. We propose TwinFlux, a one-step discrete-continuous trajectory generation framework based on SplitMeanFlow. TwinFlux starts from data-driven trajectory prototypes and refines them through parallel heatmap and offset branches. The heatmap branch provides topology-aware coarse localization on a BEV grid, while the offset branch predicts grid-relative geometric refinement. A differentiable trajectory decoupling-and-reconstruction module connects this representation with physical trajectories. During training, TwinFlux enforces piecewise displacement consistency in reconstructed trajectory space, aligning direct one-step prediction with accumulated sub-interval evolution without Jacobian-vector-product computation or inference overhead. Experiments on NAVSIMv1 and NAVSIMv2 show that TwinFlux outperforms recent end-to-end planning baselines while maintaining real-time inference.

Agentic workloads have emerged as a major workload for LLM inference. They differ significantly from chat-only workloads, requiring long-context processing, the ability to handle multimodal inputs, and structured multi-turn interactions with tool calling capabilities. As a result, their context exhibits structure that can carry different importance along three key axes: temporal recency to the current turn, modality such as text or image tokens, and semantic role such as user queries, tool calls, observations, or reasoning. These axes capture distinct token behaviors and lead to different sensitivities to KV-cache compression. However, existing KV-cache quantization methods are typically homogeneous or exploit only heterogeneity on a single dimension, such as temporal proximity or modality, overlooking the interactions among them. To this end, we introduce TriAxialKV, a novel mixed-precision KV-cache quantization scheme that assigns each token a triaxial tag, calibrates per-tag sensitivity, and allocates INT2/INT4 bitwidths under a fixed memory budget. We implement TriAxialKV as an end-to-end serving system, comprising calibration, mixed-precision quantization and memory management, and custom fused Triton decode kernels. When using Qwen3-VL-32B-Thinking as a computer-use agent operating the OSWorld, TriAxialKV matches the accuracy of SGLang with BF16 KV cache while supporting 4.5$\times$ KV cache size and achieving 30\% higher end-to-end throughput, when running on real GPU systems.

Large language models rely on positional representations for long context modeling, yet are typically trained on short sequences and evaluated at much longer lengths. Bridging this gap requires positional encodings remaining distinguishable at large distances while generalizing beyond the training length. In this paper, we identify a structural limitation of existing rotary-based positional encodings: all positional dimensions are controlled by a single global index, which couples training-time positional variation with long-range extrapolation. To address this, we propose Tree Rotary Positional Encoding (TPE), a structured multi-scale positional encoding designed for training from scratch that represents absolute positions through com positions of different components, avoiding single-index extrapolation. We further devise an Offset-based Positional Training (OPT) strategy to improve learning interactions across TPE components, enabling better generalization to longer con texts. We theoretically analyze that its multi-scale decomposition enables effective combinatorial position coverage. Experimental results show strong gains under extreme length extrapolation: with a 1.2B model trained from scratch on length 512, our TPE achieves a 64× extrapolation to 32K tokens, reducing perplexity from 4532.21 (RoPE) to 149.96, with comparable inference-time efficiency.

Many systems represent graphs as sequences by visiting nodes one at a time, for example, a molecule written as a SMILES string or a program written as a token stream from an AST traversal. The same graph can be traversed in many ways, producing different sequences for the same underlying object. Sequence Transformers treat these as distinct inputs and produce distinct embeddings, even though the graph remains unchanged. Existing graph-native Transformers address this by operating directly on the graph, but many practical pipelines receive serialized inputs and cannot be redesigned. We provide a theoretical characterization in three parts. Tree-positional encoding achieves structural invariance for acyclic graphs under canonical-root serialization but is insufficient for cyclic graphs due to spanning-tree non-uniqueness. Augmenting with cycle-membership encoding derived from the canonical cycle basis introduces a traversal-invariant anchor on cycle vertices. The resulting Tree+Cycle Positional Encoding is a drop-in replacement for sinusoidal PE within graph-aware serialization pipelines (those preserving token-to-atom alignment for structural tokens), requiring no architectural changes to the sequence model. It applies to any domain where labeled graphs are given as sequences with this alignment property. We validate the approach on two testbeds. On synthetic cycle counting and ring membership tasks, it outperforms the GIN baseline by $2\times$ on cycle counting and matches it on ring membership, demonstrating that pre-computed cycle structure encoded as PE matches message-passing GNNs at end-task performance. On molecular property prediction, it achieves $0.977 \pm 0.029$ mean cosine similarity across re-rootings ($n = 24{,}960$), outperforms a parameter-matched graph-native Transformer (Graphormer) on BACE and BBBP, and enables fragment-level interpretability with $+5$ points on alert alignment over a methodologically matched sinusoidal baseline.

High-contrast multiscale PDE problems are common in real-world applications, yet current neural PDE solvers struggle to achieve sufficient accuracy on such tasks. The Generalized Multiscale Finite Element Method (GMsFEM) addresses this by compressing fine-scale heterogeneity into localized basis functions which are used to obtain more accurate solutions than neural PDE solvers. However, constructing these basis functions requires solving many local eigenvalue problems—the major computational bottleneck. We address this issue by proposing **Transolver-GMsFEM**, a new hybrid framework that utilizes the efficiency of neural PDE solver for predicting multiscale basis functions while preserving the solution quality of GMsFEM. Experiments on 2D/3D steady-state and time-dependent high-contrast multiscale PDEs on irregular grids show proposed method achieves over $100\times$ speedup for basis construction. Crucially, our experiments demonstrate that Transolver-GMsFEM significantly outperforms state-of-the-art neural PDE solvers in both accuracy and robustness, especially in out-of-distribution tasks where pure neural PDE solvers dramatically fail.

Analyzing the generalization of graph neural networks (GNNs) on node classification is challenging: message passing induces dependencies that break the i.i.d. assumption underlying standard inductive generalization theory. While distribution-free transductive theory resolves this dependency issue, existing classical bounds are either intractable or correlate poorly with empirical generalization. To fill this gap, we propose a transductive generalization bound based on optimal transport, connecting generalization to intra-class concentration and inter-class separation in the feature space. Empirically, our bound aligns strongly with the generalization gap. Building on this representation-based approach, we analyze how feature geometry evolves under repeated message passing. This explains the non-monotonic relationship between GNN depth and generalization, providing new insights into oversmoothing research. Practically, our bound serves as a geometry-aware regularizer that corrects the harmful behavior of message passing, yielding consistent performance improvements.

Meta pseudo-labeling improves semi-supervised learning by updating a teacher according to whether its pseudo-labels help a student improve on labeled data. Existing one-step meta-gradient methods, however, differentiate through the student update, introducing mixed higher-order derivatives, extra memory cost, and noisy minibatch meta-gradients. We propose Trajectory-Matching Meta Pseudo-Labeling (TMPL), a first-order alternative that extracts labeled-data feedback from recent student optimization trajectories. We show that the one-step meta objective is locally equivalent, up to second-order terms in the student step size, to maximizing alignment between the outer gradient and the pseudo-label-induced student gradient. TMPL approximates this alignment without differentiating through the student update by matching finite differences of the outer objective and the pseudo-label-induced student objective along recent student displacements. Its implementation stores only a FIFO cache of detached scalar objective values, rather than student computation graphs or past student networks. We prove that small trajectory-matching error controls the gradient mismatch within the span of recent displacements, with an explicit residual for unexplored directions. On CIFAR10, CIFAR100, SVHN, and STL10, TMPL improves over MPL in all eight evaluated label regimes, obtains the best result in five settings, and remains competitive with strong SSL baselines. On CIFAR100 with 2500 labels, TMPL reduces peak memory by 39.7\% relative to MPL and 54.0\% relative to a raw differentiable meta-gradient implementation. Ablations identify the directional trajectory-matching term as the main source of improvement, while alignment diagnostics show that TMPL recovers MPL-like gradient alignment after a short warm-up.

Hamiltonian Neural Networks (HNNs) produce stable long-horizon rollouts by integrating a learned Hamiltonian with a symplectic scheme. Standard Monte Carlo (MC) dropout conflicts with this per-trajectory interpretation because resampling the dropout mask inside a leapfrog integrator means successive substeps follow different subnetworks, so a single MC rollout no longer corresponds to any one sampled Hamiltonian. We propose trajectory-consistent dropout, implemented as Fixed-mask MC, where each stochastic rollout selects one mask from a finite bank and reuses it across the full integration path. This restores a coherent per-rollout Hamiltonian sample and makes uncertainty decomposition operational. Crossing the mask axis with an initial-condition ensemble separates model-sample uncertainty from sensitivity to the initial state. On coupled-pendulum rollouts, Fixed-mask MC reduces mean energy drift by 72% relative to Standard MC. Under held-out mass ratios, Fixed-mask MC increases the epistemic share of predictive variance by 16.9 percentage points from in-distribution to out-of-distribution, compared with 4.2 percentage points for Standard MC, indicating a substantially stronger shift of the uncertainty budget toward model uncertainty when the physics moves outside training support. Spring-chain and transverse-field Ising experiments show that the same axis-preserving decomposition transfers to structured pairwise and latent quantum dynamics, although point-prediction and likelihood gains remain system-dependent. These results position Fixed-mask MC as a single-training-run route to trajectory-consistent, physically interpretable uncertainty in structured neural dynamical models.

Although existing candidate trajectory evaluators have substantially improved end-to-end planning accuracy, their underlying mechanism remains suboptimal. Model-based evaluators typically make scoring future-aware by explicitly predicting candidate-conditioned future states over the planning horizon, which we term rollout. However, rollout incurs high inference cost and accumulates prediction errors. We argue that planning does not require reconstructing a full future scene for each candidate, but only future-relevant information for reliable comparison. We therefore propose RFWorld, a Rollout-Free World model for end-to-end trajectory evaluation. RFWorld constructs a shared scene memory and shapes it into a future-readable representation via lightweight training-time temporal readout with semantic supervision, keeping training overhead low. At inference time, candidate trajectories directly query the shared memory via sparse spatial readout for scoring, reducing computation by roughly the planning horizon times the number of candidate trajectories, while avoiding recursive rollout errors. Experiments on NAVSIM show that RFWorld learns a more planning-aligned world representation and achieves state-of-the-art performance.

Choosing where to place entangling gates is a central design choice in quantum machine learning circuits, yet entanglers are still typically chosen from fixed templates or by expensive search procedures requiring training or pairwise kernel evaluations. We propose the \emph{HSD-Lipschitz principle}, a training-free geometric criterion built on a simple intuition: a useful entangler should keep encoded states stable across the dataset while separating different classes. We formalise this through a two-sided bound on local light-cone subsystems. Under a light-cone locality assumption, dataset-level gradient variance is upper-bounded by reduced-state spread; under random initialisation, the expected between-class gradient signal is lower-bounded by class-conditional reduced-state distance. The resulting algorithm, HSD-greedy, adaptively grows an entanglement structure using only single-state reduced moments, estimable via classical shadows, and avoids the $\mathcal{O}(N^2)$ pairwise kernel evaluations of kernel-target alignment proxies. Empirically, both bounds hold without violation across $110$ topologies and $440$ parameter rows, and extend to $180$ additional configurations. HSD-greedy attains the strongest average AUC among training-free entangler selectors on synthetic and real-world benchmarks, at roughly $60\times$ lower selection cost than the strongest baseline in 13-qubit simulation. End-to-end execution on a 20-qubit IBM Eagle subchain substantially outperforms a fixed 19-CNOT Linear chain and matches or exceeds a matched-budget Random baseline while using far fewer two-qubit gates than the Linear chain.

The analysis of electrostatic induction effects on transmission lines in real-world power distribution systems requires inferring induced surface charge density $\sigma$ on overhead-line corridors at deployment scale, where dense $\mathcal{O}(N^3)$ boundary-element solvers for the underlying Poisson boundary integral equation (BIE) are infeasible. We present a recipe for training cheap PDE surrogates from canonical-case closed forms (flat ground, grounded sphere) plus sparse dense-solver fine-tuning where the canonical case breaks like in our case study. The recipe also avoids a structural degeneracy between training operator $A_\theta$ and solution $\sigma$ in self-supervised operator learning that tends to lead to internally consistent but non-physical solutions. The recipe combines a closed-form local-tangent-plane baseline plus a small neural correction; a frozen analytic kernel; an $SE(3)$- and scale-invariant dimensionless feature stack derived from a $2$-term identity $\sigma = -(\nabla\phi\cdot\hat{n})/(2\pi) + H\phi/(4\pi)$, exact on flat ground and the grounded sphere and supervised training against this identity. An $8$-parameter linear head recovers the analytic curvature coefficient $+1/(4\pi)$ from data to within $2\%$; holds to $1\%$ relative RMS in $\sigma$ across $12$ orders of magnitude in source-charge scale, where DeepONet, Set Transformer, and FNO baselines miss the analytic answer by orders of magnitude out-of-distribution; and matches direct-collocation boundary-element ground truth on a synthetic curved patch to $3.8\%$ relative RMS. A regime-of-validity result delineates when the canonical $2$-term identity applies; outside it (terrain curvature radius $\kappa^{-1}$ much greater than source clearance height $|h|$, the corridor regime), we extend the recipe with sparse dense-BEM-target supervision. On several industrial transmission-line corridors with native triangulated meshes, the extended recipe attains $9.2\%$ median relative RMS to dense BEM on held-out corridors, $20\times$ tighter than the analytic 2-term plug-in. Deployment: a $1.7$kB MLP, seconds per corridor on a single CPU core.

Reconstructing high-fidelity and controllable digital twins from multi-modal sensory observations is a fundamental problem in physical AI applications. While existing per-scene optimization methods handle dynamic driving scenes well, they are slow to optimize, have artifacts at novel viewpoints, and require costly manual annotations for decomposing the scene into controllable instances. Self-supervised generalizable reconstruction methods enable faster and more scalable reconstructions by learning from large datasets, but existing approaches do not fully leverage multi-modal inputs (e.g., camera and LiDAR) and lack decomposition capabilities. To address these limitations, we propose STRIDE, a self-supervised, generalizable and decomposable 4D driving scene reconstruction method. By processing multi-modal sensory inputs in a common 3D space with a Point-Transformer, STRIDE efficiently discovers spatio-temporal correspondences necessary for accurate flow prediction. By incorporating latent instance tokens, STRIDE is the first to perform feed-forward reconstruction and learnable decomposition without manual annotations. Experiments on public driving datasets show STRIDE achieves state-of-the-art performance on recovering geometry, appearance, and 3D flow. Moreover, we demonstrate how learned decompositions can enable dynamic instance manipulation and controllable simulation.

Data selection for language model pretraining faces a fundamental tension between quality and diversity. While quality filtering is empirically effective, it often induces diversity collapse: by favoring texts similar to high-quality reference corpora (e.g., educational or QA-style data), it systematically excludes valuable data from underrepresented domains. In contrast, diversified selection preserves domain balance and encourages robust downstream performance, yet existing methods either focus on coverage-oriented objectives that indirectly enhance diversity, or directly optimize for diversity via costly covariance matrix recomputation that limits scalability. To address these issues, we introduce \textbf{Leverage Score Sampling (Lev)}, which iteratively selects samples that maximally expand the determinantal volume of the embedded data via leverage scores, a computationally efficient criterion that eliminates matrix recomputation and enables scalable selection. Empirically, Lev delivers up to $65\times$ speedup and improves dataset diversity, measured by the Vendi score, by $9.2\%$ over the strong diversification baseline \textbf{DiSF}. On CommonCrawl (CC) web data selection, Lev improves accuracy across seven downstream tasks by up to $1.31\%$ over existing baselines. For domains where robust quality criteria are inherently difficult to define (e.g., code), Lev serves as an effective unsupervised curation alternative: on StarCoderData, the selected subset reduces bits-per-byte by $3.08\%$ over DiSF. Notably, we uncover a cross-domain collapse of quality filtering: CC data filtered by DCLM-fastText fail to retain sufficient code-related content, yielding inferior code performance relative to Lev-selected data. These findings advocate for integrating diversity-aware practices into quality filtering for more effective data curation in language model pretraining.

The emergence of Large Language Models (LLMs) has illuminated the potential for a general-purpose user simulator. However, existing benchmarks remain constrained to isolated scenarios, narrow action spaces, or synthetic data, failing to capture the holistic nature of authentic human behavior. To bridge this gap, we introduce OmniBehavior, the first user simulation benchmark constructed entirely from real-world data, integrating long-horizon, cross-scenario, and heterogeneous behavioral patterns into a unified framework. Based on this benchmark, we first provide empirical evidence that previous datasets with isolated scenarios suffer from tunnel vision, whereas real-world decision-making relies on long-term, cross-scenario causal chains. Extensive evaluations of state-of-the-art LLMs reveal that current models struggle to accurately simulate these complex behaviors, with performance plateauing even as context windows expand. Crucially, a systematic comparison between simulated and authentic behaviors uncovers a fundamental structural bias: LLMs tend to converge toward a positive average person, exhibiting hyper-activity, persona homogenization, and a utopian bias. This results in the loss of individual differences and long-tail behaviors, highlighting critical directions for future high-fidelity simulation research.

Knowledge distillation (KD) has become a widely adopted approach for compressing large language models (LLMs). Existing distillation paradigms for LLMs can be broadly categorized into black-box and white-box approaches. Black-box methods typically transfer the chains of thought (CoTs) generated by teacher models to student models, yet they fail to convey the intrinsic knowledge embedded within teacher models. White-box methods aim to alleviate this limitation by leveraging internal representations from teacher models. However, they still face two major challenges. First, it is difficult to identify which knowledge is essential for distillation in student models. Second, it is challenging to transfer this key knowledge from teacher models accurately. To tackle these challenges, we propose KPD, a novel Knowledge Probing-based white-box Distillation framework for LLMs, which is designed to precisely distill the knowledge that the student model lacks and can be incorporated into diverse distillation approaches. Specifically, to identify critical knowledge gaps in student models, we introduce an uncertainty-based probing method that extracts tokens prone to student errors as critical knowledge. To locate the corresponding knowledge in the teacher model, we utilize cumulative gradient calculation to probe where such knowledge is stored and then distill the target layers. Extensive experiments across multiple datasets demonstrate that KPD boosts traditional distillation methods by 0.34%-4.56% in Rouge-L scores. Further ablations show that probing both the student and teacher yields more precise distillation. Our code is available at https://anonymous.4open.science/r/KPD-CA0D.

Optimal pre-training data mixtures are vital for Large Language Models (LLMs), yet post-RL reasoning performance varies significantly across base models. This suggests that identifying "RL-friendly" pre-training data mixtures is a critical but under-explored prerequisite. This motivates us to ask: Which specific data mixtures in pre-training enhance post-RL effectiveness, and how can we evaluate a base model's suitability for RL fine-tuning? Through large-scale experiments with proxy models, we observe that (1) domain-specific data correlation strongly predicts post-RL performance, and (2) the average perplexity of the base model on $k$ RL-generated responses, $\text{avg}(k\text{-ppl})$, is a more stable and correlated predictor than traditional metrics. Building on these insights, we propose BridgeRL, a framework that treats finding optimal mixing ratios as a regression task, using $\text{avg}(k\text{-ppl})$ as the fitting objective. We train 1M/60M-parameter proxy models for regression and scale the findings to 1B/3B-parameter models. Results across online and offline RL algorithms demonstrate that BridgeRL-optimized mixtures consistently yield superior base models for RL fine-tuning.