NeurIPS 2026 论文列表

We argue that sport represents the next grand challenge for Artificial Intelligence, a domain rich enough to expose the limits of current approaches and structured enough to drive rigorous scientific progress in understanding and modelling human physical skill. Despite rapid advances in language, vision, and robotic manipulation, the physical intelligence required to learn and adapt complex motor skills remains poorly understood and largely unaddressed. We identify two intertwined gaps: the absence of models for human physical skill, and the absence of the scientific agenda needed to build them. We propose concrete directions for how the community can begin to close both.

Online platforms connect users with relevant products and services using ads. A key challenge is that a user's search query often leaves their true intent ambiguous. Typically, platforms passively predict relevance based on available signals and in some cases offer query refinements. The shift from traditional search to conversational AI provides a new approach. When a user's query is ambiguous, a Large Language Model (LLM) can proactively offer several clarifying follow-up prompts. In this paper we consider the following: what if some of these follow-up prompts can be ``sponsored,'' i.e., selected for their advertising potential. How should these ``suggestion slots'' be allocated? And, how does this new mechanism interact with the traditional ad auction that might follow? This paper introduces a formal model for designing and analyzing these interactive platforms. We use this model to investigate a critical engineering choice: whether it is better to jointly optimize the user interaction and the final ad auction, or to decouple them into separate mechanisms for the suggestion slots and another for the subsequent ad slot. We show that the VCG mechanism can be adopted to jointly optimize the sponsored suggestion and the ads that follow; while this mechanism is more complex, it achieves outcomes that are efficient and truthful. On the other hand, we prove that the simple-to-implement modular approach suffers from strategic inefficiency: its Price of Anarchy is unbounded, for various natural choices for the two mechanisms. While we show that this inefficiency can be mitigated through revenue redistribution, we argue that the resulting mechanism sacrifices the practical simplicity that motivated the modular design in the first place.

Contemporary systems serving large language models (LLMs) have adopted prefill-decode disaggregation to better load-balance between the compute-bound prefill phase and the memory-bound decode phase. Under this design, prefill workers generate a KV cache that must be transferred to decode workers before token generation can begin. With these workers residing on different physical systems, this transfer becomes a significant bottleneck to serving LLMs at scale. This bottleneck gets exacerbated for long-input and agentic workloads. Existing lossless codecs are not suited to this setting as they primarily target offline weight compression, run on the CPU, or use variable-length coding whose decompression is fast but compression is too slow to keep up with KV production during prefill. We introduce SplitZip, a GPU-friendly lossless compressor for KV-cache transfer that preserves KV tensors bitwise and integrates into existing serving frameworks without changes to model execution. SplitZip exploits redundancy in floating-point exponents of KV activations, encoding the most frequent exponent values with fixed-length codes and routing rare exponents through a sparse escape stream of (position, value). An offline calibrated top-16 exponent codebook eliminates online-histogramming, while the regular dense path and sparse escape correction make both encoding and decoding efficient on GPUs. On real BF16 activation tensors, SplitZip achieves 613.3 GB/s compression throughput and 2181.8 GB/s decompression throughput, substantially outperforming prior lossless compressors on the latency-critical codec path. End-to-end transfer experiments show up to 1.32× speedup for BF16 KV-cache transfer, 1.30× speedup for TTFT, and 1.23× increase on Request Throughput. The same approach extends to FP8 KV caches, providing up to 1.14× compression over native E5M2.

Latent 3D representations have significantly expanded the capabilities of modern shape modeling, enabling compact encoding of 3D scenes and supporting powerful 3D generative models. Despite this progress, current representations struggle to capture the fine details of complex objects, fundamentally limited by the capacity of their latents. However, scaling latent capacity at training time is computationally expensive and often infeasible under memory limits, and naively increasing the number of latents at inference fails to make effective use of the added capacity. In this paper, we address both challenges with split-and-scale, a method that effectively expands latent capacity at inference while keeping training cost tractable. Our key observation is that by representing 3D scenes as continuous functions of 3D coordinates, a single pretrained tokenizer can be applied at inference to arbitrarily small sub-regions of a scene, allocating the same latent capacity to a smaller spatial extent and thus capturing far higher detail. We validate this insight by conducting extensive ablations to study the trade-offs between compute, memory, latent capacity, and reconstruction quality, demonstrating our inference-time scaling method achieves quality competitive with much larger models that exceed single-GPU memory limits. We further demonstrate that split-and-scale supports high-quality generative modeling, training an autoregressive 3D generator that performs competitively with state-of-the-art baselines.

We introduce Split-RL, a reinforcement learning (RL) algorithm based on decision trees. It uses guidance labels to explicitly partition the state-space and isolate localized conflicting signals. RL policies are often trained by mixing contradictory feedback that is localized in space and time. For example, a robot may prioritize speed in open areas versus precision in tight gaps. These regions are often easily detectable from sensor data or a human operator. Standard neural networks (NNs) lack the structural mechanism to isolate these signals. While Gradient Boosting Trees (GBT) provides the inductive bias to explicitly partition the state-space, standard tree-fitting procedures fit only aggregated gradients, merging contradictory updates before they reach the leaves. Split-RL leverages this bias to integrate guidance labels into tree construction, routing these updates into disjoint regions of the state-space to prevent signal interference during training. Such labels can arise from simple heuristics, sensor-derived events, or existing rule-based systems, allowing Split-RL to incorporate rule-derived structure while retaining a learned policy. We theoretically show how early gradient aggregation loses objective-specific information and characterize when the Split-RL score isolates conflicting updates. Finally, we evaluate Split-RL on constrained tasks and offline imitation learning from mixed-quality datasets. Across constrained domains with spatial, rare-event, and temporal conflicts, Split-RL consistently outperforms existing methods by achieving low-cost, feasible solutions while maintaining competitive rewards. In offline settings, Split-RL localizes the tradeoff between imitation and policy improvement, outperforming other methods and achieving near-expert performance across varying dataset sizes.

This work investigates multi-objective imitation learning: the problem of recovering policies that lie on the Pareto front given demonstrations from multiple Pareto-optimal experts in a Multi-Objective Markov Decision Process (MOMDP). Standard imitation approaches are ill-equipped for this regime, as naively aggregating conflicting expert trajectories can result in dominated policies. To address this, we introduce Multi-Output Augmented Behavioral Cloning (MA-BC), an algorithm that systematically partitions divergent expert data while pooling state-action pairs where no behavior conflict is observed. Theoretically, we prove that MA-BC converges to Pareto-optimal policies at a faster statistical rate than any learner that considers each expert dataset independently. Furthermore, we establish a novel lower bound for multi-objective imitation learning, demonstrating that MA-BC is minimax optimal. Finally, we empirically validate our algorithm across diverse discrete environments and, guided by our theoretical insights, extend and evaluate MA-BC on a continuous Linear Quadratic Regulator (LQR) control task.

Primitive splatting has become a powerful representation for efficient differentiable rendering, but existing density-control strategies remain largely heuristic and often suffer from uncontrolled primitive growth. In this work, we present \textbf{Moment-Preserving Density Control (MPDC)}, a general theoretical framework for densification in primitive splatting. Unlike conventional density-control strategies that \emph{select first and split later}, MPDC follows a \emph{split-then-select} paradigm. Our key insight is that a principled split should first preserve the current rendering, rather than immediately perturb the image. By matching local moments, MPDC decomposes a primitive into multiple offspring while keeping the rendered output, and hence the loss, unchanged up to higher-order error. Although such a split does not directly reduce the loss, it changes the parameter space: a saddle point in the original parameterization may no longer remain a saddle point after splitting. This provides a distinct saddle-escaping mechanism from prior approaches that move primitives along negative-curvature directions. Building on this view, we derive closed-form splitting rules for different primitive parameterizations and then select only primitives whose moment-preserving splits reduce an upper bound of the loss through a splitting-matrix criterion. Experiments on three diverse primitive splatting methods show that MPDC substantially reduces primitive counts without sacrificing rendering quality, while improving memory efficiency and rendering speed. Code will be released upon publication.

Flow matching is an emerging, scalable generative framework for characterizing continuous normalizing flows with wide-range applications. However, state-of-the-art methods are not well-suited for modeling dynamical systems, as they construct conditional paths that are restricted to linear interpolants, a suboptimal supervision signal, which may not capture the system's underlying state evolution. Moreover, constructing unified paths to satisfy multi-marginal constraints across observations is challenging, since naïve higher-order polynomials tend to be unstable and oscillatory. To address these limitations, we introduce SplineFlow, a theoretically grounded flow matching algorithm that jointly models conditional paths across observations via B-spline interpolation. Specifically, SplineFlow exploits the smoothness and stability of B-spline bases to learn the complex underlying dynamics in a structured manner while ensuring the multi-marginal requirements are met. Comprehensive experiments across deterministic and stochastic dynamical systems under various configurations, as well as cellular trajectory inference tasks, demonstrate that SplineFlow outperforms existing baselines, especially when the underlying dynamics are of higher degree or in irregular sampling regimes.

Novel view synthesis methods such as 3D Gaussian Splatting degrade under sparse-view settings, suffering from an inability to extrapolate beyond observed regions. To enable high fidelity reconstruction and rendering from sparse views, inpainting of sparsely observed areas and completion of occluded regions is required. Unlike existing approaches that perform these tasks using 2D inpainting diffusion models or geometric-only 3D completion models, we propose a fully 3D scene completion framework, called InvisiSplat, that performs geometry and appearance completion directly in 3D. Our method consists of a Gaussian Splat VAE which learns a sparse point cloud latent space that predicts Gaussian Splat parameters from the latents, as well as a two-step flow model that learns to generate samples conditioned on the point cloud latents, different from other approaches that use tokens without 3D coordinates. Our flow model utilizes alternating local 3D attention and global attention, which balances the needs for precise local geometry and large-scale spatial context. Across several datasets, we demonstrate that our method produces 33% - 82% higher fidelity 3D geometry over prior work while attaining competitive performance on appearance metrics when compared to existing approaches.

E(3)-equivariant networks are promising for 3D atomistic system modeling, yet their scalability is limited by the $O(L^6)$ complexity of the Clebsch-Gordan Tensor Product (CGTP). The recently proposed Gaunt Tensor Product (GTP) reduces the complexity but is unable to capture the antisymmetric paths, resulting in incomplete expressivity. In this work, we present SpinGT, an approach to overcome the GTP incompleteness by generalizing from scalar functions to Spin-Weighted Spherical Harmonics (SWSH). By relying on the algebraic properties of SWSH, SpinGTP recovers the missing antisymmetric interactions while maintaining the asymptotic efficiency of GTP. It also allows for a more expressive equivariant basis that naturally accounts for the parity-odd components of tensor products. We evaluate SpinGTP across diverse benchmarks, including Tetris, 3BPA, SPICE-MACE-OFF, and OC20. Our results show that SpinGTP achieves accuracies comparable to full CGTP. Notably, by explicitly capturing antisymmetric paths, SpinGTP exhibits superior performance in tasks involving chiral materials and non-centrosymmetric geometries. This work provides a scalable, complete, and mathematically rigorous path toward high-order equivariance in large-scale 3D atomistic system simulations.

Parameter initialization shapes training dynamics, convergence, and performance in neural networks. In spiking neural networks (SNNs), analytical initialization is complicated by three additional mechanisms—binary spike outputs, temporal recurrence (leak), and reset-induced drops in membrane potential—which together suppress activity propagation: (1) over time, where recurrence and reset reduce individual neurons' firing rate, and (2) across depth, where deficits in upstream activity compromise downstream layers, known as spike-rate collapse. Prior initialization methods address only subsets of these challenges. We derive closed-form weight and bias distributions for initialization that jointly account for temporal recurrence, refractory reset, and signal propagation across depth. The method is data-agnostic: it requires only the architecture and neuron hyperparameters. Our derivation centers around a bias correction that yields stationary firing rates and membrane variance, with a principled default spike probability of $p = 0.5$ that maximizes per-neuron Bernoulli entropy—counteracting dead neurons ($p \approx 0$) and saturated neurons ($p \approx 1$) at initialization. In controlled simulations across 30 layers, it maintains target firing rates and membrane variance at the individual-neuron level, unlike alternatives tested. Across UEA multivariate time-series classification, neuromorphic classification, and continuous-control reinforcement learning, our SNNs rank first in every paradigm without per-paradigm tuning.

Most time-series anomaly detectors ask whether an observation can be predicted or reconstructed. We ask a different question: can a detector’s own spiking dynamics become anomaly evidence? We study this question for periodic and quasi-periodic time series and propose SPIRE, a phase-conditioned spiking anomaly detector. SPIRE uses period-aware current formation to expose phase-aligned cross-period residuals to leaky integrate-and-fire neurons. We refer to this conversion as eventification: after residual injection, recurrence violations induce abnormal bursts, silences, or phase-shifted spike trains. SPIRE then constructs phase-conditioned normal templates of spike states and scores deviations in residual energy, firing-rate patterns, and burst/silence statistics, instead of relying solely on output-space prediction or reconstruction errors. This separates the operational protocol, including causal current-step detection, one-step prediction, and non-causal reconstruction, from the source of anomaly evidence, namely output errors, spike dynamics, or both. On TSB-AD-U and TSB-AD-M, SPIRE establishes new best VUS-PR among neural time-series anomaly detectors. Spike-native scores remain competitive without reconstruction error, hybrid scoring consistently improves error-only scoring, and replacing LIF neurons with continuous activations in matched ANN counterparts reduces detection performance under the same period-aware architecture. Periodicity-stratified analyses and spike-state visualizations further show that the gains are strongest when phase recurrence is reliable, supporting the proposed spike-as-detector mechanism. These results suggest that phase-conditioned spiking dynamics can serve as a first-class anomaly detection signal for periodic time series, rather than merely an efficient computational substrate.

Spiking Neural Networks (SNNs) offer a distinctive paradigm for temporal modeling through their intrinsic membrane potential dynamics. However, existing SNN-based forecasting methods focus exclusively on temporal processing, lacking mechanisms to capture spatial dependencies among variables. To bridge this gap, we propose SpikeSTAG, a neuromorphic spatiotemporal architecture that integrates graph-based spatial reasoning into spike-driven temporal computation. Central to our approach is the Dendritic Graph Module, which reinterprets spectral graph convolutions as biological dendritic integration -- coupling multi-scale spatial aggregation with the temporal dynamics of spiking neurons within a single computational unit. To adaptively fuse the resulting spatial and temporal representations, we further introduce a Dual-Stream Integration Module that employs competitive gating and coincidence-based amplification, selectively enhancing consistent spatiotemporal patterns while suppressing conflicting noise. Extensive experiments demonstrate that SpikeSTAG establishes a new state-of-the-art among SNN-based models and surpasses representative ANN baselines, while reducing theoretical energy consumption by approximately 33.3\% compared to Transformer architectures.

Two-photon calcium imaging is a standard tool for recording large neural populations in vivo, yet inferring spikes accurately across the growing diversity of calcium indicators remains an open problem. Existing supervised methods achieve reasonable in-domain accuracy but generalize poorly to unseen indicators, because different indicators induce distinct fluorescence kinetics and signal statistics while existing architectures remain relatively simple generic temporal regressors without dynamics-matched inductive bias. We propose SpikeSSL, a universal spike inference framework whose temporal backbone is a bank of bidirectional IIR state-space layers broadly motivated by calcium dynamics. A multi-modal conditioning encoder maps indicator identity, sampling rate, and trace-level signal statistics into a global conditioning vector that modulates the backbone via Adaptive Layer Normalization, while a heteroscedastic variance head provides calibrated per-frame uncertainty. On a benchmark with five fixed evaluation splits built from 33 public ground-truth datasets, SpikeSSL achieves state-of-the-art performance in both in-domain and zero-shot leave-one-indicator-out settings. We also develop a biophysical simulation pipeline capable of generating paired fluorescence-spike traces with systematically varied kinetic parameters, spike statistics, response nonlinearities, baseline drift, and noise. Using this pipeline, we synthesize approximately 11{,}000 simulated traces. Augmenting training with these data effectively closes the cross-indicator domain gap and improves zero-shot generalization.

Neural avalanches and turbulence-like brain dynamics are usually measured after neural activity has been coarse-grained into continuous fields, leaving open which spike-level mechanisms can generate these macroscopic observables. We build a spatial leaky integrate-and-fire spiking neural network and explicitly transform spikes into activity-density and Hilbert phase fields. A delayed, distance-dependent, passive-dendrite regime reproducibly generates turbulence-like field structure, including high-amplitude phase-defect tracks, structure-function scaling, and power-law-favored continuous-field avalanche tails. Controls show that firing rate, vortex count, and avalanche tail fits are individually insufficient: destroying delayed propagation, dendritic filtering, or spike timing suppresses key field signatures, while random-space nulls can retain many mathematical phase defects but lose spatial scaling and synaptic-delay transfer. Biologically motivated gates further shape the regime: PV-like perisomatic inhibition clamps phase dynamics, SST-like dendritic inhibition and projection-specific inhibitory facilitation preserve long-lived tracks, and a rate-constrained projection-STP regime maintains similar dynamics at 12.25 Hz across 12 seeds. These results use SNNs as a mechanistic testbed for spike-derived brain turbulence observables and show why phase defects and avalanche-like statistics must be interpreted jointly with spatial scaling and spike-level propagation.

Spiking Neural Networks (SNNs) promise energy-efficient inference, but adapting large pre-trained SNNs to new tasks is expensive because BPTT memory and runtime scale with the number of simulation steps $T$. We observe that weights in pre-trained SNNs are strongly concentrated near zero, and under thresholded dynamics many such synapses are functionally silent. Based on this, we propose \textbf{Spike-SFT}, a two-stage adaptation framework. Stage 1 (\textbf{Selective Parameter Enhancement}, SPE) fine-tunes only a small-magnitude subset via masked updates with low-rank regularization, progressive re-selection, and sparse-gradient storage, reducing memory while maintaining competitive accuracy. Stage 2 (\textbf{PickIt}) fuses multiple SPE-adapted models by alignment and interference-aware delta merging with spike-statistics calibration, yielding a single merged model with zero inference-time overhead. Across several SNN backbones and benchmarks, Spike-SFT offers a favorable accuracy--cost trade-off, improving fine-tuning efficiency (time/memory) while retaining strong accuracy, and enabling zero-overhead weight-space fusion via PickIt.

Spiking Neural Networks (SNNs) offer a promising energy-efficient alternative to Artificial Neural Networks (ANNs) through event-driven, multiplication-free computation. However, when applied to downstream tasks such as Neural Radiance Fields (NeRF), SNNs suffer from significant information loss, resulting in a noticeable performance gap. In this paper, we present \textit{Spik-NeRF v2} to advance SNN-based neural rendering. We propose the $\pm$I-LIF spiking neuron, which extends I-LIF to support signed integer values during training, thereby mitigating information loss. During inference, it is converted to ternary spikes $\{-1, 0, 1\}$, preserving event-driven properties with addition-only operations. Furthermore, we introduce a re-parameterization technique that transforms a trained I-LIF-based Spik-NeRF with $t$ timesteps into an equivalent $\pm$I-LIF-based model with $t/2$ timesteps. This enables faster inference while preserving rendering quality, overcoming the suboptimal performance of directly trained $\pm$I-LIF models with reduced timesteps. Extensive experiments on synthetic and realistic datasets demonstrate that Spik-NeRF v2 surpasses existing SNN-based NeRF methods and achieves rendering quality comparable to ANN-based approaches.

Energy-based models (EBMs) are flexible generative architectures inspired by statistical physics, but their learning and generative properties remain poorly understood. Here, we analyze a solvable EBM in the high-dimensional limit: the spherical Boltzmann machine (SBM). Combining tools from random matrix theory and dynamical mean-field theory, we: solve exact equations describing the training dynamics of the SBM; compute the Bayesian evidence, which acts as a partition function in parameter space and encodes global properties of the trained model; and uncover cascades of phase transitions that occur both during training and as a function of hyperparameters, related to successive alignment and condensation of the top modes of the coupling matrix to the data. We connect these transitions to sampling-time generative phenomena in a teacher-student scenario, including: sampling temperature tuning, double descent as a function of regularization strength, tempered posterior effects, and out-of-equilibrium effects during training that induce biases in the trained model. We provide numerical evidence demonstrating that all these phenomena appear in standard generative architectures, beyond the SBM.

Active view selection for 3D Gaussian Splatting (3DGS) requires information-theoretic grounding, computational efficiency, and strong reconstruction quality, yet existing methods satisfy these only partially. Information-theoretic approaches quantify gain over the full parameter space via costly Fisher computation under a Laplace approximation; faster alternatives sacrifice the grounding they started from. We propose SpheriBED, a Bayesian experimental design framework that defines the information objective over per-Gaussian spherical appearance—the quantity each observation fundamentally measures—rather than the full parameter vector, yielding exact closed-form posteriors without Laplace approximation. Scoring a candidate view requires only a single forward rasterization pass with no backward pass or per-candidate optimization. Extensive experiments across benchmarks demonstrate that SpheriBED consistently improves active reconstruction performance and provides more reliable uncertainty quantification compared to state-of-the-art methods.