NeurIPS 2026 论文列表

Speculative decoding accelerates LLM inference but suffers from performance degradation when target models are fine-tuned for specific domains. A naive solution is to retrain draft models for every target model, which is costly and inefficient. To address this, we introduce a practical parameter- and data-efficient framework named Efficient Draft Adaptation, abbreviated as EDA, for efficiently adapting draft models. EDA introduces three innovations: (1) a decoupled architecture that utilizes shared and private components to model the shared and target-specific output distributions separately, enabling parameter-efficient adaptation by updating only the lightweight private component; (2) a data regeneration strategy that utilizes the fine-tuned target model to regenerate training data, thereby improving the alignment between training and speculative decoding, leading to higher average acceptance length; (3) a sample selection mechanism that prioritizes high-value data for efficient adaptation. Our experiments show that EDA effectively restores speculative performance on fine-tuned models, achieving superior average acceptance lengths with significantly reduced training costs compared to full retraining. Code will be released upon acceptance.

Reinforcement learning (RL) has become a representative post-training paradigm for large language models (LLMs), enabling strong reasoning and agentic capabilities. However, its rollout generation remains a dominant training bottleneck because it relies on sequential autoregressive (AR) decoding, where a small number of long-tailed responses often determine completion time. Speculative decoding (SD) can reduce inference latency while preserving model quality by rapidly drafting tokens and accepting them through parallel verification. Applying SD to RL rollouts, however, introduces challenges absent from standard LLM inference: (i) algorithmically, the continuously evolving target model makes static drafters stale; (ii) system-wise, rollout decoding moves across regimes, from large active batches where SD can be compute-bound and ineffective to shrinking-batch tails where SD becomes beneficial. Existing RL-SD approaches address aspects of this problem, but either yield low effective accepted lengths that limit speedup or rely on auxiliary drafters requiring pretraining and online adaptation, increasing system complexity. We present EfficientRollout, an SD framework designed to accelerate RL rollouts while addressing these challenges. EfficientRollout induces a quantized drafter directly from the target model, keeping it coupled to the evolving policy without separate drafter training before or during RL. It then uses a dynamic SD toggle policy that enables SD only in beneficial regimes identified by system-aware roofline modeling. It further adapts drafting budgets using acceptance-behavior signals observed during training, better realizing the potential accepted length. Under realistic RL workload, EfficientRollout reduces rollout and end-to-end latency by up to 19.6% and 12.7%, respectively, over a standard accelerated AR rollout baseline, while preserving final model quality.

Training Neural ODEs requires backpropagating through an ODE solve. The state-of-the-art backpropagation method is recursive checkpointing that balances recomputation with memory cost. Here, we introduce a class of algebraically reversible ODE solvers that significantly improve upon both the time and memory cost of recursive checkpointing. The reversible solvers presented calculate exact gradients, are high-order and numerically stable -- strictly improving on previous reversible architectures. On scientific modeling and time series classification experiments, reversible solvers reduce the training time by more than $2\times$ while using at least $10\times$ less memory on average than recursive checkpointing.

Reliable AI evaluation is a prerequisite for measuring progress and for deployment in safety-critical settings. Unfortunately, even gathering frontier system outputs on a full suite of relevant benchmarks can be expensive, let alone adding expert review or running evaluation inside of an optimization loop. Existing approaches to sample-efficient evaluation address this concern only partially: they typically assume abundant calibration data, pretrained error-relevant embeddings, or a fixed benchmark. Meanwhile, optimization loops require repeated evaluation and the ability to surface a long tail of errors; in fact, in real world settings, the long tail of errors often drives human-in-the-loop iterative system improvement. Working in the regime in which the only available information is system inputs and one or more cheap surrogate measures of system error, we derive an optimal importance sampler for error estimation and analyze its theoretical properties. Going further, we show how the same sampler can naturally discover and rank error patterns. On standard benchmarks for frontier model question answering (MMLU-Pro) and agentic coding (TerminalBench 2.0) we show our method consistently outperforms standard Monte Carlo on estimating aggregate error, recovering failure modes and calculating their prevalence, and detecting poison agent/environment injections.

Extending 3D Gaussian Splatting (3DGS) to 4D physical simulation remains challenging. Based on the Material Point Method (MPM), existing methods either rely on manual parameter tuning or distill dynamics from video diffusion models, limiting the generalization and optimization efficiency. Recent attempts using LLMs/VLMs suffer from a text/image-to-3D perceptual gap, yielding unstable physics behavior. In addition, they often ignore the surface structure of 3DGS, leading to implausible motion. We propose FastPhysGS, a fast and robust framework for physics-based dynamic 3DGS simulation: (1) Instance-aware Particle Filling (IPF) with Monte Carlo Importance Sampling (MCIS) to efficiently populate interior particles while preserving geometric fidelity; (2) Bidirectional Graph Decoupling Optimization (BGDO), an adaptive strategy that rapidly optimizes material parameters predicted from a VLM. Experiments show FastPhysGS achieves high-fidelity physical simulation in 1 minute using only 7 GB runtime memory, outperforming prior works with broad potential applications.

We study the classical problem of linear regression under heteroskedastic noise, where observations arise from multiple sources with unknown and potentially unequal variances. Specifically, we consider a setting with $n$ sources, each providing a linear measurement of an unknown $d$-dimensional parameter vector $\beta^*$, where each source is associated with an unknown noise variance. We focus on the classic "subset-of-signals'' model, where one assumes that $m$ of the sources have a relatively low noise, formally, with variance of at most 1. Our goal is to accurately estimate $\beta^\*$ despite the presence of high-variance sources. We show that if $m$ is sufficiently large, it is possible to recover $\beta^*$ with sub-constant error. Specifically, we prove a recovery error bound of $\tilde{O} \left(\frac{\sqrt{nd}}{m}\right)$, significantly improving upon previously known results for this setting.

Log-Gaussian Cox Processes (LGCP) are essential for modeling spatial point patterns but suffer from high computational costs and intractable likelihoods. We propose VoGCAM, an efficient Variational Voronoi Gaussian Coordinate Ascent Maximization framework for fitting LGCPs. Our approach first approximates the intractable integral in the LGCP likelihood using a flexible Voronoi tessellation, which incorporates observed points as integration nodes. By applying variational Gaussian approximation, we derive an Evidence Lower Bound (ELBO) that admits an explicit and closed-form expression. To optimize this objective, we develop a novel coordinate ascent algorithm that updates parameter blocks via Newton and fixed-point methods. We further enhance scalability by adopting a Nearest Neighbor Gaussian Process (NNGP) prior and utilizing the Woodbury formula to reduce matrix inversion costs. Theoretically, we prove the existence and uniqueness of the optimal solution and establish the convergence of our algorithm. Numerical experiments on synthetic and real-world data demonstrate that VoGCAM offers superior computational efficiency and inferential accuracy over state-of-the-art methods like INLA and VIFRK.

Optimal Transport (OT) plans provide correspondences between distributions supporting alignment tasks in various domains. Sliced transport plans have been recently proposed as a computationally efficient alternative to OT plans. These methods optimize a one-dimensional projection (slice) to obtain a conditional transport plan that minimizes the transport cost in the ambient space. Despite their efficiency, it remains unclear whether learned slicers transfer to new distribution pairs under shift, an issue central to evolving data and repeated OT computations over related distributions. We study the min-Sliced Transport Plan (min-STP) framework and examine slicer transferability: can a slicer learned on one distribution pair produce effective transport plans for unseen pairs? Theoretically, we show that optimized slicers remain close under slight perturbations of the data distributions, enabling efficient transfer across related tasks. To further improve scalability, we introduce a minibatch formulation of min-STP and provide statistical guarantees on its accuracy. Empirically, we demonstrate that the transferable min-STP achieves strong one-shot matching performance and facilitates amortized training for point cloud and image analysis. Our code is available at https://anonymous.4open.science/r/Min-STP-CF74.

Spiking neural networks (SNNs) are a promising paradigm for efficient neuromorphic computing, yet their training remains challenging due to the non-differentiability nature of spike firing. Backpropagation through time (BPTT) with surrogate gradients (SG) has become a mainstream approach due to its superior performance. However, this method incurs high computational and memory demands during training, while its update rule depends on specific neuronal dynamics. Furthermore, when targeting neuromorphic hardware implementation, the temporal error-propagation process and the full membrane-potential access required by SG are difficult to realize; these can introduce additional readout overhead, measurement noise, or perturbations to the system dynamics. To address these issues, we propose the input-driven derivative-free training (IDDFT) method. Rather than relying on membrane-potential-based surrogate derivatives, IDDFT constructs derivative-free error signals by applying a relaxed nonlinearity to the inputs, thereby avoiding the temporal error-propagation process and reducing the dependence of the update rule on specific neuronal dynamics. By eliminating access to internal membrane-potential states, our method reduces computational and memory costs, enhances compatibility with neuromorphic hardware, and enables training of black-box SNN models. We validate the IDDFT method through theoretical analysis and systematic experiments, demonstrating its effectiveness as an input-driven, derivative-free mechanism for constructing update signals. When integrated with a biologically inspired training strategy, IDDFT maintains comparable performance while substantially enhancing robustness to the choice of relaxed nonlinearities. Based on the resulting bio-inspired combined framework, we conduct evaluations on CIFAR-10, CIFAR-100, CIFAR10-DVS, and Tiny-ImageNet. Experimental results demonstrate that our method achieves performance comparable to BPTT and state-of-the-art methods, while exhibiting remarkable robustness under adversarial attacks.

Reinforcement-learning policies for robot locomotion can fail at deployment when operating conditions shift (e.g., rough or slippery terrain, payload changes, sensing degradation), and retraining or manual recalibration is often infeasible under on-device latency and memory constraints. We study test-time adaptation (TTA) for robotic control: adapting a pretrained policy online and self-supervisedly during execution, without access to rewards. Our starting point is a lightweight baseline that updates only the actor using a frozen pretrained critic as a deployment-time performance surrogate. Building on this, we introduce TEMPO, a test-time entropy-regularized, memory-guided policy optimization method that stabilizes critic-driven updates under severe shift. TEMPO combines (i) an entropy-promoting regularizer on the critic’s predictive distribution to mitigate overconfident extrapolation, and (ii) a score-based memory, inspired by prioritized replay, that prioritizes low-value (“hard”) observations and applies importance sampling to focus limited computation on the most informative deployment conditions. Across Go1, Go2, and G1 in MuJoCo Playground under four representative shifts and multiple architectures, TEMPO yields consistent gains, reaching up to 80\% improvement in a single-device setting. We further validate on a physical Unitree Go2 with an added calf payload, where fully on-device adaptation improves performance over the non-adapted baseline across real-world episodes.

LLM-based workflows compose specialized agents to execute complex tasks, and these agents usually share substantial context, allowing KV-Cache reuse to save computation. Existing approaches either manage KV-Cache at agent level and fail to exploit the reuse opportunities within workflows, or manage cache at the workflow level but assume that each workflow calls a static sequence of agents. However, practical workflows are typically dynamic, where the sequence of invoked agents and thus induced cache reuse opportunities depend on the context of each task. To serve such dynamic workflows efficiently, we build a system dubbed PBKV (\textbf{P}rediction-\textbf{B}ased \textbf{KV}-Cache Management). For each workflow, PBKV predicts the agent invocations in several future steps by fusing the guidance from historical workflows and context of the target workflow. Based on the predictions, PBKV estimates the reuse potential of cache entries and keeps the high-potential entries in GPU memory. To be robust to prediction errors, PBKV utilizes the predictions conservatively during both cache eviction and prefetching. Experiments on three workflow benchmarks show that PBKV achieves up to $1.85\times$ speedup over LRU on dynamic workflows, and up to $1.26\times$ speedup over the SOTA baseline KVFlow on the static workflow.

Scaling long-context capabilities is crucial for Large Language Models (LLMs). However, real-world data contain a large number of sequences with heterogeneous lengths. Existing training libraries for LLMs rely on static parallelism strategies, which suffer from severe load imbalance, redundant communication, and suboptimal hardware utilization under data heterogeneity. In this work, we propose Flexible Context Parallelism (FCP), an efficient parallelism strategy that adaptively reconfigures communication groups and context parallelism degrees during LLM training. We generalize more flexible non-power-of-two parallelism degrees and develop a polynomial-time algorithm to generate near-optimal parallelism strategies with only millisecond-level overhead per training batch. FCP is able to maintain high hardware efficiency even under extreme data heterogeneity. Experimental results demonstrate that FCP significantly outperforms Megatron-LM and DeepSpeed in both LLM and MLLM training, achieving up to 1.47 $\times$ speedup in average throughput while maintaining near-linear scaling efficiency across large-scale clusters. For extremely unbalanced batches, FCP even achieves 2.24 $\times$ speedup.

The Segment Anything Model 3 (SAM 3) has achieved significant progress in *Promptable Concept Segmentation (PCS)* by processing short noun phrases to generate segmentation masks with unique instance identifiers. While SAM3 excels at single-concept segmentation, it falls short in complex, real-world environments where multiple concepts must be segmented simultaneously. In particular, SAM3 typically fails to simultaneously process concepts with semantic overlap, leading to semantic misclassifications and redundant mask predictions. Moreover, as the number of concepts increases, the independent inference paradigm introduces prohibitive inference latency. To address these limitations, we propose the **D**ense **C**ompetitive **R**epresentations **SAM** (**DCR-SAM**) framework. By decoupling cross-modal interactions, the proposed method alleviates the inference latency. To resolve semantic misclassifications, DCR-SAM dynamically aligns textual concepts with visual representations and incorporates a dense competition head to enforce explicit inter-class competition. Furthermore, a learnable background token is applied to absorb non-target objects dynamically. These mechanisms effectively suppress overlapping predictions and generate high-fidelity masks. Extensive experimental evaluations across multiple benchmarks demonstrate that the proposed framework: I) achieves a 2.3\% $\sim$ 10.7\% performance improvement over state-of-the-art methods, II) delivers a 33$\times$ inference speedup compared to the native SAM 3, and III) exhibits strong robustness across diverse scenarios. All code will be released.

Fast and accurate retrosynthesis prediction is desired for downstream drug discovery and synthetic planning tasks. Currently, training and sampling state-of-the-art discrete diffusion or flow-based models for retrosynthesis requires significant computational resources. In this work, we propose FlashRetro, an Integral Flow Matching (IFM) framework with Latent Inversion for efficient retrosynthesis prediction. FlashRetro learns finite-interval latent transport rather than local instantaneous velocity, directly matching the transport quantity required for one-step latent inversion and avoiding test-time numerical integration. For inference, FlashRetro uses a principled 1-NFE Latent Inversion rule that maps a noise latent conditioned on the product latent to the reactant latent with a single learned integral-transport update. Experimental results on standard benchmarks (USPTO-50K) show that FlashRetro achieves superior top@1 accuracy, outperforming prior discrete flow-matching methods by 13.5\% and diffusion-based baselines by 14.2\%, while its average inference time is only 5.1 ms per reactant---38$\times$ faster than multi-step diffusion-based models and nearly 22$\times$ faster than recent discrete flow models. These results show that FlashRetro provides an effective path toward highly efficient 1-NFE retrosynthesis prediction with flow-based models.

Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they still suffer from overthinking, generating redundant reasoning steps which incur substantial token consumption. Existing methods, such as suppressing reflective keywords or forcing shorter reasoning lengths, attempt to mitigate this issue but inevitably truncate necessary steps and induce underthinking, thereby compromising performance. To address this dilemma, we investigate the latent representations and observe that efficient reasoning steps naturally cluster into a concentrated region in latent space, while those deviating from this region tend to produce verbose sequences. To leverage this, we keep reasoning focused within this region via a quadratic program which projects deviating hidden states back into the region. Then we propose a novel training-free framework to achieve efficient reasoning that reduces token generation costs without sacrificing performance. Extensive experiments conducted on four models ranging from 1.5B to 14B, and across six benchmarks in math reasoning, coding, and scientific QA, validate the effectiveness of our method, up to a 13.4\% improvement in accuracy while reducing generated tokens by 11.8\% to 52.8\%. Code and models will be publicly available.

Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughput. In this work, we present Token-Superposition Training (TST), a simple drop-in method that significantly improves the data throughput per FLOPs during pre-training without modifying the parallelism, optimizer, tokenizer, data, or model architecture. TST is done in two phases: (i) A highly efficient superposition phase where we combine many contiguous tokens into one bag and train using a multi-hot cross-entropy (MCE) objective, and (ii) a recovery phase where we revert back to standard training. We extensively evaluate TST on the scale of 270M and 600M parameters and validate on 3B and a 10B A1B mixture of experts model, demonstrating that it is highly robust in different settings. Ultimately, TST consistently outperforms baseline loss and downstream evaluations, and under equal-loss settings, TST yields up to a 2.5x reduction in total pre-training time at the 10B A1B scale.

Domain translation requires a delicate balance between realism, input-output alignment, and output diversity. Entropic optimal transport (EOT) provides a principled formulation of this trade-off, but its practical use remains challenging. Directly maximizing entropy of a stochastic transport plan requires evaluating log densities of generator-induced distributions, which scales poorly with dimension. In contrast, diffusion models make density information accessible in high dimensions through noising the corresponding distributions and approximating their score functions. In this work, we introduce the diffusive entropy regularizer that measures diversity after progressively noising the conditional output distribution, making the entropy term compatible with score estimation. The resulting **Diffusive EOT** retains the main theoretical guarantees of EOT: a unique solution, controllable diversity, and convergence to unregularized OT solution in the zero-regularization limit. We then introduce **DM-EOT**, a practical algorithm for approximately solving the Diffusive EOT that combines diffusion-based distribution matching with transport cost and diffusive entropy penalties. DM-EOT supports both fast one-step generation and higher-fidelity diffusion-based multi-step sampling. Both variants achieve comparable or superior performance on unpaired domain translation benchmarks among one-to-many baselines with comparable inference cost and diversity.

Reinforcement learning (RL) post-training aligns diffusion-based generators with human preferences, yet existing RL methods suffer from poor compatibility with off-policy learning and few-step distilled models. These limitations are especially severe in the video generation area, as practical video generation pipelines often rely on few-step distilled generators. Furthermore, due to complex spatial-temporal dynamics and higher dimensions, near-on-policy video rollouts are both expensive to collect and often imperfect. Relying on such rollouts alone can amplify artifacts and is prone to reward hacking. To address these issues, we propose Forward-Consistent Reward Matching (FCRM), an efficient off-policy RL framework for video generation. FCRM converts the forward denoising loss into a positive loss-induced score and formulates the reward alignment as a one-step GFlowNet matching problem. The resulting residual is pointwise in a clean sample space that naturally supports off-policy learning and few-step generators. To avoid biased gradients, we introduce a double-sampling estimator for the squared residual objective. Theoretically, minimizing the proposed matching residual bounds the KL divergence between the learned distribution and the optimal reward-tilted distribution. Experiments on standard video generation benchmarks validate FCRM across online, replay, offline, and few-step settings and outperform SOTA methods.

Cross-domain open-vocabulary learning poses a unique and underexplored challenge, requiring models to generalize across both domain shifts and category shifts. To tackle this, we propose MAP: a parameter-efficient Multi-source domain-Adaptive Prompt tuning framework that leverages multiple labeled source domains to improve learning in novel, unlabeled target domains with unseen categories. MAP consists of two key components: Multi-Source Prompt Learning (MSPL) and Unsupervised Target Prompt Learning (UTPL). MSPL disentangles domain-invariant category semantics from domain-specific visual patterns by jointly learning shared and domain-aware prompts. UTPL enhances generalization in the unlabeled target domain by enforcing prediction consistency under text-guided style augmentations, introducing a novel entropy-minimization objective without relying on pseudo-labels. Together, these components enable effective alignment of visual and textual representations across both domains and categories. In addition, we present a theoretical analysis of the proposed prompts, examining their behavior through the lenses of fidelity and distinction. Extensive experiments on challenging CDOV benchmarks demonstrate that MAP achieves state-of-the-art performance with significantly fewer additional parameters.