NeurIPS 2026 Papers

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.

Deep graph learning models deployed in real-world systems often need to cope with non-stationary environments, where the underlying graph distribution drifts continually over time. Prevailing solutions rely on training auxiliary generative modules to synthesize memory graphs for cross-domain adaptation, which incurs substantial computational overhead and scales poorly under prolonged distribution shifts. We argue that a more economical path exists: rather than generating memory, one can crystallize it. To this end, we propose Efficient Memory Crystallization (EMC), a training-free test-time framework that distills each incoming graph domain into a compact, semantically faithful memory through a closed-form solution to a memory-oriented distribution-matching objective, thereby eliminating redundant domain information under continual covariate shifts. To preserve both generalizability and adaptability as the model traverses a long sequence of target domains, EMC further models inter-domain dependencies through state-evolving memories and admits a theoretically grounded, tighter generalization error bound than direct adaptation. Extensive experiments demonstrate the superior performance of EMC over state-of-the-art baselines on graphs under non-stationary distribution shifts, while reducing average runtime by 87.4% and GPU memory consumption by 92.4% relative to the recent competitor, making continual graph adaptation practical at scale.

Learning the natural parameters $z \in \mathbb{R}^n$ of discrete distributions $\mu_z$ from independent samples constrained to a subset $S \subseteq \\{0,1\\}^n$ is a foundational challenge in high-dimensional statistics. Existing methods for efficiently estimating truncated Boolean product distributions, notably the work of [Fotakis et al' COLT'20, Algorithmica '22], require either strong local connectivity assumptions on $S$ -- a property denoted *fatness* -- or stringent anti-concentration assumptions and necessitate the total mass of the truncation set to be a constant with respect to $n$. Moreover, the results in [Fotakis et al' COLT'20, Algorithmica '22] suffer from sample complexities that scale as $\Omega(2^n)$ if the mass of $S$ is exponentially small in $n$. In this work, we circumvent these limitations by analyzing the geometry of $S$ under the measure $\mu_z$. We refine the existing parameter estimation guarantees under the fatness assumption, improving the prior sample complexity to $\mathcal{O}( \log n / \epsilon^2)$ for $\ell_\infty$-recovery, matching the untruncated minimax rate. We further generalize fatness using the notion of influence utilized in the analysis of Boolean functions and provide sufficient conditions for efficient inference. Notably, unlike previous work, our method does not require sampling at arbitrary parameterizations of the model and instead relies on gradient descent. Lastly, we establish a theoretical lower bound demonstrating the sample complexity exhibits an intrinsic exponential dependence on the width of the model and the minimum distance between elements in the set.

Label distribution leakage in federated learning (FL) poses a critical privacy threat, exposing population-level patterns beyond individual data breaches. Building on known correlations between class sample frequencies and classifier weight magnitudes, we demonstrate how adversaries can exploit these relationships to infer label distributions from shared model parameters in FL. To characterize this threat, we propose WLIA (Weight Norm-based Label Distribution Inference Attack), which infers client label distributions by analyzing variations in classifier weight norms across communication rounds. WLIA operates on the classifier layer without requiring auxiliary data, synthetic samples, or meta-classifiers, enabling broader applicability across heterogeneous model architectures. To counter this threat, we introduce RNR (Randomized Weight Norm Regularization), a defense mechanism that disrupts frequency-weight correlations by randomly regularizing weight norms during local training. RNR adds only a penalty term to the cross-entropy loss, making it efficient and easy to integrate. Comprehensive experiments across six datasets demonstrate that WLIA achieves superior inference accuracy compared to existing attacks, while RNR effectively mitigates leakage with minimal impact on utility.

Large language model (LLM) inference serving is undergoing rapid growth and large-scale deployment, motivating us to rethink how the inference process itself can be leveraged to enable efficient task-specific LLM adaptation. In this paper, we propose a forward-only approach for efficient LLM adaptation with forward-only passes in LLM inference serving. We exploit the angle concentration of activations induced by each singular value decomposition (SVD) component to measure its contribution—_dispersed_ or _concentrated_—to the angle concentration of the hidden states. Based on this, our forward-only search then efficiently identifies the weight matrix with the highest dispersion that merits rank reduction. We then selectively remove the higher-order components and retain the lower-order components in SVD. Empirical results across diverse datasets demonstrate the competitive accuracy of our forward-only approach, while theoretical analysis shows lower peak memory and greater speedup than the gradient-based approach, and greater speedup than the exhaustive search approach. The extended experiments further present the robustness and generalization of our forward-only approach to various LLMs with up to 57B parameters. The code is included in the supplementary material.

Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps. Despite their low inference cost, these approaches often suffer from training instability and limited scalability. Sphere Encoder is a recent alternative that produces high-quality images in only a few steps; however, it requires repeated transitions between the pixel space and latent space during inference while jointly optimizing reconstruction and generation within a single architecture. This design leads to computational inefficiency and objective conflict between reconstruction and generation. To address these limitations, we decouple the framework into a fixed pretrained image encoder and a separate latent denoising model trained entirely in a spherical latent space. Our approach eliminates repeated pixel-space operations during training and inference, improving efficiency and allowing reconstruction and generation to specialize independently. On Animal-Faces, Oxford-Flowers and ImageNet-1K datasets, our method significantly outperforms Sphere Encoder in both generation quality and inference speed, while achieving competitive results against strong few-step and multi-step baselines.

Asynchronous reinforcement learning (RL) is an effective paradigm for improving the training efficiency of large language model (LLM) post-training by decoupling rollout generation from policy optimization. However, this decoupling introduces stale off-policy samples generated by earlier behavior policies, leading to distribution shift and unstable policy updates. Recent replay selection methods such as D-ARL mitigate this issue by selecting variance-aware samples, but require expensive current-policy evaluation over replay responses and mainly rely on variance reduction or current-policy matching as the selection criterion. To address these limitations, we propose GA-ARL, an efficient Gradient-Aware Asynchronous Reinforcement Learning framework for LLM post-training. GA-ARL derives an analytic target distribution from the KL-regularized RL objective and introduces an advantage-weighted variant to account for both policy preference and gradient strength. During training, GA-ARL maintains a replay buffer containing samples from recent behavior policies and selects low-discrepancy samples according to the advantage-weighted analytic target, avoiding additional current-policy evaluation during replay scoring. GA-ARL outperforms SOTA asynchronous methods across mathematical, logical, and code reasoning benchmarks, achieving the best average accuracy on both Qwen3-1.7B and Qwen3-4B, with improvements of up to 6.1%. Meanwhile, compared with the SOTA D-ARL, GA-ARL reduces wall-clock training time by 25.3% on average by avoiding additional current-policy evaluation during replay selection.

Structured sparsity extends classical sparse learning by encouraging sparsity at the level of predefined groups rather than individual parameters. This paradigm is widely adopted in modern machine learning and is typically enforced by sparsity-inducing norms. In real pipelines, the optimal group partition is often unknown a priori and does not remain static after initial training. Parameter groupings are often modified as domain knowledge or upstream representation evolves. Standard approaches require retraining the model from scratch under the new target partition, which discards the optimization effort already invested and becomes computationally prohibitive at scale. In this work, we focus on the group-wise $\ell_{p,1}$-norm, a flexible regularization family that encompasses classical group Lasso and other sparse variants. We develop a principled algorithmic framework that leverages the pre-trained optimum to fine-tune model weights toward a new desired group structure without full retraining. Technically, we decompose arbitrary group-wise transitions into a sequence of tractable primitives and derive the closed-form learning dynamics for each sub-action. Extensive experiments on real-world datasets demonstrate that our method achieves significant acceleration while provably recovering the correct optimal solution.

Exhaustively evaluating many large language models (LLMs) on a large suite of benchmarks is expensive. We cast benchmarking as finite-population inference and, under a fixed query budget, seek tight confidence intervals (CIs) for model accuracy with valid frequentist coverage. We propose *Factorized Active Querying* (FAQ), which (a) leverages historical information through a Bayesian factor model; (b) adaptively selects questions using a hybrid variance-reduction/active-learning sampling policy; and (c) maintains validity through *Pro-Active Inference*---a finite-population extension of active inference (Zrnic & Candès, 2024) that enables direct question selection while preserving coverage. With negligible overhead cost, FAQ delivers up to $5\times$ effective sample size gains over strong baselines on two benchmark suites, across varying historical-data missingness levels: this means that it matches the CI width of uniform sampling while using up to $5\times$ fewer queries. We release our source code and our curated datasets to support reproducible evaluation and future research.

Pre-trained diffusion and flow policies have emerged as powerful backbones for robotics, yet adapting them to novel tasks via reinforcement learning (RL) remains computationally unstable, sample inefficient and lacks theoretical guarantees. Prior approaches that fine-tune the latent noise space bypass costly backpropagation through time but struggle with "noise aliasing," where determining the optimal noise input to the pre-trained generative model requires repeatedly refitting separate Q-value networks. This paper resolves these challenges by introducing a novel theoretical framework demonstrating that imposing a linear structure on the environment induces a Latent Noise Linear Markov Decision Process (LNL-MDP). By treating the pre-trained model as a virtual dataset, our LNL-MDP fine tune framework falls under the FineTuneRL theory with near-optimal guarantee. To translate this idealized theory into a practical methodology, we derive the Bridge Equation which eliminates the noise aliasing problem. Leveraging this insight, we propose Latent Representation Bridging for Diffusion (LARBRID), an algorithm that efficiently learns the representation space from the LNL-MDP and optimal noises to steer the pre-trained model to act optimally in given tasks. We demonstrate that LARBRID is exceptionally sample efficient, yielding up to $2\text{-}3\times$ performance increases on challenging control problems across a diverse suite of robotic locomotion and manipulation tasks.

Construction-based neural routing solvers, typically composed of an encoder and a decoder, have emerged as a promising approach for solving vehicle routing problems. While recent studies suggest that shifting parameters from the encoder to the decoder enhances performance, most works restrict the decoder size to 1–3M parameters, leaving the effects of scaling largely unexplored. To address this gap, we conduct a systematic study comparing two distinct strategies: scaling depth versus scaling width. We synthesize these strategies to construct a suite of 12 model configurations, spanning a parameter range from 1M to $\sim$150M, and extensively evaluate their scaling behaviors across three critical dimensions: parameter efficiency, data efficiency, and compute efficiency. Our empirical results reveal that parameter count is insufficient to accurately predict the model performance, highlighting the critical and distinct roles of model depth (layer count) and width (embedding dimension). Crucially, we demonstrate that scaling depth yields superior performance gains to scaling width. Based on these findings, we provide and experimentally validate a set of design principles for the efficient allocation of parameters and compute resources to enhance the model performance.

Dataset distillation seeks to synthesize a highly compact surrogate dataset that achieves performance comparable to the original dataset on downstream tasks. For the scenario where pre-trained self-supervised models serve as priors, traditional $\textit{Linear Gradient Matching}$ optimizes synthetic images by encouraging them to mimic the gradient updates induced by real images on the linear probe or classifier. However, this batch-level formulation requires loading thousands of real images and applying multiple differentiable augmentations to synthetic images at each distillation step, leading to substantial computational and memory overheads. In this paper, we revisit the linear gradient and theoretically derive that it is essentially a $\textit{local}$ relative distribution directed from target class centers toward non-target class centers, which we term ``flow”. This property causes instability and suboptimality, often necessitating expensive multiple augmentations to compensate. To address this, we introduce $\textit{Statistical Flow Matching}$, a stable and efficient supervised learning framework that optimizes synthetic images by aligning $\textit{global}$ statistical flows in the original data. Our approach loads raw statistics only once and performs a single augmentation pass on the synthetic data, achieving performance comparable to or better than the state-of-the-art method with 10× less GPU memory usage and 4× faster distillation time. Moreover, increasing the number of augmentations for our method yields further performance gains while incurring lower additional cost.

The computational complexity of anonymous games has been a central theme in algorithmic game theory, with foundational contributions by Daskalakis and Papadimitriou [2015], Goldberg and Turchetta [2017], and Cheng et al. [2017] establishing that the landscape of equilibrium computation admits a PTAS. In this paper, we investigate the class of $n$-player anonymous games with linear utilities and two actions. While finding an equilibrium in anonymous games is PPAD-hard for arbitrary utility functions—even with a constant number of actions [Chen et al., 2015]—we show that this linear structure allows for significant algorithmic improvements. Exploiting the fact that payoffs depend solely on the first moment of the players’ strategy distribution, we provide the first algorithm for computing exact Nash equilibria that runs in time polynomial in the number of players $n$. We achieve this by establishing a novel combinatorial characterization of the Nash equilibria. Finally, we establish a novel connection between Nash equilibria in these games and non-convex non-concave min-max optimization. Despite the technical challenges posed by this structural property, we design a sequential best-response dynamic that provably converges to an $\epsilon$-Nash equilibrium in $\mathcal{O}(\frac{1}{\epsilon})$ steps.