论文检索

Probabilistic Methods · Everything Else

Daniel Csillag, Pedro Dall’Antonia, Claudio Struchiner, Guilherme Tegoni Goedert

Prediction-powered inference is a recent methodology for the safe use of black-box ML models to impute missing data, strengthening inference of statistical parameters. However, many applications require strong properties besides valid inference, such as privacy, robustness or validity under continuous distribution shifts; deriving prediction-powered methods with such guarantees is generally an arduous process, and has to be done case by case. In this paper, we resolve this issue by connecting prediction-powered inference with conformal prediction: by performing imputation through a calibrated set-predictor, we attain validity while achieving additional guarantees in a natural manner. We instantiate our procedure for the inference of means, Z- and M-estimation, as well as e-values and e-value-based procedures. Furthermore, in the case of e-values, ours is the first general prediction-powered procedure that operates off-line. We demonstrate these advantages by applying our method on private and time-series data. Both tasks are nontrivial within the standard prediction-powered framework but become natural under our method.

General Machine Learning · Data

Zhongzhi Li, Xuansheng Wu, Yijiang Li, Lijie Hu, Ninghao Liu

The diversity of post-training data is critical for effective downstream performance in large language models (LLMs). Many existing approaches to constructing post-training data quantify diversity using text-based metrics that capture linguistic variation, but such metrics provide only weak signals for the task-relevant features that determine downstream performance. In this work, we introduce ***Feature Activation Coverage* (FAC)** which measures data diversity in an interpretable feature space. Building upon this metric, we further propose a diversity-driven data synthesis framework, named **FAC Synthesis**, that first uses a sparse autoencoder to identify missing features from a seed dataset, and then generates synthetic samples that explicitly reflect these features. Experiments show that our approach consistently improves both data diversity and downstream performance on various tasks, including instruction following, toxicity detection, reward modeling, and behavior steering. Interestingly, we identify a shared, interpretable feature space across model families (i.e., LLaMA, Mistral, and Qwen), enabling cross-model knowledge transfer. Our work provides a solid and practical methodology for exploring data-centric optimization of LLMs.

General Machine Learning · Data

Zhongzhi Li, Xuansheng Wu, Yijiang Li, Lijie Hu, Ninghao Liu

The diversity of post-training data is critical for effective downstream performance in large language models (LLMs). Many existing approaches to constructing post-training data quantify diversity using text-based metrics that capture linguistic variation, but such metrics provide only weak signals for the task-relevant features that determine downstream performance. In this work, we introduce ***Feature Activation Coverage* (FAC)** which measures data diversity in an interpretable feature space. Building upon this metric, we further propose a diversity-driven data synthesis framework, named **FAC Synthesis**, that first uses a sparse autoencoder to identify missing features from a seed dataset, and then generates synthetic samples that explicitly reflect these features. Experiments show that our approach consistently improves both data diversity and downstream performance on various tasks, including instruction following, toxicity detection, reward modeling, and behavior steering. Interestingly, we identify a shared, interpretable feature space across model families (i.e., LLaMA, Mistral, and Qwen), enabling cross-model knowledge transfer. Our work provides a solid and practical methodology for exploring data-centric optimization of LLMs.

General Machine Learning · Causality

Connor T Jerzak, Priyanshi Chandra, Rishi Hazra

We study offline learning of factored stochastic policies over extremely large, combinatorial action spaces and show how standard conjoint data can be used to estimate such policies with asymptotically valid uncertainty under conditions. Conjoint analyses typically report AMCEs by averaging over opponent attributes and thus ignore strategic interdependence. We instead learn \emph{stochastic interventions}---product-of-Categorical policies over factor levels—that (i) optimize expected outcomes in an average-case setting and (ii) extend to a two-player \emph{minimax} (adversarial) setting that realistically captures simultaneous strategic candidate selection. Methodologically, we derive a closed-form solution for the average-case optimizer under two-way interactions with $L_2$ variance regularization, and provide a general gradient-based procedure for richer model classes. Uncertainty from the outcome model propagates asymptotically to both the optimal policy and its value via a Delta method approximation. We further model institutional details (e.g., primaries) inside the minimax objective and introduce a data-driven measure of strategic divergence between parties. On synthetic data, we empirically characterize finite-sample error and coverage as dimensionality and $n$ vary. On a U.S. presidential conjoint, adversarially learned policies produce restricted-equilibrium vote shares that align with historical election ranges in our data, in stark contrast to non-adversarial (averaging) optimizers.

Deep Learning · Generative Models and Autoencoders

Austin Xu, Xuan-Phi Nguyen, Yilun Zhou, Chien-Sheng Wu, Caiming Xiong, Shafiq Joty

Finetuning specialized generative evaluators has emerged as a popular paradigm to meet the increasing demand for scalable evaluation during both training and test-time. However, recent work has largely focused on applying new methodology, such as reinforcement learning (RL), to training evaluators, shying away from large-scale, data-driven development. In this work, we focus on data scaling, curating a set of 2.5M samples spanning five unique evaluation tasks (pairwise, step-level, reference-free and reference-based verification, and single rating) and multiple domains focused on reasoning evaluation. With our data, we train Foundational Automatic Reasoning Evaluators (FARE), a family of 8B and 20B (with 3.6B active) parameter evaluators, with a simple iterative rejection-sampling supervised finetuning (SFT) approach. FARE-8B challenges larger specialized RL-trained evaluators and FARE-20B sets the new standard for open-source evaluators, surpassing specialized 70B+ evaluators. Beyond static benchmarks, we evaluate FARE in real-world tasks: As inference-time rerankers, FARE-20B achieves near-oracle performance on MATH. As verifiers in RL training, FARE improves the downstream RL-trained model performance by up to 14.1\% vs. string-matching verifiers. When initialized from FARE, a continually-finetuned FARE-Code outperforms gpt-oss-20B by 65% on evaluating test-case quality

Kuan Li, Zhongwang Zhang, Huifeng Yin, Rui Ye, Yida Zhao, Liwen Zhang, Litu Ou, Ding-Chu Zhang, Xixi Wu, Xinmiao Yu 等

To significantly advance the capabilities of open-source web agents, we present WebSailor-V2, a complete post-training pipeline encompassing data construction, Supervised Fine-Tuning (SFT), and Reinforcement Learning (RL). Our methodology features two key innovations: (1) On the data front, we developed SailorFog-QA-2, a novel dataset built from a densely interconnected knowledge graph that introduces a wide variety of uncertainties beyond simple obfuscation, fostering more sophisticated reasoning. (2) For training, we engineered a dual-environment RL framework, combining a high-fidelity simulator for rapid, low-cost algorithmic iteration with a robust, managed real-world environment for stable final policy training, all integrated within a symbiotic data-policy feedback loop. Trained on the Qwen3-30B-A3B model, WebSailor-V2 achieves state-of-the-art results, scoring 35.3 on BrowseComp-EN, 44.1 on BrowseComp-ZH, and 30.6 on Humanity's Last Exam (HLE). Notably, our 30B-A3B MOE agent significantly outperforms all existing open-source agents and surpasses even the 671B DeepSeek-V3.1, demonstrating performance competitive with leading proprietary systems.

Computer Vision · Segmentation

Tianpei Zou, Guo Yu, Ya Wu, Fan Lu, Eric Zhongcong Xu, Zhang Bo, Ziqiao Wang, Sanqing Qu, Guang Chen

Open-set Test-time Adaptation (OSTTA) has been introduced to address the challenges of both online model optimization and open-set recognition. Despite the demonstrated success of OSTTA methodologies in 2D image recognition, their application to 3D point cloud semantic segmentation is still hindered by the complexities of point cloud data, particularly the imbalance between known (in-distribution, ID) and unknown (out-of-distribution, OOD) data, where known samples dominate and unknown instances are often sparse or even absent. In this paper, we propose a simple yet effective strategy, termed Geometry-guided Out-of-Distribution Modeling (GOOD), specifically designed to address OSTTA for 3D point cloud semantic segmentation. Technically, we first leverage geometric priors to cluster the point cloud into superpoints, thereby mitigating the numerical disparity between individual points and providing a more structured data representation. Then, we introduce a novel confidence metric to effectively distinguish between known and unknown superpoints. Additionally, prototype-based representations are integrated to enhance the discrimination between ID and OOD regions, facilitating robust segmentation. We validate the efficacy of GOOD across four benchmark datasets. Remarkably, on the Synth4D to SemanticKITTI task, GOOD outperforms HGL by 1.93%, 8.99%, and 7.91% in mIoU, AUROC, and FPR95, respectively.

Reinforcement Learning · Deep RL

Fang Wu, Weihao Xuan, Heli Qi, Aaron Tu, Ximing Lu, Li Li, Yejin Choi

Although Reinforcement Learning with Verifiable Rewards (RLVR) has become an essential component for developing advanced reasoning skills in language models, contemporary studies have documented training plateaus after thousands of optimization steps, i.e., notable decreases in performance gains despite increased computational investment. This limitation stems from the sparse exploration patterns inherent in current RLVR practices, where models rely on limited rollouts that often miss critical reasoning paths and fail to provide systematic coverage of the solution space. We present DeepSearch, a framework that integrates Monte Carlo Tree Search (MCTS) directly into RLVR training. In contrast to existing methods that rely on tree search only at inference, DeepSearch embeds structured search into the training loop, enabling systematic exploration and fine-grained credit assignment across reasoning steps. Through training-time exploration, DeepSearch addresses the fundamental bottleneck of insufficient exploration, which leads to diminishing performance gains over prolonged training. Our contributions include: (1) a global frontier selection strategy that prioritizes promising nodes across the search tree, (2) selection with entropy-based guidance that identifies confident paths for supervision, and (3) adaptive replay buffer training with solution caching for efficiency. Experiments on mathematical reasoning benchmarks show that DeepSearch achieves an average accuracy of 62.95% and establishes a new state-of-the-art reasoning model, while using 5.7x fewer GPU hours than extended training approaches. These results highlight the importance of strategic exploration over brute-force scaling and demonstrate the promise of algorithmic innovation for advancing RLVR methodologies. DeepSearch establishes a new direction for scaling reasoning capabilities through systematic search rather than prolonged computation.

Xinhao Zhong, Shuoyang Sun, Xulin Gu, Chenyang Zhu, Bin Chen, Yaowei Wang

Dataset distillation aims to generate compact synthetic datasets that enable models trained on them to achieve performance comparable to those trained on full real datasets, while substantially reducing storage and computational costs. Early bi-level optimization methods (e.g., MTT) have shown promising results on small-scale datasets, but their scalability is limited by high computational overhead. To address this limitation, recent decoupled dataset distillation methods (e.g., SRe$^2$L) separate the teacher model pre-training from the synthetic data generation process. These methods also introduce random data augmentation and epoch-wise soft labels during the post-evaluation phase to improve performance and generalization. However, existing decoupled distillation methods suffer from inconsistent post-evaluation protocols, which hinders progress in the field. In this work, we propose **R**ectified **D**ecoupled **D**ataset **D**istillation (RD$^3$), and systematically investigate how different post-evaluation settings affect test accuracy. We further examine whether the reported performance differences across existing methods reflect true methodological advances or stem from discrepancies in evaluation procedures. Our analysis reveals that much of the performance variation can be attributed to inconsistent evaluation rather than differences in the intrinsic quality of the synthetic data. In addition, we identify general strategies that improve the effectiveness of distilled datasets across settings. By establishing a standardized benchmark and rigorous evaluation protocol, RD$^3$ provides a foundation for fair and reproducible comparisons in future dataset distillation research.

Mingjun Wang, Yihan Wen, Yuntao Lu, Fengrui Liu, Yuxiang Zhao, Boyu Han, Jianan Mu, Yibo Lin, Runsheng Wang, Bei Yu 等

Integrated circuit (IC) designs require transforming high-level specifications into physical layouts, demanding extensive expertise and specialized tools, as well as months of time and numerous iterations. While machine learning (ML) has shown promise in various research domains, the lack of large-scale, open datasets limits its application in chip design. To address this limitation, we introduce CircuitNet 3.0, a large-scale, comprehensive, and open-source dataset curated to facilitate the evaluation of ML models on challenging timing and power prediction tasks. Starting with a diverse set of 8,659 validated open-source designs, we employ a systematic framework to generate over 15,000 instances. Through specialized syntax-tree mutation strategies and principled, task-oriented filtering methodology, we enrich each design with multi-modal information spanning multiple design stages, including complete design flow documentation, register-transfer-level (RTL) designs and corresponding netlists, detailed physical layouts, and comprehensive performance metrics. The experimental results demonstrate that ML models leveraging the enriched multi-stage, multi-modal circuit representations significantly improve performance over existing open-source datasets in electronic design automation (EDA) tasks, paving the way for efficient and accessible circuit representation learning. The dataset and codes are available in \url{https://github.com/sklp-eda-lab/iclr-circuitnet_3.0/}.

Applications · Time Series

Jongwon Kim, Samuel Yoon, Young Ko, Yerin Kim, Sung Kim, JAEUNG TAE

This paper introduces a methodology for anomaly detection in time series using Time Series Foundation Models (TFMs). While TFMs have achieved strong success in forecasting, their role in anomaly detection remains underexplored. We identify two key challenges when applying TFMs to reconstruction-based anomaly detection and propose solutions. The first challenge is overgeneralization, where TFMs reconstruct both normal and abnormal data with similar accuracy, masking true anomalies. We find that this effect often occurs in data with strong low-frequency components. To address it, we propose a complexity metric, $\alpha$, that reflects how difficult the data is for TFMs and design a Complexity-Aware Ensemble (CAE) that adaptively balances TFMs with a statistical model. The second challenge is overstationarization, caused by instance normalization layers that improve forecasting accuracy but remove essential statistical features such as mean and variance, which are critical for anomaly detection. We resolve this by reintroducing these features into the reconstruction process without retraining the TFMs. Experiments on 23 univariate and 17 multivariate benchmark datasets demonstrate that our method significantly outperforms both deep learning and statistical baselines. Furthermore, we show that our complexity-based metric, $\alpha$, provides a theoretical foundation for improved anomaly detection, and we briefly explore prediction-based anomaly detection using TFMs.

General Machine Learning · Causality

Konstantin Hess, Dennis Frauen, Mihaela van der Schaar, Stefan Feuerriegel

Estimating heterogeneous treatment effects (HTEs) in time-varying settings is particularly challenging, as the probability of observing certain treatment sequences decreases exponentially with longer prediction horizons. Thus, the observed data contain little support for many plausible treatment sequences, which creates severe overlap problems. Existing meta-learners for the time-varying setting typically assume adequate treatment overlap, and thus suffer from exploding estimation variance when the overlap is low. To address this problem, we introduce a novel overlap-weighted orthogonal WO meta-learner for estimating HTEs that targets regions in the observed data with high probability of receiving the interventional treatment sequences. This offers a fully data-driven approach through which our WO-learner can counteract instabilities as in existing meta-learners and thus obtain more reliable HTE estimates. Methodologically, we develop a novel Neyman-orthogonal population risk function that minimizes the overlap-weighted oracle risk. We show that our WO-learner has the favorable property of Neyman-orthogonality, meaning that it is robust against misspecification in the nuisance functions. Further, our WO-learner is fully model-agnostic and can be applied to any machine learning model. Through extensive experiments with both transformer and LSTM backbones, we demonstrate the benefits of our novel WO-learner.

Kaiyue Wen, David Hall, Tengyu Ma, Percy Liang

AdamW has long been the dominant optimizer in language model pretraining, despite numerous claims that alternative optimizers offer 1.4 to 2$\times$ speedup. We posit that two methodological shortcomings have obscured fair comparisons and hindered practical adoption: (i) unequal hyperparameter tuning and (ii) limited or misleading evaluation setups. To address these two issues, we conduct a systematic study of ten deep learning optimizers across four model scales (0.1B–1.2B parameters) and data-to-model ratios (1--8$\times$ the Chinchilla optimum). We find that fair and informative comparisons require rigorous hyperparameter tuning and evaluations across a range of model scales and data-to-model ratios, performed at the end of training. First, optimal hyperparameters for one optimizer may be suboptimal for another, making blind hyperparameter transfer unfair. Second, the actual speedup of many proposed optimizers over well-tuned baselines is lower than claimed and decreases with model size to only 1.1$\times$ for 1.2B parameter models. Thirdly, comparing intermediate checkpoints before reaching the target training budgets can be misleading, as rankings between two optimizers can flip during training due to learning rate decay. Through our thorough investigation, we find that all the fastest optimizers such as Muon and Soap, use matrices as preconditioners --- multiplying gradients with matrices rather than entry-wise scalars. However, the speedup of matrix-based optimizers is inversely proportional to model scale, decreasing from 1.4$\times$ over AdamW for 0.1B parameter models to merely 1.1$\times$ for 1.2B parameter models.

General Machine Learning · Representation Learning

Seok-Hwan Oh, Myeong-Gee Kim, Guil Jung, hyeonjik lee, Young-Min Kim, Sang-yun Kim, Hyuksool Kwon, Hyeon-min Bae

Diagnostic accuracy of ultrasound imaging is limited by qualitative variability and its reliance on the expertise of medical professionals. Such challenges increase demand for computer-aided diagnostic systems that enhance diagnostic accuracy and efficiency. However, the unique texture and structural attributes of ultrasound images, and the scarcity of large-scale ultrasound datasets hinder the effective application of conventional machine learning methodologies. To address the challenges, we propose Anatomy-aware Representation Learning (ARL), a novel self-supervised representation learning framework specifically designed for medical ultrasound imaging. ARL incorporates an anatomy-adaptive Vision Transformer (A-ViT). The A-ViT is parameterized, using the proposed large-scale medical ultrasound dataset, to provide anatomy-aware feature representations. Through extensive experiments across various ultrasound-based diagnostic tasks, including breast and thyroid cancer, cardiac view classification, and gallbladder tumor and COVID-19 identification, we demonstrate that ARL significantly outperforms existing self-supervised learning baselines. The experiments demonstrate the potential of ARL in advancing medical ultrasound diagnostics by providing anatomy-specific feature representation

Shohei Taniguchi, Masahiro Suzuki, Yutaka Matsuo

Diffusion models are powerful generative models for continuous signals, such as images and videos. However, real-world digital data are quantized; hence, they take not continuous values but only a finite set of discrete values. For example, pixels in 8‑bit images can take only 256 discrete values. In existing diffusion models, quantization is either ignored by treating data as continuous, or handled by adding small noise to make the data continuous. Neither approach guarantees that samples from the model will converge to the finite set of quantized points. In this work, we propose a methodology to explicitly account for quantization within diffusion models. Specifically, by adopting a particular form of parameterization, we guarantee that samples from the reverse diffusion process converge to quantized points. In experiments, we demonstrate that our quantization-aware model can substantially improve the performance of diffusion models for density estimation, and achieve state‑of‑the‑art results on pixel‑level image generation in likelihood evaluation. In particular, for CIFAR‑10 image generation, the negative log‑likelihood improves substantially from 2.42 to 0.27, approaching the theoretical lower bound.

Social Aspects · Accountability, Transparency and Interpretability

Wengang Li, Lingqi Zhang, Toshio Endo, Mohamed Wahib

Mixture-of-Experts (MoE) has been a prevalent method for scaling up large language models at a reduced computational cost. Despite its effectiveness, the routing mechanism of MoE still lacks a clear understanding from the perspective of cross-layer mechanistic interpretability. We propose a light-weight methodology at which we can break down the routing decision for MoE to the contribution of model components, in a recursive fashion. We use our methodology to dissect the routing mechanism by decomposing the input of routers into model components. We study how different model components contribute to the routing in different widely used open models. Our findings on four different LLMs reveal patterns such as: a) MoE layer outputs usually contribute more than attention layer outputs to the routing decisions of subsequent layers, b) *MoE entanglement* at which MoE firing up in layers consistently correlate with firing up of MoE in subsequent layers, and c) some components can persistently influence the routing in many following layers. Our study also includes findings on how different models have different patterns when it comes to long-range and short-range inhibiting/promoting effects that components can have over MoE in subsequent layers. Our results indicate the importance of quantifying the impact of components across different layers on MoE to understand the routing mechanism.

Computer Vision · Image and Video Generation

Xin Luo, Jiahao Wang, Chenyuan Wu, Shitao Xiao, Xiyan Jiang, Defu Lian, Jiajun Zhang, Dong Liu, Zheng Liu

Instruction-guided image editing has achieved remarkable progress, yet current models still face challenges with complex instructions and often require multiple samples to produce a desired result. Reinforcement Learning (RL) offers a promising solution, but its adoption in image editing has been severely hindered by the lack of a high-fidelity, efficient reward signal. In this work, we present a comprehensive methodology to overcome this barrier, centered on the development of a state-of-the-art, specialized reward model. We first introduce $\textbf{EditReward-Bench}$, a comprehensive benchmark to systematically evaluate reward models on editing quality. Guided by this benchmark, we develop $\textbf{EditScore}$, an efficient model to evaluate the quality of instruction-guided editing. Through meticulous data curation and filtering, EditScore effectively matches the performance of learning proprietary VLMs. Furthermore, coupled with an effective self-ensemble strategy tailored for the generative nature of EditScore, our largest variant even surpasses GPT-5 in the benchmark. We then demonstrate that a high-fidelity reward model is the key to unlocking online RL for image editing. Our experiments show that, while even the largest open-source VLMs fail to provide an effective learning signal, EditScore enables efficient and robust policy optimization. Applying our framework to a strong base model, OmniGen2, results in a final model that shows a substantial and consistent performance uplift. Overall, this work provides the first systematic path from benchmarking to reward modeling to RL training in image editing, showing that a high-fidelity, domain-specialized reward model is the key to unlocking the full potential of RL in this domain. Our code, models, and benchmark will be released publicly.

Applications · Physics

Alessandro Trenta, Andrea Cossu, Davide Bacciu

Real-world phenomena typically involve multiple, interwoven dynamics that can be elegantly captured by systems of Partial Differential Equations (PDEs). However, accurately solving such systems remains a challenge. In this paper, we introduce ComPhy (CP), a novel modular framework designed to leverage the inherent physical structure of the problem to solve systems of PDEs. CP assigns each PDE to a dedicated learning module, each capable of incorporating state-of-the-art methodologies such as Physics-Informed Neural Networks or Neural Conservation Laws. Crucially, CP introduces an end-to-end alignment mechanism, explicitly designed around the physical interplay of shared variables, enabling knowledge transfer between modules, and promoting solutions that are the result of the collective effort of all modules. CP is the first approach specifically designed to tackle systems of PDEs, and our results show that it outperforms state-of-the-art approaches where a single model is trained on all PDEs at once.

Jintian Zhang, Kewei Xu, Jingsheng Zheng, Zhuoyun Yu, Yuqi Zhu, Yujie Luo, Lanning Wei, Shuofei Qiao, Lun Du, Da Zheng 等

LLMs and Agents have achieved impressive progress in code generation, mathematical reasoning, and scientific discovery. However, existing benchmarks primarily measure correctness, overlooking the diversity of methods behind solutions. True innovation depends not only on producing correct answers but also on the originality of the approach. We present \textbf{InnoGym}, the first benchmark and framework designed to systematically evaluate the innovation potential of AI agents. InnoGym introduces two complementary metrics: performance gain, which measures improvement over the best-known solutions, and novelty, which captures methodological differences from prior approaches. The benchmark includes 18 carefully curated tasks from real-world engineering and scientific domains, each standardized through resource filtering, evaluator validation, and solution collection. In addition, we provide \textbf{iGym}, a unified execution environment for reproducible and long-horizon evaluations. Extensive experiments show that while some agents produce novel approaches, their lack of robustness limits performance gains. These results highlight a key gap between creativity and effectiveness, underscoring the need for benchmarks that evaluate both.

Deep Learning · Attention Mechanisms

Aakash Sunil Lahoti, Kevin Li, Berlin Chen, Caitlin Wang, Aviv Bick, Zico Kolter, Tri Dao, Albert Gu

Scaling inference-time compute has emerged as an important driver of LLM performance, making inference efficiency a central focus of model design alongside model quality. While current Transformer models deliver strong quality, their quadratic compute and linear memory requirements make inference expensive. This has spurred the development of sub-quadratic models with reduced compute and constant memory requirements. However, many recent linear models trade off model quality and capability for algorithmic efficiency, failing on tasks such as state tracking. Moreover, their theoretically linear inference remains hardware-inefficient in practice. Guided by an inference-first perspective, we introduce three core methodological improvements inspired by the state space model (SSM) viewpoint of linear models. We combine: (1) a more expressive recurrence derived from SSM discretization, (2) a complex-valued state update rule enabling richer state tracking, and (3) a multi-input, multi-output (MIMO) formulation that improves model performance without increasing decode latency. Together with architectural refinements, Mamba-3 achieves significant gains across retrieval, state-tracking, and downstream language modeling tasks. At the 1.5B scale, Mamba-3 improves average downstream accuracy by 0.6 percentage points compared to the next best model (Gated DeltaNet), with the MIMO variant further improving accuracy by an additional 1.2 points, for a total gain of 1.8 points. Across state-size experiments, Mamba-3 achieves comparable perplexity to Mamba-2 despite using half the state size. These results demonstrate that Mamba-3 advances the performance–efficiency frontier.