ICLR 2026 Papers

Well-designed open-source software drives progress in Machine Learning (ML) research. While static graph ML enjoys mature frameworks like PyTorch Geometric and DGL, ML for temporal graphs (TG), networks that evolve over time, lacks comparable infrastructure. Existing TG libraries are often tailored to specific architectures, hindering support for diverse models in this rapidly evolving field. Additionally, the divide between continuous- and discrete-time dynamic graph methods (CTDG and DTDG) limits direct comparisons and idea transfer. To address these gaps, we introduce Temporal Graph Modelling (TGM), a research-oriented library for ML on temporal graphs, the first to unify CTDG and DTDG approaches. TGM offers first-class support for dynamic node features, time-granularity conversions, and native handling of link-, node-, and graph-level tasks. Empirically, TGM achieves an average 7.8× speedup across multiple models, datasets, and tasks compared to the widely used DyGLib, and an average 175× speedup on graph discretization relative to available implementations. Beyond efficiency, we show in our experiments how TGM unlocks entirely new research possibilities by enabling dynamic graph property prediction and time-driven training paradigms, opening the door to questions previously impractical to study.

Increasing test-time computation is a straightforward approach to enhancing the quality of responses in Large Language Models (LLMs). While Best-of-N sampling and Self-Consistency with majority voting are simple and effective, they require a fixed number of sampling responses for each query, regardless of its complexity. This could result in wasted computation for simpler questions and insufficient exploration for more challenging ones. In this work, we argue that model confidence of responses can be used for improving the efficiency of test-time scaling. Unfortunately, LLMs are known to be overconfident and provide unreliable confidence estimation. To address this limitation, we introduce Self-Calibration by distilling Self-Consistency-derived confidence into the model itself. This enables reliable confidence estimation at test time with one forward pass. We then design Calibrated Test-Time Scaling (CaTS), adapting common repeated sampling methods, such as self-consistency and Best-of-N to handle queries of various difficulty. We also show that CaTS-SC is provably better than vanilla self-consistency. Experiments on three LLMs across nine datasets demonstrate the effectiveness of our approach. Specifically, applying confidence-based Early Stopping (CaTS-ES) to Best-of-N improves MathQA accuracy from 73.7 to 83.6 with a sample budget of 16 responses, demonstrating the effectiveness of the confidence-based sampling strategy at inference time.

Using a nearly-frozen pretrained model, the continual representation learning paradigm reframes parameter updates as a similarity-matching problem to mitigate catastrophic forgetting. However, directly leveraging pretrained features for downstream tasks often suffers from multicollinearity in the similarity-matching stage, and more advanced methods can be computationally prohibitive for real-time, low-latency applications. Inspired by the fly olfactory circuit, we propose Fly-CL, a bio-inspired framework compatible with a wide range of pretrained backbones. Fly-CL substantially reduces training time while achieving performance comparable to or exceeding that of current state-of-the-art methods. We theoretically show how Fly-CL progressively resolves multicollinearity, enabling more effective similarity matching with low time complexity. Extensive simulation experiments across diverse network architectures and data regimes validate Fly-CL’s effectiveness in addressing this challenge through a biologically inspired design.

Degradation-agnostic image restoration aims to handle diverse corruptions with one unified model, but faces fundamental challenges in balancing efficiency and performance across different degradation types. Existing approaches either sacrifice efficiency for versatility or fail to capture the distinct representational requirements of various degradations. We present MIRAGE, an efficient framework that addresses these challenges through two key innovations. First, we propose a channel-wise functional decomposition that systematically repurposes channel redundancy in attention mechanisms by assigning CNN, attention, and MLP branches to handle local textures, global context, and channel statistics, respectively. This principled decomposition enables degradation-agnostic learning while achieving superior efficiency-performance trade-offs. Second, we introduce manifold regularization that performs cross-layer contrastive alignment in Symmetric Positive Definite (SPD) space, which empirically improves feature consistency and generalization across degradation types. Extensive experiments across five degradation settings demonstrate that MIRAGE achieves state-of-the-art performance with remarkable efficiency, outperforming existing methods in both single and mixed degradation scenarios while showing strong zero-shot generalization to unseen domains.

Is bigger always better for time series foundation models? With the question in mind, we explore an alternative to training a single, large monolithic model: building a portfolio of smaller, pretrained forecasting models. By applying ensembling or model selection over these portfolios, we achieve competitive performance on large-scale benchmarks using much fewer parameters. We explore strategies for designing such portfolios and find that collections of specialist models consistently outperform portfolios of independently trained generalists. Remarkably, we demonstrate that post-training a base model is a compute-effective approach for creating sufficiently diverse specialists, and provide evidences that ensembling and model selection are more compute-efficient than test-time fine-tuning.

Large Language Models (LLMs) face significant inference latency challenges stemming from their autoregressive design and large size. To address this, speculative decoding emerges as a solution, enabling the simultaneous generation and validation of multiple tokens. While recent approaches like EAGLE-2 and EAGLE-3 improve speculative decoding using dynamic tree structures, they often neglect the impact of crucial system variables such as GPU devices and batch sizes. Therefore, we introduce a new dynamic tree decoding approach called CAST that takes into account inference costs, including factors such as GPU configurations and batch sizes, to dynamically refine the tree structure. Through comprehensive experimentation across six diverse tasks and utilizing six distinct LLMs, our methodology demonstrates remarkable results, achieving speeds up to 5.2 times faster than conventional decoding methods. Moreover, it generally outperforms existing state-of-the-art techniques from 5% to 20%.

Large Language Models (LLMs) have revolutionized numerous fields, yet their adaptation to specialized tasks in privacy-sensitive domains such as healthcare and finance remains constrained due to the scarcity of accessible training data caused by stringent privacy requirements. Secure Multi-party Computation (MPC)-based privacy-preserving machine learning provides theoretical guarantees for the privacy of model parameters and data. However, its application to LLMs has been predominantly limited to inference, as fine-tuning introduces significant efficiency challenges, particularly in backward propagation, optimizer, and self-attention operations. To address these challenges, we propose SecP-Tuning, the first MPC-based framework designed for efficient, privacy-preserving prompt tuning of LLMs. SecP-Tuning innovatively integrates Forward-only Tuning (FoT) through the ''data owner-server interaction" paradigm, effectively removing the need for privacy-preserving computations in backward propagation and optimization processes. Furthermore, it devises an efficient privacy-preserving Random Feature Attention (RFA), effectively mitigating the computational complexity of softmax-based self-attention and circumventing MPC-incompatible nonlinear operations. Experimental results demonstrate that, compared to full-Parameter Supervised Fine-Tuning (SFT) and gradient-based prompt tuning, SecP-Tuning achieves approximately 12$\times$ and 16$\times$ end-to-end acceleration, as well as 18$\times$ and 20$\times$ reductions in communication overhead, respectively. Moreover, it delivers performance comparable to gradient-based methods across multiple few-shot tasks. Additionally, the ''black-box/API-style" privacy-preserving tuning paradigm of SecP-Tuning effectively avoids memory leakage risks caused by gradient/parameter transmission, thereby striking an optimal balance between efficiency, accuracy, deployability, and privacy.

Generating (pseudo-)random variates lies at the core of probabilistic machine learning and prediction algorithms and yet remains a major bottleneck due to its high computational and energy cost. In this paper, we introduce a general and scalable sampling strategy that enables fast and energy-efficient random variate generation from arbitrary distributions. Our approach is based on efficient lookup tables combined with a fast index sampling scheme. Using only a handful of fast and energy-efficient compute operations on simple array structures, we achieve superior speed, energy efficiency, and precision at near-optimal entropy cost compared to state-of-the-art techniques. Microbenchmarking our approach with a C implementation shows up to 40\% savings in time and 60\% in energy compared to state-of-the-art approaches. Compared to commonly employed Python samplers we achieve a 100x time improvement.

Low-Rank Adaptation (LoRA) is a widely adopted technique for parameter-efficient fine-tuning, but its slow convergence has spurred the development of numerous variants. Nevertheless, current approaches struggle to achieve simultaneous improvements in performance, memory footprint, and computational efficiency. To address this challenge, we revisit the causes of LoRA’s slow convergence and, based on these insights, propose \textbf{M}atr\textbf{i}x \textbf{S}hard \textbf{S}haring (MiSS) that shards the original weight matrix and updates by sharing a single trainable matrix $\boldsymbol{D}$ initialized to zero. To simultaneously ensure computational efficiency, low memory footprint, and scalable serving, we introduce MiSS$^e$. Through theoretical analyses and empirical results, our method reduces optimization complexity while maintaining strong performance, striking a favorable balance between performance, memory, and efficiency. Furthermore, we provide a comprehensive analysis of different PEFT methods with respect to memory usage, initialization time, and computational efficiency. By mapping the Pareto frontier, we show that MiSS achieves a favorable balance across these dimensions, integrating the strengths of prior approaches.

Small Language Models (SLMs) are attractive for cost-sensitive and resource-limited settings due to their efficient, low-latency inference. However, they often struggle with complex, knowledge-intensive tasks that require structured reasoning and effective retrieval. To address these limitations, we propose FutureMind, a modular reasoning framework that equips SLMs with strategic thinking-pattern priors via adaptive knowledge distillation from large language models (LLMs). FutureMind introduces a dynamic reasoning pipeline composed of four key modules: Problem Analysis, Logical Reasoning, Strategy Planning, and Retrieval Guidance. This pipeline is augmented by three distinct retrieval paradigms that decompose complex queries into tractable subproblems, ensuring efficient and accurate retrieval execution. Extensive experiments on multi-hop QA benchmarks, including 2WikiMultihopQA, MuSiQue, Bamboogle, and Frames, demonstrate the superiority of FutureMind. It consistently outperforms strong baselines such as Search-o1, achieving state-of-the-art results under zero-training conditions across diverse SLM architectures and scales. Beyond empirical gains, our analysis reveals that the process of thinking-pattern distillation is restricted by the cognitive bias bottleneck between the teacher (LLMs) and student (SLMs) models. This provides new perspectives on the transferability of reasoning skills, paving the way for the development of SLMs that combine efficiency with genuine cognitive capability.

Training Large Language Models (LLMs) faces severe memory constraints due to the increasing size of model parameters and optimizer states. The Muon optimizer, which is based on matrix orthogonalization, has recently demonstrated significant potential and offers considerable memory advantages over AdamW by utilizing only the first moment. However, how to apply memory-reduction techniques to further compress the optimizer states of Muon remains underexplored. Directly applying existing methods may encounter significant difficulties due to the orthogonalization process. In this work, we investigate the low-bit compression of Muon and systematically analyze the quantization error exacerbated by orthogonalization. We identify that the error primarily originates from the top singular subspace and the outlier patterns of moment matrix appearing across both dimensions. To address this, we propose 4-bit-Muon-GRASP (GRid And Subspace Preserving), which compresses the Muon optimizer states to 4 bits using grid quantization, while preserving the top singular subspace with minimal overhead. We evaluate 4-bit-Muon-GRASP through pre-training on LLaMA-130M, 350M, and 1.1B architectures and fine-tuning on 7B models for various reasoning tasks. Extensive experiment results show that our 4-bit-Muon-GRASP achieves accuracy comparable to full-precision counterparts while reducing training memory consumption by up to 28\%. Code will be made public upon acceptance.

Large language models (LLMs) are deployed on mobile devices to power killer applications such as intelligent assistants. LLMs pre-trained on general corpora often hallucinate when handling personalized or unseen queries, leading to incorrect or outdated responses. Knowledge editing addresses this by identifying and adjusting a small crucial portion of model weights, without compromising the general knowledge. However, prior knowledge editing methods are impractical to run on local devices due to the resource-heavy backpropagation (BP) needed for updates. We present MobiEdit, the first mobile knowledge editing framework that enables efficient LLM personalization on commercial off-the-shelf (COTS) mobile devices. MobiEdit replaces full-precision BP with quantized forward-only gradient estimation, thus compatible with the energy-efficient mobile neural processing units (NPUs). To further improve gradient estimation efficiency, we introduce two optimizations: an early stopping mechanism that adaptively terminates editing upon success and prefix activation reusing that reduce redundant computation across steps. Our approach enables real-time editing of 3B-parameter models (Qwen2.5-3B-Instruct and Llama3.2-3B-Instruct) on COTS mobile devices with 7.1$\times$ less memory, 15.8 $\times$ less energy and 3.4$\times$ less latency compared to previous knowledge editing methods.

Incorporating metadata in Large Language Models (LLMs) pretraining has recently emerged as a promising approach to accelerate training. However prior work highlighted only one useful signal—URLs, leaving open the question of whether other forms of metadata could yield greater benefits. In this study, we investigate a wider range of metadata types and find other types of metadata, such as fine-grained indicators of document quality that can also accelerate pretraining when prepended. We identify a common feature among effective metadata: they encode information at a finer granularity. We further introduce metadata appending as a means of improving training efficiency, where predicting an appropriate metadata as auxiliary task can help speed up pretraining. In addition, learnable meta-tokens trained with masked loss can recover part of the speedup by inducing quality-aware latent structure. Using probing, we analyze latent representations to understand how metadata shapes learning. Together, these results yield practical guidelines for integrating metadata to improve both the efficiency and effectiveness of LLM pretraining.

Modeling non-stationary processes, where statistical properties vary across the input domain, is a critical challenge in machine learning; yet most scalable methods rely on a simplifying assumption of stationarity. This forces a difficult trade-off: use expressive but computationally demanding models like Deep Gaussian Processes, or scalable but limited methods like Random Fourier Features (RFF). We close this gap by introducing Random Wavelet Features (RWF), a framework that constructs scalable, non-stationary kernel approximations by sampling from wavelet families. By harnessing the inherent localization and multi-resolution structure of wavelets, RWF generates an explicit feature map that captures complex, input-dependent patterns. Our framework provides a principled way to generalize RFF to the non-stationary setting and comes with a comprehensive theoretical analysis, including positive definiteness, unbiasedness, and uniform convergence guarantees. We demonstrate empirically on a range of challenging synthetic and real-world datasets that RWF outperforms stationary random features and offers a compelling accuracy-efficiency trade-off against more complex models, unlocking scalable and expressive kernel methods for a broad class of real-world non-stationary problems.

Learned optimizers (LOs) have the potential to significantly reduce the wall-clock training time of neural networks. However, they can struggle to optimize unseen tasks (*meta-generalize*), especially when training networks wider than those seen during meta-training. To address this, we derive the Maximal Update Parametrization ($\mu$P) for two state-of-the-art learned optimizer architectures and propose a simple meta-training recipe for $\mu$-parameterized LOs ($\mu$LOs). Our empirical evaluation demonstrates that LOs meta-trained with our recipe substantially improve meta-generalization to wider unseen tasks when compared to LOs trained under standard parametrization (SP) using the same compute budget. We also empirically observe that $\mu$LOs exhibit unexpectedly improved meta-generalization to deeper networks ($5\times$ meta-training) and surprising generalization to much longer training horizons ($25\times$ meta-training) when compared to SP LOs.

Token filtering has been proposed to enhance the utility of large language models (LLMs) by eliminating inconsequential tokens during training. While using fewer tokens is expected to reduce computational workloads, existing methods have not yet achieved a real-world efficiency boost. This is primarily due to two factors: (1) existing work has inadequate sparsity for speedup, and (2) token filtering operates within a sparsity range that is non-standard in existing machine learning (ML) libraries and thus cannot be efficiently supported. This paper presents Centrifuge, a system that leverages algorithm and system co-design to unleash the full efficiency of token filtering in LLM training. At the algorithm level, Centrifuge filters activations of inconsequential tokens in the attention backward kernel to amplify the sparsity in backward computation. At the system level, Centrifuge proposes an automatic workflow that transforms sparse GEMM into dimension-reduced dense GEMM for optimized efficiency using standard ML libraries. Evaluations on models with various scales—from 1.1B to 40B—demonstrate that Centrifuge reduces backpropagation time by up to 49.9\% and end-to-end training time by up to 34.7\% when filtering 50\% of tokens. Utility assessments indicate that Centrifuge preserves the utility benefits of token filtering and significantly enhances model performance by up to 26.6\% compared to standard training. Centrifuge is designed for seamless integration into existing LLM training frameworks, enabling systems already utilizing token filtering to accelerate training with just one line of code.

Recent theoretical advances reveal that the Hadamard product induces nonlinear representations and implicit high-dimensional mappings for the field of deep learning, yet their practical deployment in efficient vision models remains underdeveloped. To address this gap, we introduce the Adaptive Cross-Hadamard (ACH) module, a novel operator that embeds learnability through differentiable discrete sampling and dynamic softsign normalization. This enables parameter-free feature reuse while stabilizing gradient propagation. Integrated into Hadaptive-Net (Hadamard Adaptive Network) via neural architecture search, our approach achieves unprecedented efficiency. Comprehensive experiments demonstrate state-of-the-art accuracy/speed trade-offs on image classification task, establishing Hadamard operations as fundamental building blocks for efficient vision models.

Vector Quantization (VQ) underpins modern discrete visual tokenization. However, training quantization modules for state-of-the-art VQ-based models requires significant computational resources which, in practice, all but prevents the development of novel, cutting-edge VQ techniques under resource constraints. To address this limitation, we propose VQ-Transplant, a simple framework that enables plug-and-play integration of new VQ modules into frozen, pre-trained tokenizers by replacing their native VQ modules. Crucially, the proposed transplantation process preserves all encoder-decoder parameters, obviating the need for costly end-to-end retraining when modifying the quantization method. To mitigate decoder-quantization mismatch, we introduce a lightweight decoder adaptation strategy (trained for only 5 epochs on ImageNet-1k) to align feature priors with the new quantization space. In our empirical evaluation, we find that VQ-Transplant allows obtaining near state-of-the-art reconstruction fidelity for industry-level models like VAR while reducing the training cost by 95%. VQ-Transplant democratizes quantization research by enabling resource-efficient integration of novel VQ techniques while matching industry-level reconstruction performance.

Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time. The primary culprits are the activations, whose memory footprints scale linearly with sequence length. We introduce OOMB, a highly memory-efficient training system that directly confronts this barrier. Our approach employs a chunk-recurrent training framework with on-the-fly activation recomputation, which maintains a constant activation memory footprint ($\mathcal{O}(1)$) and shifts the primary bottleneck to the growing KV cache. To manage the KV cache, OOMB integrates a suite of synergistic optimizations: a paged memory manager for both the KV cache and its gradients to eliminate fragmentation, asynchronous CPU offloading to hide data transfer latency, and page-level sparse attention to reduce both computational complexity and communication overhead. The synergy of these techniques yields exceptional efficiency. Our empirical results show that for every additional 10K tokens of context, the end-to-end training memory overhead increases by a mere 10MB for Qwen2.5-7B. This allows training Qwen2.5-7B with a 4M-token context on a single H200 GPU, a feat that would otherwise require a large cluster using context parallelism. This work represents a substantial advance in resource efficiency for long-context LLM training. The source code is available for review at https://anonymous.4open.science/r/oomb/README.md.