ICLR 2026 论文列表

Adaptive optimizers can reduce to normalized steepest descent (NSD) when only adapting to the current gradient, suggesting a close connection between the two algorithmic families. A key distinction in their analyses, however, lies in the smoothness assumptions they rely on. In the convex setting, adaptive optimizers are governed by a stronger adaptive smoothness condition, while NSD relies on the standard notion of smoothness. We extend the theory of adaptive smoothness to the nonconvex setting and show that it precisely characterizes the convergence of adaptive optimizers. Moreover, we establish that adaptive smoothness enables acceleration of adaptive optimizers with Nesterov momentum, a guarantee unattainable under standard smoothness. We further develop an analogous comparison for stochastic optimization by introducing adaptive variance, which parallels adaptive smoothness and leads to qualitatively stronger guarantees than the standard variance.

Deploying large language models (LLMs) on mobile platforms faces significant challenges due to the limited memory and shared computational resources of the device. Resource availability may be an issue as it is directly impacted by on the current device workload, adding to the uncertainty of model deployment. We introduce UniQL, a unified post-training quantization and low-rank compression framework, with on-device configurable pruning rates for edge LLMs. UniQL is a general framework that integrates quantization and low-rank compression for Transformers, State Space Models (SSMs), and hybrid models to cater to diverse edge applications. In our proposed joint framework, we introduce an efficient structured weight-sorting that speeds up the computation by 20×, quantization-aware singular value decomposition (SVD) decompositions to minimize the quantization errors, state-aware weight sorting for SSMs, and a fused rotary embedding (RoPE) kernel for the pruned models. Our framework performs weight-sorting, fine-tuning, and quantization in the cloud in a one-shot fashion, while enabling on-device configurable pruning rates up to 35%. Our experiments show that quantized and pruned models offer a memory reduction of 4×–5.7× and a token throughput improvement of 2.7×–3.4×, maintaining accuracy within 5% of the original models at 15% pruning rates across Transformers (Llama3 and Qwen2.5), SSMs (Mamba2), and hybrid models (Nemotron-H and Bamba-v2). The code and quantized models will be released at: https://github.com/.

Large Reasoning Models (LRMs) have shown remarkable capabilities in solving complex problems through reinforcement learning (RL), particularly by generating long reasoning traces. However, these extended outputs often exhibit substantial redundancy, which limits the efficiency of LRMs. In this paper, we investigate RL-based approaches to promote reasoning efficiency. Specifically, we first present a unified framework that formulates various efficient reasoning methods through the lens of length-based reward shaping. Building on this perspective, we propose a novel **L**ength-b**A**sed **S**t**E**p **R**eward shaping method (LASER), which employs a step function as the reward based on target length. LASER surpasses previous methods, achieving a superior trade-off between performance and efficiency. Next, we further extend LASER based on two key intuitions: (1) The reasoning behavior of the model evolves dynamically during training, necessitating reward specifications that are also adaptive and dynamic; (2) Rather than uniformly encouraging shorter or longer chains of thought (CoT), we posit that length-based reward shaping should be difficulty-aware i.e., it should penalize lengthy CoTs more for easy queries. This approach is expected to facilitate a combination of fast and slow thinking, leading to a better overall tradeoff. The resulting method is termed LASER-D (**D**ynamic and **D**ifficulty-aware). Experiments on five open-weight models from 1.5B to 32B demonstrate that our approach significantly enhances both reasoning performance and response length efficiency. For instance, LASER-D achieves a **5.3** improvement on AIME2024 while reducing token usage by **64**%. Further analysis reveals that our RL-based compression produces more concise reasoning patterns with less redundant ``self-reflections''.

Recent works have explored reference-based super-resolution (RefSR) to mitigate hallucinations in diffusion-based image restoration. A key challenge is that real-world degradations make correspondences between low-quality (LQ) inputs and reference (Ref) images unreliable, requiring adaptive control of reference usage. Existing methods either ignore LQ–Ref correlations or rely on brittle explicit matching, leading to over-reliance on misleading references or under-utilization of valuable cues. To address this, we propose Ada-RefSR, a single-step diffusion framework guided by a "Trust but Verify " principle: reference information is leveraged when reliable and suppressed otherwise. Its core component, Adaptive Implicit Correlation Gating (AICG), employs learnable summary tokens to distill dominant reference patterns and capture implicit correlations with LQ features. Integrated into the attention backbone, AICG provides lightweight, adaptive regulation of reference guidance, serving as a built-in safeguard against erroneous fusion. Experiments on multiple datasets demonstrate that Ada-RefSR achieves a strong balance of fidelity, naturalness, and efficiency, while remaining robust under varying reference alignment. Code and models are available at https://github.com/vivoCameraResearch/AdaRefSR.

Differential Privacy (DP) is becoming central to large-scale training as privacy regulations tighten. We revisit how DP noise interacts with *adaptivity* in optimization through the lens of *stochastic differential equations*, providing the first SDE-based analysis of private optimizers. Focusing on DP-SGD and DP-SignSGD under per-example clipping, we show a sharp contrast under fixed hyperparameters: DP-SGD converges at a privacy-utility trade-off $O(1/\varepsilon^2)$ with speed independent of $\varepsilon$, while DP-SignSGD converges at a speed *linear* in $\varepsilon$ with a $O(1/\varepsilon)$ trade-off, dominating in high-privacy or high-noise regimes. Under optimal learning rates, both methods reach comparable theoretical asymptotic performance; however, the optimal learning rate of DP-SGD scales linearly with $\varepsilon$, while that of DP-SignSGD is essentially $\varepsilon$-independent. This makes adaptive methods far more practical, as their hyperparameters transfer across privacy levels with little or no re-tuning. Empirical results confirm our theory across training and test metrics, and extend from DP-SignSGD to DP-Adam.

Large Vision-Language Models (LVLMs) have achieved substantial progress in cross-modal tasks. However, due to language bias, LVLMs are susceptible to object hallucination, which can be primarily divided into category, attribute, and relation hallucination, significantly impeding the trustworthy AI applications. Editing the internal activations of LVLMs has shown promising effectiveness in mitigating hallucinations with minimal cost. However, previous editing approaches neglect the effective guidance offered by factual textual semantics, thereby struggling to explicitly mitigate language bias. To address these issues, we propose Adaptive Factual-guided Visual-Textual Editing for hallucination mitigation (AFTER), which comprises Factual-Augmented Activation Steering (FAS) and Query-Adaptive Offset Optimization (QAO), to adaptively guides the original biased activations towards factual semantics. Specifically, FAS is proposed to provide factual and general guidance for activation editing, thereby explicitly modeling the precise visual-textual associations. Subsequently, QAO introduces a query-aware offset estimator to establish query-specific editing from the general steering vector, enhancing the diversity and granularity of editing. Extensive experiments on standard hallucination benchmarks across three widely adopted LVLMs validate the efficacy of the proposed AFTER, notably achieving up to a 16.3% reduction of hallucination over baseline on the AMBER benchmark. Our code and data will be released for reproducibility.

Incorporating demonstration data into reinforcement learning (RL) can greatly accelerate learning, but existing approaches often assume demonstrations are optimal and fully aligned with the target task. In practice, demonstrations are frequently sparse, suboptimal, or misaligned, which can degrade performance when these demonstrations are integrated into RL. We propose Adaptive Policy Composition (APC), a hierarchical model that adaptively composes multiple data-driven Normalizing Flow (NF) priors. Instead of enforcing strict adherence to the priors, APC estimates each prior's applicability to the target task while leveraging them for exploration. Moreover, APC either refines useful priors, or sidesteps misaligned ones when necessary to optimize downstream reward. Across diverse benchmarks, APC accelerates learning when demonstrations are aligned, remains robust under severe misalignment, and leverages suboptimal demonstrations to bootstrap exploration while avoiding performance ceilings caused by overly strict adherence to suboptimal demonstrations.

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.

Model merging has emerged as a promising approach for unifying independently fine-tuned models into an integrated framework, significantly enhancing computational efficiency in multi-task learning. Recently, several SVD-based techniques have been introduced to exploit low-rank structures for enhanced merging, but their reliance on heuristically designed rank selection often leads to inter-task interference and suboptimal performance. In this paper, we propose AdaRank, a model merging framework that replaces this heuristic selection by adaptively selecting the beneficial singular components of task vectors to merge multiple models. We first show empirically that (i) selecting only the top singular components of task vectors can cause critical interference with other tasks, and (ii) assigning fixed ranks does not align with the varying complexity of tasks and layers. AdaRank addresses both issues by adapting per-component masks, indicating the selection of the component, to the unlabeled test data with entropy minimization. Our experimental findings show that AdaRank consistently improves existing merging methods across diverse backbones from different modalities, largely narrowing the performance gap against individually fine-tuned models.

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.

Spectral Graph Neural Networks (GNNs) achieve strong performance in node classification, yet their node distinguishability remains poorly understood. We analyze how graph matrices and node features jointly influence node distinguishability. Further, we derive a theoretical lower bound on the number of distinguishable nodes, which is governed by two key factors: distinct eigenvalues in the graph matrix and nonzero frequency components of node features in the eigenbasis. Based on these insights, we propose AdaSpec, an adaptive graph matrix generation module that enhances node distinguishability of spectral GNNs without increasing the order of computational complexity. We prove that AdaSpec preserves permutation equivariance, ensuring that reordering the graph nodes results in a corresponding reordering of the node embeddings. Experiments across eighteen benchmark datasets validate AdaSpec's effectiveness in improving node distinguishability of spectral GNNs.

Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through iterative denoising. However, current parallel decoding strategies rely on fixed, input-agnostic heuristics (e.g., confidence thresholds), which fail to adapt to input-specific characteristics, resulting in suboptimal speed-quality trade-offs across diverse NLP tasks. In this work, we explore a more flexible and dynamic approach to parallel decoding. We propose **Learning to Parallel Decode (Learn2PD)**, a framework that trains a lightweight and adaptive filter model to predict, for each token position, whether the current prediction matches the final output. This learned filter approximates an oracle parallel decoding strategy that unmasks tokens only when correctly predicted. Importantly, the filter model is learned in a post-training manner, requiring only a small amount of computation to optimize it (minute-level GPU time). Additionally, we introduce **End-of-Text Prediction (EoTP)** to detect decoding completion at the end of sequence, avoiding redundant decoding of padding tokens. Experiments on the LLaDA benchmark demonstrate that our method achieves up to **22.58×** speedup without any performance drop, and up to **57.51×** when combined with KV-Cache.

Sampling efficiency is a key bottleneck in reinforcement learning with verifiable rewards. Existing group-based policy optimization methods, such as GRPO, allocate a fixed number of rollouts for all training prompts. This uniform allocation implicitly treats all prompts as equally informative, and could lead to inefficient computational budget usage and impede training progress. We introduce VIP, a Variance-Informed Predictive allocation strategy that allocates a given rollout budget to the prompts in the incumbent batch to minimize the expected gradient variance of the policy update. At each iteration, VIP uses a lightweight Gaussian process model to predict per-prompt success probabilities based on recent rollouts. These probability predictions are translated into variance estimates, which are then fed into a convex optimization problem to determine the optimal rollout allocations under a hard compute budget constraint. Empirical results show that VIP consistently improves sampling efficiency and achieves higher performance than uniform or heuristic allocation strategies in multiple benchmarks.

Diffusion models (DMs) have recently shown remarkable performance on inverse problems (IPs). Optimization-based methods can fast solve IPs using DMs as powerful regularizers, but it is susceptible to local minima and noise overfitting. Although DMs can provide strong priors for Bayesian approaches, enforcing measurement consistency during the denoising process leads to manifold infeasibility issues. We propose Noise-space Hamiltonian Monte Carlo (N-HMC), a posterior sampling method that treats reverse diffusion as a deterministic mapping from initial noise to clean images. N-HMC enables comprehensive exploration of the solution space, avoiding local optima. By moving inference entirely into the initial-noise space, N-HMC keeps proposals on the learned data manifold. We provide a comprehensive theoretical analysis of our approach and extend the framework to a noise-adaptive variant (NA-NHMC) that effectively handles IPs with unknown noise type and level. Extensive experiments across four linear and three nonlinear inverse problems demonstrate that NA-NHMC achieves superior reconstruction quality with robust performance across different hyperparameters and initializations, significantly outperforming recent state-of-the-art methods. Code will be made available on GitHub upon publication.

Despite recent advances in state space models (SSMs) such as Mamba across various sequence domains, research on their standalone capacity for time series classification (TSC) has remained limited. We propose MambaSL, a framework that minimally redesigns the selective SSM and projection layers of a single-layer Mamba, guided by four TSC-specific hypotheses. To address benchmarking limitations—restricted configurations, partial University of East Anglia (UEA) dataset coverage, and insufficiently reproducible setups—we re-evaluate 20 strong baselines across all 30 UEA datasets under a unified protocol. Our results show that MambaSL achieves state-of-the-art performance on the UEA benchmark among 21 models, with statistically significant average improvements over baselines while ensuring reproducibility via public checkpoints.

On-the-Fly Category Discovery (OCD) aims to address the limitations of transductive learning and closed-set prediction in category discovery tasks by enabling real-time classification of potential future categories using prior knowledge. Existing OCD approaches typically rely on hash-based encodings that map features into low-dimensional hash spaces and directly classify test samples using these encodings. Despite efforts to mitigate the sensitivity of hash functions during testing, these methods still suffer from severe overestimation of the number of categories. In this work, we thoroughly analyze the practical limitations of current OCD methods and formally identify a performance lower bound for the task. Based on this insight, we reformulate OCD into two sub-tasks: Open-Set Recognition and an Fully Novel OCD setting. For all samples, we employ a soft class thresholding strategy to directly detect known classes, which significantly enhances the deployment feasibility of OCD to downstream tasks. For outlier samples, we propose Adaptive Gaussian Expansion (AGE), a dynamic category discovery method that models the Probability Density Functions (PDF) of different classes to uncover potential novel categories in real time. Extensive experiments across multiple datasets demonstrate that our method achieves state-of-the-art performance.

In this paper, we revisit stochastic gradient descent (SGD) with AdaGrad-type preconditioning. Our contributions are twofold. First, we develop a unified convergence analysis of SGD with adaptive preconditioning under anisotropic or matrix smoothness and noise assumptions. This allows us to recover state-of-the-art convergence results for several popular adaptive gradient methods, including AdaGrad-Norm, AdaGrad, and ASGO/One-sided Shampoo. In addition, we establish the fundamental connection between two recently proposed algorithms, Scion and DASGO, and provide the first theoretical guarantees for the latter. Second, we show that the convergence of methods like AdaGrad and DASGO can be provably accelerated beyond the best-known rates using Nesterov momentum. Consequently, we obtain the first theoretical justification that AdaGrad-type algorithms can simultaneously benefit from both diagonal preconditioning and momentum, which may provide an ultimate explanation for the practical efficiency of Adam.

Deep Reinforcement Learning has achieved remarkable progress in solving NP-hard scheduling problems. However, existing methods primarily focus on optimizing average performance over training instances, overlooking the core objective of solving each individual instance with high quality. While several instance-wise adaptation mechanisms have been proposed, they are test-time approaches only and cannot share knowledge across different adaptation tasks. Moreover, they largely rely on gradient-based optimization, which could be ineffective in dealing with combinatorial optimization problems. We address the above issues by proposing an instance-wise meta-learning framework. It trains a meta model to acquire a generalizable initialization that effectively guides per-instance adaptation during inference, and overcomes the limitations of gradient-based methods by leveraging a derivative-free optimization scheme that is fully GPU parallelizable. Experimental results on representative scheduling problems demonstrate that our method consistently outperforms existing learning-based scheduling methods and instance-wise adaptation mechanisms under various task sizes and distributions.

Irregular multivariate time series (IMTS) are prevalent in critical domains like healthcare and finance, where accurate forecasting is vital for proactive decision-making. However, the asynchronous sampling and irregular intervals inherent to IMTS pose two core challenges for existing methods: (1) how to accurately represent the raw information of irregular time series without introducing data distortion, and (2) how to effectively capture the complex dynamic dependencies between observation points. To address these challenges, we propose the Adaptive Spatio-Temporal Graph Interaction (ASTGI) framework. Specifically, the framework first employs a Spatio-Temporal Point Representation module to encode each discrete observation as a point within a learnable spatio-temporal embedding space. Second, a Neighborhood-Adaptive Graph Construction module adaptively builds a causal graph for each point in the embedding space via nearest neighbor search. Subsequently, a Spatio-Temporal Dynamic Propagation module iteratively updates information on these adaptive causal graphs by generating messages and computing interaction weights based on the relative spatio-temporal positions between points. Finally, a Query Point-based Prediction module generates the final forecast by aggregating neighborhood information for a new query point and performing regression. Extensive experiments on multiple benchmark datasets demonstrate that ASTGI outperforms various state-of-the-art methods.