ICLR 2026 论文列表

Spiking Neural Networks (SNNs) have emerged as an efficient neuromorphic computing paradigm, offering low energy consumption and strong representational capacity through binary spike-based information processing. However, their performance is heavily shaped by the input encoding method. While direct encoding has gained traction for its efficiency and accuracy, it proves less robust than traditional rate encoding. To illuminate this issue, we introduce Gradient Temporal Collinearity (GTC), a principled measure that quantifies the directional alignment of gradient components across time steps, and we show—both empirically and theoretically—that elevated GTC in direct encoding undermines robustness. Guided by this insight, we propose Structured Temporal Orthogonal Decorrelation (STOD), which integrates parametric orthogonal kernels with structured constraints into the input layer of direct encoding to diversify temporal features and effectively reduce GTC. Extensive experiments on visual classification benchmarks, show that STOD consistently outperforms state-of-the-art methods in robustness, highlighting its potential to drive SNNs toward safer and more reliable deployment.

We study the problem of online learning in Stackelberg games with side information between a leader and a sequence of followers. In every round the leader observes contextual information and commits to a mixed strategy, after which the follower best-responds. We provide learning algorithms for the leader which achieve O(T^{1/2}) regret under bandit feedback, an improvement from the previously best-known rates of O(T^{2/3}). Our algorithms rely on a reduction to linear contextual bandits in the utility space: In each round, a linear contextual bandit algorithm recommends a utility vector, which our algorithm inverts to determine the leader's mixed strategy. We extend our algorithms to the setting in which the leader's utility function is unknown, and also apply it to the problems of bidding in second-price auctions with side information and online Bayesian persuasion with public and private states. Finally, we observe that our algorithms empirically outperform previous results on numerical simulations.

Speech emotion recognition (SER) hinges on front-ends that expose informative time-frequency (TF) structure from raw speech. Classical short-time Fourier and wavelet transforms impose fixed resolution trade-offs, while prior "superlet" variants rely on integer orders and hand-tuned hyperparameters. We revisit TF analysis from first principles and formulate a learnable continuum of superlet transforms. Starting from DC-corrected analytic Morlet wavelets, we define superlets as multiplicative ensembles of wavelet responses and realize learnable fractional orders via softmax-normalized weights over discrete orders, computed as a log-domain geometric mean. We establish admissibility (zero mean) and continuity in order and frequency, and characterize approximate analyticity by bounding negative-frequency leakage as a function of an effective cycle parameter. Building on these results, we introduce the Learnable Fractional Superlet Transform (LFST), a fully differentiable front-end that jointly optimizes (i) a monotone, log-spaced frequency grid, (ii) frequency-dependent base cycles, and (iii) learnable fractional-order weights, all trained end-to-end. LFST further includes a learnable asymmetric hard-thresholding (LAHT) module that promotes sparse, denoised TF activations while preserving transients; we provide sufficient conditions for boundedness and stability under mild cycle and grid constraints. To exploit LFST for SER, we design the Spectro-Temporal Emotion Encoder (STEE), which consumes two-channel TF maps, magnitude $S$ and phase-congruency $\kappa$, through a compact multi-scale stack with residual temporal and depthwise-frequency blocks, Adaptive FiLM gating, axial (time-axis) self-attention, global attentive pooling, and a lightweight classifier. The full LFST+STEE system is trained in a standard train-validate-test regime using focal loss with optional class rebalancing, and is validated on IEMOCAP, EMO-DB, and the private NSPL-CRISE dataset under standard protocols. By unifying a principled, learnable TF transform with a compact encoder, LFST+STEE replaces ad hoc front-ends with a mathematically grounded alternative that is differentiable, stable, and adaptable to data, enabling systematic ablations over frequency grids, cycle schedules, and fractional orders within a single end-to-end model. The source code for this paper is shared in this anonymous repository: https://anonymous.4open.science/r/LFST-for-SER-C5D2.

Objective assessment of audio source‑separation systems still mismatches subjective human perception, especially when interference from competing talkers and distortion of the target signal interact. We introduce Perceptual Separation (PS) and Perceptual Match (PM), a complementary pair of measures that, by design, isolate these leakage and distortion factors. Our intrusive approach generates a set of fundamental distortions, e.g., clipping, notch filter, and pitch shift from each reference waveform signal in the mixture. Distortions, references, and system outputs from all sources are independently encoded by a pre-trained self-supervised model, then aggregated and embedded with a manifold learning technique called diffusion maps, which aligns Euclidean distances on the manifold with dissimilarities of the encoded waveform representations. On this manifold, PM captures the self‑distortion of a source by measuring distances from its output to its reference and associated distortions, while PS captures leakage by also accounting for distances from the output to non‑attributed references and distortions. Both measures are differentiable and operate at a resolution as high as 75 frames per second, allowing granular optimization and analysis. We further derive, for both measures, frame-level deterministic error radius and non-asymptotic, high-probability confidence intervals. Experiments on English, Spanish, and music mixtures show that, against 14 widely used measures, the PS and PM are almost always placed first or second in linear and rank correlations with subjective human mean-opinion scores.

Molecular conformer generation is a fundamental task for drug discovery and material design. Although deep generative models have progressed in this area, existing methods often overlook the hierarchical structural organization inherent to molecules, leading to poor-quality generated conformers. To address this challenge, we demonstrate that capturing the spatial arrangement of key substructures, such as scaffolds, is essential, as they serve as anchors that define the overall molecular distribution. In this paper, we propose a hierarchical multi-scale molecular conformer generation framework (MSGEN), designed to enhance key substructure awareness by leveraging spatially informed guidance. Our framework initiates the generation process from coarse-grained key substructures, progressively refining the conformer by utilizing these coarser-scale structures as conditional guidance for subsequent finer-scale stages. To bridge scale discrepancies between stages, we introduce a molecular upsampling technique that aligns the structural scales, ensuring smooth propagation of geometric guidance. Extensive experiments on standard benchmarks demonstrate that our framework integrates seamlessly with a wide range of existing molecular generative models and consistently generates more stable and chemically plausible molecular conformers.

Many black-box techniques for quantifying the uncertainty of large language models (LLMs) rely on repeated LLM sampling, which can be computationally expensive. Therefore, practical applicability demands reliable estimation from few samples. Semantic entropy (SE) is a popular sample-based uncertainty estimator with a discrete formulation attractive for the black-box setting. Recent extensions of SE exhibit improved LLM hallucination detection, but do so with less interpretable methods that admit additional hyperparameters. For this reason, we revisit the canonical discrete semantic entropy (DSE) estimator, finding that it underestimates the ``true'' semantic entropy, as expected from theory. We propose a modified semantic alphabet size estimator, and illustrate that using it to adjust DSE for sample coverage results in more accurate SE estimation in our setting of interest. Furthermore, we find that two semantic alphabet size estimators, including our proposed, flag incorrect LLM responses as well or better than many top-performing alternatives, with the added benefit of remaining highly interpretable.

Diffusion Transformers (DiTs) have emerged as powerful generative models, but their iterative denoising structure and deep transformer blocks incur substantial computational overhead, limiting the accessibility and practical deployment of high-quality video generation. To address this bottleneck, we propose ScalingCache, a training-free acceleration framework specifically designed for DiTs. ScalingCache exploits the inherent redundancy in model representations by performing lightweight offline analysis on a small number of samples and dynamically reusing previously computed activations during inference, thereby avoiding full computation at certain denoising steps. Experimental results demonstrate that ScalingCache achieves significant acceleration in both image and video generation tasks while maintaining near-lossless generation quality. On widely used video generation models including Wan2.1 and HunyuanVideo, it achieves approximately 2.5$\times$ acceleration with only 0.5$\%$ drop in VBench scores; on FLUX, it achieves 3.1$\times$ near-lossless acceleration, with human preference tests showing comparable quality to original outputs. Moreover, under similar acceleration ratios, ScalingCache outperforms prior state-of-the-art caching strategies, achieving a 45$\%$ reduction in LPIPS for text-to-image generation and 20$-$30$\%$ reduction for text-to-video generation, highlighting its superior fidelity preservation.

Adversarial samples exploit irregularities in the manifold "learned" by deep learning models to cause misclassifications. The study of these adversarial samples provides insight into the features a model uses to classify inputs, which can be leveraged to improve robustness against future attacks. However, much of the existing literature focuses on constrained adversarial samples, which do not accurately reflect test-time errors encountered in real-world settings. To address this, we propose `NatADiff', an adversarial sampling scheme that leverages denoising diffusion to generate natural adversarial samples. Our approach is based on the observation that natural adversarial samples frequently contain structural elements from the adversarial class. Deep learning models can exploit these structural elements to shortcut the classification process, rather than learning to genuinely distinguish between classes. To leverage this behavior, we guide the diffusion trajectory towards the intersection of the true and adversarial classes, combining time-travel sampling with augmented classifier guidance to enhance attack transferability while preserving image quality. Our method achieves comparable white-box attack success rates to current state-of-the-art techniques, while exhibiting significantly higher transferability across model architectures and improved alignment with natural test-time errors as measured by FID. These results demonstrate that NatADiff produces adversarial samples that not only transfer more effectively across models, but more faithfully resemble naturally occurring test-time errors when compared with other generative adversarial sampling schemes.

Large language models excel with reinforcement learning (RL), but fully unlocking this potential requires a mid-training stage. Intuitively, an effective mid-training stage should both learn a strong policy prior and enable fast learning through online interactions. We formalize this intuition by presenting the first theoretical result on how mid-training shapes post-training: it acquires strong policy priors by efficiently pruning the action space and accelerates RL convergence by shortening the effective planning horizon. Moreover, we prove that temporal abstractions simultaneously compress the size of the action set and reduce the decision horizon, thereby improving regret minimization after training. Building on these insights, we introduce Reasoning as Action Abstractions (RA3), a scalable mid-training algorithm. Specifically, we derive a temporal variational bound and optimize it by iteratively discovering temporally-consistent latent structures via RL, then fine-tuning on the bootstrapped data. Experiments on code generation tasks demonstrate the effectiveness of our approach. Across multiple base models, RA3 improves the average performance on HumanEval and MBPP by 8 and 4 points over the base model and the next-token prediction baseline. Furthermore, RA3 achieves faster convergence and higher asymptotic performance in RLVR on HumanEval+, MBPP+, LiveCodeBench, and Codeforces.

Generalist robot policies, trained on large and diverse datasets, have demonstrated the ability to generalize across a wide spectrum of behaviors, enabling a single policy to act in varied real-world environments. However, they still fall short on new tasks not covered in the training data. When finetuned on limited demonstrations of a new task, these policies often overfit to the specific demonstrations---not only losing their prior abilities to solve a wide variety of generalist tasks but also failing to generalize within the new task itself. In this work, we aim to develop a method that preserves the generalization capabilities of the generalist policy during finetuning, allowing a single policy to robustly incorporate a new skill into its repertoire. Our goal is a single policy that both learns to generalize to variations of the new task and retains the broad competencies gained from pretraining. We show that this can be achieved through a simple yet effective strategy: interpolating the weights of a finetuned model with that of the pretrained model. We show, across extensive simulated and real-world experiments, that such model merging produces a single model that inherits the generalist abilities of the base model and learns to solve the new task robustly, outperforming both the pretrained and finetuned model on out-of-distribution variations of the new task. Moreover, we show that model merging enables continual acquisition of new skills in a lifelong learning setting, without sacrificing previously learned generalist abilities.

Inverse Reinforcement Learning aims to recover reward models from expert demonstrations, but traditional methods yield black-box models that are difficult to interpret and debug. In this work, we introduce GRACE (**G**enerating **R**ewards **A**s **C**od**E**), a method for using Large Language Models within an evolutionary search to reverse-engineer an interpretable, code-based reward function directly from expert trajectories. The resulting reward function is executable code that can be inspected and verified. We empirically validate GRACE on the MuJoCo, BabyAI and AndroidWorld benchmarks, where it efficiently learns highly accurate rewards, even in complex, multi-task settings. Further, we demonstrate that the resulting reward leads to strong policies, compared to both competitive Imitation Learning and online RL approaches with ground-truth rewards. Finally, we show that GRACE is able to build complex reward APIs in multi-task setups.

Recent years have witnessed remarkable progress in multimodal learning within computational pathology. Existing models primarily rely on vision and language modalities; however, language alone lacks molecular specificity and offers limited pathological supervision, leading to representational bottlenecks. In this paper, we propose STAMP, a Spatial Transcriptomics-Augmented Multimodal Pathology representation learning framework that integrates spatially-resolved gene expression profiles to enable molecule-guided joint embedding of pathology images and transcriptomic data. Our study shows that self-supervised, gene-guided training provides a robust and task-agnostic signal for learning pathology image representations. Incorporating spatial context and multi-scale information further enhances model performance and generalizability. To support this, we constructed SpaVis-6M, the largest Visium-based spatial transcriptomics dataset to date, and trained a spatially-aware gene encoder on this resource. Leveraging hierarchical multi-scale contrastive alignment and cross-scale patch localization mechanisms, STAMP effectively aligns spatial transcriptomics with pathology images, capturing spatial structure and molecular variation. We validate STAMP across six datasets and four downstream tasks, where it consistently achieves strong performance. These results highlight the value and necessity of integrating spatially resolved molecular supervision for advancing multimodal learning in computational pathology. The code is included in the supplementary materials. The pretrained weights and SpaVis-6M will be released for community development after reviewing the manuscript.

The proliferation of Large Language Models (LLMs) in function calling is pivotal for creating advanced AI agents, yet their large scale hinders widespread adoption, necessitating transferring their capabilities into smaller ones. However, existing paradigms are often plagued by overfitting, training instability, ineffective binary rewards for multi-solution tasks, and the difficulty of synergizing techniques. We introduce STAR: Similarity-guided Teacher-Assisted Refinement, a novel holistic framework that effectively transfers LLMs' capabilities to super-tiny models. STAR consists of two core technical innovations: (1) Constrained Knowledge Distillation (CKD), a training objective that augments top-k forward KL divergence to suppress confidently incorrect predictions, ensuring training stability while preserving exploration capacity for downstream RL. STAR holistically synergizes these strategies within a cohesive training curriculum, enabling super-tiny models to achieve exceptional performance on complex function calling tasks; (2) Similarity-guided RL (Sim-RL), a RL mechanism that introduces a fine-grained, similarity-based reward. This provides a robust, continuous, and rich signal for better policy optimization by evaluating the similarity between generated outputs and the ground truth. Extensive experiments on challenging and renowned benchmarks demonstrate the effectiveness of our method. Our STAR models establish SOTA in their size classes, significantly outperforming baselines. Remarkably, our 0.6B STAR model achieves the best performance among all open models under 1B, surpassing even several well-known open models at a larger scale. STAR demonstrates a training framework that distills capabilities of LLMs into super-tiny models, paving the way for powerful, accessible, and efficient AI agents.

Large time series models (LTMs) have recently demonstrated powerful capabilities for universal forecasting. However, these models still struggle to address the variety and nonstationarity of time series, resulting in an unsatisfying balance between forecasting performance and generalizability. Instead of breeding unceasingly new models for diverse domains, this paper proposes a novel framework, time-series adaptive transformation optimization (TATO), that enables a frozen pre-trained LTM to fit various downstream domains through an empirically optimal time-series transformation pipeline. Three representative types of time series transformations, including context slicing, scale normalization, and outlier correction, are constructed to help LTMs fit the target domain. A two-stage ranking is also designed to ensure the optimization's robustness by filtering out transformation pipelines with shortcomings in specific metrics. Extensive evaluations on state-of-the-art pre-trained LTMs and widely used datasets demonstrate that TATO performs universally well and significantly enhances domain-adaptive forecasting performance, achieving a maximum MSE reduction of 68.4% and an average decrease of 16.0%. In most cases, the time required by TATO to optimize time series transformation pipelines is under 2 minutes, making it practical for real-world applications. We have published the source code of TATO at https://anonymous.4open.science/r/TATO-D55C.

A key step in protein optimization is modeling the fitness landscape, which maps proteins to functional assay readouts. Existing methods typically either use property-agnostic likelihoods/embeddings from pretrained protein language models (PLMs) for fitness prediction, or assume independent mutational effects, limiting their ability to capture higher-order interactions. In this work, we introduce RankFlow, a conditional flow framework that refines PLM representations to be a property-aligned distribution via a tailored energy function and captures multi-mutation interactions through learnable embeddings. To align optimization with evaluation protocols, we propose the Rank-Consistent Conditional Flow Loss (RC$^2$), a differentiable ranking objective that enforces the correct order of mutants rather than absolute values, which improves out-of-distribution generalization. Finally, we introduce a Property-guided Steering Gate (PSG) that concentrates learning on positions carrying signals for the target property while suppressing unrelated evolutionary biases. Across ProteinGym, PEER, and FLIP benchmarks, RankFlow obtains state-of-the-art ranking accuracy and stronger generalization.

Multi-view clustering improves clustering performance by integrating complementary information from multiple views. However, existing methods often suffer from two limitations: i) the neglect of preserving sample neighborhood structures, which weakens the consistency of inter-sample relationships across views; and ii) inability to adaptively utilize inter-view similarity, resulting in representation conflicts and semantic degradation. To address these issues, we propose a novel framework named Relationship Alignment for View-aware Multi-view Clustering (RAV). Our approach first constructs a sample relationship matrix based on the deep features of each view and aligns it with the global relationship matrix to enhance neighborhood consistency across views and facilitate the accurate measurement of inter-view similarity. Simultaneously, we introduce a view-aware adaptive weighting mechanism for label contrastive learning. This mechanism dynamically adjusts the contrastive intensity between view pairs based on the similarity of their deep features: higher-similarity views lead to stronger label alignment, while lower-similarity views reduce the weighting to prevent forcing inconsistent views into agreement. This strategy effectively promotes cluster-level semantic consistency while preserving natural inter-view relationships. Extensive experiments demonstrate that our method consistently outperforms state-of-the-art approaches on multiple benchmark datasets.

Reinforcement learning (RL) based on the final answer's reward has driven recent progress in small language models (SLMs) on reasoning-heavy tasks such as math and code. However, applying the same techniques to retrieval-augmented generation (RAG) benchmarks like multi-hop QA has yielded limited gains—often trailing supervised or prompting-only baselines. Instead, we argue that a viable path for RL in multi-hop QA is to use test-time scaling judiciously, for optimizing both the final answer accuracy and the efficiency in reaching that answer. We propose FrugalRAG, a two-stage finetuning framework that adaptively _reduces_ the number of retrieval steps based on a question's difficulty. First, we train an SLM with supervised finetuning on a full-exploration policy that generates broad sub-queries. Then, we apply RL to adaptively prune search depth based on question difficulty, directly rewarding policies that balance correctness with frugality. Unlike prior approaches requiring 10× more data, our method achieves competitive performance with only ~1,000 examples. On HotPotQA and other multi-hop QA benchmarks, FrugalRAG attains state-of-the-art efficiency–accuracy tradeoffs, cutting retrieval cost nearly in half. Moreover, on the challenging BrowseCompPlus benchmark, it surpasses SLM-based and other baselines after training on only 200 examples. These results demonstrate the use of RL—not to increase reasoning steps but to reduce them—as an effective solution for scalable, efficient RAG.

Inference-time control of diffusion models aims to steer model outputs to satisfy new constraints without retraining. Previous approaches have mostly relied on heuristic guidance or have been coupled with Sequential Monte Carlo (SMC) for bias correction. In this paper, we propose a flexible alternative based on replica exchange, an algorithm designed initially for sampling problems. We refer to this method as the CREPE (Controlling with REPlica Exchange). Unlike SMC, CREPE: (i) generates particles sequentially, (ii) maintains high diversity in the generated samples after a burn-in period, and (iii) enables online refinement or early termination. We demonstrate its versatility across various tasks, including temperature annealing, reward tilting, model composition and classifier-free guidance debiasing, with competitive performance compared to prior SMC methods.

Text summarization is a core task in natural language processing (NLP). With the rapid growth of information, handling long documents has become increasingly demanding, making summarization essential. Existing research mainly focuses on model improvements and sentence-level pruning, but often overlooks global structure, leading to disrupted coherence and weakened downstream performance. Some studies employ large language models (LLMs), which achieve higher accuracy but incur substantial resource and time costs. To address these issues, this paper introduces the first summarization method based on global structure awareness using topological data analysis (TDA). The method summarizes text efficiently while preserving semantic cores and logical dependencies. Specifically, we construct a semantic-weighted graph from sentence embeddings, where persistent homology identifies core semantics and logical structures, preserved in a ``protection pool'' as the backbone for summarization. We design a topology-guided iterative strategy, where lightweight proxy metrics approximate sentence importance to avoid repeated high-cost computations, thus preserving structural integrity while improving efficiency. To further enhance long-text processing, we propose a hierarchical strategy that integrates segment-level and global summarization. Experiments on multiple datasets demonstrate that GloSA-sum reduces redundancy while preserving semantic and logical integrity, striking a balance between accuracy and efficiency, and further benefits LLM downstream tasks by shortening contexts while retaining essential reasoning chains.