ICLR 2026 论文列表

When model predictions inform downstream decisions, a natural question is under what conditions can the decision-makers simply respond to the predictions as if they were the true outcomes. The recently proposed notion of decision calibration addresses this by requiring predictions to be unbiased conditional on the best-response actions induced by the predictions. This relaxation of classical calibration avoids the exponential sample complexity in high-dimensional outcome spaces. However, existing guarantees are limited to linear losses. A natural strategy for nonlinear losses is to embed outcomes $y$ into an $m$-dimensional feature space $\phi(y)$ and approximate losses linearly in $\phi(y)$. Yet even simple nonlinear functions can demand exponentially large or infinite feature dimensions, raising the open question of whether decision calibration can be achieved with complexity independent of the feature dimension $m$. We begin with a negative result: even verifying decision calibration under standard deterministic best response inherently requires sample complexity polynomial in $m$. To overcome this barrier, we study a smooth variant where agents follow quantal responses. This smooth relaxation admits dimension-free algorithms: given $\mathrm{poly}(|\mathcal{A}|,1/\epsilon)$ samples and any initial predictor $p$, our introducded algorithm efficiently test and achieve decision calibration for broad function classes which can be well-approximated by bounded-norm functions in (possibly infinite-dimensional) separable RKHS, including piecewise linear and Cobb–Douglas loss functions.

The message passing–readout framework has become the de facto standard of graph neural networks (GNNs) for material property prediction. However, most existing readout functions are built on an atom-decomposable inductive bias, i.e. the material-level property or feature can be reasonably assigned to contributions of individual atoms. This is a strong bias and may not hold for all properties, limiting the application scenarios (e.g. gas adsorption or separation of Metal Organic Frameworks, MOFs). In this work, we propose a region-based decomposition perspective, reformulating material properties as integrals over space and pooling contributions from spatial regions rather than atoms. Specifically, we propose a novel readout function named SpatialRead. SpatialRead introduces additional spatial nodes to represent a voxelized space, transforming the atomic isomorphic graph into a heterogeneous atom–space graph with unidirectional message flow from atoms to spatial nodes. To combine the two types of inductive bias, multimodal methods can be used to fuse the features of atoms the spatial nodes. Such a region-based readout function is especially suited for spatial properties such as gas adsorption capacity, separation ratio. Extensive experiments demonstrate that a simple PaiNN–Transformer-based SpatialRead trained from scratch outperforms state-of-the-art pre-trained foundation models on these special tasks. Our results highlight the importance of designing physically grounded readout functions tailored to the target property. The code and dataset can be found in github https://github.com/nankusa/SpatialRead.

Multimodal large language models built on the Mamba architecture offer efficiency advantages, yet remain hampered by redundant visual tokens that inflate inference cost, with the prefill stage accounting for the majority of total inference time. We introduce Delta-guided Two stage Pruning (DTP), a method that progressively reduces token redundancy through selective pruning at early layer and complete pruning at late layer. Unlike Transformer-oriented pruning methods, our approach derives token importance directly from Mamba’s internal parameters. The statistical distribution of these importance scores, combined with implicit attention patterns, then provides the basis for determining both the pruning layers and the tokens to be removed. Extensive evaluation across diverse benchmarks shows that DTP cuts computation by nearly 50\%, maintains higher task performance than existing pruning methods, and further achieves over a 35\% reduction in prefill latency. Beyond efficiency, our analysis reveals previously underexplored behaviors of visual tokens within Mamba layers, suggesting a principled perspective for designing future pruning techniques in Mamba-based Multimodal Large Language Models.

Boolean functions constitute a fundamental object of study in machine learning and, more broadly, in theoretical computer science. Among their various complexity measures, Fourier sparsity, defined as the number of nonzero Fourier coefficients in a Boolean function’s Fourier expansion, serves as a key indicator of structural simplicity. For over three decades, learning Boolean functions with sparse Fourier representations has been a central focus of computational learning theory. A notable achievement in this line of work is the development of learning algorithms whose complexity primarily depends on the Fourier sparsity parameter. However, these approaches generally assume prior knowledge of this parameter. In this work, we address this gap in the literature on learning Fourier-sparse Boolean functions. Specifically, we study the problem of Fourier sparsity testing: given query access to a Boolean function $f : \mathbb{F}_2^n \to \{-1, +1\}$, decide whether it is $s$-Fourier sparse or far (under Hamming distance) from every such function. Our contributions are twofold. On the algorithmic side, we design a new tester with query complexity $\widetilde{O}(s^4)$, independent of the ambient dimension. On the lower bound side, we prove that any tester requires at least $\Omega(s)$ queries. Both bounds improve upon the best known results of Gopalan et al.\ (SICOMP 2011), who presented a tester with query complexity $\widetilde{O}(s^{14})$ and a lower bound of $\Omega(\sqrt{s})$. For our upper bound, we introduce a refined notion of a sampler from the junta testing framework of Chakraborty et al.\ (ICALP 2011) and combine it with $\ell_1$-minimization-based compressed sensing techniques to construct our tester. In the process, we develop a novel method for sampling the leaves of parity decision trees associated with Fourier-sparse Boolean functions. The lower bound is obtained via a reduction from communication complexity, crucially leveraging structural properties of the Fourier coefficients of a specific class of cryptographically hard functions.

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.

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.

The human brain exhibits remarkable efficiency in processing sequential information, a capability deeply rooted in the temporal selectivity and stochastic competition of neuronal activation. Current continual learning in spiking neural networks (SNNs) faces a critical challenge: balancing task-specific selectivity with adaptive resource allocation and enhancing the robustness with perturbations to mitigate catastrophic forgetting. Considering the intrinsic temporal dynamics of spiking neurons instead of traditional K-winner-take-all (K-WTA) based on firing rate, we explore how to leave networks robust to temporal perturbations in SNNs on lifelong learning tasks. In this paper, we propose Randomized Temporal K-winner-take-all (RTK-WTA) SNNs for lifelong learning, a biologically grounded approach that integrates trace-dependent neuronal activation with probabilistic top-k selection. By dynamically prioritizing neurons based on their spatiotemporal relevance, RTK-WTA SNNs emulate the brain’s ability to modulate neural resources in spatial and temporal dimensions while introducing controlled randomness to prevent overlapping task representations. The proposed RTK-WTA SNNs enhance inter-class margins and robustness through expanded feature space utilization theoretically. The experimental results show that RTK-WTA surpasses deterministic K-WTA by 3.07–5.0\% accuracy on splitMNIST and splitCIFAR100 with elastic weight consolidation. Controlled stochasticity balances temporal coherence and adaptability, offering a scalable framework for lifelong learning in neuromorphic systems.

Network alignment (NA) aims to identify node correspondence across different networks and serves as a critical cornerstone behind various downstream multi-network learning tasks. Despite growing research in NA, there lacks a comprehensive library that facilitates the systematic development and benchmarking of NA methods. In this work, we introduce PLANETALIGN, a comprehensive Python library for network alignment that features a rich collection of built-in datasets, methods, and evaluation pipelines with easy-to-use APIs. Specifically, PLANETALIGN integrates 18 datasets and 14 NA methods with extensible APIs for easy use and development of NA methods. Our standardized evaluation pipeline encompasses a wide range of metrics, enabling a systematic assessment of the effectiveness, scalability, and robustness of NA methods. Through extensive comparative studies, we reveal practical insights into the strengths and limitations of existing NA methods. We hope that PLANETALIGN can foster a deeper understanding of the NA problem and facilitate the development and benchmarking of more effective, scalable, and robust methods in the future. The The source code of PLANETALIGN is available at https://anonymous.4open.science/r/PlanetAlign-E9BA

Large language models (LLMs) with Process Reward Models (PRMs) have shown strong reasoning ability, yet their potential in Operations Research (OR) remains unexplored. We present the first PRM tailored for OR, but find that directly training on mainstream datasets yields surprisingly weak performance. To understand this gap, we conduct a systematic analysis and identify the primary bottleneck: the datasets themselves, where over 30\% of annotations are severely flawed. To overcome these limitations, we first collect all existing synthetic datasets and apply a carefully designed filtering pipeline to construct a high-quality seed dataset. Building upon this seed, we then build OR-ProcessQA, the first large-scale dataset for OR with step-by-step supervision, where diverse solution pathways are generated via Monte Carlo Tree Search (MCTS) and each step is validated for logical consistency by GPT-4o. Building on this foundation, we train OR-PRM, the first Process Reward Model in the OR domain, designed to evaluate and guide reasoning at every step rather than only the final outcome. Together, these advances enable OR-PRM to substantially improve LLMs’ reasoning capability, achieving a maximum absolute improvement of 12.5\% over the base model in Best-of-N settings, and highlighting the power of process-oriented supervision for reliable problem solving in operations research.

In this paper, we propose a rotation-constrained compensation method to address the errors introduced by structured pruning of large language models (LLMs). LLMs are trained on massive datasets and accumulate rich semantic knowledge in their representation space. In contrast, pruning is typically carried out with only a small amount of calibration data, which makes output mismatches unavoidable. Although direct least-squares fitting can reduce such errors, it tends to overfit to the limited calibration set, destructively modifying pretrained weights. To overcome this difficulty, we update the pruned parameters under a rotation constraint. This constrained update preserves the geometry of output representations (i.e., norms and inner products) and simultaneously re-aligns the pruned subspace with the original outputs. Furthermore, in rotation-constrained compensation, removing components that strongly contribute to the principal directions of the output makes error recovery difficult. Since input dimensions with large variance strongly affect these principal directions, we design a variance-aware importance score that ensures such dimensions are preferentially kept in the pruned model. By combining this scoring rule with rotation-constrained updates, the proposed method effectively compensates errors while retaining the components likely to be more important in a geometry-preserving manner. In the experiments, we apply the proposed method to Llama-7B and Llama-2-13B, and evaluate it on WikiText-2 and multiple language understanding benchmarks. The results demonstrate consistently better perplexity and task accuracy compared with existing baselines. Codes are available at \url{https://anonymous.4open.science/r/anonymous-llm-pruning-D884/}.

Accurate crowd simulation is crucial for public safety management, emergency evacuation planning, and intelligent transportation systems. However, existing methods, which typically model crowds as a collection of independent individual trajectories, are limited in their ability to capture macroscopic physical laws. This microscopic approach often leads to error accumulation and compromises simulation stability. Furthermore, deep learning-driven methods tend to suffer from low inference efficiency and high computational overhead, making them impractical for large-scale, efficient simulations. To address these challenges, we propose the Spatio-Temporal Decoupled Differential Equation Network (STDDN), a novel framework that guides microscopic trajectory prediction with macroscopic physics. We innovatively introduce the continuity equation from fluid dynamics as a strong physical constraint. A Neural Ordinary Differential Equation (Neural ODE) is employed to model the macroscopic density evolution driven by individual movements, thereby physically regularizing the microscopic trajectory prediction model. We design a density-velocity coupled dynamic graph learning module to formulate the derivative of the density field within the Neural ODE, effectively mitigating error accumulation. We also propose a differentiable density mapping module to eliminate discontinuous gradients caused by discretization and introduce a cross-grid detection module to accurately model the impact of individual cross-grid movements on local density changes. The proposed STDDN method has demonstrated significantly superior simulation performance compared to state-of-the-art methods on long-term tasks across four real-world datasets, as well as a major reduction in inference latency.

Large Language Models are prone to memorizing sensitive, copyrighted, or hazardous content, posing significant privacy and legal concerns. Retraining from scratch is computationally infeasible, whereas current unlearning methods exhibit unstable trade-offs between forgetting and utility, frequently producing incoherent outputs on forget prompts and failing to generalize due to the persistence of lexical-level and semantic-level associations in attention. We propose Attention Smoothing Unlearning (ASU), a principled framework that casts unlearning as self-distillation from a forget-teacher derived from the model’s own attention. By increasing the softmax temperature, ASU flattens attention distributions and directly suppresses the lexical-level and semantic-level associations responsible for reconstructing memorized knowledge. This results in a bounded optimization objective that erases factual information yet maintains coherence in responses to forget prompts. Empirical evaluation on TOFU, MUSE, and WMDP, along with real-world and continual unlearning scenarios across Question Answering (QA) and text completion, demonstrates that ASU outperforms the baselines for most of the unlearning scenarios, delivering robust unlearning with minimal loss of model utility.

Recent neural solvers have demonstrated promising performance in learning to solve routing problems. However, existing studies are primarily based on one-off training on one or a set of predefined problem distributions and scales, i.e., tasks. When a new task arises, they typically rely on either zero-shot generalization, which may be poor due to the discrepancies between the new task and the training task(s), or fine-tuning the pretrained solver on the new task, which possibly leads to catastrophic forgetting of knowledge acquired from previous tasks. This paper explores a novel lifelong learning paradigm for neural VRP solvers, where multiple tasks with diverse distributions and scales arise sequentially over time. Solvers are required to effectively and efficiently learn to solve new tasks while maintaining their performance on previously learned tasks. Consequently, a novel framework called Lifelong Learning Router with Behavior Consolidation (LLR-BC) is proposed. LLR-BC consolidates prior knowledge effectively by aligning behaviors of the solver trained on a new task with the buffered ones in a decision-seeking way. To encourage more focus on crucial experiences, LLR-BC assigns greater consolidated weights to decisions with lower confidence. Extensive experiments on capacitated vehicle routing problems and traveling salesman problems demonstrate LLR-BC’s effectiveness in training high-performance neural solvers in a lifelong learning setting, addressing the catastrophic forgetting issue, maintaining their plasticity, and improving zero-shot generalization ability.

Denoising diffusions sample from a probability distribution $\mu$ in $\mathbb{R}^d$ by constructing a stochastic process $(\hat{\mathbf{x}}_t:t\ge 0)$ in $\mathbb{R}^d$ such that $\hat{\mathbf{x}}_0$ is easy to sample, but the distribution of $\hat{\mathbf{x}}_T$ at large $T$ approximates $\mu$. The drift $\mathbf{m}:\mathbb{R}^{d}\times\mathbb{R}\to\mathbb{R}^d$ of this diffusion process is learned by minimizing a score-matching objective. Is every probability distribution $\mu$, for which sampling is tractable, also amenable to sampling via diffusions? We address this question by studying its relation to information-computation gaps in statistical estimation. Earlier work in this area constructs broad families of distributions $\mu$ for which sampling is easy, but approximating the drift $\mathbf{m}(\mathbf{y},t)$ is conjectured to be intractable, and provides rigorous evidence for intractability. We prove that this implies a failure of sampling via diffusions. First, there exist drifts whose score matching objective is superpolynomially close to the optimum value (among polynomial time drifts) and yet yield samples with distribution that is very far from the target one. Second, any polynomial-time drift that is also Lipschitz continuous results in equally incorrect sampling. We instantiate our results on the toy problem of sampling a sparse low-rank matrix, and further demonstrate empirically the failure of diffusion-based sampling. Our work implies that caution should be used in adopting diffusion sampling when other approaches are available.

Large language models remain vulnerable to jailbreak attacks, inputs crafted to bypass safety mechanisms and elicit harmful responses, despite advances in alignment and instruction tuning. Existing attacks often rely on prompt rewrites, dense optimization, or ad hoc heuristics, and lack interpretability and robustness. We propose **Head-Masked Nullspace Steering (HMNS)**, a circuit-level intervention that (i) identifies attention heads most causally responsible for a model’s default behavior, (ii) suppresses their write paths via targeted column masking, and (iii) injects a perturbation constrained to the orthogonal complement of the muted subspace. This geometry-aware intervention preserves fluency while steering the model toward completions that differ from baseline routing. HMNS operates in a closed-loop detection–intervention cycle, re-identifying causal heads and reapplying interventions across multiple decoding attempts. Across multiple jailbreak benchmarks, strong safety defenses, and widely used language models, HMNS attains state-of-the-art attack success rates with fewer queries than prior methods. Ablations confirm that nullspace-constrained injection, residual norm scaling, and iterative re-identification are key to its effectiveness. To our knowledge, this is the first jailbreak method to leverage geometry-aware, interpretability-informed interventions, highlighting a new paradigm for controlled model steering and adversarial safety circumvention.

Learning PDE dynamics with neural solvers can significantly improve wall-clock efficiency and accuracy compared with classical numerical solvers. In recent years, foundation models for PDEs have largely adopted multi-scale windowed self-attention, with the scOT backbone in Poseidon serving as a representative example. However, because of their locality, truly globally consistent spectral coupling can only be propagated gradually through deep stacking and window shifting. This weakens global coupling and leads to error accumulation and drift during closed-loop rollouts. To address this, we propose DRIFT-Net. It employs a dual-branch design comprising a spectral branch and an image branch. The spectral branch is responsible for capturing global, large-scale low-frequency information, whereas the image branch focuses on local details and nonstationary structures. Specifically, we first perform controlled, lightweight mixing within the low-frequency range. Then we fuse the spectral and image paths at each layer via bandwise weighting, which avoids the width inflation and training instability caused by naive concatenation. The fused result is transformed back into the spatial domain and added to the image branch, thereby preserving both global structure and high-frequency details across scales. Compared with strong attention-based baselines, DRIFT-Net achieves lower error and higher throughput with fewer parameters under identical training settings and budget. On Navier--Stokes benchmarks, the relative $L_{1}$ error is reduced by 7%-54%, the parameter count decreases by about 15%, and the throughput remains higher than scOT. Ablation studies and theoretical analyses further demonstrate the stability and effectiveness of this design. The code is available at https://anonymous.4open.science/r/DRIFT-Net-26D6.

For overparameterized linear regression with isotropic Gaussian design and minimum-$\ell_p$ interpolator $p\in(1,2]$, we give a unified, high-probability characterization for the scaling of the family of parameter norms $ \\{ \lVert \widehat{w_p} \rVert_r \\}_{r \in [1,p]} $ with sample size. We solve this basic, but unresolved question through a simple dual-ray analysis, which reveals a competition between a signal *spike* and a *bulk* of null coordinates in $X^\top Y$, yielding closed-form predictions for (i) a data-dependent transition $n_\star$ (the "elbow"), and (ii) a universal threshold $r_\star=2(p-1)$ that separates $\lVert \widehat{w_p} \rVert_r$'s which plateau from those that continue to grow with an explicit exponent. This unified solution resolves the scaling of *all* $\ell_r$ norms within the family $r\in [1,p]$ under $\ell_p$-biased interpolation, and explains in one picture which norms saturate and which increase as $n$ grows. We then study diagonal linear networks (DLNs) trained by gradient descent. By calibrating the initialization scale $\alpha$ to an effective $p_{\mathrm{eff}}(\alpha)$ via the DLN separable potential, we show empirically that DLNs inherit the same elbow/threshold laws, providing a predictive bridge between explicit and implicit bias. Given that many generalization proxies depend on $\lVert \widehat {w_p} \rVert_r$, our results suggest that their predictive power will depend sensitively on which $l_r$ norm is used.

We introduce a straightforward yet effective method to empirically measure and regularize memorization in deep neural networks for classification tasks. Our approach augments each training sample with auxiliary random labels, which are then predicted by a random label prediction head (RLP-head). RLP-heads can be attached at arbitrary depths of a network, predicting random labels from the corresponding intermediate representation and thereby enabling analysis of how memorization capacity evolves across layers. By interpreting the RLP-head performance as an empirical estimate of Rademacher complexity, we obtain a direct measure of both sample-level memorization and model capacity. We leverage this random label accuracy metric to analyze generalization and overfitting in different models and datasets. Building on this approach, we further propose a novel regularization technique based on the output of the RLP-head, which demonstrably reduces memorization. Interestingly, our experiments reveal that reducing memorization can either improve or impair generalization, depending on the dataset and training setup. These findings challenge the traditional assumption that overfitting is equivalent to memorization and suggest new hypotheses to reconcile these seemingly contradictory results.

The comprehensive understanding capabilities of world models for driving scenarios have significantly improved the planning accuracy of end-to-end autonomous driving frameworks. However, the redundant modeling of static regions and the lack of deep interaction with trajectories hinder world models from exerting their full effectiveness. In this paper, we propose Temporal Residual World Model (TR-World), which focuses on dynamic object modeling. By calculating the temporal residuals of scene representations, the information of dynamic objects can be extracted without relying on detection and tracking. TR-World takes only temporal residuals as input, thus predicting the future spatial distribution of dynamic objects more precisely. By combining the prediction with the static object information contained in the current BEV features, accurate future BEV features can be obtained. Furthermore, we propose Future-Guided Trajectory Refinement (FGTR) module, which conducts interaction between prior trajectories (predicted from the current scene representation) and the future BEV features. This module can not only utilize future road conditions to refine trajectories, but also provides sparse spatial-temporal supervision on future BEV features to prevent world model collapse. Comprehensive experiments conducted on the nuScenes and NAVSIM datasets demonstrate that our method, namely ResWorld, achieves state-of-the-art planning performance. The code is available at https://github.com/mengtan00/ResWorld.git.