ICLR 2026 Papers

Training large models with distributed data parallelism (DDP) requires frequent communication of gradients across workers, which can saturate bandwidth. Infrequent communication strategies (e.g., Local SGD) reduce this overhead but, when applied to adaptive optimizers, often suffer a performance gap relative to fully synchronous DDP. We trace this gap to a time-scale mismatch: the optimizer's fast-moving momentum, tuned for frequent updates, decays too quickly to smooth gradients over long intervals, leading to noise-dominated optimization. To address this, we propose MT-DAO, a family of optimizers that employs multiple slow- and fast-moving first momenta or the gradient to track update dynamics across different time scales, for which we provide the first convergence guarantees. Empirically, for language-model pre-training, this eliminates the performance gap with DDP, outperforming infrequent-communication baselines in perplexity and reducing iso-token wall-clock time by 6-27% on Ethernet interconnects. At the 720M scale, MT-DAO reaches a target perplexity in 24% fewer steps and 35% less time than the single-momentum DDP baseline. MT-DAO enables effective cross-datacenter training and training over wide geographic areas.

Universal MLIPs (uMLIPs) demonstrate broad applicability across diverse material systems and have emerged as a powerful and transformative paradigm in chemical and computational materials science. Equivariant uMLIPs achieve state-of-the-art accuracy in a wide range of benchmarks by incorporating equivariant inductive bias. However, the reliance on tensor products and high-degree representations makes them computationally costly. This raises a fundamental question: as quantum mechanical-based datasets continue to expand, can we develop a more compact model to thoroughly exploit high-dimensional atomic interactions? In this work, we present MatRIS (Materials Representation and Interaction Simulation), an invariant uMLIP that introduces attention-based modeling of three-body interactions. MatRIS leverages a novel separable attention mechanism with linear complexity $O(N)$, enabling both scalability and expressiveness. MatRIS delivers accuracy comparable to that of leading equivariant models on a wide range of popular benchmarks (Matbench-Discovery, MatPES, MDR phonon, Molecular dataset, etc). Taking Matbench-Discovery as an example, MatRIS achieves an F1 score of up to 0.847 while improving training efficiency by 13.0–13.5$\times$ at comparable accuracy. The work indicates that our carefully designed invariant models can match or exceed the accuracy of equivariant models at a fraction of the cost, shedding light on the development of accurate and efficient uMLIPs.

Reinforcement Learning with verifiable rewards (RLVR) has emerged as a primary learning paradigm for enhancing the reasoning capabilities of multi-modal large language models (MLLMs). However, during RL training, the enormous state space of MLLM and sparse rewards often leads to entropy collapse, policy degradation, or over-exploitation of suboptimal behaviors. This necessitates an exploration strategy that maintains productive stochasticity while avoiding the drawbacks of uncontrolled random sampling, yielding inefficient exploration. In this paper, we propose CalibRL, a hybrid-policy RLVR framework that supports controllable exploration with expert guidance, enabled by two key mechanisms. First, a distribution-aware advantage weighting scales updates by group rareness to calibrate the distribution, therefore preserving exploration. Meanwhile, the asymmetric activation function (LeakyReLU) leverages the expert knowledge as a calibration baseline to moderate overconfident updates while preserving their corrective direction. CalibRL increases policy entropy in a guided manner and clarifies the target distribution by estimating the on-policy distribution through online sampling. Updates are driven by these informative behaviors, avoiding convergence to erroneous patterns. Importantly, these designs help alleviate the distributional mismatch between the model’s policy and expert trajectories, thereby achieving a more stable balance between exploration and exploitation. Extensive experiments across eight benchmarks, including both in-domain and out-of-domain settings, demonstrate consistent improvements, validating the effectiveness of our controllable hybrid-policy RLVR training. Code is available at https://github.com/zhh6425/CalibRL.

Asynchronous stochastic gradient methods are central to scalable distributed optimization, particularly when devices differ in computational capabilities. Such settings arise naturally in federated learning, where training takes place on smartphones and other heterogeneous edge devices. In addition to varying computation speeds, these devices often hold data from different distributions. However, existing asynchronous SGD methods struggle in such heterogeneous settings and face two key limitations. First, many rely on unrealistic assumptions of similarity across workers' data distributions. Second, methods that relax this assumption still fail to achieve theoretically optimal performance under heterogeneous computation times. We introduce Ringleader ASGD, the first asynchronous SGD algorithm that attains the theoretical lower bounds for parallel first-order stochastic methods in the smooth nonconvex regime, thereby achieving optimal time complexity under data heterogeneity and without restrictive similarity assumptions. Our analysis further establishes that Ringleader ASGD remains optimal under arbitrary and even time-varying worker computation speeds, closing a fundamental gap in the theory of asynchronous optimization.

Recent advances in applying reinforcement learning (RL) to large language models (LLMs) have led to substantial progress. In particular, a series of remarkable yet often counterintuitive phenomena have been reported in LLMs, exhibiting patterns not typically observed in traditional RL settings. For example, notable claims include that a single training example can match the performance achieved with an entire dataset, that the reward signal does not need to be very accurate, and that training solely with negative samples can match or even surpass sophisticated reward-based methods. However, the precise conditions under which these observations hold—and, critically, when they fail—remain unclear. In this work, we identify a key factor that differentiates RL observations: whether the pretrained model already exhibits strong *Model-Task Alignment*, as measured by pass@k accuracy on the evaluated task. Through a systematic and comprehensive examination of a series of counterintuitive claims, supported by rigorous experimental validation across different model architectures and task domains, our findings show that while standard RL training remains consistently robust across settings, many of these counterintuitive results arise only when the model and task already exhibit strong model-task alignment. In contrast, these techniques fail to drive substantial learning in more challenging regimes, where standard RL methods remain effective.

Functional data, representing curves or trajectories, are ubiquitous in fields like biomedicine and motion analysis. A fundamental challenge is phase variability—temporal misalignments that obscure underlying patterns and degrade model performance. Current methods often address registration (alignment) and classification as separate, sequential tasks. This paper introduces DeepFRC, an end-to-end deep learning framework that jointly learns diffeomorphic warping functions and a classifier within a unified architecture. DeepFRC combines a neural deformation operator for elastic alignment, a spectral representation using Fourier basis for smooth functional embedding, and a class-aware contrastive loss that promotes both intra-class coherence and inter-class separation. We provide the first theoretical guarantees for such a joint model, proving its ability to approximate optimal warpings and establishing a data-dependent generalization bound that formally links registration fidelity to classification performance. Extensive experiments on synthetic and real-world datasets demonstrate that DeepFRC consistently outperforms state-of-the-art methods in both alignment quality and classification accuracy, while ablation studies validate the synergy of its components. DeepFRC also shows notable robustness to noise, missing data, and varying dataset scales. Code is available at https://github.com/Drivergo-93589/DeepFRC.

The success of Transformers lies in their ability to improve inference through two complementary strategies: the permanent refinement of model parameters via _in-weight learning_ (IWL), and the ephemeral modulation of inferences via _in-context learning_ (ICL), which leverages contextual information maintained in the model's activations. Evolutionary biology tells us that the predictability of the environment across timescales predicts the extent to which analogous strategies should be preferred. Genetic _evolution_ adapts to stable environmental features by gradually modifying the genotype over generations. Conversely, environmental volatility favors _plasticity_, which enables a single genotype to express different traits within a lifetime, provided there are reliable cues to guide the adaptation. We operationalize these dimensions (environmental stability and cue reliability) in controlled task settings (sinusoid regression and Omniglot classification) to characterize their influence on learning in Transformers. We find that stable environments favor IWL, often exhibiting a sharp transition when conditions are static. Conversely, reliable cues favor ICL, particularly when the environment is volatile. Furthermore, an analysis of learning dynamics reveals task-dependent transitions between strategies (ICL $\to$ IWL and vice versa). We demonstrate that these transitions are governed by (1) the asymptotic optimality of the strategy with respect to the environment, and (2) the optimization cost of acquiring that strategy, which depends on the task structure and the learner's inductive bias.

Puzzlehunts are a genre of complex, multi-step puzzles lacking well-defined problem definitions. In contrast to conventional reasoning benchmarks consisting of tasks with clear instructions and constrained environments, puzzlehunts requires discovering the underlying problem structure from multimodal evidence and iterative reasoning, mirroring real-world domains such as scientific discovery, exploratory data analysis, or investigative problem-solving. Despite progress in foundation models, their performance on open-ended settings remains largely untested. We introduce PuzzleWorld, a comprehensive benchmark of 667 puzzlehunt-style problems designed to assess step-by-step, open-ended, and creative multimodal reasoning. Each puzzle is annotated with the final solution, detailed reasoning traces, and cognitive skill labels, enabling holistic benchmarking and fine-grained diagnostic analysis. Most state-of-the-art models achieve only 1-4\% final answer accuracy. On PuzzleWorld, the best model solves only 14\% of puzzles and reaches 40\% stepwise accuracy, matching human puzzle novices but falling significantly behind puzzle enthusiasts. To demonstrate the value of our reasoning annotations, we show that fine-tuning a small model on reasoning traces boosts stepwise accuracy from 4\% to 11\%, which translates to improvements in downstream visual reasoning tasks. Our detailed error analysis reveals that current models exhibit myopic reasoning, are bottlenecked by the limitations of language-based inference, and lack sketching capabilities crucial for visual and spatial reasoning. We will publicly release PuzzleWorld to support future work on building more general, open-ended, and creative reasoning systems.

Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for enhancing the reasoning ability of Large Language Models (LLMs). Yet current RLVR methods often explore poorly, leading to premature convergence and entropy collapse. Moreover, they tend to produce poorly calibrated policies that remain confident in their generations regardless of correctness. To address this challenge, we introduce **Curiosity-Driven Exploration (CDE)**, a framework that leverages the model's intrinsic sense of curiosity to guide exploration. We formalize curiosity with signals from both the actor and the critic: for the actor, we use perplexity over its generated response, and for the critic, we use the variance of value estimates from a multi-head critic architecture. Both signals serve as an exploration bonus within the RLVR framework to guide the model. Our theoretical analysis shows that the actor-wise bonus inherently penalizes overconfident errors and promotes diversity among correct responses; moreover, we connect the critic-wise bonus to the well-established count-based exploration bonus in RL. Empirically, our method achieves an approximate **+3** point improvement over standard RLVR using GRPO/PPO on AIME benchmarks.

Existing anomaly detection (AD) methods for tabular data usually rely on some assumptions about anomaly patterns, leading to inconsistent performance in real-world scenarios. While Large Language Models (LLMs) show remarkable reasoning capabilities, their direct application to tabular AD is impeded by fundamental challenges, including difficulties in processing heterogeneous data and significant privacy risks. To address these limitations, we propose LLM-DAS, a novel framework that repositions the LLM from a data processor to an algorithmist. Instead of being exposed to raw data, our framework leverages the LLM's ability to reason about algorithms. It analyzes a high-level description of a given detector to understand its intrinsic weaknesses and then generates detector-specific, data-agnostic Python code to synthesize ``hard-to-detect'' anomalies that exploit these vulnerabilities. This generated synthesis program, which is reusable across diverse datasets, is then instantiated to augment training data, systematically enhancing the detector's robustness by transforming the problem into a more discriminative two-class classification task. Extensive experiments on 36 TAD benchmarks show that LLM-DAS consistently boosts the performance of mainstream detectors. By bridging LLM reasoning with classic AD algorithms via programmatic synthesis, LLM-DAS offers a scalable, effective, and privacy-preserving approach to patching the logical blind spots of existing detectors.

Deep generative models have recently garnered significant attention across various fields, from physics to chemistry, where sampling from unnormalized Boltzmann-like distributions represents a fundamental challenge. In particular, autoregressive models and normalizing flows have become prominent due to their appealing ability to yield closed-form probability densities. Moreover, it is well-established that incorporating prior knowledge—such as symmetries—into deep neural networks can substantially improve training performances. In this context, recent advances have focused on developing symmetry-equivariant generative models, achieving remarkable results. Building upon these foundations, this paper introduces Symmetry-Enforcing Stochastic Modulation (SESaMo). Similar to equivariant normalizing flows, SESaMo enables the incorporation of inductive biases (e.g., symmetries) into normalizing flows through a novel technique called \textit{stochastic modulation}. This approach enhances the flexibility of the generative model by enforcing exact symmetries while, for the first time, enabling the model to learn broken symmetries during training. Our numerical experiments benchmark SESaMo in different scenarios, including an 8-Gaussian mixture model and physically relevant field theories, such as the $\phi^4$ theory and the Hubbard model.

Protein structure tokenizers enable the creation of multimodal models of protein structure, sequence, and function. Current approaches to protein structure tokenization rely on bespoke components that are invariant to spatial symmetries, but that are challenging to optimize and scale. We present Kanzi, a flow-based tokenizer for tokenization and generation of protein structures. Kanzi consists of a diffusion autoencoder trained with a flow matching loss. We show that this approach simplifies several aspects of protein structure tokenizers: frame-based representations can be replaced with global coordinates, complex losses are replaced with a single flow matching loss, and SE(3)-invariant attention operations can be replaced with standard attention. We find that these changes stabilize the training of parameter-efficient models that outperform existing tokenizers on reconstruction metrics at a fraction of the model size and training cost. An autoregressive model trained with Kanzi outperforms similar generative models that operate over tokens, although it does not yet match the performance of state-of-the-art continuous diffusion models.

High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preservation of fine-grained visual detail. We present $\textit{Latent Wavelet Diffusion (LWD)}$, a lightweight training framework that significantly improves detail and texture fidelity in ultra-high-resolution (2K-4K) image synthesis. LWD introduces a novel, frequency-aware masking strategy derived from wavelet energy maps, which dynamically focuses the training process on detail-rich regions of the latent space. This is complemented by a scale-consistent VAE objective to ensure high spectral fidelity. The primary advantage of our approach is its efficiency: LWD requires no architectural modifications and adds zero additional cost during inference, making it a practical solution for scaling existing models. Across multiple strong baselines, LWD consistently improves perceptual quality and FID scores, demonstrating the power of signal-driven supervision as a principled and efficient path toward high-resolution generative modeling.

The ultimate goal of expressive speech-to-speech translation (S2ST) is to accurately translate spoken content while preserving the speaker identity and emotional style. However, progress in this field is largely hindered by three key challenges: the scarcity of paired speech data that retains expressive styles, the complexity of multi-stage processing pipelines, and the limited transfer of translation capabilities from large language models (LLMs). In this work, we address these challenges by introducing UniSS, a novel single-stage framework for expressive S2ST. Our approach features carefully designed speech semantic and style modeling, enabling seamless integration with existing text-based LLM frameworks to develop a unified text-speech language model. To transfer translation capabilities from text to speech, we propose a cross-modal chain-of-thought prompting process that progressively aligns audio semantics with text and ensures style preservation in the decoded results. Furthermore, we construct and release a large-scale, high-quality expressive S2ST dataset, UniST, comprising 44.8k hours of data. Experimental results show that UniSS significantly outperforms previous methods in translation fidelity and speech quality while preserving voice, emotion, and duration consistency. Our work establishes a simpler and more effective paradigm for building the next generation of expressive S2ST systems. Audio samples are available at https://uniss-s2st.github.io/.

Chain-of-Thought (CoT) reasoning has proven effective in enhancing Large Language Models (LLMs) on complex tasks by decomposing problems into step-wise solutions. However, extending CoT to multi-modal settings remains challenging, as it requires modeling transitions of visual states alongside textual reasoning. Existing approaches often underperform due to limited capacity to model visual transitions or fragmented architectures. To overcome this limitation, we introduce Uni-CoT, a Unified Chain-of-Thought framework that captures structured visual transitions and seamlessly aligns them with textual logic, enabling coherent multimodal reasoning. To mitigate the computational and training challenges inherent to multi-modal reasoning, Uni-CoT introduces a two-level reasoning paradigm: a macro-level CoT for high-level planning and a micro-level CoT for localized subtask execution. This hierarchical design reduces computational overhead while maintaining coherence. Additionally, Uni-CoT incorporates a structured training paradigm with auxiliary tasks to stabilize optimization and improve generalization. Experiments on reasoning-driven image generation and understanding benchmarks demonstrate that Uni-CoT achieves state-of-the-art performance and remarkable generalization, underscoring its potential for complex multi-modal reasoning.

We study multi-user contextual bandits where users are related by a graph and their reward functions exhibit both non-linear behavior and graph homophily. We introduce a principled joint penalty for the collection of user reward functions $\\{f_u\\}$, combining a graph smoothness term based on RKHS distances with an individual roughness penalty. Our central contribution is proving that this penalty is equivalent to the squared norm within a single, unified _multi-user RKHS_. We explicitly derive its reproducing kernel, which elegantly fuses the graph Laplacian with the base arm kernel. This unification allows us to reframe the problem as learning a single "lifted" function, enabling the design of principled algorithms, LK-GP-UCB and LK-GP-TS, that leverage Gaussian Process posteriors over this new kernel for exploration. We provide high-probability regret bounds that scale with an _effective dimension_ of the multi-user kernel, replacing dependencies on user count or ambient dimension. Empirically, our methods outperform strong linear and non-graph-aware baselines in non-linear settings and remain competitive even when the true rewards are linear. Our work delivers a unified, theoretically grounded, and practical framework that bridges Laplacian regularization with kernelized bandits for structured exploration.

Time series foundation models (TSFMs) are a potential class of powerful, general-purpose tools for forecasting and related temporal tasks, but their behavior is strongly shaped by subtle inductive biases in their design. Rather than developing a new model and claiming that it is better than existing TSFMs, e.g., by winning on existing benchmarks, our objective is to understand how the various "knobs" of the training process affect model quality. Using a mix of theory and controlled empirical evaluation, we identify and show how various design choices (e.g., patch size, embedding choice, training objective, etc.) lead to implicit biases in fundamental model properties (e.g., temporal behavior, geometric structure, how aggressively or not the model regresses to the mean, etc.), and how these biases can be intuitive or counterintuitive, depending on properties of the model and data. We illustrate in a case study on outlier handling how multiple biases interact in complex ways.

Recent advances in deep reinforcement learning (RL) have achieved strong results on high-dimensional control tasks, but applying RL to reachability problems raises a fundamental mismatch: reachability seeks to maximize the set of states from which a system remains safe indefinitely, while RL optimizes expected returns over a user-specified distribution. This mismatch can result in policies that perform poorly on low-probability states that are still within the safe set. A natural alternative is to frame the problem as a robust optimization over a set of initial conditions that specify the initial state, dynamics and safe set, but whether this problem has a solution depends on the feasibility of the specified set, which is unknown a priori. We propose Feasibility-Guided Exploration (FGE), a method that simultaneously identifies a subset of feasible initial conditions under which a safe policy exists, and learns a policy to solve the reachability problem over this set of initial conditions. Empirical results demonstrate that FGE learns policies with over 50% more coverage than the best existing method for challenging initial conditions across tasks in the MuJoCo simulator and the Kinetix simulator with pixel observations.

This paper introduces a novel watermarking method for diffusion models. It is based on guiding the diffusion process using the gradient computed from any off-the-shelf watermark decoder. The gradient is guided further using different image augmentations, increasing robustness to attacks against which the decoder was not originally robust, without retraining or fine-tuning. The methodology effectively allows to convert any post-hoc watermarking scheme into a scheme embedding the signal during the diffusion process. We show that this approach is complementary to watermarking techniques modifying the variational autoencoder at the end of the diffusion process. We validate the methods on different diffusion models and detectors. The watermarking guidance does not significantly alter the generated image for a given seed and prompt, preserving both the diversity and quality of generation.