ICML 2026 论文列表

By leveraging differentiable dynamics, Reparameterization Policy Gradient (RPG) achieves high sample efficiency. However, current approaches are hindered by two critical limitations: the under-utilization of computationally expensive dynamics Jacobians and inherent training instability. While sample reuse offers a remedy for under-utilization, no prior principled framework exists, and naive attempts risks exacerbating instability. To address these challenges, we propose Reparameterization Proximal Policy Optimization (RPO). We first establish that under sample reuse, RPG naturally optimizes a PPO-style surrogate objective via Backpropagation Through Time, providing a unified framework for both on- and off-policy updates. To further ensure stability, RPO integrates a clipped policy gradient mechanism tailored for RPG and employs explicit Kullback-Leibler divergence regularization. Experimental results demonstrate that RPO maintains superior sample efficiency and consistently outperforms or achieves state-of-the-art performance across diverse tasks.

Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained by the theory that such recursion increases a network’s depth, allowing it to compactly emulate the capacity of larger models. However, the performance of recursively added layers remains behind the capabilities of one‑pass models with the same feed-forward depth. This means that in the looped version, not every recursive step effectively contributes to depth. This raises the question: when and why does latent reasoning improve performance, and when does it result in dead compute? In our work, we analyze the algorithms that latent reasoning provides answer to this question. We show that latent reasoning can be formalized as a classifier‑free guidance and policy improvement algorithm. Building on these insights, we propose to use a training schemes from RL and diffusion methods for latent reasoning modles. Using the Tiny Recursive Model as our testbed, we show that with our modifications we can avoid dead compute steps and reduce the total number of forward passes by 18× while maintaining performance. Broadly speaking, we show how a policy improvement perspective on recursive steps can explain model behavior and provide insights for further improvements.

Understanding how anatomical shapes evolve in response to developmental covariates—and quantifying their spatially varying uncertainties—is critical in healthcare research. Existing approaches typically rely on global time-warping formulations that ignore spatially heterogeneous dynamics. We introduce \texttt{PRISM}, a novel framework that bridges implicit neural representations with uncertainty-aware statistical shape analysis. \texttt{PRISM} models the conditional distribution of shapes given covariates, providing spatially continuous estimates of both the population mean and covariate-dependent uncertainty at arbitrary locations. A key theoretical contribution is a closed-form Fisher Information metric that enables efficient, analytically tractable local temporal uncertainty quantification via automatic differentiation. Experiments on three synthetic datasets and one clinical dataset demonstrate \texttt{PRISM}'s strong performance across diverse tasks—from modeling shape evolution to anomaly detection—within a unified framework, while providing interpretable and clinically meaningful uncertainty estimates.

Flow Matching shows great promise in offline reinforcement learning (RL), yet optimizing these iterative policies via Backpropagation Through Time (BPTT) is unstable. While prevailing paradigms circumvent this by distilling multi-step flows into single-step approximations, such methods may limit the benefits of iterative refinement. To avoid these sacrifices, we propose Direct Flow Q-Learning (DFQL), a streamlined framework that attains superior results by optimizing flow matching policies without BPTT or distillation. DFQL derives a surrogate objective that directly injects terminal Q-value gradients as a guidance term into each step velocity field, ensuring stable optimization while preserving iterative expressive capacity. Across 73 challenging tasks in OGBench and D4RL, DFQL achieves state-of-the-art results. Additionally, DFQL extends seamlessly to the offline-to-online setting, delivering substantial performance gains without further modification.

Policy-gradient methods are widely used in reinforcement learning, yet training often becomes unstable or slows down as learning progresses. We study this phenomenon through the **noise-to-signal ratio** (NSR) of a policy-gradient estimator, defined as the estimator variance (noise) normalized by the squared norm of the true gradient (signal). Our main result is that, for (i) finite-horizon linear systems with Gaussian policies and linear state-feedback, and (ii) finite-horizon polynomial systems with Gaussian policies and polynomial feedback, the NSR of the REINFORCE estimator can be characterized exactly—either in closed form or via numerical moment-evaluation algorithms—without approximation. For general nonlinear dynamics and expressive policies (including neural policies), we further derive a general upper bound on the variance. These characterizations enable a direct examination of how NSR varies across policy parameters and how it evolves along optimization trajectories (e.g. SGD and Adam). Across a range of examples, we find that the NSR landscape is highly non-uniform and typically increases as the policy approaches an optimum; in some regimes it blows up, which can trigger training instability and policy collapse.

Deep Multi-View Clustering (MVC) aims to learn a unified semantic representation from diverse data sources without supervision. However, current approaches relying on flat Euclidean embeddings often fail to model data uncertainty, resulting in rigid alignment where high-quality views are forced to drift toward corrupted ones. To address these challenges, we propose the Hyperbolic Asymmetric Multi-view Clustering (HAMC) framework. HAMC maps view-specific features into the Poincaré ball and uses radial geometry as a confidence proxy, encouraging confident representations to occupy larger radial distances while allowing ambiguous or noisy samples to remain closer to the origin. To mitigate noise, we introduce an asymmetric view alignment mechanism, enabling reliable views to unidirectionally guide unreliable ones. Furthermore, a consensus-aware cluster learning strategy is designed to construct robust global pseudo-labels via a confidence-based screening scheme, refining the cluster structure. Extensive experiments against 13 baselines demonstrate that HAMC achieves state-of-the-art performance.

In reinforcement learning (RL), agents benefit from exploration *only* because they repeatedly encounter similar states: trying different actions can improve performance or reduce uncertainty; without such retries, a greedy policy is optimal. We formalize this intuition with **ReMax**, an objective that evaluates a policy by the expected maximum return over $M$ samples ($M \in \mathbb{N}$), while accounting for return uncertainty. Optimizing this objective induces stochastic exploration as an emergent property, without explicit bonus terms. For efficient policy optimization, we derive a new policy-gradient formulation for ReMax and introduce **Re**Max **PPO** (**RePPO**), a PPO variant that optimizes ReMax while generalizing the discrete retry count $M$ to a continuous parameter $m > 0$, enabling fine-grained control of exploration. Empirically, RePPO promotes exploration—without any explicit exploration bonuses—on the MinAtar and Craftax benchmarks. The official code is available at https://github.com/nissymori/remax-rl.

Deep neural networks achieve impressive results across diverse applications, yet their overconfidence on unseen inputs necessitates reliable epistemic uncertainty modeling. Existing methods for uncertainty modeling face a fundamental dilemma: Bayesian approaches provide principled estimates but remain computationally prohibitive, while efficient second-order predictors lack rigorous connections between their specific objectives and epistemic uncertainty quantification. To resolve this dilemma, we introduce **D**irichlet-**a**pproximated **p**ossibilistic **p**osterior p**r**edictions (DAPPr), a principled framework grounded in possibility theory. We define a possibilistic posterior over parameters, project it to the prediction space via supremum operators, and approximate the projected posterior using learnable Dirichlet possibility functions. This projection-and-approximation strategy yields a simple training objective with closed-form solutions. Despite its simplicity, extensive experiments across diverse benchmarks show that DAPPr achieves competitive or superior uncertainty quantification performance over state-of-the-art second-order predictors while maintaining both principled derivation and computational efficiency.

Large Reasoning Models (LRMs) solve complex tasks by generating long Chain-of-Thought (CoT) sequences; however, the emergent dynamics governing reasoning trajectories are not well understood and can lead to inconsistencies and reasoning pathologies. In this work, we propose to approximate LRM's emerging hierarchical reasoning dynamics as a trajectory within a Finite State Machine (FSM) transitioning among six abstract cognitive states. We demonstrate that these states and transitions can be captured in the latent state of the model. We believe that this representation can have different applications in the interpretability and optimization of LRM models. For example, by analyzing the topology of these transitions, we identify statistical shifts in reasoning strategies that help identify effective reasoning chains from those that fail. To illustrate these potential advantages, we propose $Q$-Value guided steering, a training-free inference-time control method that treats reasoning as a planning problem. We estimate the long-horizon utility of state transitions and apply sparse, orthogonal activation steering at sentence boundaries to align the CoT generation with optimal reasoning policies. Experiments across four benchmarks (AIME25, MATH-500, GSM8k, and GPQA Diamond) using three state-of-the-art open reasoning models demonstrate that $Q$-Value steering policy achieves significant performance gains with "surgical'' efficiency, often requiring $25\times$ fewer interventions than greedy and weighted baselines, which suggests that reasoning can be effectively controlled by guiding high-level cognitive dynamics rather than micro-managing token generation. Code is available at: https://github.com/shahariar-shibli/CoT-FSM.

Offline goal-conditioned RL (GCRL) learns goal-reaching policies from static datasets, but real-world environments are often partially observable, so the collected trajectories are only partly consistent with the Markov assumption while other segments remain history-dependent. History-aware sequence models such as Decision Transformer (DT) are a natural fit for long-term dependency modeling, yet pure attention is inefficient and brittle when handling local Markovian structure and long-range context simultaneously. Although recent hybrid architectures (e.g., LSDT) introduce local extractors, their fixed-window extraction cannot adapt the effective memory to varying dependency lengths, often truncating long-range context instead of compressing it. Moreover, under sparse rewards, return-to-go (RTG) becomes non-discriminative across sub-trajectories, offering little guidance for stitching goal-reaching behaviors from diverse demonstrations. To address these limitations, we propose QHyer (Q-conditioned Hybrid Attention-Mamba Transformer), which replaces RTG with a Normalizing Flows (NFs) parameterized goal-reaching Q-estimator used directly as conditioning tokens, and a gated Hybrid Attention-Mamba backbone whose selective state-space dynamics enable content-adaptive history compression while attention captures global goal-directed dependencies. Extensive experiments on OGBench and D4RL demonstrate that QHyer achieves state-of-the-art performance on both non-Markovian and Markovian datasets, validating its effectiveness for diverse scenarios.

Despite the recent success of Multimodal Large Language Models (MLLMs), existing approaches predominantly assume the availability of multiple modalities during training and inference. In practice, multimodal data is often incomplete because modalities may be missing, collected asynchronously, or available only for a subset of examples. In this work, we propose PRIMO, a supervised latent-variable imputation model that quantifies the predictive impact of any missing modality within the multimodal learning setting. PRIMO enables the use of all available training examples, whether modalities are complete or partial. Specifically, it models the missing modality through a latent variable that captures its relationship with the observed modality in the context of prediction. During inference, we draw many samples from the learned distribution over the missing modality to both obtain the marginal predictive distribution (for the purpose of prediction) and analyze the impact of the missing modalities on the prediction for each instance. We evaluate PRIMO on a synthetic XOR dataset, Audio-Vision MNIST, and MIMIC-III for mortality and ICD-9 prediction. Across all datasets, PRIMO obtains performance comparable to unimodal baselines when a modality is fully missing and to multimodal baselines when all modalities are available. PRIMO quantifies the predictive impact of a modality at the instance level using a variance-based metric computed from predictions across latent completions. We visually demonstrate how varying completions of the missing modality result in a set of plausible labels.

We introduce Conditional Clifford-Steerable CNNs (C-CSCNNs), a unified framework that incorporates equivariance to arbitrary pseudo-Euclidean groups and significantly improves the expressivity of standard CSCNNs. We show that the kernel basis of the standard formulation is incomplete, limiting model capacity. To address this, we augment the kernels with equivariant representations of the input feature field. We derive the equivariance constraint for these input-dependent kernels and show how it can be solved efficiently via implicit parameterization. We empirically validate on multiple PDE forecasting tasks, including fluid dynamics and relativistic electrodynamics, where our method consistently outperforms standard CSCNNs and performs on par with state-of-the-art baselines.

Reinforcement learning (RL) has achieved impressive results across various domains, yet the resulting policies often fail to generalize beyond the specific tasks encountered during training. This lack of robustness limits their deployment in real-world scenarios where diverse and unpredictable task demands exist. In this work, we provide a theoretical analysis of policy networks under Markov Decision Processes (MDPs) and demonstrate that adapting only the linear layers placed before and after a policy backbone is sufficient for task adaptation. Based on this insight, we propose the Adaptive Policy Backbone (APB), which consists of a frozen backbone paired with lightweight, task-specific pre- and post-backbone linear layers. Our results demonstrate that learning only these lightweight task-specific linear layers is sufficient to achieve performance on par with standard RL, even when the backbone is randomly initialized. Furthermore, we find that this structural constraint can enhance the generalization capability of the resulting policies. This advantage extends to out-of-distribution tasks, where representative meta-RL baselines often struggle.

Estimating free energy differences quantifies thermodynamic preferences in molecular interactions, which is central to chemistry and drug discovery. Despite fruitful progress, existing methods still face key limitations: classical computational approaches remain prohibitively expensive due to their reliance on extensive molecular dynamics simulations, while deep learning-based methods are constrained by either less-expressive generative models or input dimensions tied to a specific system, resulting in negligible generalization. To address these challenges, we propose CARD, a generative framework that employs a novel radix-based decomposition to bijectively convert 3D coordinates into mixed discrete-continuous sequences, enabling coarse-to-fine autoregressive modeling with enhanced expressiveness. Notably, the model corresponds to a distribution with zero free energy, serving as a proposal for absolute free energy computation of arbitrary systems without relying on alchemical pathways. Experiments across diverse tasks demonstrate that CARD matches the accuracy of classical computational methods on unseen systems with diverse topologies, while achieving an approximately 40-fold speedup in inference.

High-dimensional datasets often concentrate near low-dimensional structures, but estimating their geometry from samples typically relies on graphs and kernels that scale poorly with dataset size and dimension. We propose **Riemannian metric matching**: a denoising probabilistic framework for learning the Riemannian geometry of data using neural networks. Specifically, we learn the *carré du champ* operator, which, using diffusion geometry, gives us access to the Riemannian geometry toolkit for downstream machine learning and statistical tasks. Our key observation is that the carré du champ operator can be formulated as a conditional expectation over random perturbations of the data, which can be exploited for sample-wise training and constant cost, amortized inference without explicit kernel construction. Empirically, metric matching rivals or improves the accuracy of $k$-NN-based diffusion geometry estimators, while enabling amortized inference that is up to $400\times$ faster, and supports graph-free geometric analysis on high-dimensional images where nearest neighbors break down.

Knowledge distillation improves large language model (LLM) reasoning by compressing the knowledge of a teacher LLM to train smaller LLMs. On-policy distillation advances this approach by having the student sample its own trajectories while a teacher LLM provides dense token-level supervision, addressing the distribution mismatch between training and inference in off-policy distillation methods. However, on-policy distillation typically requires a separate, often larger, teacher LLM and does not explicitly leverage ground-truth solutions available in reasoning datasets. Inspired by the intuition that a sufficiently capable LLM can rationalize external privileged reasoning traces and teach its weaker self, we introduce On-Policy Self-Distillation (OPSD), a learning algorithm where a single LLM acts as both teacher and student with different contexts. The teacher policy conditions on privileged information while the student policy sees only the question; training minimizes the per-token divergence between these distributions over the student's own rollouts. We demonstrate the efficacy of our method on multiple mathematical reasoning benchmarks, achieving superior token efficiency compared to reinforcement learning methods and better performance over off-policy distillation methods.

Irregular time series arise ubiquitously in real-world systems, where observations are sparse, asynchronous, and governed by underlying continuous-time dynamics. Existing continuous–discrete state-space models typically rely on path-based variational inference, which is computationally expensive or constrained by restrictive posterior assumptions. We propose SDEVI, a novel framework that performs variational inference directly on the joint distribution over discrete-time observations, while guaranteeing consistency with an underlying continuous process governed by a Stochastic Differential Equation(SDE). SDEVI employs a variational posterior induced by linear time-varying SDEs as a scalable inference backbone. To enable intricate dynamics modeling for real-world data, we introduce non-linear-SDE-induced variational inference and generalize our framework to the complex domain. Extensive experiments across healthcare, physics, climate, and IoT benchmarks demonstrate state-of-the-art performance on interpolation, extrapolation, regression, and classification tasks.

We study off-policy evaluation (OPE) under strategic behavior where decision subjects (or agents) respond to a decision maker's policy by strategically modifying their covariates. Such behavior induces a policy-dependent covariate shift, breaking the standard assumption in existing methods that covariates are exogenous to the policy. Related work addresses this challenge by imposing strong assumptions such as repeated interactions or full knowledge of agents’ response behavior, substantially limiting its applicability to OPE. In contrast, we consider a one-shot OPE setting where the decision maker has only partial knowledge of the agents' response behavior. Our key insight is that disclosing local information through post-hoc explanations reveals agents’ pre-strategic covariates prior to adaptation, mitigating the information loss induced by strategic behavior. Leveraging this structure, we estimate a statistical model for the agents’ responses and construct a doubly robust estimator for policy value. By assuming that the agents' cost sensitivity follows a conditional log-normal distribution, we establish consistency of the proposed estimator and validate our approach empirically. More broadly, our results highlight how interaction design can mitigate information asymmetry by revealing otherwise hidden structure in agents' strategic responses.

Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to the inherent distributional shift and value function overestimation bias. These issues become even more noticeable in zero-shot reinforcement learning, where an agent trained on reward-free data must adapt to new tasks at test time without additional training. In this work, we address the off-policy problem in a zero-shot setting by discovering a theoretical connection of successor measures to stationary density ratios. Using this insight, our algorithm can infer optimal importance sampling ratios, effectively performing a stationary distribution correction with an optimal policy for any task on the fly. We benchmark our method in motion tracking tasks on SMPL Humanoid, continuous control on ExoRL, and for the long-horizon OGBench tasks. Our technique seamlessly integrates into forward-backward representation frameworks and enables fast-adaptation to new tasks in a training-free regime. More broadly, this work bridges off-policy learning and zero-shot adaptation, offering benefits to both research areas.