ICLR 2026 论文列表

Survival analysis plays a critical role in modeling time-to-event outcomes across various domains. Although recent advances have focused on improving _predictive accuracy_ and _concordance_, fine-grained _calibration_ remains comparatively underexplored. In this paper, we propose a survival modeling framework based on the Individually Calibrated Asymmetric Laplace Distribution (ICALD), which unifies _parametric_ and _nonparametric_ approaches based on the ALD. We begin by revisiting the probabilistic foundation of the widely used _pinball_ loss in _quantile regression_ and its reparameterization as the _asymmetry form_ of the ALD. This reparameterization enables a principled shift to _parametric_ modeling while preserving the flexibility of _nonparametric_ methods. Furthermore, we show theoretically that ICALD, with the _quantile regression_ loss is probably approximately individually calibrated. Then we design an extended ICALD framework that supports both _pre-calibration_ and _post-calibration_ strategies. Extensive experiments on 14 synthetic and 7 real-world datasets demonstrate that our method achieves competitive performance in terms of _predictive accuracy_, _concordance_, and _calibration_, while outperforming 12 existing baselines including recent _pre-calibration_ and _post-calibration_ methods.

Probabilistic forecasting of joint distributions for irregular time series with missing values is an underexplored area in machine learning. Existing models, such as Gaussian Process Regression and ProFITi, are limited: while ProFITi is highly expressive due to its use of normalizing flows, it often produces unrealistic predictions because it lacks marginalization consistency—marginal distributions of subsets of variables may not match those predicted directly, leading to inaccurate marginal forecasts when trained on joints. We propose MOSES (Mixtures of Separable Flows), a novel model that parametrizes a stochastic process via a mixture of normalizing flows, where each component combines a latent multivariate Gaussian with separable univariate transformations. This design allows MOSES to be analytically marginalized, enabling accurate and reliable predictions for various probabilistic queries. Experiments on four datasets show that MOSES achieves highly accurate joint and marginal predictions. Thanks to its inherent marginalization consistency, MOSES significantly outperforms all baselines—including ProFITi—on marginal predictions. For joint predictions, it beats all other consistent models and performs close to or slightly worse than ProFITi.

Auto-regressive large language models (LLMs) exhibit a non-trivial capacity to "anticipate'' long-range future tokens despite being trained to predict only one token at a time. Nevertheless, how to systematically profile, enhance and leverage such capacity to practically improve LLM reasoning performance remains unclear. In this paper, we propose **Next Token-Bag Exploitation (Next-ToBE)** to tackle this challenge. Next-ToBE quantifies LLM’s anticipatory capacity by measuring how well tokens in the future window are pre-captured by the model’s current softmax probabilities. This capacity is strongly correlated with LLM generative quality but often suppressed by the rigid one-hot objective in next-token prediction. To address this, we replace the {one-hot target vector} in next-token prediction with a soft target distribution spanning additional future tokens. Specifically, the immediate next token retains the highest importance, while more distant ``look-ahead tokens'' are also included to enrich supervision, with their importance dynamically determined by temporal and semantic relevance patterns to inject forward-looking pressure. Besides, the fitting process emphasizes the model’s intrinsic anticipatory tendency, thus preserving the confidence and fidelity of the pre-trained model to improve training stability. Overall, Next-ToBE not only effectively activates LLM anticipatory capacity through fine-tuning, yielding notable gains in reasoning performance with higher memory and computational efficiency against the MTP baselines, but also shows great potential in pretraining setting by successfully cultivating this capacity from scratch. These highlight its value as an effective strategy to extend the prediction horizon of LLMs, enabling them to see further, and reason better.

Most state-of-the-art probabilistic time series forecasting models rely on sampling to represent future uncertainty. However, this paradigm suffers from inherent limitations, such as lacking explicit probabilities, inadequate coverage, and high computational costs. In this work, we introduce **Probabilistic Scenarios**, an alternative paradigm designed to address the limitations of sampling. It operates by directly producing a finite set of {Scenario, Probability} pairs, thus avoiding Monte Carlo-like approximation. To validate this paradigm, we propose **TimePrism**, a simple model composed of only three parallel linear layers. Surprisingly, TimePrism achieves 9 out of 10 state-of-the-art results across five benchmark datasets on two metrics. The effectiveness of our paradigm comes from a fundamental reframing of the learning objective. Instead of modeling an entire continuous probability space, the model learns to represent a set of plausible scenarios and corresponding probabilities. Our work demonstrates the potential of the Probabilistic Scenarios paradigm, opening a promising research direction in forecasting beyond sampling.

We present ProbHardE2E, a probabilistic forecasting framework that incorporates hard operational/physical constraints and provides uncertainty quantification. Our methodology uses a novel differentiable probabilistic projection layer (DPPL) that can be combined with a wide range of neural network architectures. DPPL allows the model to learn the system in an end-to-end manner, compared to other approaches where constraints are satisfied either through a post-processing step or at inference. ProbHardE2E optimizes a strictly proper scoring rule, without making any distributional assumptions on the target, which enables it to obtain robust distributional estimates (in contrast to existing approaches that generally optimize likelihood-based objectives, which can be biased by their distributional assumptions and model choices); and it can incorporate a range of non-linear constraints (increasing the power of modeling and flexibility). We apply ProbHardE2E in learning partial differential equations with uncertainty estimates and to probabilistic time-series forecasting, showcasing it as a broadly applicable general framework that connects these seemingly disparate domains.

Efficient sampling from high-dimensional and multimodal unnormalized probability distributions is a central challenge in many areas of science and machine learning. We focus on Boltzmann generators (BGs) that aim to sample the Boltzmann distribution of physical systems, such as molecules, at a given temperature. Classical variational approaches that minimize the reverse Kullback–Leibler divergence are prone to mode collapse, while annealing-based methods, commonly using geometric schedules, can suffer from mass teleportation and rely heavily on schedule tuning. We introduce *Constrained Mass Transport* (CMT), a variational framework that generates intermediate distributions under constraints on both the KL divergence and the entropy decay between successive steps. These constraints enhance distributional overlap, mitigate mass teleportation, and counteract premature convergence. Across standard BG benchmarks and the here introduced *ELIL tetrapeptide*, the largest system studied to date without access to samples from molecular dynamics, CMT consistently surpasses state-of-the-art variational methods, achieving more than 2.5× higher effective sample size while avoiding mode collapse.

Flow matching has proven to be a powerful density estimator, yet it often fails to explicitly capture the rich inherent latent structure of complex data. To address this limitation, we introduce Structured Flow Autoencoders (SFA), a family of probabilistic models that augments Continuous Normalizing Flows (CNFs) with graphical models. At the core of SFA is a novel flow matching based objective, which explicitly accounts for latent variables, enabling simultaneous learning of likelihood and posterior. We demonstrate the versatility of SFA across settings, including models with continuous and mixture latent variables, as well as latent dynamical systems. Empirical studies show that SFA outperforms Variational Autoencoders (VAE) and their graphical model extensions, achieving better data fit while simultaneously retaining meaningful latent variables as structured representations.

Text embeddings are essential components in modern NLP pipelines. Although numerous embedding models have been proposed, no single model consistently dominates across domains and tasks. This variability motivates the use of ensemble techniques to combine complementary strengths. However, most existing ensemble methods operate on deterministic embeddings and fail to account for model-specific uncertainty, limiting their robustness and reliability in downstream applications. To address these limitations, we propose Uncertainty-driven Embedding Convolution (UEC). UEC first transforms deterministic embeddings into probabilistic ones in a post-hoc manner. It then computes adaptive ensemble coefficients based on embedding uncertainty, derived from a principled surrogate-loss formulation. Additionally, UEC employs an uncertainty-aware similarity function that directly incorporates uncertainty into the similarity scoring, providing a theoretically grounded and efficient surrogate to distributional distances. Extensive experiments on diverse benchmarks demonstrate that UEC consistently improves both performance and robustness by leveraging principled uncertainty modeling.

Transformer-based models for amortized probabilistic inference, such as neural processes, prior-fitted networks, and tabular foundation models, excel at single-pass *marginal* prediction. However, many real-world applications require coherent *joint distributions* that capture dependencies between predictions. While purely autoregressive architectures efficiently generate such distributions, they sacrifice the flexible set-conditioning that makes these models powerful for meta-learning. Conversely, the standard approach to obtain joint distributions from set-based models requires expensive re-encoding of an updated context set at each autoregressive step. We introduce a *causal autoregressive buffer* that preserves the advantages of both paradigms. Our approach decouples context encoding from updating the conditioning set. The model processes the context once and caches it, while a dynamic buffer captures target dependencies: as targets are incorporated, they enter the buffer and attend to both the cached context and previously buffered targets. This enables efficient batched autoregressive generation and one-pass joint predictive density evaluation. Training seamlessly integrates set-based and autoregressive modes at minimal additional cost. Across synthetic functions, EEG signals, cognitive models, and tabular data, our method matches the predictive accuracy of strong baselines while delivering up to $20\times$ faster joint sampling.

Reinforcement Learning (RL) has demonstrated significant success in optimizing complex control and planning problems. However, scaling RL to real-world applications with multiple, potentially conflicting requirements requires an effective handling of constraints. We propose a novel approach to constraint satisfaction in RL algorithms, focusing on incrementally improving policy safety rather than directly projecting the policy onto a feasible region. We accomplish this by first solving a nonparametric surrogate problem which is guaranteed to contract towards the feasible set, and then cloning that solution into a neural network policy. As a result, our approach improves stability, particularly during early training stages, when the policy lacks knowledge of constraint boundaries. We provide general theoretical results guaranteeing convergence to the safe set for this class of incremental systems. Notably, even the simplest algorithm produced by our theory produces comparable or superior performance when compared to highly tuned constrained RL baselines in challenging constrained environments.

Reward models are crucial for aligning large language models (LLMs) with human values and intentions. Existing approaches follow either Generative (GRMs) or Discriminative (DRMs) paradigms, yet both suffer from limitations: GRMs typically demand costly point-wise supervision, while DRMs produce uncalibrated relative scores that lack probabilistic interpretation. To address these challenges, we introduce a novel reward modeling paradigm: Probabilistic Reward Model (PRM). Instead of modeling reward as a deterministic scalar, our approach treats it as a random variable, learning a full probability distribution for the quality of each response. To make this paradigm practical, we present its closed-form, discrete realization: the **Ordinal Probabilistic Reward Model** (OPRM), which discretizes the quality score into a finite set of ordinal ratings. Building on OPRM, we propose a data-efficient training strategy called **Region Flooding Tuning** (RgFT). It enables rewards to better reflect absolute text quality by incorporating quality-level annotations, which guide the model to concentrate the probability mass within corresponding rating sub-regions. Experiments on various reward model benchmarks show that our method improves accuracy by **2.9% ～ 7.4%** compared to prior reward models, demonstrating strong performance and data efficiency. Analysis of the score distribution provides evidence that our method captures not only relative rankings but also absolute quality. Our models, data, and code will be released and open-sourced.

The rapid scaling of large language models(LLMs) has made inference efficiency a primary bottleneck in the practical deployment. To address this, semi-structured sparsity offers a promising solution by strategically retaining $N$ elements out of every $M$ weights, thereby enabling hardware-friendly acceleration and reduced memory. However, existing (N:M)-compatible approaches typically fall into two categories: rule-based layerwise greedy search, which suffers from considerable errors, and gradient-driven combinatorial learning, which incurs prohibitive training costs. To tackle these challenges, we propose a novel linear-space probabilistic framework named MaskPro, which aims to learn a prior categorical distribution for every $M$ consecutive weights and subsequently leverages this distribution to generate the (N:M)-sparsity throughout an $N$-way sampling without replacement. Furthermore, to mitigate the training instability induced by the high variance of policy gradients in the super large combinatorial space, we propose a novel update method by introducing a moving average tracker of loss residuals instead of vanilla loss. Finally, we conduct comprehensive theoretical analysis and extensive experiments to validate the superior performance of MaskPro, as well as its excellent scalability in memory efficiency and exceptional robustness to data samples.