ICML 2026 Papers

Automated proving of polynomial inequalities is a fundamental challenge in automated mathematical reasoning, where rich algebraic structure and a rapidly growing certificate search space hinder scalability. Purely symbolic approaches provide strong guarantees but often scale poorly as the number of variables or the degree increases, due to expensive algebraic manipulations and rapidly growing intermediate expressions. In parallel, LLM-guided methods have made notable progress, particularly on competition-style inequalities with a small number of variables. To address the remaining scalability challenges, we propose NSPI, a neuro-symbolic framework that combines the complementary strengths of LLMs and symbolic computation for polynomial-inequality proving. Concretely, an LLM proposes a conjecture in the form of an approximate polynomial Sum-Of-Squares (SOS) decomposition; we refine it via symbolic computation to obtain an exact polynomial SOS representation, which directly proves the target inequality, and we further certify the proof in Lean, yielding an end-to-end pipeline from heuristic discovery to machine-checked proof. Experiments on challenging benchmarks involving polynomials with up to 10 variables demonstrate the effectiveness and scalability of the proposed method.

Low-precision training is critical for optimizing the trade-off between model quality and training costs, necessitating the joint allocation of model size, dataset size, and numerical precision. While empirical scaling laws suggest that quantization impacts effective model and data capacities or acts as an additive error, the theoretical mechanisms governing these effects remain largely unexplored. In this work, we initiate a theoretical study of scaling laws for low-precision training within a high-dimensional sketched linear regression framework. By analyzing multiplicative (signal-dependent) and additive (signal-independent) quantization, we identify a critical dichotomy in their scaling behaviors. Our analysis reveals that in the worst case, while both schemes introduce an additive error and degrade the effective data size, they exhibit distinct effects on effective model size: multiplicative quantization maintains the full-precision model size, whereas additive quantization reduces the effective model size. Numerical experiments validate our theoretical findings. By rigorously characterizing the complex interplay among model scale, dataset size, and quantization error, our work provides a principled theoretical basis for optimizing training protocols under practical hardware constraints.

Relative spatial relations provide a compact representation of spatial structure and are fundamental to relative spatial reasoning in 3D layout generation. Recent works leverage Multimodal Large Language Models (MLLMs) to infer such relations, but the inferred relations are often unreliable and are typically handled with post-hoc heuristics. In this paper, we propose R$^3$L, a general framework that improves the reliability and consistency of relative spatial reasoning for 3D layout generation. Our key motivation is that multi-hop reasoning requires repeated reference-frame transformations, which accumulate errors in inferred relations and lead to semantic and metric drift. To mitigate this, we propose invariant spatial decomposition to break coupled relation chains, and consistent spatial imagination to promote self-consistency through an imagine-and-revise loop. We further introduce supportive spatial optimization to ease pose optimization via global-to-local coordinate re-parameterization. Extensive experiments across diverse scene types and instructions demonstrate that R$^3$L produces more physically feasible and semantically consistent layouts. Notably, our analysis shows that resolving frame-induced inconsistencies is crucial for reliable multi-hop relative spatial reasoning. The code is available at https://github.com/Neal2020GitHub/R3L.

The Earth's subsurface is a cornerstone of modern society, providing essential energy resources like hydrocarbons, geothermal, and minerals while serving as the primary reservoir for $CO_2$ sequestration. However, full physics numerical simulations of these systems are notoriously computationally expensive due to geological heterogeneity, high resolution requirements, and the tight coupling of physical processes with distinct propagation time scales. Here we propose the $\textbf{Adaptive Physics Transformer}$ (APT), a geometry-, mesh-, and physics-agnostic neural operator that explicitly addresses these challenges. APT fuses a graph-based encoder to extract high-resolution local heterogeneous features with a global attention mechanism to resolve long-range physical impacts. Our results demonstrate that APT outperforms state-of-the-art architectures in subsurface tasks across both regular and irregular grids with robust super-resolution capabilities. Notably, APT is the first architecture that learns directly from HR-adaptive mesh refinement simulations. We also demonstrate APT's favorable scaling behavior and cross-dataset learning capability, positioning it as a robust and scalable backbone for large-scale subsurface foundation model development.

Tree ensembles are machine learning models with strong predictive performance and interpretability, and remain widely used for tabular data. Standard pruning methods for tree ensembles typically optimize an accuracy-compression trade-off and may change a subset of predictions, potentially compromising decision consistency. Faithful pruning methods address this issue by preserving prediction equivalence over the entire input space, but this requirement leads to lower compression ratios. We propose **PINE**, a pruning method that provides strong guarantees within an in-distribution region. PINE preserves prediction equivalence within this region and controls the region size using a single parameter $\alpha$ via conformal calibration. Experiments on 12 public tabular datasets show that PINE improves the compression ratio by up to 30% while preserving predictions at a comparable level to existing faithful pruning methods.

Training-free diffusion guidance offers a flexible framework for leveraging off-the-shelf classifiers without additional training. Yet, current approaches hinge on posterior approximations via Tweedie’s formula, which often yield unreliable guidance, particularly in low-density regions. Stochastic optimal control (SOC), in contrast, enables principled posterior sampling but remains computationally prohibitive for efficient inference. In this work, we reconcile the strengths of these paradigms by introducing Stein Diffusion Guidance (SDG), a novel training-free framework grounded in a surrogate SOC objective. We establish a new theoretical bound on the SOC value function, revealing the necessity of correcting approximate posteriors to reflect true diffusion dynamics. Building on Stein variational inference, SDG computes the steepest descent direction that minimizes the Kullback-Leibler divergence between approximate and true posteriors. By integrating a principled Stein correction mechanism along with a novel running cost functional, SDG enables effective guidance in low-density regions. Our experiments on diverse image-guidance tasks and on challenging small-ligand sampling for protein docking suggest that SDG consistently outperforms standard training-free guidance methods and highlights its potential for broader posterior sampling problems beyond high-density regimes.

Language models are increasingly used not only as standalone predictors but also as components in larger inference systems, from test-time scaling to multi-agent collaboration. We study *language model networks*, where pre-trained language models serve as reusable nodes and intelligence emerges from their topology, communication, and optimization. Existing systems mostly communicate through natural language: easy to deploy, but discrete, inefficient, and hard to optimize from end-task supervision. We propose LMNet, a dense and differentiable realization of this paradigm. LMNet uses stripped LLMs as vertex modules and trainable seq2seq modules as communication edges, enabling intermediate nodes to exchange dense vectors while preserving natural-language input and output at the system boundary. By bypassing intermediate embedding and de-embedding, LMNet enables efficient information transfer, end-to-end gradient optimization, and learned communication beyond hand-designed protocols. Experiments show performance with small additional training cost and effective adaptation under limited supervision.

We propose a data augmentation method for offline reinforcement learning, motivated by active positioning problems. Particularly, our approach enables the training of off-policy models from a limited number of suboptimal trajectories. We introduce a trajectory-based augmentation technique that exploits task structure and the geometric relationship between rewards, value functions, and mathematical properties of logging policies. During data collection, our augmentation supports suboptimal logging policies, leading to higher data quality and improved offline reinforcement learning performance. We provide theoretical justification for these strategies and validate them empirically across positioning tasks of varying dimensionality and under partial observability.

LoRA has become a widely adopted method for PEFT, and its initialization methods have attracted increasing attention. However, existing methods have notable limitations: many methods do not incorporate target-domain data, while gradient-based methods exploit data only at a shallow level by relying on one-step gradient decomposition. In this paper, we establish a theoretical framework for data-aware LoRA initialization. Starting from minimizing the expectation of the parameter discrepancy between the fine-tuned and target models, we derive an optimization problem with two components: a bias term, which is related to the parameter distance between the fine-tuned and target models, and is approximated using a Fisher–gradient formulation to preserve anisotropy; and a variance term, which accounts for the uncertainty introduced by sampling stochasticity through the Fisher information. Solving this problem yields an optimal initialization strategy for LoRA, based on which we develop an efficient algorithm, LoRA-DA. Empirical results across multiple benchmarks demonstrate that LoRA-DA consistently improves final accuracy over existing initialization methods. Additional studies show faster, more stable convergence, robustness across ranks, and only a small initialization overhead for LoRA-DA. The source code is available at https://github.com/zqy0126/LoRA-DA.

Long-video temporal reasoning remains a bottleneck for Large Video Language Models (LVLMs). Existing reinforcement-learning approaches reward only final-answer correctness, so they cannot distinguish answers reached through grounded reasoning from those reached through fabricated chronology; the intermediate temporal claims that constitute the reasoning are never verified. We trace this gap to a structural correspondence between two kinds of traces: a video has its own temporal trace, an ordered sequence of how events unfold, while a model's answer is built up through a reasoning trace, an ordered sequence of intermediate temporal claims. Correct reasoning requires the latter to mirror the former, claim by claim. We act on this correspondence with two contributions. We introduce Temporal Reasoning Traces (TRT), a structured index of a video's ordered event chains that exposes a small set of deterministic verification primitives, materializing the temporal trace as a programmatically queryable object. We then propose temporal-enhanced GRPO, a reinforcement-learning procedure whose reward decomposes into per-block components, each computed by a TRT primitive on a typed think block of the reasoning trace. Because the reward is fully symbolic, fabricated temporal claims are caught at the per-claim level rather than masked by a correct final answer. Across long-video reasoning benchmarks, our model achieves state-of-the-art performance, with the largest gains on out-of-domain reasoning tasks such as Video-Holmes, CG-Bench-Reasoning, and VRBench.

Flow-based text-to-image models follow deterministic trajectories, making it costly to explore diverse modes under limited sampling budgets. Existing approaches to improving diversity often rely on retraining or degrade image fidelity. To address this limitation, we present a training-free, inference-time control mechanism that makes the flow itself diversity-aware. Our core insight is to encourage diversity through guidance that is geometrically decoupled from the model’s quality-seeking direction. Our method simultaneously encourages lateral spread among trajectories via a feature-space objective and reintroduces uncertainty through a time-scheduled stochastic perturbation. Crucially, this perturbation is projected to be orthogonal to the generation flow, a geometric constraint that allows it to boost variation without degrading image details or prompt fidelity. Theoretically, we show that this design monotonically increases a volume surrogate while approximately preserving the marginal distribution, providing a principled explanation for the robustness of generation quality. Empirically, across multiple text-to-image settings under fixed sampling budgets, our method consistently improves diversity metrics such as the Vendi Score and Brisque over strong baselines, while upholding image quality and alignment.

The advancement of LLMs and their accessibility have triggered renewed interest in multi-agent reinforcement learning as robust and adaptive frameworks for dynamically changing environments. This paper introduces RL-Focal, a two-stage RL agent framework that routes and ensembles LLMs. First, we develop the Decider RL-agent, which learns to dynamically select an ensemble of small size ($m_i$) among $N$ LLMs ($m_i \ll N$) for incoming queries from a user-defined downstream task $i$, by maximizing both error-diversity and reasoning-performance of the selected ensemble through iterative updates of task-adaptive rewards and policy. Second, to enable effective fusion of dynamically selected LLMs, we develop the stage-2 Fusion RL-agent, which learns to resolve reasoning conflicts from different LLMs and dynamically adapt to different ensemble teams composed by the Decider Agent for different downstream tasks. {\em Third}, we introduce the focal diversity metric to better model the error correlations among multiple LLMs further improving the generalization performance of the Decider Agent, which actively prunes the ensemble combinations. By focal diversity, we enhance performance across tasks by effectively promoting reward-aware and policy-adaptive ensemble selection and inference fusion. Extensive evaluations on five benchmarks show that RL-Focal achieves the performance improvement of 8.48\% with an ensemble of small size compared to the best individual LLM in a pool and offers stronger robustness. Code is available at \url{https://anonymous.4open.science/r/rl-focal-8DCF/}

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 present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and input preprocessing pipeline. The key idea is a task-level side channel induced by ViT-style patchification: when a synthetic grid image is aligned with the hidden patch grid, boundary cues are erased at tokenization, causing periodic accuracy drop. By sweeping the grid cell size and measuring these collapses, we infer the patch size; by introducing padding and a consistency-check test, we further identify whether preprocessing is dynamic- or fixed-resolution and recover the target resize resolution. Across open-source Qwen-VL variants and proprietary models including GPT and Claude, we reliably recover tokenizer-related parameters. Finally, we show that such leakage enables preprocessing-aware transfer attacks and model-targeted adversarial manipulation.

Estimating treatment effects from observational text is increasingly practical with Large Language Models (LLMs). However, applying causal representation learning directly to high-dimensional LLM embeddings faces a fundamental barrier: empirical Wasserstein matching suffers from the curse of dimensionality, rendering standard generalization guarantees effectively vacuous. We propose SPIKED-CFR, a framework bridging this gap by assuming a Spiked Structure, where treatment selection bias is assumed to manifest primarily as a low-dimensional treated--control discrepancy in the semantic representation. We develop Wasserstein Projection Pursuit, a minimax objective that adversarially learns an orthogonal projection on the Stiefel manifold to identify and balance only this subspace while preserving prognostic information. Under a spiked structure, we show the projected discrepancy can be estimated at a rate governed by the intrinsic dimension $k \ll D$, and we derive a tighter PEHE generalization bound that depends on $k$ rather than the ambient embedding dimension. Experiments on four semi-synthetic benchmarks and four real-world clinical benchmarks demonstrate improved accuracy and robustness over strong baselines.

Test-time compute (TTC) has become an increasingly prominent paradigm for enhancing large language models (LLMs). Despite the empirical success of methods such as best-of-$n$ (BoN) sampling and sequential revision, their fundamental limits remain unclear. We address this gap by analyzing a mixture-of-reference policy model and proving that standard BoN is inherently suboptimal. To move closer to the optimal frontier, we study reward-filtered sequential inference, a simple procedure that selectively incorporates only high-reward generations into the context. This mechanism concentrates computation on superior policy candidates and suppresses inferior ones. On the theoretical side, we show that reward-filtered sequential inference yields strictly stronger guarantees than standard TTC paradigms. On the empirical side, we evaluate such an inference strategy across diverse benchmarks and observe consistent improvements over widely used approaches, demonstrating the practical effectiveness of our framework.

Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex, multi-modal behaviors. However, existing methods face a stark trade-off: slow, iterative models like diffusion policies are computationally expensive, while fast, single-step models like consistency policies often suffer from degraded performance. In this paper, we demonstrate that it is possible to bridge this gap. The key to moving beyond the limitations of individual methods, we argue, lies in a unifying perspective that views modern generative models—including diffusion, flow matching, and consistency models—as specific instances of learning a continuous-time generative trajectory governed by an Ordinary Differential Equation (ODE). This principled foundation provides a clearer design space for generative policies in RL and allows us to propose *Generative Trajectory Policies* (GTPs), a new and more general policy paradigm that learns the entire solution map of the underlying ODE. To make this paradigm practical for offline RL, we further introduce two key theoretically principled adaptations. Empirical results demonstrate that GTP achieves state-of-the-art performance on D4RL benchmarks -- it significantly outperforms prior generative policies, achieving perfect scores on several notoriously hard AntMaze tasks.

We study the correlation clustering problem in the node-arrival data stream model. Unlike previous work, where the stream consists of the graph's edges, we focus on the setting in which the stream contains only the nodes. This model better reflects many real-world scenarios in which the data stream naturally consists of raw objects (e.g., images, tweets), and the similar/dissimilar edges are derived through a similarity function. We present *C*$^4$*Approx*, a streaming algorithm that approximates the cost of correlation clustering using sublinear space in the number of nodes and a constant number of passes. We further complement this result with lower bounds. Experiments on real-world datasets show that by storing only 2\% of the nodes, our algorithm achieves performance comparable to the classic *Pivot* algorithm and the more recent *PrunedPivot* algorithm, even on sparse graphs.

Language models famously improve under a smooth scaling law, but some specific capabilities exhibit sudden breakthroughs in performance. Advocates of "emergence" view these capabilities as unlocked at a specific scale, but others attribute breakthroughs to superficial metric thresholding effects. We propose that breakthroughs are instead driven by continuous changes in the probability distribution of training outcomes when performance is bimodally distributed across random seeds. We show that different random seeds can produce either smooth or emergent scaling trends in synthetic length generalization tasks, multiple choice question answering, and grammatical generalization. We reveal that sharp breakthroughs in metrics are produced by underlying continuous changes in their distribution across seeds. These distributions may become abruptly bimodal at a capacity threshold—but this threshold appears at scales well before most seeds achieve breakthrough. Our observations hold true even under continuous loss metrics, confirming that random variation must be considered when predicting a model's performance from its scale.