ICLR 2026 Papers

Neural networks applied to sequential decision-making tasks typically rely on latent representations of environment states. While environment dynamics dictate how semantic states evolve, the corresponding latent transitions are usually left implicit, leaving room for misalignment between the two. We propose to model latent dynamics explicitly by drawing an analogy between Markov decision process (MDP) trajectories and ordinary differential equation (ODE) flows: in both cases, the current state fully determines its successors. Building on this view, we introduce a neural ODE–based regularization method that enforces latent embeddings to follow consistent ODE flows, thereby aligning representation learning with environment dynamics. Although broadly applicable to deep learning agents, we demonstrate its effectiveness in reinforcement learning by integrating it into Actor–Critic algorithms, where it yields major performance gains across various standard Atari benchmarks for A2C as well as gridworld environments for PPO.

Large Language Models (LLMs) are increasingly deployed in multi-agent systems, where effective inter-model communication is crucial. Existing communication protocols either rely on natural language, incurring high inference costs and information loss, or on hidden states, which suffer from information concentration bias and inefficiency. To address these limitations, we propose KVComm, a novel communication framework that enables efficient communication between LLMs through selective sharing of KV pairs. KVComm leverages the rich information encoded in the KV pairs while avoiding the pitfalls of hidden states. We introduce a KV layer-wise selection strategy based on attention importance scores with a Gaussian prior to identify the most informative KV pairs for communication. Extensive experiments across diverse tasks and model pairs demonstrate that KVComm achieves comparable performance to the upper-bound method, which directly merges inputs to one model without any communication, while transmitting as few as 30\% of layers' KV pairs. Our study highlights the potential of KV pairs as an effective medium for inter-LLM communication, paving the way for scalable and efficient multi-agent systems.

A reliable representation of uncertainty is essential for the application of modern machine learning methods in safety-critical settings. In this regard, the use of credal sets (i.e., convex sets of probability distributions) has recently been proposed as a suitable approach to representing epistemic uncertainty. However, as with other approaches to epistemic uncertainty, training credal predictors is computationally complex and usually involves (re-)training an ensemble of models. The resulting computational complexity prevents their adoption for complex models such as foundation models and multi-modal systems. To address this problem, we propose an efficient method for credal prediction that is grounded in the notion of relative likelihood and inspired by techniques for the calibration of probabilistic classifiers. For each class label, our method predicts a range of plausible probabilities in the form of an interval. To produce the lower and upper bounds of these intervals, we propose a technique that we refer to as decalibration. Extensive experiments show that our method yields credal sets with strong performance across diverse tasks, including coverage–efficiency evaluation, out-of-distribution detection, and in-context learning. Notably, we demonstrate credal prediction on models such as TabPFN and CLIP—architectures for which the construction of credal sets was previously infeasible.

Spatio-temporal point process (STPP) data appear in many domains. A natural way to model them is to describe how the instantaneous event rate varies over space and time given the observed history which enables interpretation, interaction detection, and forecasting. Traditional parametric kernel-based models, while historically dominant, struggle to capture complex nonlinear patterns. In contrast, deep learning methods leverage the representational power of neural networks to aggregate historical events and integrate spatio-temporal point processes. However, existing deep learning methods often process space and time independently, overlooking the spatio-temporal dependencies. To address this limitation, we propose a novel method called Topology-ENhanced Diffusion Model (TEN-DM), including two key components namely spatio-temporal graph construction and multimodal topological feature representation learning. Further, we use temporal query technique to effectively capture periodic temporal patterns for learning effective temporal representations. Extensive experiments show the effectiveness of TEN-DM on multiple STPP datasets compared to state-of-the-art methods.

Modern optimizers like Adam and Muon are central to training large language models, but their reliance on first- and second-order momenta introduces significant memory overhead, which constrains scalability and computational efficiency. In this work, we re-frame the exponential moving average (EMA) used in these momenta as the training of a linear regressor via online gradient flow. Building on this equivalence, we introduce LoRA-Pre, a novel low-rank optimizer designed for efficient pre-training. Specifically, LoRA-Pre reduces the optimizer's memory footprint by decomposing the full momentum matrix into a compact low-rank subspace within the online linear learner, thereby maintaining optimization performance while improving memory efficiency. We empirically validate LoRA-Pre's efficacy by pre-training models from the Llama architecture family, scaling from 60M to 1B parameters. LoRA-Pre achieves the highest performance across all model sizes. Notably, LoRA-Pre demonstrates remarkable rank efficiency, achieving comparable or superior results using only 1/8 the rank of baseline methods. Beyond pre-training, we evaluate LoRA-Pre's effectiveness in fine-tuning scenarios. With the same rank, LoRA-Pre consistently outperforms all efficient fine-tuning baselines. Specifically, compared to standard LoRA, LoRA-Pre achieves substantial improvements of 3.14 points on Llama-3.1-8B and 6.17 points on Llama-2-7B, validating our approach's effectiveness across both pre-training and fine-tuning paradigms.

DNA methylation (DNAm) is a key epigenetic modification that regulates gene expression and is pivotal in development and disease. However, profiling DNAm at genome scale is challenging: of $\textasciitilde$28 million CpG sites in the human genome, only about 1–3\% are typically assayed in common datasets due to technological limitations and cost. Recent deep learning approaches, including masking-based generative Transformer models, have shown promise in capturing DNAm–gene expression relationships, but they rely on partially observed DNAm values for unmeasured CpGs and cannot be applied to completely unmeasured samples. To overcome this barrier, we introduce MethylProphet, a gene-guided, context-aware Transformer model for whole-genome DNAm inference without any measured DNAm input. MethylProphet compresses comprehensive gene expression profiles ($\textasciitilde$25K genes) through an efficient bottleneck multilayer perceptron, and encodes local CpG sequence context with a specialized DNA tokenizer. These representations are integrated by a Transformer encoder to predict site-specific methylation levels. Trained on large-scale pan-tissue whole-genome bisulfite sequencing data from ENCODE (1.6 billion CpG–sample pairs, $\textasciitilde$322 billion tokens), MethylProphet demonstrates strong performance in hold-out evaluations, accurately inferring DNAm at unmeasured CpGs and generalizing to unseen samples. Furthermore, application to TCGA pan-cancer data (chromosome 1, 9,194 samples; $\textasciitilde$450 million training pairs, 91 billion tokens) highlights its potential for pan-cancer whole-genome methylome imputation. MethylProphet offers a powerful and scalable foundation model for epigenetics, providing high-resolution methylation landscape reconstruction and advancing both biological research and precision medicine.

Many real-world classification problems, such as plant identification, have extremely long-tailed class distributions. In order for prediction sets to be useful in such settings, they should (i) provide good class-conditional coverage, ensuring that rare classes are not systematically omitted from the prediction sets, and (ii) be a reasonable size, allowing users to easily verify candidate labels. Unfortunately, existing conformal prediction methods, when applied to the long-tailed setting, force practitioners to make a binary choice between small sets with poor class-conditional coverage or sets with very good class-conditional coverage but that are extremely large. We propose methods with guaranteed marginal coverage that smoothly trade off between set size and class-conditional coverage. First, we introduce a new conformal score function, coined prevalence-adjusted softmax, that targets macro-coverage, a relaxed notion of class-conditional coverage. Second, we propose a label-weighted conformal prediction method that allows us to interpolate between marginal and class-conditional conformal prediction. We demonstrate our methods on Pl@ntNet-300K and iNaturalist-2018, two long-tailed image datasets with 1,081 and 8,142 classes, respectively.

Graphon models have emerged as powerful tools for modeling complex network structures by capturing connection probabilities among nodes. A key challenge in their application lies in accurately characterizing the graphon function, particularly with respect to parameters that govern its smoothness, which significantly impact the estimation accuracy. In this article, we propose a novel graphon cross-validation method for selecting tuning parameters and estimation approaches. Our method is both theoretically sound and computationally efficient. We show that our proposed cross-validation score is asymptotically parallel to the estimation error. Through extensive simulations and real-world applications, we demonstrate that our method consistently delivers superior computational efficiency and accuracy.

Predicting spatial gene expression from H\&E histology offers a scalable and clinically accessible alternative to sequencing, but realizing clinical impact requires models that generalize across cancer types and capture biologically coherent signals. Prior work is often limited to per-cancer settings and variance-based evaluation, leaving functional relevance underexplored. We introduce HistoPrism, an efficient transformer-based architecture for pan-cancer prediction of gene expression from histology. To evaluate biological meaning, we introduce a pathway-level benchmark, shifting assessment from isolated gene-level variance to coherent functional pathways. HistoPrism not only surpasses prior state-of-the-art models on highly variable genes and, but more importantly, achieves substantial gains on pathway-level prediction, demonstrating its ability to recover biologically coherent transcriptomic patterns. With strong pan-cancer generalization and improved efficiency, HistoPrism establishes a new standard for clinically relevant transcriptomic modeling from routinely available histology.

Node affinity prediction is a common task that is widely used in temporal graph learning with applications in social and financial networks, recommender systems, and more. Recent works have addressed this task by adapting state-of-the-art dynamic link property prediction models to node affinity prediction. However, simple heuristics, such as persistent forecast or moving average, outperform these models. In this work, we analyze the challenges in training current Temporal Graph Neural Networks for node affinity prediction and suggest appropriate solutions. Combining the solutions, we develop NAVIS - Node Affinity prediction model using VIrtual State, by exploiting the equivalence between heuristics and state space models. While promising, training NAVIS is non-trivial. Therefore, we further introduce a novel loss function for node affinity prediction. We evaluate NAVIS on TGB and show that it outperforms the state of the art, including heuristics.

Accurate simulation of flow fields around tandem geometries is critical for engineering design but remains computationally intensive. Existing machine learning approaches typically focus on simpler cases and lack evaluation on multi-body configurations. To support research in this area, we present **TandemFoilSet**: five tandem-airfoil datasets (4152 tandem-airfoil simulations) paired with four single-airfoil counterparts, for a total of 8104 CFD simulations. We provide benchmark results of a curriculum learning framework using a directional integrated distance representation, residual pre-training, training schemes based on freestream conditions and smooth-combined estimated fields, and a domain decomposition strategy. Evaluations demonstrate notable gains in prediction accuracy. We believe these datasets will enable future work on scalable, data-driven flow prediction for tandem-airfoil scenarios.

Conformal prediction provides a model-agnostic framework for uncertainty quantification with finite-sample validity guarantees, making it an attractive tool for constructing reliable prediction sets. However, existing approaches commonly rely on residual-based conformity scores, which impose geometric constraints and struggle when the underlying distribution is multimodal. In particular, they tend to produce overly conservative prediction areas centred around the mean, often failing to capture the true shape of complex predictive distributions. In this work, we introduce JAPAN (Joint Adaptive Prediction Areas with Normalising-Flows), a flow-based framework that uses density estimates for several conformal scores. By leveraging flow-based models, JAPAN estimates the (predictive) density and constructs prediction areas by thresholding on the estimated density scores, enabling compact, potentially disjoint, and context-adaptive regions that retain finite-sample coverage guarantees. We theoretically motivate the efficiency of JAPAN and empirically validate it across multivariate regression and forecasting tasks, demonstrating good calibration and tighter prediction areas compared to existing baselines. Furthermore, several density-based conformity scores showcase the flexibility of our proposed framework.

Rotary Position Embeddings (RoPE) are widely used in Transformers to encode positional information in token representations, yet the internal frequency structure of RoPE remains poorly understood. Previous studies have reported conflicting findings on the roles of high- and low-frequency dimensions, offering empirical observations but no unifying explanation. In this paper, we present a systematic framework that bridges these disparate results. We introduce Frequency Entropy (FE), a metric that quantifies the effective utilization of each RoPE frequency dimension, and we provide an analysis of how RoPE’s sinusoidal components contribute to model representations on a per-dimension basis. Based on an analysis of the Llama-4 model, which incorporates both RoPE and NoPE layers, we find that the periodicity captured by FE appears in RoPE layers but not in NoPE layers. Furthermore, FE identifies dimensions in which energy concentrates under RoPE. These characteristics are observed across the spectrum rather than being confined to specific dimensions. Moreover, attenuating extreme-entropy dimensions at inference yields downstream accuracy that is statistically indistinguishable from the baseline, with modest perplexity improvements on average, suggesting that such dimensions are often redundant. Overall, FE provides a simple, general diagnostic for RoPE with implications for analysis and design.

Diffusion models deliver state-of-the-art image quality. However, sampling is costly at inference time because it requires many model evaluations (number of function evaluations, NFEs). To reduce NFEs, classical ODE multistep methods have been adopted. Yet differences in the choice of prediction type (noise/data/velocity) and integration domain (half log-SNR/noise-to-signal ratio) lead to different outcomes. We introduce Dual-Solver, which generalizes multistep samplers by introducing learnable parameters that continuously (i) interpolate among prediction types, (ii) select the integration domain, and (iii) adjust the residual terms. It maintains the traditional predictor-corrector structure and guarantees second-order local accuracy. These parameters are learned with a classification-based objective using a frozen pretrained classifier (e.g., ViT or CLIP). On ImageNet class-conditional generation (DiT, GM-DiT) and text-to-image (SANA, PixArt-$\alpha$), Dual-Solver improves FID and CLIP scores in the low-NFE regime ($3\le$ NFE $\le 9$) across backbones.

State-of-the-art protein structure predictors have revolutionized structural biology, yet quadratic memory growth with token length makes end-to-end inference impractical for large complexes beyond a few thousand tokens. We introduce \textsc{HierAFold}, a hierarchical pipeline that exploits the modularity of large complexes via PAE-guided (Predicted Aligned Error) subunit decomposition, targeted interface-aware refinement, and confidence-weighted assembly. PAE maps localize rigid intra-chain segments and sparse inter-chain interfaces, enabling joint refinement of likely interacting subunits to capture multi-body cooperativity without increasing memory. \textsc{HierAFold} matches AlphaFold3 accuracy, raises success rates from 49.9\% (CombFold) to 73.1\% on recent PDB set. While for large complexes, it cuts peak memory by $\sim$25\,GB on a 4{,}000-token target ($\sim$40\%), successfully models complexes with over $5{,}000$ tokens that are out-of-memory for AlphaFold3, and raises success rates by two-fold compared with CombFold.