ICLR 2026 Papers

Map generation tasks, featured by extensive non-structural vectorized data (e.g., points, polylines, and polygons), pose significant challenges to common pixel-wise generative models. Past works, by segmenting and then performing various vectorized post-processing, usually sacrifice accuracy. Motivated by the recent huge success of auto-regressive visual-language modeling, we propose the first map foundational model: Map Auto-Regressor (MARS), that is capable of generating both multi-polyline road networks and polygon buildings in a unified manner. We collected by far the largest multi-class map dataset, MAP-3M, to support the robust training. Extensive benchmarks highlight the superiority of MARS against literature works. Meanwhile, benefited from the auto-regressive and teaching-forcing based training, we develop the “Chat with MARS” capability that enables interactive human-in-the-loop map generation and correction.

Recently, there has been a growing interest in Long-term Time Series Forecasting (LTSF), which involves predicting long-term future values by analyzing a large amount of historical time-series data to identify patterns and trends. Significant challenges exist in LTSF due to its complex temporal dependencies and high computational demands. Although Transformer-based models offer high forecasting accuracy, they are often too compute-intensive to be deployed on devices with hardware constraints. In this paper, we propose MixLinear, which synergistically combines orthogonal segment-based trend extraction in the time domain with adaptive low-rank spectral filtering in the frequency domain. Our approach exploits the complementary structural sparsity of time series: local temporal patterns are efficiently captured through mathematically linear transformations that separate intra-segment and inter-segment correlations, while global trends are compressed into an ultra-low-dimensional frequency latent space through learnable rank-constrained filters. By reducing the parameter scale of a downsampled $n$-length input/output one-layer linear model from $O(n^2)$ to $O(n)$, MixLinear achieves efficient computation without sacrificing accuracy. Extensive evaluations show that MixLinear achieves forecasting performance comparable to, or surpasses, state-of-the-art models with significantly fewer parameters ($0.1K$), which makes it well suited for deployment on devices with limited computational capacity.

Multivariate time series forecasting (MTSF) plays a vital role in numerous real-world applications, yet existing models remain constrained by their reliance on a limited historical context. This limitation prevents them from effectively capturing global periodic patterns that often span cycles significantly longer than the input horizon—despite such patterns carrying strong predictive signals. Naïve solutions, such as extending the historical window, lead to severe drawbacks, including overfitting, prohibitive computational costs, and redundant information processing. To address these challenges, we introduce the Global Temporal Retriever (GTR), a lightweight and plug-and-play module designed to extend any forecasting model’s temporal awareness beyond the immediate historical context. GTR maintains an adaptive global temporal embedding of the entire cycle and dynamically retrieves and aligns relevant global segments with the input sequence. By jointly modeling local and global dependencies through a 2D convolution and residual fusion, GTR effectively bridges short-term observations with long-term periodicity without altering the host model architecture. Extensive experiments on six real-world datasets demonstrate that GTR consistently delivers state-of-the-art performance across both short-term and long-term forecasting scenarios, while incurring minimal parameter and computational overhead. These results highlight GTR as an efficient and general solution for enhancing global periodicity modeling in MTSF tasks. Code is available at this repository: https://github.com/macovaseas/GTR.

Object counting is a fundamental task in computer vision, with broad applicability in many real-world scenarios. Fully-supervised counting methods require costly point-level annotations per object. Few weakly-supervised methods leverage only image-level object counts as supervision and achieve fairly promising results. They are, however, often limited to counting a single category, \eg person. In this paper, we propose WS-COC, the first MLLM-driven weakly-supervised framework for class-agnostic object counting. Instead of directly fine-tuning MLLMs to predict object counts, which can be challenging due to the modality gap, we incorporate three simple yet effective strategies to bootstrap the counting paradigm in both training and testing: First, a divide-and-discern dialogue tuning strategy is proposed to guide the MLLM to determine whether the object count falls within a specific range and progressively break down the range through multi-round dialogue. Second, a compare-and-rank count optimization strategy is introduced to train the MLLM to optimize the relative ranking of multiple images according to their object counts. Third, a global-and-local counting enhancement strategy aggregates and fuses local and global count predictions to improve counting performance in dense scenes. Extensive experiments on FSC-147, CARPK, PUCPR+, and ShanghaiTech show that WS-COC matches or even surpasses many state-of-art fully-supervised methods while significantly reducing annotation costs.

Table Question Answering (Table QA) in real-world settings must operate over both structured databases and semi-structured tables containing textual fields. However, existing benchmarks are tied to fixed data formats and have not systematically examined how representation itself affects model performance. We present the first controlled study that isolates the role of table representation by holding content constant while varying structure. Using a verbalization pipeline, we generate paired structured and semi-structured tables, enabling direct comparisons across modeling paradigms. To support detailed analysis, we introduce a diagnostic benchmark with splits along table size, join requirements, query complexity, and schema quality. Our experiments reveal consistent trade-offs: SQL-based methods achieve high accuracy on structured inputs but degrade on semi-structured data, LLMs exhibit flexibility but reduced precision, and hybrid approaches strike a balance, particularly under noisy schemas. These effects intensify with larger tables and more complex queries. Ultimately, no single method excels across all conditions, and we highlight the central role of representation in shaping Table QA performance. Our findings provide actionable insights for model selection and design, paving the way for more robust hybrid approaches suited for diverse real-world data formats.

Open-ended segmentation requires models capable of generating free-form descriptions of previously unseen concepts and regions. Despite advancements in model development, current evaluation protocols for open-ended segmentation tasks fail to capture the true semantic accuracy of the generated descriptions. We empirically demonstrate that embedding‐based similarity score mappings diverge significantly from human judgments. To address this issue, we introduce a novel mapping function that considers multiple lexical relationships between free‐form outputs and test‐vocabulary labels, yielding much closer alignment with human annotations. We integrate this mapping into a robust evaluation framework and re‐benchmark previous state‐of‐the‐art methods. Additionally, we present the first Multi-modal Large‐Language Model trained with a contrastive objective to jointly align visual regions and textual descriptions, achieving new state‐of‐the‐art results in open‐ended panoptic segmentation.

A central goal in systems biology and drug discovery is to predict the transcriptional response of cells to perturbations. This task is challenging due to the noisy, sparse nature of single-cell measurements and the fact that perturbations often induce population-level shifts rather than changes in individual cells. Existing deep learning methods typically assume cell-level correspondences, limiting their ability to capture such global effects. We present **scDFM**, a generative framework based on conditional flow matching that models the full distribution of perturbed cells conditioned on control states. By incorporating an MMD objective, our method aligns perturbed and control populations beyond cell-level correspondences. To further improve robustness to sparsity and noise, we propose the Perturbation-Aware Differential Transformer architecture (PAD-Transformer), a backbone that leverages gene interaction graphs and differential attention to capture context-specific expression changes. **scDFM** outperforms prior methods across multiple genetic and drug perturbation benchmarks, excelling in both unseen and combinatorial settings. In the combinatorial setting, it reduces MSE by 19.6\% over the strongest baseline. These results highlight the importance of distribution-level generative modeling for robust $\textit{in silico}$ perturbation prediction. The code is available at https://github.com/AI4Science-WestlakeU/scDFM.

Tool-augmented large language models (LLMs), hereafter LLM agents, leverage external tools to solve diverse tasks and interface with the real world. However, current training practices largely rely on supervised fine-tuning (SFT) over static trajectories or reinforcement learning (RL) on narrow tasks, which generalize poorly beyond development settings and lead to brittleness with new tools and unseen workflows. Because code execution reflects many structures of real-world workflows, we use coding problems as a structured substrate to build tool-use agent training environments with diverse task configurations. To this end, we introduce **CodeGym**, a scalable framework that synthesizes diverse, verifiable, and controllable multi-turn tool-use environments for agent RL, enabling LLM agents to explore and master various workflows actively. CodeGym converts static coding problems into interactive environments by extracting atomic functions or logic into callable tools, yielding verifiable tasks that span various tool-execution workflows. Models of varying sizes and chain-of-thought configurations, trained in CodeGym, exhibit consistent out-of-distribution generalizability; for example, Qwen2.5-32B-Instruct achieves an absolute accuracy gain of 8.7 points on the OOD benchmark $\tau$-Bench. These results highlight CodeGym as a step toward scalable general-purpose RL environments for training tool-use behaviors that align with real-world agent workflows.

From adversarial robustness to multi-agent learning, many machine learning tasks can be cast as finite-sum min–max optimization or, more generally, as variational inequality problems (VIPs). Owing to their simplicity and scalability, stochastic gradient methods with constant step size are widely used, despite the fact that they converge only up to a bias term. Among the many heuristics adopted in practice, two classical techniques have recently attracted attention to mitigate this issue: \emph{\small Random Reshuffling} of data and \emph{\small Richardson–Romberg extrapolation} across iterates. In this work, we show that their composition not only cancels the leading linear bias term, but also yields an asymptotic cubic refinement. To the best of our knowledge, our work provides the first theoretical guarantees for such a synergy in structured non-monotone VIPs. Our analysis proceeds in two steps: (i) by smoothing the discrete noise induced by reshuffling, we leverage tools from continuous-state Markov chain theory to establish a law of large numbers and a central limit theorem for its iterates; and (ii) we employ spectral tensor techniques to prove that extrapolation debiases and sharpens the asymptotic behavior %accelerates convergence even under the biased gradient oracle induced by reshuffling. Finally, extensive experiments validate our theory, consistently demonstrating substantial speedups in practice.

Semantic representations can be framed as a structured, dynamic knowledge space through which humans navigate to retrieve and manipulate meaning. To investigate how humans traverse this geometry, we introduce a framework that represents concept production as navigation through embedding space. Using different transformer text embedding models, we construct participant-specific semantic trajectories based on cumulative embeddings and extract geometric and dynamical metrics, including distance to next, distance to centroid, entropy, velocity, and acceleration. These measures capture both scalar and directional aspects of semantic navigation, providing a computationally grounded view of semantic representation search as movement in a geometric space. We evaluate the framework on four datasets across different languages, spanning different property generation tasks: Neurodegenerative, Swear verbal fluency, Property listing task in Italian, and in German. Across these contexts, our approach distinguishes between clinical groups and concept types, offering a mathematical framework that requires minimal human intervention compared to typical labor-intensive linguistic pre-processing methods. Comparison with a non-cumulative approach reveals that cumulative embeddings work best for longer trajectories, whereas shorter ones may provide too little context, favoring the non-cumulative alternative. Critically, different embedding models yielded similar results, highlighting similarities between different learned representations despite different training pipelines. By framing semantic navigation as a structured trajectory through embedding space, bridging cognitive modeling with learned representation, thereby establishing a pipeline for quantifying semantic representation dynamics with applications in clinical research, cross-linguistic analysis, and the assessment of artificial cognition. https://github.com/jesuinovieira/semtraj-iclr2026

Temporal Video Grounding (TVG) aims to localize video segments corresponding to a given textual query, which often describes human actions. However, we observe that current methods, usually optimizing for high temporal Intersection-over-Union (IoU), frequently struggle to accurately recognize or understand the underlying actions in both the video and query, thus reducing the effectiveness of these methods. To address this, we propose a novel TVG framework that integrates inversion-based TVG as auxiliary objectives to maintain the model's action understanding ability. We introduce three kinds of inversion TVG tasks derived from the original TVG annotations: (1) Verb Completion, predicting masked verbs (actions) in queries given video segments; (2) Action Recognition, identifying query-described actions; and (3) Video Description, generating descriptions containing query-relevant actions given video segments. These inversion tasks are entirely derived from the original TVG tasks and are probabilistically integrated with them within a reinforcement learning framework. By leveraging carefully designed reward functions, the model preserves its ability to understand actions, thereby improving the accuracy of temporal grounding. Experiments show our method outperforms state-of-the-art approaches, achieving a 7.1\% improvement in R1@0.7 on Charades-STA for a 3B model.

Cartographic reasoning is the skill of interpreting geographic relationships by aligning legends, map scales, compass directions, map texts, and geometries across one or more map images. Although essential as a concrete cognitive capability and for critical tasks such as disaster response and urban planning, it remains largely unevaluated. Building on progress in chart and infographic understanding, recent large vision language model (LVLM) works on map visual question-answering (VQA) often simplify maps as a special case of charts. In contrast, map VQA demands comprehension of layered symbology (e.g., symbols, geometries, and text labels) as well as spatial relations tied to orientation and distance that often span multiple maps and are not captured by chart-style evaluations. To address this gap, we introduce FRIEDA, a benchmark for testing complex open-ended cartographic reasoning in LVLMs. FRIEDA sources real map images from documents and reports in various domains (e.g., geology, urban planning, and environmental assessment) and geographical areas. Following classifications in Geographic Information System (GIS) literature, FRIEDA targets all three categories of spatial relations: topological (border, equal, intersect, within), metric (distance), and directional (orientation). All questions require multi-step inference, and many require cross-map grounding and reasoning. We evaluate eleven state-of-the-art LVLMs under two settings: (1) the direct setting, where we provide the maps relevant to the question, and (2) the contextual setting, where the model may have to identify the maps relevant to the question before reasoning. Even the strongest models, Gemini-2.5-Pro and GPT-5-Think, achieve only 38.20\% and 37.20\% accuracy, respectively, far below human performance of 84.87\%. These results reveal a persistent gap in multi-step cartographic reasoning, positioning FRIEDA as a rigorous benchmark to drive progress on spatial intelligence in LVLMs.

Ensuring native-like quality of large language model (LLM) responses across many languages is challenging. To address this, we introduce MENLO, a framework that operationalizes the evaluation of native-like response quality based on audience design-inspired mechanisms. Using MENLO, we create a dataset of 6,423 human-annotated prompt–response preference pairs covering four quality dimensions with high inter-annotator agreement in 47 language varieties. Our evaluation reveals that zero-shot LLM judges benefit significantly from pairwise evaluation and our structured annotation rubrics, yet they still underperform human annotators on our dataset. We demonstrate substantial improvements through fine-tuning with reinforcement learning, reward shaping, and multi-task learning approaches. Additionally, we show that RL-trained judges can serve as generative reward models to enhance LLMs' multilingual proficiency, though discrepancies with human judgment remain. Our findings suggest promising directions for scalable multilingual evaluation and preference alignment. We release our dataset and evaluation framework to support further research in multilingual LLM evaluation.

Large language model agents operate in partially observable, long-horizon settings where obtaining supervision remains a major bottleneck. We address this by leveraging a source of supervision overlooked in existing post-training methods: ``unintended yet successful'' goals embedded within agent rollouts. We introduce Hindsight Supervised Learning (HSL), where an auxiliary LLM reviews each completed trajectory and relabels it with natural-language goals the agent actually achieved. HSL then pairs the trajectory with its relabeled goals and uses these pairs for additional fine-tuning. To mitigate suboptimality in the relabeled data, HSL incorporates irrelevant-action masking and sample reweighting. We show that HSL is flexible and compatible with existing post-training pipelines. It improves both SFT and DPO, with larger gains on long-horizon embodied and web agent tasks such as ALFWorld and WebShop. Moreover, HSL is sample-efficient: on ALFWorld, it surpasses baselines trained on the full dataset while using only one quarter of the ground-truth demonstrations.

The demand for efficient deployment of large language models (LLMs) has driven interest in quantization, which reduces inference cost, and parameter-efficient fine-tuning (PEFT), which lowers training overhead. This motivated the development of quantization-aware PEFT to produce accurate yet efficient quantized models. In this setting, reducing quantization error prior to fine-tuning is crucial for achieving high model accuracy. However, existing methods that rely on low-rank adaptation suffer from limited representational capacity. Recent Fourier-related transform (FT)-based adapters offer greater representational power than low-rank adapters, but their direct integration into quantized models often results in ineffective error reduction and increased computational overhead. To overcome these limitations, we propose QWHA, a method that integrates FT-based adapters into quantized models by employing the Walsh-Hadamard Transform (WHT) as the transform kernel, together with a novel adapter initialization scheme incorporating adaptive parameter selection and value refinement. We demonstrate that QWHA effectively mitigates quantization errors while facilitating fine-tuning, and that its design substantially reduces computational cost. Experimental results show that QWHA consistently outperforms baselines in low-bit quantization accuracy and achieves significant training speedups over existing FT-based adapters.

Uncertainty Quantification (UQ) is paramount for inference in engineering applications. A common inference task is to recover full-field information of physical systems from a small number of noisy observations, a usually highly ill-posed problem. Critically, engineering systems often have complicated and variable geometries prohibiting the use of standard Bayesian UQ. In this work, we introduce Geometric Autoencoders for Bayesian Inversion (GABI), a framework for learning geometry-aware generative models of physical responses that serve as highly informative geometry-conditioned priors for Bayesian inversion. Following a “learn first, observe later” paradigm, GABI distills information from large datasets of systems with varying geometries, without requiring knowledge of governing PDEs, boundary conditions, or observation processes, into a rich latent prior. At inference time, this prior is seamlessly combined with the likelihood of the specific observation process, yielding a geometry-adapted posterior distribution. Our proposed framework is architecture agnostic. A creative use of Approximate Bayesian Computation (ABC) sampling yields an efficient implementation that utilizes modern GPU hardware. We test our method on: steady-state heat over rectangular domains; Reynold-Averaged Navier-Stokes (RANS) flow around airfoils; Helmholtz resonance and source localization on 3D car bodies; RANS airflow over terrain. We find: the predictive accuracy to be comparable to deterministic supervised learning approaches in the restricted setting where supervised learning is applicable; UQ to be well calibrated and robust on challenging problems with complex geometries. The method provides a flexible geometry-aware train-once-use-anywhere foundation model which is independent of any particular observation process.

Knowledge Distillation (KD) is a widely adopted framework for compressing large models into compact student models by transferring knowledge from a high-capacity teacher. Despite its success, KD presents two persistent challenges: (1) the trade-off between optimizing for the primary task loss and mimicking the teacher's outputs, and (2) the gradient disparity arising from architectural and representational mismatches between teacher and student models. In this work, we propose Dynamic Trade-off Optimization for Knowledge Distillation (DTO-KD), a principled multi-objective optimization formulation of KD that dynamically balances task and distillation losses at the gradient level. Specifically, DTO-KD resolves two critical issues in gradient-based KD optimization: (i) gradient conflict, where task and distillation gradients are directionally misaligned, and (ii) gradient dominance, where one objective suppresses learning progress on the other. Our method adapts per-iteration trade-offs by leveraging gradient projection techniques to ensure balanced and constructive updates. We evaluate DTO-KD on large-scale benchmarks including ImageNet-1K for classification and COCO for object detection. Across both tasks, DTO-KD consistently outperforms prior KD methods, yielding state-of-the-art accuracy and improved convergence behavior. Furthermore, student models trained with DTO-KD exceed the performance of their non-distilled counterparts, demonstrating the efficacy of our multi-objective formulation for KD.

Real-world videos often show routine activities punctuated by memorable, surprising events. However, most Video-LLMs process videos by sampling frames uniformly, likely missing critical moments that define a video's narrative. We introduce SPIKE, an inference-time framework that quantifies Bayesian Surprise as the belief update triggered by new visual evidence in the video stream, identifying moments where new visual evidence conflicts with prior beliefs. SPIKE effectively localizes surprise in videos, correlated with humans on positive (FunQA) and negative (Oops!) surprise benchmarks. SPIKE-RL further improves on SPIKE's ability to detect surprise, leveraging GRPO to refine its belief hypotheses based on a reward signal from the video caption. SPIKE and SPIKE-RL guide query-agnostic surprise-weighted frame sampling, which allocates more frames to interesting moments in the video. With this strategy, we achieve consistent performance gains on five downstream benchmarks. By enabling Video-LLMs to track beliefs and register surprise, our work paves the way for more robust models that can revise their understanding in response to new information.

Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences can be expensive and time-consuming, which forms a strong barrier for PbRL. In this work, we address the problem of low query efficiency in offline PbRL, pinpointing two primary reasons: inefficient exploration and overoptimization of learned reward functions. In response to these challenges, we propose a novel algorithm, Offline PbRL via In-Dataset Exploration (OPRIDE), designed to enhance the query efficiency of offline PbRL. OPRIDE consists of two key features: a principled exploration strategy that maximizes the informativeness of the queries and a discount scheduling mechanism aimed at mitigating overoptimization of the learned reward functions. Through empirical evaluations, we demonstrate that OPRIDE significantly outperforms prior methods, achieving strong performance with notably fewer queries. Moreover, we provide theoretical guarantees of the algorithm's efficiency. Experimental results across various locomotion, manipulation, and navigation tasks underscore the efficacy and versatility of our approach.