ICML 2026 Papers

Large Multimodal Models (LMMs) demonstrate impressive in-context learning abilities from few multimodal demonstrations, yet the internal mechanisms supporting such task learning remain opaque. Building on prior work of Large Language Models, we show that a small subset of attention heads in Large Multimodal Models is responsible for transmitting representations of visual relations. The activations of these attention heads, termed $\textit{function vectors}$, can be extracted and manipulated to alter an LMM’s performance on relational tasks. First, using synthetic and real image datasets, we apply causal mediation analysis to identify attention heads that strongly influence relational predictions, and extract multimodal function vectors that improve zero-shot accuracy at inference time. We further demonstrate that these multimodal function vectors can be fine-tuned with a modest amount of training data, while keeping LMM parameters frozen, to significantly outperform in-context learning baselines. Finally, we show that relation-specific function vectors can be linearly combined to solve analogy problems involving novel and untrained visual relations, highlighting the strong generalization ability of this approach. Through experiments on two LMMs, including OpenFlamingo and Qwen3-VL, our results show that these models encode visual relational knowledge within localized internal structures, which can be systematically extracted and optimized, thereby advancing our understanding of model modularity and enhancing control over relational reasoning in LMMs.

Effectively scaling GUI automation is essential for computer-use agents (CUAs); however, existing work primarily focuses on scaling GUI grounding rather than the more crucial GUI planning, which requires more sophisticated data collection. In reality, the exploration process of a CUA across apps/desktops/web pages typically follows a tree structure, with earlier functional entry points often being explored more frequently. In this work, we find that organizing large-scale GUI trajectories into tree structures can effectively eliminate redundant exploration costs, while each branch node also provides key reasoning evidence for distinguishing adjacent trajectories. Therefore, we propose TreeCUA to efficiently scale GUI automation with tree-structured verifiable evolution. We propose a multi-agent collaborative framework to explore the environment, verify actions, summarize trajectories, and evaluate quality to generate high-quality and scalable GUI trajectories. To improve efficiency, we devise a novel tree-based topology to store and replay duplicate exploration nodes, and design an adaptive exploration algorithm to balance the depth (i.e., trajectory difficulty) and breadth (i.e., trajectory diversity). Moreover, we develop world knowledge guidance and global memory backtracking to avoid low-quality generation. Finally, we naturally extend and propose the TreeCUA-DPO method from abundant tree node information, improving GUI planning capability by referring to the branch information of adjacent trajectories. Experimental results show that TreeCUA and TreeCUA-DPO offer significant improvements, and out-of-domain (OOD) studies further demonstrate strong generalization. All trajectory node information and code will be open-sourced.

Natural language data follows a power-law distribution, with most knowledge and skills appearing at very low frequency. While a common intuition suggests that reweighting or curating data toward a uniform distribution may help models better learn these long-tail skills, we find a counterintuitive result: across a wide range of compositional reasoning tasks, such as state tracking and multi-step arithmetic, training under power-law distributions consistently outperforms training under uniform distributions. To understand this advantage, we introduce a minimalist skill-composition task and show that learning under a power-law distribution provably requires significantly less training data. Our theoretical analysis reveals that power law sampling induces a beneficial asymmetry that improves the pathological loss landscape, which enables models to first acquire high-frequency skill compositions with low data complexity, which in turn serves as a stepping stone to efficiently learn rare long-tailed skills. Our results offer an alternative perspective on what constitutes an effective data distribution for training models.

Vision-and-Language Navigation (VLN) empowered by Multimodal Large Language Models (MLLMs) is promise, yet remains challenged by long-horizon tasks with complex user instructions. Existing approaches that continuously condition on full instructions incur high latency due to abundant visual tokens and exacerbates instruction interference, where irrelevant text noise induces hallucinations. To address these limitations, we propose IDEAL-VLN ( \textbf{I}nstruction \textbf{DE}composition and \textbf{A}ction a\textbf{L}ignment ), a novel paradigm that reformulates navigation as a causal inference chain. We decompose the task into two sequential steps: Semantic Anchoring and Action Alignment. We adopt a \textit{Think-Before-Act} mechanism that first infers the immediate semantic anchor from the global context and then generates actions conditioned solely on this anchor. This design constructs an explicit information bottleneck, suppressing spurious correlations from irrelevant instruction. Moreover, to alleviate cognitive collapse and limited exploration during training, we introduce a hierarchical correction framework that combines semantic-level thought correction with a spatially-aware adaptive intervention strategy. This strategy adjusts expert intervention probability based on geodesic distance, effectively defining a semantic safety boundary. To support this paradigm, we contribute the Instruction-Aligned Navigation Dataset containing 160K image-text pairs. Extensive experiments demonstrate that IDEAL-VLN achieves state-of-the-art performance and robustness across major benchmarks while significantly reducing inference costs.

Watermarking has emerged as a critical solution for the detection and provenance tracing of content generated by large language models. However, existing methods still suffer from significant limitations, including difficulties in achieving efficient and personalized attribution, substantial degradation of generation quality, and low robustness against attacks. To address these challenges, we propose IPMark, the first IP-inspired hierarchical personalized watermarking framework. Specifically, to enable personalization and efficient detection, IPMark employs a hierarchical addressing framework to structurally organize model and user identities. Subsequently, addressing the inherent semantic distortion caused by token-level watermarking, we design a semantic-syntactic dual-stream embedding strategy. Centered on sentence-level candidate selection and reinforced by dual signals from syntactic and semantic features, this approach optimizes the injection process, thereby significantly enhancing generation quality while ensuring strong robustness. Experimental results demonstrate that IPMark achieves the lowest perplexity among baselines, ensuring superior generation quality while maintaining strong robustness and significantly reducing detection latency through hierarchical retrieval. Our code is available at https://github.com/nwlt/IPMark.

Large Language Models (LLMs) have demonstrated remarkable general capabilities, but enhancing skills such as reasoning often demands substantial computational resources and may compromise generalization. While Parameter-Efficient Fine-Tuning (PEFT) methods offer a more resource-conscious alternative, they typically require retraining for each LLM backbone due to architectural dependencies. To address these challenges, we propose Universal Reasoner (UniR)—a lightweight, composable, and plug-and-play reasoning module that can be used with larger frozen LLMs to provide specialized reasoning capabilities. Specifically, UniR decomposes the reward into a standalone reasoning module trained in a decoupled manner using verifiable rewards, effectively translating trajectory-level signals into token-level guidance. Once trained, UniR is combined with frozen LLMs at inference time by simply adding its output logits to those of the backbone. This additive structure enables modular composition: multiple UniR modules trained for different tasks can be jointly applied by summing their logits, enabling complex reasoning via composition. Furthermore, UniR demonstrates weak-to-strong generalization, where reasoning modules trained on smaller models effectively guide much larger LLMs in the same model family, and generalize across domains such as in vision language models and medical reasoning. Experiments on mathematical reasoning and machine translation show that UniR surpasses existing fine-tuning methods. Code is open-sourced at https://github.com/hangeol/UniR.

Data-Free Quantization (DFQ) addresses data security concerns by synthesizing samples, without accessing real data. It has garnered increasing attention in the context of Vision Transformers (ViTs), owing to the superiority of the self-attention mechanism compared to classical convolutional operation. However, previous DFQ arts for ViTs often suffer from a distribution mismatch between synthetic samples and input distribution expected by quantized models $Q$, resulting in the suboptimal performance. In this paper, we propose a novel Masked Attention Alignment approach for Data-Free Quantization of ViTs, named MaskAQ, revealing that: 1) the semantics in the self-attention mechanism is predominantly localized to a sparse subset of patches, called informative regions; 2) the informative regions dominate the mutual information between synthetic samples and $Q$'s outputs. To these ends, we incorporate differential entropy maximum over patch similarity of synthetic samples, to decouple informative regions from noisy background. To couple with varied $Q$, the informative regions are selected to align full-precision models with $Q$ via a masked attention alignment objective, thus yielding high-quality synthetic samples. Furthermore, a periodic sample refreshing strategy comes up to endow MaskAQ with the capacity to continually adapt to the evolving state of $Q$ throughout the training process, to preserve desirable mutual information with synthetic samples. Extensive experiments verify the merits of MaskAQ over state-of-the-art approaches across multiple backbones and downstream tasks. Our code is available at https://github.com/hfutqian/MaskAQ.

Prompt learning has recently emerged as a dominant paradigm to tackle the missing modalities challenge. However, existing methods often overlook the internal structural information of prompt vectors, limiting performance in guiding frozen backbone models under diverse missing modality scenarios. To address this, we propose a Structured Prompt Refining (SPR) network that refines the internal structure of prompt vectors across multiple dimensions: (1) a Global Interaction Fusion Module captures bidirectional interactions across prompt layers, thereby mitigating sub-optimal adaptation from inconsistent guidance under missing modalities, (2) a Local Feature Refinement Module structures adjacent prompt vectors into coherent semantic units, leveraging local contextual relationships to maintain semantic integrity during modality absence, and (3) a Channel Feature Selection Module uses point-wise gating to adaptively suppress noise and enhance critical channels based on the specific missing modality. Using only 0.8% trainable parameters, SPR achieves significant improvements on three mainstream multimodal classification datasets. Notably, it surpasses state-of-the-art by 3.8% in F1-Macro on the MM-IMDB dataset, even at a 90% modality missing rate. Extensive experiments and in-depth ablations validate SPR's effectiveness and robustness under various missing conditions.

While on-policy distillation offers dense supervision for training small reasoning models, its optimization dynamics in the multimodal domain remain under-explored. In this work, we challenge the standard monolithic view of Vision-Language Model (VLM) distillation by mathematically decomposing the loss into two distinct components: the language prior and visual grounding. Our analysis uncovers that gradient vectors for these components are nearly orthogonal, indicating that the objective of aligning with the teacher's language distribution is geometrically independent from the objective of matching its visual perception. Consequently, standard optimization passively follows a suboptimal compromise trajectory that implicitly balances the two objectives. Hypothesizing that visual grounding constitutes the primary bottleneck for vision-language reasoning, we introduce Visual Gradient Steering (VGS), a method that dynamically reorients the update vector to prioritize the visual subspace. Experimental results on multiple distillation settings and complex multimodal benchmarks demonstrate that VGS significantly outperforms the standard monolithic formulation of on-policy distillation, achieving superior grounding with minimal training overhead.

While widespread, Transformers lack inductive biases for geometric symmetries common in science and computer vision. Existing equivariant methods often sacrifice the efficiency and flexibility that make Transformers so effective through complex, computationally intensive designs. We introduce the Platonic Transformer to resolve this trade-off. By defining attention relative to reference frames from the Platonic solid symmetry groups, our method induces a principled weight-sharing scheme. This enables combined equivariance to continuous translations and Platonic symmetries, while preserving the exact architecture and computational cost of a standard Transformer. Furthermore, we show that this attention is formally equivalent to a dynamic group convolution, which reveals that the model learns adaptive geometric filters and enables a *highly scalable, linear-time convolutional variant*. Across diverse benchmarks in computer vision (CIFAR-10), 3D point clouds (ScanObjectNN), and molecular dynamics, property prediction and generation (OMol25, ProteinMD, QM9), the Platonic Transformer achieves competitive performance by leveraging these geometric constraints at no additional cost.

Solving complex geometric problems inherently requires interleaved reasoning: a tight alternation between constructing diagrams and performing logical deductions. Although recent Multimodal Large Language Models (MLLMs) have demonstrated strong capabilities in visual generation and plotting, we identify a counter-intuitive and underexplored phenomenon. Naively applying Supervised Fine-Tuning (SFT) on interleaved plot–solution data leads to a substantial degradation in reasoning performance compared to text-only baselines. We argue that this failure stems from a fundamental limitation of SFT, which primarily induces distributional alignment: the model learns to reproduce the surface format of interleaved plotting but fails to internalize the causal dependency between the generated plot and reasoning steps. To overcome this limitation, we propose Faire (**F**unctional **a**lignment for **i**nterleaved **re**asoning), a reinforcement learning framework that enforces three casual constraints to move beyond superficial imitation toward functional alignment. Extensive experiments show that Faire induces a qualitative shift in model behavior in which the plotting is effectively internalized, yielding competitive performance on challenging geometric reasoning benchmarks.

Large Language Models (LLMs) represent a promising frontier for recommender systems, yet their development has been impeded by the absence of predictable scaling laws, which are crucial for guiding research and optimizing resource allocation. We hypothesize that this may be attributed to the inherent noise, bias, and incompleteness of raw user interaction data in prior continual pre-training (CPT) efforts. This paper introduces a novel, layered framework for generating high-quality synthetic data that circumvents such issues by creating a curated, pedagogical curriculum for the LLM. We provide powerful, direct evidence for the utility of our curriculum by showing that standard sequential models trained on our principled synthetic data significantly outperform ($+130\%$ on recall@100 for SasRec) models trained on real data in downstream ranking tasks, demonstrating its superiority for learning generalizable user preference patterns. Building on this, we empirically demonstrate, for the first time, robust power-law scaling for an LLM that is continually pre-trained on our high-quality, recommendation-specific data. Our experiments reveal consistent and predictable perplexity reduction across multiple synthetic data modalities. These findings establish a foundational methodology for reliable scaling LLM capabilities in the recommendation domain, thereby shifting the research focus from mitigating data deficiencies to leveraging high-quality, structured information.

Transformers serve as the foundation of most modern large language models. To mitigate the quadratic complexity of standard full attention, various efficient attention mechanisms, such as linear and hybrid attention, have been developed. A fundamental gap remains: their expressive power relative to full attention lacks a rigorous theoretical characterization. In this work, we theoretically characterize the performance differences among these attention mechanisms. Our theory applies to all linear attention variants that can be formulated as a recurrence, including Mamba, DeltaNet, etc. Specifically, we establish an expressiveness hierarchy: for the sequential function composition-a multi-step reasoning task that must occur within a model’s forward pass, an $(L+1)$-layer full attention network is sufficient, whereas any hybrid network interleaving $L-1$ layers of full attention with a substantially larger number ($2^{3L^2}$) of linear attention layers cannot solve it. This result demonstrates a clear separation in expressive power between the two types of attention. Our work provides the first provable separation between hybrid attention and standard full attention, offering a theoretical perspective for understanding the fundamental capabilities and limitations of different attention mechanisms.

Test-time scaling for complex reasoning tasks shows that leveraging inference-time compute, by methods such as independently sampling and aggregating multiple solutions, results in significantly better task outcomes. However, a critical bottleneck is *verification*: sampling is only effective if correct solutions can be reliably identified among candidates. While existing approaches typically evaluate candidates independently via scalar scoring, we demonstrate that models are substantially stronger at **pairwise verification**. Leveraging this insight, we introduce **V₁**, a framework that unifies generation and verification through efficient pairwise ranking. V₁ comprises two components: **V₁-Infer**, an uncertainty-guided algorithm using a tournament-based ranking that dynamically allocates self-verification compute to candidate pairs whose relative correctness is most uncertain; and **V₁-PairRL**, an RL framework that **jointly trains** a single model as both generator and pairwise self-verifier, ensuring the verifier adapts to the generator's evolving distribution. On competitive code generation, SWE and terminal-based agents, math reasoning, and medical QA benchmarks, V₁-Infer improves Pass@1 by up to 10% over pointwise verification and outperforms SoTA aggregation-based test-time scaling while being more efficient. Furthermore, V₁-PairRL achieves test-time scaling gains of 3.8–10pp over standard RL and pointwise joint training on code, math, and non-verifiable domains, and improves base Pass@1 by up to 8.7pp over standard RL. [Project page & code](https://harmandotpy.github.io/v1-verification/).

Recent progress in large-scale robotic datasets and vision-language models (VLMs) has advanced research on vision-language-action (VLA) models. However, existing VLA models still face two fundamental challenges: (\textit{i}) producing precise low-level actions from high-dimensional observations, (\textit{ii}) bridging domain gaps across heterogeneous data sources, including diverse robot embodiments and human demonstrations. Existing methods often encode latent variables from either visual dynamics or robotic actions to guide policy learning, but they fail to fully exploit the complementary multi-modal knowledge present in large-scale, heterogeneous datasets. In this work, we present \textbf{XR-1}, a novel framework for versatile and scalable VLA learning across diverse robots, tasks, and environments. At its core, XR-1 introduces the \emph{Unified Vision-Motion Codes (UVMC)}, a discrete latent representation learned via a dual-branch VQ-VAE that jointly encodes visual dynamics and robotic motion. UVMC addresses these challenges by (\textit{i}) serving as an intermediate representation between the observations and actions, and (\textit{ii}) aligning multimodal dynamic information from heterogeneous data sources to capture complementary knowledge. To effectively exploit UVMC, we propose a \emph{three-stage training paradigm}: (\textit{i}) self-supervised UVMC learning, (\textit{ii}) UVMC-guided pretraining on large-scale cross-embodiment robotic datasets, and (\textit{iii}) task-specific post-training. We validate XR-1 through extensive real-world experiments with more than 12,000 rollouts on six different robot embodiments, spanning over 120 diverse manipulation tasks. XR-1 consistently outperforms state-of-the-art baselines such as $\pi_0$ and GR00T-N1.5 while demonstrating strong generalization to novel objects, background variations, distractors, and illumination changes. Our project is at \href{https://xr-1-vla.github.io/}{https://xr-1-vla.github.io/}.

Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or the existence of a stronger model able to solve the problem. However, many difficult problems remain intractable for even current frontier models, preventing the extraction of valid training signals. A promising alternative is to leverage high-quality expert human solutions, yet naive imitation of this data fails because it is fundamentally out-of-distribution: expert solutions are typically didactic, containing implicit reasoning gaps intended for human readers rather than computational models. Furthermore, high-quality expert solutions are expensive, necessitating generalizable sample-efficient training methods. We propose Distribution Aligned Imitation Learning (DAIL), a two-step self-distillation method that bridges the distributional gap by first transforming expert solutions into detailed, in-distribution reasoning traces and then applying a contrastive objective to focus learning on expert insights and methodologies. We find that DAIL can leverage fewer than 1000 high-quality expert solutions to achieve up to 31% pass@128 gains on Qwen2.5-Instruct and Qwen3, double reasoning efficiency, and enable out-of-domain generalization.

Modern decision transformers, trained similarly to LLMs, can achieve strong in-distribution performance in complex sequential domains like chess, but it remains unclear to what extent they reason systematically about rules and strategy. We study the reasoning capabilities of a 270M-parameter chess transformer trained via behavior cloning on standard chess. To investigate its abilities, we construct out-of-distribution test sets ---including board states and variants never seen during training---designed to reveal failures of systematic generalization. Our analysis shows that the model exhibits robust rule-based reasoning, consistently generating legal moves in novel configurations, but its strategic reasoning is more limited. The model generates high-quality moves on curated OOD puzzles and shows basic strategy adaptation in full games. It underperforms symbolic AI algorithms that rely on explicit search, although the performance gap is smaller when playing against human users on Lichess. Moreover, the training dynamics reveals distinct phases in how the model learns to respect the fundamental constraints, suggesting an emergent compositional understanding of the game.

Photoplethysmography (PPG), a non-invasive measure of changes in blood volume, is widely used in both wearable devices and clinical settings. Recent PPG foundation models either use open-source ICU datasets with pretraining paradigms that require curated data and thus complicate generalization to field-like data, or use closed-source field-like PPG data. In contrast, we propose a PPG foundation model that does not require high-quality or field-like pretraining data, and instead leverages accompanying electrocardiogram and respiratory signals in ICU datasets to select contrastive samples during pretraining. Our approach allows the model to retain and learn from noisy PPG segments, improving robustness at inference. Our model, pretrained on 3x fewer subjects than existing state-of-the-art approaches, achieves performance improvements on 14 out of 15 diverse downstream tasks, including field-like daily activity and heart rate prediction. Our results demonstrate that multimodal supervision can integrate complementary physiological information to improve the robustness of PPG foundation models and enhance their generalization to consumer-grade data.

Test-time strategies have shown remarkable success in improving large language models, but their application to next-token prediction (NTP) autoregressive (AR) image generation remains largely underexplored. Existing test-time scaling (TTS) methods for visual autoregressive models (VAR) rely on frequent partial decoding and external reward models, which are inefficient and often ineffective for NTP-based image generation due to the inherent instability of intermediate decoding results. To address these limitations, we propose **ScalingAR**, a novel test-time scaling framework tailored for NTP-based AR image generation. ScalingAR introduces *token entropy* as a confidence signal and operates at two complementary levels: (***i***) ***Profile Level***, integrates intrinsic uncertainty and conditional utilization into a unified confidence state, and (***ii***) ***Policy Level***, leverages this state for adaptive trajectory pruning and dynamic guidance scheduling. Without requiring early decoding or auxiliary rewards, ScalingAR achieves significant improvements across diverse benchmarks. Experiments show that ScalingAR **(I)** improves base models by 12.5% on GenEval and 15.2% on TIIF-Bench, **(II)** reduces visual token consumption by 62.0% while outperforming baselines, and **(III)** enhances robustness, mitigating performance degradation by 26.0% in challenging scenarios. These results establish ScalingAR as a robust and efficient test-time scaling solution for autoregressive image generation.