ICML 2026 论文列表

Medical foundation models (MFMs) aim to learn universal representations from multimodal medical images that can generalize effectively to diverse downstream clinical tasks. However, most existing MFMs suffer from information ambiguity that blends multimodal representations in a single embedding space, leading to the degradation of modality specificity and diversity. In this paper, we propose M-IDoL, a self-supervised ***M***FM that introduces ***I***nformation ***D***ecomposition for multim***o***dal representation ***L***earning via two objectives: i) maximizing inter-modality entropy by dispersing multimodal representations into separable Mixture-of-Experts (MoE) subspaces to achieve representation specificity across modalities; and ii) minimizing intra-modality uncertainty by performing fine-grained semantic discrimination within each MoE subspace to enrich representation diversity per modality. By pre-training on 1.15 million medical images, M-IDoL i) delivers superior generalization across 21 downstream clinical tasks, outperforming 20 foundation models on five imaging modalities (e.g., X-ray, fundus, OCT, dermoscopy and pathology), and ii) learns modality-specific and diverse representations, showing clearer separation of feature clusters across modalities and finer-grained feature discrimination within each modality.

Large language models (LLMs) perform inference by following a fixed depth and order, non-recurrent execution of all layers. We reveal the wide existence of training-free, flexible, dynamic *program-of-layers (PoLar)*, where pretrained layers can be packed as modules and then skipped or looped to form a customized program for each input. For most inputs, substantially shorter program executions can achieve the same or better accuracy, while incorrect predictions of the original LLM can be corrected by alternative programs with fewer layers. These observations indicate that inference admits multiple valid latent computations beyond the standard forward pass. To efficiently achieve PoLar in practice, we propose a lightweight PoLar prediction network, which learns to generate execution programs that dynamically skip or repeat pretrained layers for each input. Experiments on mathematical reasoning benchmarks demonstrate that PoLar consistently improves accuracy over standard inference and prior dynamic-depth methods, often while executing fewer layers, and that these gains persist under out-of-distribution evaluation. Our results suggest that fixed-depth execution captures only a narrow subset of an LLM’s latent reasoning capacity.

Audio agents are increasingly deployed to execute tools from spoken requests, yet audio tool use poses challenges beyond text-only function calling: perception errors (e.g., homophones, noise, disfluencies) can corrupt entities and arguments, and natural interactions often require clarification that changes the tool-calling protocol. We introduce BFCL Audio, a large-scale benchmark for audio function calling with 6.2K expert-verified tasks across two suites that mirror common deployments: BFCL Text Audio (pipelined $\text{ASR}\rightarrow\text{LLM}\rightarrow\text{tools}$ via transcripts) and BFCL True Audio (end-to-end $\text{audio-in}\rightarrow\text{tool calls}$). BFCL Audio includes controlled speech and acoustic perturbations (accent and speaking-rate variation, content disfluencies, and background noise) generated through a controllable audio synthesis/augmentation pipeline. We provide automatic grading for both function names and argument values using AST-based matching for single-turn calls and response/state-based metrics for multi-turn interactions, enabling scalable evaluation without LLM judges. Across a broad set of models, we propose a failure-mode taxonomy and analyze which speech and noise factors most strongly impact tool-calling accuracy. We release the benchmark, evaluation harness, and audio pipeline to support research on reliable speech-based agents.

The longitudinal management of blinding fundus diseases constitutes a Partially Observable Markov Decision Process (POMDP) necessitating a critical precision-risk trade-off between intervention and over-treatment, as true pathology is often obscured in static observations. However, existing paradigms fail to address this complexity. Traditional vision models remain uninterpretable and memoryless, and while Vision-Language Models (VLMs) excel in semantic understanding, they rely on unsafe open-loop text reasoning lacking the anatomical grounding essential for clinical safety. Furthermore, robust learning is hindered by the scarcity of process supervision in sparse clinical records. To bridge this gap, we introduce the Logic-Constrained Abductive Data Engine. Operating on a ``Propose-and-Verify'' paradigm, it validates MLLM-proposed biomarkers against clinical and temporal logic to reconstruct dense pathological states from sparse outcomes. Building on this foundation, we propose ORBIT, the first ophthalmic Prognostic World Model. Uniquely, ORBIT employs counterfactual visual foresight to imagine anatomical futures under different treatments, anchoring decisions in Closed-Loop Anatomical Verification rather than linguistic probabilities. Experiments demonstrate that ORBIT effectively captures disease evolution and establishes a new paradigm for human-in-the-loop longitudinal decision support and anatomically grounded treatment planning.

Foundation models have driven rapid progress in computer vision, yet the two dominant paradigms, vision-language foundation models (VLMs) and vision-only foundation models (VFMs), remain only partially compatible. VLMs offer language-grounded semantic alignment but are often visually coarse, while VFMs learn discriminative perceptual geometry but lack semantic grounding. We propose **GPUA**, a *Geometry-Preserving Unsupervised Alignment* framework that integrates the complementary strengths of VFMs and VLMs. Inspired by cross-lingual alignment, **GPUA** treats VFM features as a *visual language* and learns an *orthogonal* mapping that translates the VFM space into the VLM semantic space, preserving geometry and narrowing the modality gap without labels or model parameter updates. **GPUA** is task-agnostic and requires only feature-level access to pretrained models. Experiments across diverse benchmarks demonstrate improved cross-model compatibility and strong gains in downstream zero-shot recognition and segmentation with negligible overhead. Our code is available at: https://github.com/Yuteam14/GPUA.

Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generation tasks. In this work, we propose LaViDa-R1, a multimodal, general-purpose reasoning dLLM. Unlike existing works that build reasoning dLLMs through task-specific reinforcement learning, LaViDa-R1 incorporates diverse multimodal understanding and generation tasks in a unified manner. In particular, LaViDa-R1 is built with a novel unified post-training framework that seamlessly integrates supervised finetuning (SFT) and multi-task reinforcement learning (RL). It employs several novel training techniques, including answer-forcing, tree search, and complementary likelihood estimation, to enhance effectiveness and scalability. Extensive experiments demonstrate LaViDa-R1's strong performance on a wide range of multimodal tasks, including visual math reasoning, reason-intensive grounding, and image editing.

Human vision is foveated, with variable resolution peaking at the center of a large field of view; this reflects an efficient trade-off for active sensing, allowing eye-movements to bring different parts of the world into focus with other parts of the world in context. In contrast, most computer vision systems encode the visual world at a uniform resolution, raising challenges for processing full-field high-resolution images efficiently. We propose a foveated vision interface (FOVI) based on the human retina and primary visual cortex (V1), that reformats a variable-resolution retina-like sensor array into a uniformly dense, V1-like sensor manifold. Receptive fields are defined as k-nearest-neighborhoods (kNNs) on the sensor manifold, enabling kNN-convolution via a novel kernel mapping technique. We demonstrate two use cases: (1) an end-to-end kNN-convolutional architecture, and (2) a foveated adaptation of the DINOv3 ViT foundation model, leveraging low-rank adaptation (LoRA). These models provide competitive performance with a fraction of the pixels and computational cost of full resolution non-foveated baselines, opening pathways for efficient and scalable active sensing for high-resolution egocentric vision. Code (https://github.com/nblauch/fovi) and pre-trained models (https://huggingface.co/fovi-pytorch) are available.

Despite significant recent progress of Multimodal Large Language Models (MLLMs), current MLLMs are challenged by "spatio-temporal" prompts, i.e., prompts that refer to 1) the entirety of an environment encoded in a point cloud that the MLLM should consider; and simultaneously also refer to 2) actions that happened in part of the environment and are encoded in a short ego-centric video clip. However, such a holistic spatio-temporal understanding is important for agents operating in the real world. To address this challenge, we first develop a framework to collect a large-scale dataset. Using the collected "Reasoning about Environments and Actions" (REA) dataset, we show that recent MLLMs indeed struggle to correctly answer "spatio-temporal" prompts. Building on this dataset, we study two spatio-temporal LLM (STLLM) baselines: 1) STLLM-3D, which directly fuses point cloud, video, and text representations as inputs to the LLM; and 2) STLLM-Aligner, which aligns spatial context with video and text before LLM decoding. Both baselines aim to enhance spatial understanding of environments and temporal grounding of egocentric observations. On REA, the STLLM baselines outperform existing models, demonstrating the effectiveness of our designs.

The Fisher Information Matrix (FIM) provides a principled geometric framework for parameter sensitivity in neural networks, but directly computing and using the full FIM is infeasible in high-dimensional models. As a result, most existing methods rely on diagonal approximations that discard important correlation structure. We introduce Matrix-free Fisher Factorization (MFF), a GPU-tractable algorithm that captures both diagonal and off-diagonal dependencies without materializing the full matrix. For post-training neural network layer compression, we prove that under Matrix-Variate Normal assumptions, MFF yields GFWSVD, a unique closed-form linear layer decomposition that optimally minimizes the expected second-order loss increase. Experiments on controlled numerical benchmarks with large neural networks show that GFWSVD achieves up to 50\% compression while matching or exceeding state-of-the-art diagonal and activation-based baselines across most tasks, and it reliably avoids collapse in dense architectures such as Llama 3. Moreover, when used to initialize existing optimization pipelines (e.g., Dobi-SVD), GFWSVD better preserves accuracy at 40\% parameter reduction in regimes where standard methods substantially degrade. Together, these results position MFF and GFWSVD as foundational algorithmic primitives for scalable, second-order-aware neural network approximation and parameter sensitivity.

Multimodal large language models (MLLMs) are pushing recommender systems (RecSys) toward content-grounded retrieval and ranking via cross-modal fusion. We find that while cross-modal consensus often mitigates conventional poisoning that manipulates interaction logs or perturbs a single modality, it also introduces a new attack surface where synchronised multimodal poisoning can reliably steer fused representations along stable semantic directions during fine-tuning. To characterise this threat, we formalise cross-modal interactive poisoning and propose VENOMREC, which performs Exposure Alignment to identify high-exposure regions in the joint embedding space and Cross-modal Interactive Perturbation to craft attention-guided coupled token--patch edits. Experiments on four real-world multimodal datasets demonstrate that VENOMREC consistently outperforms strong baselines, achieving 0.73 mean ER@20 and improving over the strongest baseline by +0.52 absolute ER points on average, while maintaining comparable recommendation utility. Code is available at https://github.com/GuoweiGuan666/VenomRec.

Speculative decoding (SD) has emerged as a key solution to accelerate the inference of autoregressive models. However, in the field of image generation, it faces the challenge of low acceptance rates, and directly relaxing its criteria leads to degradation in image quality. In this paper, we propose a novel content-aware speculative decoding algorithm, termed CSD, which integrates an entropy-based probability relaxation mechanism with an optimal resampling strategy to enhance the inference efficiency for autoregressive image generation. By leveraging the informational uncertainty inherent in different regions of an image, CSD dynamically adjusts the acceptance probability of candidate tokens, increasing the acceptance rate in low-detail areas to accelerate generation. Moreover, a distribution alignment filter is introduced to ensure the output distribution to be aligned with the target model, which significantly improves the generative quality. Experiments conducted on Lumina-mGPT and Janus-Pro demonstrate that the superiority of the proposed CSD. Our source code is available at https://github.com/aderfebr/CSD.

Rotary Position Embedding (RoPE) is widely adopted in large language models, but when applied to vision-language models (VLMs) it couples text and image position indices and can introduce spurious cross-modal relative-position bias. We propose *Per-Token Distance* (PTD) to quantify cross-modal positional disentanglement, and we prove that $\mathrm{PTD}=0$ is a sufficient condition to eliminate the geometric attention bias induced by RoPE. Guided by this criterion, we introduce Circle-RoPE, which remaps 2D image-token coordinates onto an annulus orthogonal to the text position axis, yielding a cone-like geometry where each text token is equidistant to all image tokens while preserving intra-image spatial structure. We further propose Alternating Geometry Encoding (AGE) to synergize complementary geometric priors by alternating the decoupled geometry of Circle-RoPE and the grid-based prior of standard RoPE across layers. This design ensures both rigorous cross-modal disentanglement and the preservation of fine-grained intra-image spatial structure, and experiments on diverse VLM backbones and multimodal benchmarks show consistent gains in spatial grounding and visual reasoning. The code is available at https://github.com/lose4578/CircleRoPE.

Vision–language models such as CLIP embed images and text into a shared space, but still suffer from a modality gap, where image and text features cluster separately and nearest neighbors are dominated by same-modality rather than true cross-modal matches. Existing works alleviate the modality gap by strengthening cross-modal losses, post-processing embeddings or similarities, or imposing geometric regularization, but they primarily enforce global alignment and can distort local geometry, limiting gains in local ranking and zero-shot accuracy. We propose Fractal Spectral Alignment (FSAlign), which reduces the modality gap by shaping and matching the multi-scale geometry of image and text embeddings. By enforcing Ahlfors-regularity and sub-Gaussian heat kernel bounds, FSAlign constructs a shared fractal multi-scale structure for multiple modalities. This structure captures geometry across scales, from local neighborhoods to global structure, and ensures shared fractal spectral geometry across modalities. Based on this structure, we introduce a fractal spectral zeta score derived from multi-scale heat kernels and minimize the discrepancy between pairwise image–text samples to align their multi-scale neighborhoods. We theoretically demonstrate that FSAlign can guarantee the alignment of local spectral measures and global fractional Dirichlet energies.

Foundation models for intracranial neural recordings aim to learn generalizable representations from large-scale unlabeled data. However, existing approaches rely on suboptimal tokenization schemes -- treating individual electrode channels as independent tokens or aggregating them into a single brain-wide representation -- which fail to capture the brain’s inherent functional modularity. We introduce NeuroCLUS, a foundation model that learns to represent neural activity through data-driven functional clusters. NeuroCLUS is built on a novel two-stage pre-training framework. First, a spatial-temporal model learns a functional context graph between channels via a functional context prediction task. Second, this graph guides a soft clustering of channels into a set of learnable prototype tokens, enabling the transformer backbone to process coherent functional units rather than raw channels. Evaluated across a diverse range of decoding paradigms -- including speech perception, speech production, and seizure detection -- NeuroCLUS consistently achieves state-of-the-art performance. The discovered functional clusters align with established neurophysiology and offer enhanced interpretability. Our work demonstrates that explicitly modeling functional neural groupings significantly improves the efficiency, generalization, and interpretability of foundation models for intracranial decoding.

Vision-Language Navigation (VLN) requires agents to follow natural language instructions by grounding them in sequential visual observations over long horizons. Explicit reasoning could enhance temporal consistency and perception–action alignment, but reasoning at fixed steps often leads to suboptimal performance and unnecessary computation. To address this, we propose AdaNav, an uncertainty-based adaptive reasoning framework for VLN. At its core is the Uncertainty-Adaptive Reasoning Block (UAR), a lightweight plugin that dynamically triggers reasoning. We introduce Action Entropy as a policy prior for UAR and progressively refine it through a Heuristics-to-RL training method, enabling agents to learn difficulty-aware reasoning policies under the strict data limitations of embodied tasks. Results show that with only 6K training samples, AdaNav achieves substantial gains over closed-source models trained on million-scale data, improving success rate by 20% on R2R val-unseen, 11.7% on RxR-CE, and 11.4% in real-world scenes.

While video generation holds promise for embodied intelligence, current video models struggle with physical realism, and progress is hindered by the lack of standardized benchmarks. To address this gap, we introduce a comprehensive robotics benchmark, RBench, designed to evaluate robot-oriented video generation across five task domains and four distinct embodiments. By assessing task correctness and visual fidelity through reproducible metrics, our evaluation of 25 models reveals significant deficiencies in generating physically realistic robot behaviors. Furthermore, the benchmark achieves a 0.96 Spearman correlation with human judgment, validating its effectiveness. While RBench provides the necessary lens to identify these deficiencies, achieving physical realism requires moving beyond evaluation to address the critical shortage of high-quality training data. Driven by these insights, we introduce a refined four-stage data pipeline, resulting in RoVid-X, the largest open-source robotic dataset for video generation with 4 million annotated video clips, covering thousands of tasks and enriched with physical property annotations. Extensive experiments demonstrate that finetuning on RoVid-X yields consistent performance gains. Collectively, this synergistic ecosystem of evaluation and data establishes a robust foundation for rigorous assessment and scalable training of video models, accelerating the evolution of embodied AI toward physical intelligence. The code and video demos are available in the supplementary materials.

Federated learning (FL) faces significant challenges from modality heterogeneity, which motivates multimodal federated learning (MFL) to leverage complementary modalities across decentralized clients for improved performance. However, modality imbalance introduces a new attack surface, making MFL more vulnerable to membership inference attacks (MIAs), an issue that remains largely unexplored. In this work, we present the first systematic study of MIAs against MFL and propose a modality-aware attack framework. We show that multimodal models are inherently more susceptible to MIAs due to heterogeneous modality contributions, and existing attacks are suboptimal as they treat multimodal parameters as a whole. By performing MIAs on individual modalities, we find that (i) attacking the dominant modality achieves comparable accuracy with lower overhead, and (ii) different modalities expose distinct membership patterns. To identify members with different patterns, we propose a modality-aware framework that exploits cross-modal performance gaps to adaptively select attack modalities and calibrate inference results. Experiments on three datasets show our approach outperforms baselines across multiple metrics.

Symbolic regression (SR) aims to discover interpretable mathematical expressions from observed data. While recent generative approaches have shown promise in treating SR as machine translation or multimodal learning tasks using NN methods, they suffer from uncontrollable generation process and training-evaluation misalignment. The training objectives (average cross-entropy loss on a token level across the distribution of historical data) differ from the evaluation metric (fitting error for every test data / complexity), necessitating extensive heuristic post-processing. On the other hand, direct optimization methods suffer from an exponential slowdown as the dimensionality increases, non-differentiability and local optima traps. We propose **MOD-SR**, unifying multimodal distribution learning during training with direct optimization at inference time. This is achieved by modeling the task as $p(x_0 \mid \mathcal{D}, y^*)$ and employing gradient-guided diffusion in embedding space, enhanced by contrastive learning and representation alignment. Furthermore, we introduce DFEX, a fixed-depth tree relaxation method that ensures differentiability for effective gradient guidance during inference. Experiments demonstrate that MOD-SR achieves superior performance on diverse benchmarks through a unified framework integrating distribution learning and optimization. Our code is available at [https://github.com/KROX777/MOD-SR](https://github.com/KROX777/MOD-SR).

Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machine-readable formats is critical for unlocking global knowledge. However, existing benchmarks predominantly focus on high-resource languages like English and Chinese, creating an $\textit{evaluation blind spot}$ concerning model performance on other languages. While recent Vision-Language Models (VLMs) claim support for hundreds of languages, the lack of ground truth makes it impossible to empirically verify these capabilities. To bridge this gap, we introduce $\textbf{MORE}$, a large-scale benchmark designed for multilingual document parsing evaluation. MORE distinguishes itself through three key dimensions: (1) $\textbf{Unprecedented Scale}$: It covers $\textbf{149 languages}$, making it the most linguistically diverse benchmark to date; (2) $\textbf{Structural Complexity}$: Unlike previous works, it extends evaluation beyond plain text to include structural elements such as code blocks, tables, and catalogs; and (3) $\textbf{Data Authenticity}$: All samples are curated from real-world documents via a model-assisted, human-refined annotation pipeline. We evaluate state-of-the-art models using MORE, establishing new performance baselines for long-tail languages and validating the benchmark's effectiveness in diagnosing model capabilities in realistic, diverse scenarios. The MORE dataset will be available at https://github.com/zimoqingfeng/MORE.