ICLR 2026 Papers

Missing modalities present a fundamental challenge in multimodal models, often causing catastrophic performance degradation. Our observations suggest that this fragility stems from an imbalanced learning process, where the model develops an implicit preference for certain modalities, leading to the under-optimization of others. We propose a simple yet efficiency method to address this challenge. The central insight of our work is that the dominance relationship between modalities can be effectively discerned and quantified in the frequency domain. To leverage this principle, we first introduce a **F**requency **R**atio **M**etric (FRM) to quantify modality preference by analyzing features in the frequency domain. Guided by FRM, we then propose a **M**ultimodal **W**eight **A**llocation **M**odule, a plug-and-play component that dynamically re-balances the contribution of each branch during training, promoting a more holistic learning paradigm. Extensive experiments demonstrate that MWAM can be seamlessly integrated into diverse architectural backbones, such as those based on CNNs and ViTs. Furthermore, MWAM delivers consistent performance gains across a wide range of tasks and modality combinations. This advancement extends beyond merely optimizing the performance of the base model; it also manifests as further performance improvements to state-of-the-art methods addressing the missing modality problem.

Active Prompt Learning (APL) using vision-language models (\textit{e.g.}, CLIP) has attracted considerable attention for mitigating the dependence on fully labeled dataset in downstream task adaptation. However, existing methods fail to explicitly leverage prompt to guide sample selection, resulting in the selected samples being ineffective in facilitating the prompt template's downstream task adaptation, while also overlooking valuable complementary information in the unselected samples. To fill this gap, we propose a novel Prompt-Guided Self-Training Sampling Policy (PSP) for APL, which integrates Soft Actor-Critic with a customized real-pseudo hybrid reward and vectorized critics to incorporate prompts in guiding sample selection toward those that facilitate the optimization of prompt template, by jointly considering both selected and unselected samples. Specifically, PSP comprises two prominent components: Vectorized Soft Actor-Critic Sampling Policy (VSSP) and Uncertainty Augmented Self-Training (UST) mechanism. VSSP customizes a real-pseudo hybrid reward based on learned prompts and image features, which is fed into vectorized critics to estimate Q-value for each sample and compute gradients that optimize the actor, allowing it to refine its sampling policy in an End-to-End manner to identify the most informative samples for prompt learning. Moreover, UST leverages the CLIP from the previous round to generate reliable pseudo-labeled data based on uncertainty and confidence of average predictions, thereby deepening the understanding of the overall data. Extensive experiments conducted on diverse real-world datasets validate the effectiveness of our PSP.

Cell Painting combines multiplexed fluorescent staining, high‑content imaging, and quantitative analysis to generate high-dimensional phenotypic readouts to support diverse downstream tasks such as mechanism-of-action (MoA) inference, toxicity prediction, and construction of drug–disease atlases. However, existing workflows are slow, costly and difficult to interpret. Approaches for drug screening modeling predominantly focus on molecular representation learning, while neglecting actual experimental context (e.g., cell line, dosing schedule, etc.), limiting generalization and MoA resolution. We introduce CP-Agent, an agentic multimodal large language model (MLLM) capable of generating mechanism-relevant, human-interpretable rationales for cell morphological changes under drug perturbations. At its core, CP-Agent leverages a context-aware alignment module, CP-CLIP, that jointly embeds high-content images and experimental metadata to enable robust treatment and MoA discrimination (achieving a maximum F1-score of 0.896). By integrating CP-CLIP outputs with agentic tool usage and reasoning, CP‑Agent compiles rationales into a structured report to guide experimental design and hypothesis refinement. These capabilities highlight CP-Agent’s potential to accelerate drug discovery by enabling more interpretable, scalable, and context-aware phenotypic screening---streamlining iterative cycles of hypothesis generation in drug discovery.

Multimodal large language models (MLLMs) demonstrate strong video understanding by attending to visual tokens relevant to instructions. To exploit this for training-free localization, we cast video reasoning segmentation as video QA and extract attention maps via rollout. Since raw maps are too noisy to represent objects, we propose Decomposed Attention Fusion (DecAF), combining (1) contrastive object-background fusion and (2) complementary video-frame fusion. This yields cleaner attention maps focused on the target object, which can be directly converted into coarse segmentation masks and outperform existing methods. In addition, we introduce attention-guided SAM2 prompting for fine-grained masks, achieving performance comparable to training-based methods on both referring and reasoning VOS benchmarks.

We develop a novel memory representation for embodied planning models performing long-horizon mobile manipulation in dynamic, large-scale indoor environments. Prior memory representations fall short in this setting, as they struggle with object movements, suffer from computational deficiencies, and often depend on the heuristic integration of multiple models. To overcome these limitations, we present the Embodied Perception Memory (EMP), a learnable memory designed for embodied planning. EMP is implemented as a unified Vision-Language Model (VLM) that uses egocentric vision to maintain and update a textual environment representation. We further introduce two complementary methods for training planners to leverage the EMP: an imitation strategy that uses human trajectories for natural exploration and interaction, and a novel reinforcement learning approach, Dynamic Difficulty-Aware Fine-Tuning (DDAFT), which improves planning performance via difficulty-aware exploration. Our memory representation, when integrated with our planning training methods, leads to significant improvements on planning tasks, showing up to a 55% increase in success rate on the PARTNR benchmark compared to strong baselines. Also, our planning method outperforms these baselines even when they have access to groundtruth perception.

Reinforcement Learning with Verifiable Reward (RLVR) has equipped large language models (LLMs) with the capability of reasoning over complicated logical problems through policy optimization. However, conventional methods require complete annotation of the entire dataset and allocate computation uniformly over all samples. We articulate the lottery sample hypothesis in policy optimization of LLMs: a large training set contains a small subset that, when trained alone, yields performance comparable to that of the full dataset. This paper therefore explores the following question: How can we identify these lottery-winning samples from the original dataset without access to answers? Unlike prior efforts that analyze the effect of different samples in the training set with complete annotation, this paper focuses on the unsupervised discovery of critical instances for LLM reasoning and proposes a novel framework termed Complementary Conformal Selection (CONST). Specifically, CONST evaluates the importance of samples by considering two complementary components: procedural volatility and outcome volatility. Procedural volatility measures the potential variations during the LLM’s reasoning process, while outcome volatility captures inconsistencies in the final answer. Subsequently, conformal prediction is used to obtain a prediction set whose cardinality serves as the criterion for selecting the lottery-winning samples for annotation. We also provide a theoretical analysis, showing that CONST can effectively approximate the optimal policy. Extensive experiments on various LLMs across different datasets demonstrate the effectiveness of CONST.

Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number of real-world rollouts, while systematic improvement demands additional corrective data with expert labels. Both of these processes are slow, costly, and difficult to scale. World models offer a promising, scalable alternative by enabling policies to rollout within imagination space. However, a key challenge is building a controllable world model that can handle multi-step interactions with generalist robot policies. This requires a world model compatible with modern generalist policies by supporting multi-view prediction, fine-grained action control, and consistent long-horizon interactions, which is not achieved by previous works. In this paper, we make a step forward by introducing a controllable multi-view world model that can be used to evaluate and improve the instruction-following ability of generalist robot policies. Our model maintains long-horizon consistency with a pose-conditioned memory retrieval mechanism and achieves precise action control through frame-level action conditioning. Trained on the DROID dataset (95k trajectories, 564 scenes), our model generates spatially and temporally consistent trajectories under novel scenarios and new camera placements for over 20 seconds. We show that our method can accurately rank policy performance without real-world robot rollouts. Moreover, by synthesizing successful trajectories in imagination and using them for supervised fine-tuning, our approach can improve policy success by 44.7\%. Videos can be found at https://sites.google.com/view/ctrl-world.

The increasing demand for real-time interaction in online video scenarios necessitates a new class of efficient streaming video understanding models. However, existing approaches often rely on a flawed, query-agnostic ``change-is-important'' principle, which conflates visual dynamics with semantic relevance, leading to computational waste and interaction errors. To address this, we propose QueryStream, a novel framework that instills query-awareness into the core of video processing and response scheduling. QueryStream features two synergistic components: (1) Query-Aware Differential Pruning (QDP), a policy that filters the token stream by jointly assessing semantic relevance to the query and temporal novelty against a dynamically smoothed history, and (2) Relevance-Triggered Active Response (RTAR), a dual-gated mechanism that schedules responses based on both high query relevance and significant information density. As a lightweight, training-free module, QueryStream establishes a new state-of-the-art on benchmarks like StreamingBench and OVO-Bench, matching or exceeding the performance of full-token baselines while pruning over 70\% of visual tokens. Notably, our pruning mechanism generalizes to offline tasks, where it functions as an effective context-denoising module to improve accuracy on long-form videos. This work not only reveals the vast semantic redundancy in video streams relative to user intent but also establishes a promising, intent-driven direction for truly efficient and robust online video understanding.

Video anomaly detection (VAD) aims to detect anomalies that deviate from what is expected. In open-world scenarios, the expected events may change as requirements change. For example, not wearing a mask may be considered abnormal during a flu outbreak but normal otherwise. However, existing methods assume that the definition of anomalies is invariable, and thus are not applicable to the open world. To address this, we propose a novel open-world VAD paradigm with variable definitions, allowing guided detection through user-provided natural language at inference time. This paradigm necessitates establishing a robust mapping from video and textual definition to anomaly scores. Therefore, we propose LaGoVAD (**La**nguage-**g**uided **O**pen-world **V**ideo **A**nomaly **D**etector), a model that dynamically adapts anomaly definitions under weak supervision with two regularization strategies: diversifying the relative durations of anomalies via dynamic video synthesis, and enhancing feature robustness through contrastive learning with negative mining. Training such adaptable models requires diverse anomaly definitions, but existing datasets typically provide labels without semantic descriptions. To bridge this gap, we collect PreVAD (**Pre**-training **V**ideo **A**nomaly **D**ataset), the largest and most diverse video anomaly dataset to date, featuring 35,279 annotated videos with multi-level category labels and descriptions that explicitly define anomalies. Zero-shot experiments on seven datasets demonstrate LaGoVAD's SOTA performance. Our dataset and code are released at https://github.com/Kamino666/LaGoVAD-PreVAD.

Personalized text-to-image generation aims to synthesize images of user-provided concepts in diverse contexts. Despite recent progress in multi-concept personalization, most are limited to object concepts and struggle to customize abstract concepts (e.g., pose, lighting). Some methods have begun exploring multi-concept personalization supporting abstract concepts, but they require test-time fine-tuning for each new concept, which is time-consuming and prone to overfitting on limited training images. In this work, we propose a novel tuning-free method for multi-concept personalization that can effectively customize both object and abstract concepts without test-time fine-tuning. Our method builds upon the modulation mechanism in pre-trained Diffusion Transformers (DiTs) model, leveraging the localized and semantically meaningful properties of the modulation space. Specifically, we propose a novel module, Mod-Adapter, to predict concept-specific modulation direction for the modulation process of concept-related text tokens. It introduces vision-language cross-attention for extracting concept visual features, and Mixture-of-Experts (MoE) layers that adaptively map the concept features into the modulation space. Furthermore, to mitigate the training difficulty caused by the large gap between the concept image space and the modulation space, we introduce a VLM-guided pre-training strategy that leverages the strong image understanding capabilities of vision-language models to provide semantic supervision signals. For a comprehensive comparison, we extend a standard benchmark by incorporating abstract concepts. Our method achieves state-of-the-art performance in multi-concept personalization, supported by quantitative, qualitative, and human evaluations.

In this paper, we propose UniLIP, a unified framework that adapts CLIP for multimodal understanding, generation and editing. Although CLIP excels at understanding, it lacks reconstruction abilities required to be a unified visual encoder. However, previous CLIP-based unified methods fail to balance understanding and reconstruction, leading to semantic degradation or inconsistent reconstructions. In contrast, we introduce a novel two-stage training scheme with a self-distillation strategy that progressively endows CLIP with high-fidelity reconstruction abilities while preserving its original comprehension performance. For enhanced reasoning and consistency in generation and editing, we further develop a dual-condition architecture built upon the MetaQuery framework. Our architecture jointly utilizes multimodal hidden states for rich contextual details and learnable query embeddings to harness the powerful reasoning abilities of Multimodal Large Language Models (MLLMs). Leveraging advanced image representation and architectural design, UniLIP demonstrates superior instruction following and edit fidelity. With only 1B and 3B parameters, UniLIP can outperform larger unified models such as BAGEL (7B) and Uniworld-V1 (12B), achieving state-of-the-art performance of **0.90** on GenEval, **0.63** on WISE, and **3.94** on ImgEdit. These results demonstrate that UniLIP successfully expands the application of CLIP, establishing its continuous features to not only serve as the optimal choice for understanding tasks but also achieve highly competitive performance in generation and editing tasks. Code and models are available at https://github.com/nnnth/UniLIP.

Automatic radiology reporting assists radiologists in diagnosing abnormalities in radiology images, where grounding the automatic diagnosis with abnormality locations is important for the report interpretability. However, existing supervised-learning methods could lead to learning the superficial statistical correlations between images and reports, lacking multi-faceted reasoning to critique the relevant regions on which radiologists would focus. Recently, self-critical reasoning has been investigated in test-time scaling approaches to alleviate hallucinations of LLMs with increased time complexity. In this work, we focus on chest X-ray report generation with particular focus on clinical accuracy, where self-critical reasoning is alternatively introduced into the model architecture and their training objective, preferred by the real-time automatic reporting system. In particular, three types of self-critical reasoning are proposed to critique the hypotheses of grounded abnormalities compared to i) alternative abnormalities, ii) alternative patient's X-ray image, and iii) potential false negative abnormalities. To realize this, we propose a novel Radiology Self-Critiquing Reporting (RadSCR) framework, which constructs the abnormality proposals for each localized abnormality region and verify them by the proposed self-critiquing mechanisms accordingly. The critiqued results of the abnormality proposals are then integrated to generate the completed report with interpretable diagnostic process. Our experiments show the state-of-the-art performance achieved by RadSCR in the grounded report generation and diagnosis critiquing, demonstrating its effectiveness in generating the clinically accurate report.

Spatial reasoning is a key aspect of cognitive psychology and remains a bottleneck for current vision-language models (VLMs). While extensive research has aimed to evaluate or improve VLMs' understanding of basic spatial relations, such as distinguishing left from right, near from far, and object counting, these tasks cover only the most elementary layer of spatial reasoning and are largely approaching saturation in the latest reasoning models. In this work, we introduce OmniSpatial, a comprehensive and challenging benchmark for spatial reasoning, grounded in cognitive psychology. OmniSpatial covers four major categories: dynamic reasoning, complex spatial logic, spatial interaction, and perspective-taking, with 50 fine-grained subcategories. Through careful manual annotation, we construct over 8.4K question-answer pairs. Extensive experiments show that both open- and closed-source VLMs exhibit significant limitations in comprehensive spatial reasoning. We also explore two strategies—PointGraph (explicit scene graph cues) and SpatialCoT (novel-view chain-of-thought)—to bolster spatial reasoning.

Large vision-language models (LVLMs) achieve impressive performance, yet their internal decision-making processes remain opaque, making it difficult to determine if the success stems from true multimodal fusion or reliance on unimodal priors. To address this attribution gap, we introduce a novel framework using partial information decomposition (PID) to quantitatively measure the ``information spectrum'' of LVLMs—decomposing a model’s decision-relevant information into redundant, unique, and synergistic components. By adapting a scalable estimator to modern LVLM outputs, Our model-agnostic pipeline profiles 26 LVLMs on four datasets across three dimensions—\emph{breadth} (cross-model \& cross-task), \emph{depth} (layer-wise information dynamics), and \emph{time} (learning dynamics across training). Our analysis reveals two key results: (i) two task regimes (synergy-driven vs. knowledge-driven) and (ii) two stable, opposing family-level strategies (fusion-centric vs. language-centric). We also uncover a consistent three-phase pattern in layer-wise processing and identify visual instruction tuning as the key stage where fusion is learned. Together, these contributions provide a quantitative lens beyond accuracy-only evaluation and offer guidance for analyzing and designing the next generation of LVLMs.

Scaling foundation model training with Distributed Data Parallel~(DDP) methods is bandwidth-limited. Existing infrequent communication methods like Local SGD were designed to synchronize model parameters only and cannot be trivially applied to adaptive optimizers due to additional optimizer states. Heuristic approaches that keep states local or reset them lack guarantees and can be unstable in compute‑efficient batch regimes; conversely, Local Adam synchronizes all states uniformly and is provably convergent but triples communication costs. We propose Desynced Low Communication Adaptive Optimizers (DES-LOC), a family of optimizers assigning independent synchronization periods to parameters and momenta, enabling lower communication costs while preserving convergence. Our theoretical analysis shows that while parameter synchronization dominates the asymptotic rate in-expectation, high-probability convergence guarantees require at least infrequent synchronization of the second momentum. Furthermore, we prove that more frequent momentum sync permits larger stable step sizes. Experiments on language models of up to 1.7B show that DES-LOC can communicate 170x less than DDP and 2x less than the previous state-of-the-art Local Adam, enabling 1.3x–2.1x wall‑clock speedups over DDP for 1-13B models on 100Gb/s links. Furthermore, unlike previous heuristic methods, DES-LOC is robust to worker failures offering a scalable, efficient, and fault-tolerant solution for foundation model training.

Video matting is a crucial task for many applications, but existing methods face significant limitations. They are often domain-specific, focusing primarily on human portraits, and rely on the mask of first frame that is challenging to acquire for transparent or intricate objects like fire or smoke. To address these challenges, we introduce Matting Anything 2 (MAM2), a versatile and robust video matting model that handles diverse objects using flexible user prompts such as points, boxes, or masks. We first propose Promptable Dual-mode Decoder (PDD), an effective structure that simultaneously predicts a segmentation mask and a corresponding high-quality trimap, leveraging trimap-based guidance to improve generalization. To tackle prediction instability for transparent objects across video frames, we further propose a Memory-Separable Siamese (MSS) mechanism. MSS employs a recurrent approach that isolates trimap prediction from potentially interfering mask memory, significantly enhancing temporal consistency. To validate our method's performance on diverse objects, we introduce the Natural Video Matting dataset, a new benchmark with substantially greater diversity. Extensive experiments show that MAM2 possesses exceptional matting accuracy and generalization capabilities. We believe MAM2 demonstrates a significant leap forward in creating a video matting method for anything.

Automatic video polyp segmentation (VPS) is crucial for preventing and treating colorectal cancer by ensuring accurate identification of polyps in colonoscopy examinations. However, its clinical application is hampered by two key challenges: shape collapse, which compromises structural integrity, and episodic amnesia, which causes instability in challenging video sequences. To address these challenges, we present a novel video segmentation network, \emph{HFSTI-Net}, which integrates global perception with spatiotemporal consistency in spatial, temporal, and frequency domains. Specifically, to address shape collapse under low contrast or visual ambiguity, we design a Hierarchical Frequency-spatial Interaction (HFSI) module that fuses spatial and frequency cues for fine-grained boundary localization. Furthermore, we propose a recurrent mask-guided propagation (RMP) module that introduces a dual enhancement mechanism based on feature memory and mask alignment, effectively incorporating spatiotemporal information to alleviate inter-frame inconsistencies and ensuring long-term segmentation stability. Extensive experiments on the SUN-SEG and CVC-612 datasets demonstrate that our method achieves real-time inference and outperforms other state-of-the-art approaches. The codes will be made available upon publication.

Diffusion LLMs have attracted growing interest, with plenty of recent work emphasizing their great potential in various downstream tasks; yet the long‑context behavior of diffusion LLMs remains largely uncharted. We present a case study of post‑training techniques for extending the context window of diffusion LLMs (i.e., LLaDA) without retraining from scratch. We show that a simple modification to the standard Rotary Positional Embeddings (RoPE) extension effectively accommodates the probabilistic modeling inherent in the diffusion process, enabling stable scaling to longer context ranges. We further compare masking strategies used during post‑training and analyze their impact on optimization stability and long‑range recall. Instantiating these insights, we introduce UltraLLaDA, a diffusion LLM with a 128K‑token context window that, in our empirical evaluation on long‑context tasks, significantly outperforms training‑free baselines. Our experimental results highlight the special positional extension as a key lever for scaling diffusion LLMs to extended contexts and offer practical guidance for practitioners seeking 128K‑scale context via efficient post‑training.

Electroencephalography (EEG) is a noninvasive technique for measuring brain electrical activity that supports a wide range of brain-computer interaction applications. Motivated by the breakthroughs of Large Language Models (LLMs), recent efforts have begun to explore Large EEG foundation Models trained on broad unlabeled corpora. However, most advances focus on improving the backbone while neglecting the classification head. Existing models often rely on a single class token, underutilizing the spatiotemporal structure and second-order statistics that are crucial for EEG decoding. We propose Riemannian High Order Pooling (RHOP), a plug-and-play module that injects principled Riemannian statistics into the classifier. RHOP maps each token to a quotient Gaussian jointly encoding mean and second-order information, yielding scale-invariant descriptors. Tokens are then aggregated by estimating a Riemannian Gaussian on the SPD manifold, where the Fréchet mean and covariance are embedded into an SPD descriptor. The resulting normalized vector is fused with the class token for prediction. RHOP is backbone-agnostic and integrates with modern EEG foundation models, e.g., BIOT and LaBraM. Across diverse EEG benchmarks, it improves accuracy, robustness, and efficiency under full fine-tuning, linear probing, and from-scratch training settings.