ICLR 2026 Papers

Few-shot learning (FSL) aims to generalize to novel categories with only a few samples. Recent approaches incorporate large language models (LLMs) to enrich visual representations with semantic embeddings derived from class names. However, they overlook progressive and adaptive alignment between vision and language from low-level to high-level semantics, resulting in limited semantic gains. To address these challenges, we propose Dual-level Vision–Language Alignment with Reinforcement Learning gating (DVLA-RL), which consists of Dual-level Semantic Construction (DSC) and RL-gated Attention (RLA). Specifically, DSC conditions LLMs on both class names and support samples to generate discriminative attributes, progressively selects the most relevant ones, and then synthesizes them into coherent class descriptions. This process provides complementary low-level attributes and high-level descriptions, enabling both fine-grained grounding and holistic class understanding. To dynamically integrate dual-level semantics along with the visual network layers, RLA formulates cross-modal fusion as a sequential decision process. A lightweight policy trained with episodic REINFORCE adaptively adjusts the contributions of self-attention and cross-attention to integrate textual and visual tokens. As a result, shallow layers refine local attributes and deep layers emphasize global semantics, enabling more precise cross-modal alignment. This achieves class-specific discrimination and generalized representations with merely a few support samples. DVLA-RL achieves new state-of-the-art performance across nine benchmarks in three diverse FSL scenarios.

The remarkable success of multimodal large language models (MLLMs) has driven advances in multimodal embeddings, yet existing models remain inherently discriminative, limiting their ability to benefit from reasoning-driven generation paradigm. In this work, we pioneer the exploration of generative embeddings, unifying embedding tasks within a generative paradigm. We propose UME-R1, a universal multimodal embedding framework consisting of a two-stage training strategy: a cold-start supervised fine-tuning equips the model with reasoning capabilities and enables it to generate both discriminative and generative embeddings; a subsequent reinforcement learning enhances reasoning and further optimizes generative embedding quality. This pioneering work reveals four key insights: 1) generative embeddings unlock substantial performance gains over conventional discriminative embeddings by leveraging the powerful generative reasoning capabilities of MLLMs; 2) discriminative and generative embeddings are complementary, whose combined oracle performance far exceeding that of either alone; 3) RL can effectively enhance generative embeddings, establishing a scalable optimization paradigm.; 4) repeated sampling at inference boosts downstream task coverage (pass@k), highlighting the inference-time scalability potential of generative embeddings. Evaluated on the MMEB-V2 benchmark across 78 tasks spanning video, image, and visual documents, UME-R1 significantly outperforms conventional discriminative embedding models and offers a foundation for more interpretable, reasoning-driven generative multimodal embeddings.

Recent advances in large language models (LLMs) test-time computing have introduced the capability to perform intermediate chain-of-thought (CoT) reasoning (thinking) before generating answers. While increasing the thinking budget yields smooth performance improvements at inference time, the relationship between LLM capability, query complexity, and optimal budget allocation remains poorly understood for achieving compute-optimal inference. To address this challenge, we utilize $\textit{self-consistency}$, the agreement among multiple reasoning paths, as a proxy for thinking necessity. We first identify that lower self-consistency indicates when queries require extended thinking to reach correct answers. Building on this insight, we introduce $\texttt{Sonata}$ (Self-Consistency-Guided Adapter for Thinking Allocation), a lightweight approach that adaptively allocates thinking budgets to optimize the performance-efficiency tradeoff. $\texttt{Sonata}$ includes an adapter trained offline on a calibration dataset to predict self-consistency directly from the last layer hidden representations during the query prefilling stage. This prediction then guides on-the-fly budget allocation before thinking. The adapter is general, transferable across diverse tasks once trained, and introduces $<1$$\textperthousand$ computational overhead during inference. Notably, Sonata is compatible with existing CoT compression methods, enabling further efficiency gains when managing thinking budgets across queries. Extensive experiments on multiple models (Qwen3-8B, Qwen3-32B, GPT-OSS-120B, Qwen3-235B-A22B) and benchmarks~(AIME25, GSM8K, MATH500, GPQA, LiveCodeBench) demonstrate that $\texttt{Sonata}$ achieves $20\\%$ to $60\\%$ reduction in thinking tokens while maintaining the same accuracy, or up to $2\\%$ improvement in accuracy with the same token cost.

Many methods aim to enhance time series forecasting by decomposing the series through intricate model structures and prior knowledge, yet they are inevitably limited by computational complexity and the robustness of the assumptions. Our research uncovers that in the complex domain and higher-order hypercomplex spaces, the characteristic frequencies of time series naturally decrease. Leveraging this insight, we propose Numerion, a time series forecasting model based on multiple hypercomplex spaces. Specifically, grounded in theoretical support, we generalize linear layers and activation functions to hypercomplex spaces of arbitrary power-of-two dimensions and introduce a novel Real-Hypercomplex-Real Domain Multi-Layer Perceptron (RHR-MLP) architecture. Numerion utilizes multiple RHR-MLPs to map time series into hypercomplex spaces of varying dimensions, naturally decomposing and independently modeling the series, and adaptively fuses the latent patterns exhibited in different spaces through a dynamic fusion mechanism. Experiments validate the model’s performance, achieving state-of-the-art results on multiple public datasets. Visualizations and quantitative analyses comprehensively demonstrate the ability of multi-dimensional RHR-MLPs to naturally decompose time series and reveal the tendency of higher-dimensional hypercomplex spaces to capture lower-frequency features.

Personalizing text-to-image diffusion models involves integrating novel visual concepts from a small set of reference images while retaining the model’s original generative capabilities. However, this process often leads to overfitting, where the model ignores the user’s prompt and merely replicates the reference images. We attribute this issue to a fundamental misalignment between the true goals of personalization, which are subject fidelity and text alignment, and the training objectives of existing methods that fail to enforce both objectives simultaneously. Specifically, prior approaches often overlook the need to explicitly preserve the pretrained model’s output distribution, resulting in distributional drift that undermines diversity and coherence. To resolve these challenges, we introduce a Lipschitz-based regularization objective that constrains parameter updates during personalization, ensuring bounded deviation from the original distribution. This promotes consistency with the pretrained model’s behavior while enabling accurate adaptation to new concepts. Furthermore, our method offers a computationally efficient alternative to commonly used, resource-intensive sampling techniques. Through extensive experiments across diverse diffusion model architectures, we demonstrate that our approach achieves superior performance in both quantitative metrics and qualitative evaluations, consistently excelling in visual fidelity and prompt adherence. We further support these findings with comprehensive analyses, including ablation studies and visualizations.

Recent advances in multimodal large reasoning models (MLRMs) have substantially improved their ability to solve complex textual and visual tasks. However, these models tend to *overthink* on simple problems, producing unnecessarily lengthy reasoning traces, while *under-exploring* on challenging ones, leading to missed solutions. To address this imbalance, we propose **ARES**, a unified open-source framework for *adaptive reasoning* that dynamically allocates exploration effort based on task difficulty. Our approach is motivated by two key empirical findings: (i) while single-token entropy is noisy, *high window-entropy (HWE) tokens* (token-level entropies averaged under a sliding window) can reliably capture reasoning-critical moments; and (ii) reducing HWE usage benefits easy problems, while increasing it is essential for solving hard ones. Building on these insights, ARES introduces a two-stage training pipeline. In the *Adaptive Cold-Start* stage, we curate multimodal and textual data paired with reasoning traces of length proportional to problem difficulty, equipping the model with initial difficulty awareness. In the second stage, we develop *Adaptive Entropy Policy Optimization (AEPO)*, which uses HWE tokens as exploration triggers to decide *when to explore*, and a hierarchical entropy reward with dynamic KL control to decide *how much to explore*. Extensive experiments demonstrate that ARES achieves state-of-the-art performance and reasoning efficiency across diverse mathematical, logical, and multimodal benchmarks, while closing the gap to leading commercial systems under significantly lower inference costs. The anonymous code repository is available at https://anonymous.4open.science/r/ARES-60728M.

Inductive Knowledge Graph Reasoning (KGR) aims to discover facts in open-domain KGs containing unknown entities and relations, which poses a challenge for KGR models in comprehending uncertain KG components. Existing studies have proposed Knowledge Graph Foundation Models (KGFMs) that learn structural invariances across KGs to handle this uncertainty. Recently, Large Language Models (LLMs) have demonstrated strong capabilities for open-domain knowledge reasoning. As a result, the latest research has focused on LLM-based KGFMs that integrate LLM knowledge with KG context for inductive KGR. However, the intrinsic knowledge of LLMs may be overshadowed by sparse KG context, leading to LLM knowledge distortion, which can cause irreversible damage to model reasoning. Moreover, existing LLM-based KGR methods still struggle to fully constrain generative hallucinations in LLMs, severely limiting the credibility of reasoning results. To address these limitations, we propose a Knowledge Reasoning Language Model (KRLM) that achieves unified coordination between LLM knowledge and KG context throughout the KGR process. Specifically, we design a Knowledge Reasoning Language (KRL) instruction format and a KRL tokenizer to align LLM knowledge with KG representations. Then, we propose a KRL attention layer that coordinates intrinsic LLM knowledge with additional KG context through a dynamic knowledge memory mechanism. Finally, a structure-aware next-entity predictor is proposed, which strictly constrains the reasoning results within a trustworthy knowledge domain. Extensive experimental results on 25 real-world inductive KGR datasets demonstrate the significant superiority of the proposed KRLM in both zero-shot reasoning and fine-tuning scenarios.

Lipschitz-based certification offers efficient, deterministic robustness guarantees but has struggled to scale in model size, training efficiency, and ImageNet performance. We introduce \emph{LipNeXt}, the first \emph{constraint-free} and \emph{convolution-free} 1-Lipschitz architecture for certified robustness. LipNeXt is built using two techniques: (1) a manifold optimization procedure that updates parameters directly on the orthogonal manifold and (2) a \emph{Spatial Shift Module} to model spatial pattern without convolutions. The full network uses orthogonal projections, spatial shifts, a simple 1-Lipschitz $\beta$-Abs nonlinearity, and $L_2$ spatial pooling to maintain tight Lipschitz control while enabling expressive feature mixing. Across CIFAR-10/100 and Tiny-ImageNet, LipNeXt achieves state-of-the-art clean and certified robust accuracy (CRA), and on ImageNet it scales to 1–2B large models, improving CRA over prior Lipschitz models (e.g., up to $+8\%$ at $\varepsilon{=}1$) while retaining efficient, stable low-precision training. These results demonstrate that Lipschitz-based certification can benefit from modern scaling trends without sacrificing determinism or efficiency.

We present a hybrid dual-path vision encoder (Hyden) for high-resolution monocular depth, point map and surface normal estimation, surpassing state-of-the-art accuracy with a fraction of the inference cost. The architecture pairs a low-resolution Vision Transformer branch for global context with a full-resolution CNN branch for fine details, fusing features via a lightweight MLP before decoding. By exploiting the linear scaling of CNNs and constraining transformer computation to a fixed resolution, the model delivers fast inference even on multi-megapixel inputs. To overcome the scarcity of high-quality high-resolution supervision, we introduce a self-distillation framework that generates pseudo-labels from existing models at both lower resolution full images and high-resolution crops—global labels preserve geometric accuracy, while local labels capture sharper details. To demonstrate the flexibility of our approach, we integrate Hyden and our self-distillation method into DepthAnything-v2 for depth estimation and MoGe2 for surface normal and metric point map prediction, achieving state-of-the-art results on high-resolution benchmarks with the lowest inference latency among competing methods.

Optimization under heavy-tailed noise has become popular recently, since it better fits many modern machine learning tasks, as captured by empirical observations. Concretely, instead of a finite second moment on gradient noise, a bounded $\mathfrak{p}$-th moment where $\mathfrak{p}\in(1,2]$ has been recognized to be more realistic (say being upper bounded by $\sigma_{\mathfrak{l}}^{\mathfrak{p}}$ for some $\sigma_{\mathfrak{l}}\geq0$). A simple yet effective operation, gradient clipping, is known to handle this new challenge successfully. Specifically, Clipped Stochastic Gradient Descent (Clipped SGD) guarantees a high-probability rate $\mathcal{O}(\sigma_{\mathfrak{l}}\ln(1/\delta)T^{\frac{1}{\mathfrak{p}}-1})$ (resp. $\mathcal{O}(\sigma_{\mathfrak{l}}^{2}\ln^{2}(1/\delta)T^{\frac{2}{\mathfrak{p}}-2})$) for nonsmooth convex (resp. strongly convex) problems, where $\delta\in(0,1]$ is the failure probability and $T\in\mathbb{N}$ is the time horizon. In this work, we provide a refined analysis for Clipped SGD and offer two faster rates, $\mathcal{O}(\sigma_{\mathfrak{l}}d_{\mathrm{eff}}^{-\frac{1}{2\mathfrak{p}}}\ln^{1-\frac{1}{\mathfrak{p}}}(1/\delta)T^{\frac{1}{\mathfrak{p}}-1})$ and $\mathcal{O}(\sigma_{\mathfrak{l}}^{2}d_{\mathrm{eff}}^{-\frac{1}{\mathfrak{p}}}\ln^{2-\frac{2}{\mathfrak{p}}}(1/\delta)T^{\frac{2}{\mathfrak{p}}-2})$, than the aforementioned best results, where $d_{\mathrm{eff}}\geq1$ is a quantity we call the generalized effective dimension. Our analysis improves upon the existing approach in two respects: better utilization of Freedman's inequality and finer bounds for clipping error under heavy-tailed noise. In addition, we extend the refined analysis to convergence in expectation and obtain new rates that break the known lower bounds. Lastly, to complement the study, we establish new lower bounds for both high-probability and in-expectation convergence. Notably, the in-expectation lower bounds match our new upper bounds, indicating the optimality of our refined analysis for convergence in expectation.

Relational Deep Learning (RDL) is a promising approach for building state-of-the-art predictive models on multi-table relational data by representing it as a heterogeneous temporal graph. However, commonly used Graph Neural Network models suffer from fundamental limitations in capturing complex structural patterns and long-range dependencies that are inherent in relational data. While Graph Transformers have emerged as powerful alternatives to GNNs on general graphs, applying them to relational entity graphs presents unique challenges: (i) Traditional positional encodings fail to generalize to massive, heterogeneous graphs; (ii) existing architectures cannot model the temporal dynamics and schema constraints of relational data; (iii) existing tokenization schemes lose critical structural information. Here we introduce the Relational Graph Transformer (RelGT), the first graph transformer architecture designed specifically for relational tables. RelGT employs a novel multi-element tokenization strategy that decomposes each node into five components (features, type, hop distance, time, and local structure), enabling efficient encoding of heterogeneity, temporality, and topology without expensive precomputation. Our architecture combines local attention over sampled subgraphs with global attention to learnable centroids, incorporating both local and database-wide representations. Across 21 tasks from the RelBench benchmark, RelGT consistently matches or outperforms GNN baselines by up to 18%, establishing Graph Transformers as a powerful architecture for Relational Deep Learning.

We propose an accurate and interpretable fine-grained cross-view localization method that estimates the 3 Degrees of Freedom (DoF) pose of a ground-level image by matching its local features with a reference aerial image. Unlike prior approaches that rely on global descriptors or bird’s-eye-view (BEV) transformations, our method directly learns ground–aerial image-plane correspondences using weak supervision from camera poses. The matched ground points are lifted into BEV space with monocular depth predictions, and scale-aware Procrustes alignment is then applied to estimate camera rotation, translation, and optionally the scale between relative depth and the aerial metric space. This formulation is lightweight, end-to-end trainable, and requires no pixel-level annotations. Experiments show state-of-the-art accuracy in challenging scenarios such as cross-area testing and unknown orientation. Furthermore, our method offers strong interpretability: correspondence quality directly reflects localization accuracy and enables outlier rejection via RANSAC, while overlaying the re-scaled ground layout on the aerial image provides an intuitive visual cue of localization accuracy.

Deep research becomes increasingly important as people seek to solve complex problems that require gathering and synthesizing information from diverse sources. A key capability in this process is agentic search, where an LLM-agent iteratively retrieves relevant information across multiple sources while performing multi-step reasoning. However, developing effective agentic search systems is challenging due to the lack of high-quality training data that reflects the complexity of real-world research tasks. To address this gap, we introduce InfoSeek, a novel data synthesis framework that conceptualizes agentic search as a Hierarchical Constraint Satisfaction Problem (HCSP), where solving a task requires satisfying layered constraints across multiple levels of sub-problems. InfoSeek employs a Diffusion–Retrospection process: in the diffusion phase, the framework expands outward from a seed webpage, generating constraints that connect to neighboring pages and forming an exploration tree; in the retrospection phase, a subtree is sampled and backtracking constraints are introduced, which are then blurred and integrated into an HCSP instance. As a generic framework, InfoSeek can be easily extended to other domains beyond web, facilitating ad-hoc optimization of deep research. To our knowledge, InfoSeek is the first publicly released framework in this area, complete with open-source code and well-curated datasets. Extensive experiments on diverse information-seeking benchmarks show that training on InfoSeek-generated data substantially improves agentic search performance, delivering significantly larger gains than traditional datasets across diverse model backends and training strategies, thereby validating the effectiveness of our approach.

Effective information seeking in multi-turn medical dialogues is critical for accurate diagnosis, especially when dealing with incomplete information. Aligning Large Language Models (LLMs) for these interactive scenarios is challenging due to the uncertainty inherent in user-agent interactions, which we formulate as a Hierarchical Markov Decision Process (H-MDP). While conventional Reinforcement Learning (RL) methods like Group Relative Policy Optimization (GRPO) struggle with long-horizon credit assignment and Proximal Policy Optimization (PPO) suffers from unstable value estimation in this context, we propose a novel uncertainty-aware Adaptive Tree Policy Optimization (ATPO) algorithm. Our method adaptively allocates the rollout budget to states with high uncertainty, quantified by a composite metric of Bellman error and action-value variance. This strategy enables more accurate value estimation, while fostering more efficient and diverse exploration. To mitigate the high computational cost of tree-based RL, we introduce two key optimizations: an uncertainty-guided pruning mechanism to minimize the number of rollouts, and an asynchronous search architecture that leverages KV cache reuse to maximize inference throughput. Extensive experiments on three public medical dialogue benchmarks demonstrate that our algorithm significantly outperforms several strong baselines, culminating in Qwen3-8B model surpassing the much larger GPT-4o (+0.92% accuracy).

Reinforcement learning for safety-critical tasks requires policies that are both high-performing and safe throughout the learning process. While model-predictive shielding is a promising approach, existing methods are often computationally intractable for the high-dimensional, nonlinear systems where deep RL excels, as they typically rely on a patchwork of local models. We introduce **RAMPS**, a scalable shielding framework that overcomes this limitation by leveraging a learned, linear representation of the environment's dynamics. This model can range from a linear regression in the original state space to a more complex operator learned in a high-dimensional feature space. The key is that this linear structure enables a robust, look-ahead safety technique based on a *multi-step Control Barrier Function (CBF)*. By moving beyond myopic one-step formulations, **RAMPS** accounts for model error and control delays to provide reliable, real-time interventions. The resulting framework is minimally invasive, computationally efficient, and built upon robust control-theoretic foundations. Our experiments demonstrate that **RAMPS** significantly reduces safety violations compared to existing safe RL methods while maintaining high task performance in complex control environments.

The computational cost of Multimodal Large Language Models (MLLMs), driven by the quadratic complexity of processing vision tokens, remains a significant barrier to their widespread adoption. While progressive vision token pruning is a promising solution, we find that its full potential has been unrealized due to two key limitations: it misinterprets the role of shallow layers as being crucial for fusion and employs overly rigid, non-adaptive pruning schedules. To address these flaws, we introduce HiDivDrop, a framework that tailors token pruning to the true hierarchical function of MLLM layers. HiDivDrop incorporates two key innovations: (1) a Late Injection strategy that bypasses passive shallow layers, introducing visual tokens directly where active fusion begins; and (2) a Concave Pyramid Pruning scheme with an Early Exit mechanism that dynamically adjusts the pruning rate throughout the middle and deep layers. This process is optimized via an inter-layer similarity measure and a differentiable top-$k$ operator. Extensive experiments show that HiDivDrop compresses $\sim$90\% visual tokens while matching the original performance and accelerating training by 1.72$\times$. Our work not only sets a new state-of-the-art for efficient MLLM training and inference but also provides valuable insights into the hierarchical nature of multimodal fusion.

Medical Large Vision-Language Models (Med-LVLMs) have shown strong potential in multimodal diagnostic tasks. However, existing single-agent models struggle to generalize across diverse medical specialties, limiting their performance. Recent efforts introduce multi-agent collaboration frameworks inspired by clinical workflows, where general practitioners (GPs) and specialists interact in a fixed sequence. Despite improvements, these static pipelines lack flexibility and adaptability in reasoning. To address this, we propose MMedAgent-RL, a reinforcement learning (RL)-based multi-agent framework that enables dynamic, optimized collaboration among medical agents. Specifically, we train two GP agents based on Qwen2.5-VL via RL: the triage doctor learns to assign patients to appropriate specialties, while the attending physician integrates the judgments from multi-specialists and its own knowledge to make final decisions. To address the inconsistency in specialist outputs, we introduce a curriculum learning (CL)-guided RL strategy with dynamic entropy regulation, progressively teaching the attending physician to balance between imitating specialists and correcting their mistakes. Experiments on five medical VQA benchmarks demonstrate that MMedAgent-RL outperforms both open-source and proprietary Med-LVLMs. Notably, it achieves an average performance gain of 23.6\% over strong baselines.

In this work, we present Color3D, a highly adaptable framework for colorizing both static and dynamic 3D scenes from monochromatic inputs, delivering visually diverse and chromatically vibrant reconstructions with flexible user-guided control. In contrast to existing methods that focus solely on static scenarios and enforce multi-view consistency by averaging color variations which inevitably sacrifice both chromatic richness and controllability, our approach is able to preserve color diversity and steerability while ensuring cross-view and cross-time consistency. In particular, the core insight of our method is to colorize only a single key view and then fine-tune a personalized colorizer to propagate its color to novel views and time steps. Through personalization, the colorizer learns a scene-specific deterministic color mapping underlying the reference view, enabling it to consistently project corresponding colors to the content in novel views and video frames via its inherent inductive bias. Once trained, the personalized colorizer can be applied to infer consistent chrominance for all other images, enabling direct reconstruction of colorful 3D scenes with a dedicated Lab color space Gaussian splatting representation. The proposed framework ingeniously recasts complicated 3D colorization as a more tractable single image paradigm, allowing seamless integration of arbitrary image colorization models with enhanced flexibility and controllability. Extensive experiments across diverse static and dynamic 3D colorization benchmarks substantiate that our method can deliver more consistent and chromatically rich renderings with precise user control. Project Page: https://yecongwan.github.io/Color3D/.

Modern large language models (LLMs) such as GPT, Claude, and Gemini have transformed the way we learn, work, and communicate. Yet, their ability to produce highly human-like text raises serious concerns about misinformation and academic integrity, making it an urgent need for reliable algorithms to detect LLM-generated content. In this paper, we start by presenting a geometric approach to demystify rewrite-based detection algorithms, revealing their underlying rationale and demonstrating their generalization ability. Building on this insight, we introduce a novel rewrite-based detection algorithm that adaptively learns the distance between the original and rewritten text. Theoretically, we demonstrate that employing an adaptively learned distance function is more effective for detection than using a fixed distance. Empirically, we conduct extensive experiments with over 100 settings, and find that our approach demonstrates superior performance over baseline algorithms in the majority of scenarios. In particular, it achieves relative improvements from 57.8\% to 80.6\% over the strongest baseline across different target LLMs (e.g., GPT, Claude, and Gemini). A python implementation of our proposal is publicly available at https://github.com/Mamba413/L2D.