ICLR 2026 论文列表

Hateful memes have emerged as a particularly challenging form of online abuse, motivating the development of automated detection systems. Most prior approaches rely on direct detection, producing only binary predictions. Such models fail to provide the context and explanations that real-world moderation requires. Recent Explain-then-Detect approaches, using Chain-of-Thought prompting or LMM agents, perform worse than simple SFT baselines, and even advanced post-training methods such as GRPO fail to close the gap. Our analysis identifies two key issues of such systems: important policy-relevant cues such as targets and attack types are not hypothesized by the model as a likely explanation; and the binary reward signal is insufficient to guide reasoning. To address these challenges, we propose ExPO-HM (Explain-then-Detect Policy Optimization for Hateful Memes), inspired by the training and evaluation process of human annotators. ExPO-HM combines SFT warmup, GRPO with curriculum learning, and Conditional Decision Entropy (CDE) as both metric and reward for reasoning quality. Across three hateful meme benchmarks, ExPO-HM achieves state-of-the-art performance on binary detection, fine-grained classification, and reasoning quality, with up to 15\% and 17\% F1 improvement over the GRPO and DPO baselines, respectively. By moving hateful meme detection from simple binary alarms to explanation-driven detection, ExPO-HM provides accurate, interpretable, and actionable moderation support.

Tri-Planar NeRFs enable the application of powerful 2D vision models for 3D tasks, by representing 3D objects using 2D planar structures. This has made them the prevailing choice to model large collections of 3D objects. However, training Tri-Planes to model such large collections is computationally intensive and remains largely inefficient. This is because the current approaches independently train one Tri-Plane per object, hence overlooking structural similarities in large classes of objects. In response to this issue, we introduce Fused-Planes, a novel object representation that improves the resource efficiency of Tri-Planes when reconstructing object classes, all while retaining the same planar structure. Our approach explicitly captures structural similarities across objects through a latent space and a set of globally shared base planes. Each individual Fused-Planes is then represented as a decomposition over these base planes, augmented with object-specific features. Fused-Planes showcase state-of-the-art efficiency among planar representations, demonstrating $7.2 \times$ faster training and $3.2 \times$ lower memory footprint than Tri-Planes while maintaining rendering quality. An ultra-lightweight variant further cuts per-object memory usage by $1875 \times$ with minimal quality loss. Our project page can be found at https://fused-planes.github.io .

Training a single network with multiple objectives often leads to conflicting gradients that degrade shared representations, forcing them into a compromised state that is suboptimal for any single task—a problem we term latent representation collapse. We introduce Domain Expansion, a framework that prevents these conflicts by restructuring the latent space itself. Our framework uses a novel orthogonal pooling to construct a latent space where each objective is assigned to a mutually orthogonal subspace. We validate our approach on the ShapeNet benchmark, simultaneously training a model for object classification and pose estimation. Our experiments demonstrate that this structure not only prevents collapse but also yields an explicit, interpretable, and compositional latent space where concepts can be directly manipulated.

Reinforcement Learning with Verifiable Rewards (RLVR) has become a widely adopted technique for enhancing the reasoning ability of Large Language Models (LLMs). However, the effectiveness of RLVR strongly depends on the capability of base models. This issue arises because it requires the model to have sufficient capability to perform high-quality exploration, which involves both effectiveness and diversity. Unfortunately, existing methods address this issue by imitating expert trajectories, which improve effectiveness but neglect diversity. To address this, we argue that the expert only needs to provide guidance only at critical decision points rather than the entire reasoning path. Based on this insight, we propose MENTOR: Mixed-policy Expert Navigation for Token-level Optimization of Reasoning, a framework that provides expert guidance only at critical decision points to perform effective and diverse exploration in RLVR. Extensive experiments show that MENTOR enables models capture the essence of expert strategies rather than surface imitation, thereby performing high-quality exploration and achieving superior overall performance. Our code is available online.

Image-to-point cloud registration aims to estimate the 6-DoF camera pose of a query image relative to a 3D point cloud map. Existing methods fall into two categories: matching-free methods regress pose directly using geometric priors, but lack fine-grained supervision and struggle with precise alignment; matching-based methods construct dense 2D-3D correspondences for PnP-based pose estimation, but are fundamentally limited by projection ambiguity (where multiple geometrically distinct 3D points project to the same image patch, leading to ambiguous feature representations) and scale inconsistency (where fixed-size image patches correspond to 3D regions of varying physical size, causing misaligned receptive fields across modalities). To address these issues, we propose a novel ray-based registration framework that first predicts patch-wise 3D ray bundles connecting image patches to the 3D scene and then estimates camera pose via a differentiable ray-guided regression module, bypassing the need for explicit 2D-3D correspondences. This formulation naturally resolves projection ambiguity, provides scale-consistent geometry encoding, and enables fine-grained supervision for accurate pose estimation. Experiments on KITTI and nuScenes show that our approach achieves state-of-the-art registration accuracy, outperforming existing methods.

Remote photoplethysmography (rPPG) enables non-contact physiological measurement but remains highly susceptible to illumination changes, motion artifacts, and limited temporal modeling. Large Language Models (LLMs) excel at capturing long-range dependencies, offering a potential solution but struggle with the continuous, noise-sensitive nature of rPPG signals due to their text-centric design. To bridge this gap, we introduce PhysLLM, a collaborative optimization framework that synergizes LLMs with domain-specific rPPG components. Specifically, the Text Prototype Guidance (TPG) strategy is proposed to establish cross-modal alignment by projecting hemodynamic features into LLM-interpretable semantic space, effectively bridging the representational gap between physiological signals and linguistic tokens. Besides, a novel Dual-Domain Stationary (DDS) Algorithm is proposed for resolving signal instability through adaptive time-frequency domain feature re-weighting. Finally, rPPG task-specific cues systematically inject physiological priors through physiological statistics, environmental contextual answering, and task description, leveraging cross-modal learning to integrate both visual and textual information, enabling dynamic adaptation to challenging scenarios like variable illumination and subject movements. Evaluation on four benchmark datasets, PhysLLM achieves state-of-the-art accuracy and robustness, demonstrating superior generalization across lighting variations and motion scenarios.

Modern Recurrent Neural Networks have become a competitive architecture for 3D reconstruction due to their linear-time complexity. However, their performance degrades significantly when applied beyond the training context length, revealing limited length generalization. In this work, we revisit the 3D reconstruction foundation models from a Test-Time Training perspective, framing their designs as an online learning problem. Building on this perspective, we leverage the alignment confidence between the memory state and incoming observations to derive a closed-form learning rate for memory updates, to balance between retaining historical information and adapting to new observations. This training-free intervention, termed TTT3R, substantially improves length generalization, achieving a 2 $\times$ improvement in global pose estimation over baselines, while operating at 20 FPS with just 6 GB of GPU memory to process thousands of images. Code is available in https://rover-xingyu.github.io/TTT3R.

In this paper, we identify that the key criterion for determining whether a model is truly capable of novel view synthesis (NVS) is transferability: Whether any pose representation extracted from one video sequence can be used to re-render the same camera trajectory in another. We analyze prior work on self-supervised NVS and find that their predicted poses do not transfer: The same set of poses lead to different camera trajectories in different 3D scenes. Here, we present XFactor, the first geometry-free self-supervised model capable of true NVS. XFactor combines pair-wise pose estimation with a simple augmentation scheme of the inputs and outputs that jointly enables disentangling camera pose from scene content and facilitates geometric reasoning. Remarkably, we show that XFactor achieves transferability with unconstrained latent pose variables, without any 3D inductive biases or concepts from multi-view geometry — such as an explicit parameterization of poses as elements of SE(3). We introduce a new metric to quantify transferability, and through large-scale experiments, we demonstrate that XFactor significantly outperforms prior pose-free NVS transformers, and show that latent poses are highly correlated with real-world poses through probing experiments.

Incorporating multiple modalities into large language models (LLMs) is a powerful way to enhance their understanding of non-textual data, enabling them to perform multimodal tasks. Vision language models (VLMs) form the fastest growing category of multimodal models because of their many practical use cases, including in healthcare, robotics, and accessibility. Unfortunately, even though different VLMs in the literature demonstrate impressive visual capabilities in different benchmarks, they are handcrafted by human experts; there is no automated framework to create task-specific multimodal models. We introduce Mordal, an automated multimodal model search framework that efficiently finds the best VLM for a user-defined task without manual intervention. Mordal achieves this both by reducing the number of candidates to consider during the search process and by minimizing the time required to evaluate each remaining candidate. Our evaluation shows that Mordal can find the best VLM for a given problem using $8.9\times$--$11.6\times$ lower GPU hours than grid search. We have also discovered that Mordal achieves about 69\% higher weighted Kendall’s $\tau$ on average than the state-of-the-art model selection method across diverse tasks.

Modern clinical diagnosis relies on the comprehensive analysis of multi-modal patient data, drawing on medical expertise to ensure systematic and rigorous reasoning. Recent advances in Vision–Language Models (VLMs) and agent-based methods are reshaping medical diagnosis by effectively integrating multi-modal information. However, they often output direct answers and empirical-driven conclusions without clinical evidence supported by quantitative analysis, which compromises their reliability and hinders clinical usability. Here we propose MedAgent-Pro, an agentic reasoning paradigm that mirrors modern diagnosis principles via a hierarchical diagnostic workflow, consisting of disease-level standardized plan generation and patient-level personalized step-by-step reasoning. To support disease-level planning, a retrieval-augmented generation agent is designed to access medical guidelines for alignment with clinical standards. For patient-level reasoning, MedAgent-Pro leverages professional tools such as visual models to take various actions to analyze multi-modal input, and performs evidence-based reflection to iteratively adjust memory, enforcing rigorous reasoning throughout the process. Extensive experiments across a wide range of anatomical regions, imaging modalities, and diseases demonstrate the superiority of MedAgent-Pro over mainstream VLMs, agentic systems and leading expert models. Ablation studies and expert evaluation further confirm its robustness and clinical relevance. Anonymized code link is available in the reproducibility statement.

3D object detection from LiDAR point cloud data is important for autonomous driving systems. Recent two-stage 3D object detectors struggle to achieve satisfactory performance due to limitations in proposal quality, stemming from the degradation of geometric detail information in the generated proposal features caused by high sparsity and uneven distribution of point clouds, as well as a lack of effective exploitation of surrounding contextual cues in the independent proposal refinement stage. To this end, we propose a Proposal-centric Transformer Network (PTN), which includes a Hierarchical Attentive Feature Alignment (HAFA) module and a Collaborative Proposal Refinement Module (CPRM). More concretely, to obtain multi-granularity proposal representations, HAFA employs a dual-stream architecture that extracts both coarse-grained voxel features and fine-grained point features to enhance proposal features, then harmo- nizes them through a feature alignment network in a unified space. The CPRM first generates object queries for all objects and then establishes contextual-aware interactions to extract complementary information from semantically similar and spatially relevant proposals. PTN achieves promising performance on large-scale Waymo and KITTI benchmark, demonstrating the superiority of PTN.

Accurate recall from large-scale memories remains a core challenge for memory-augmented AI assistants performing question answering (QA), especially in similarity-dense scenarios where existing methods mainly rely on semantic distance to the query for retrieval. Inspired by how humans link information associatively, we propose AssoMem, a novel framework constructing an associative memory graph that anchors dialogue utterances to automatically extracted clues. This structure provides a rich organizational view of the conversational context and facilitates importance-aware ranking. Further, AssoMem integrates multi-dimensional retrieval signals—relevance, importance, and temporal alignment—using an adaptive mutual information (MI)-driven fusion strategy. Extensive experiments across three benchmarks and a newly introduced dataset, MeetingQA, demonstrate that AssoMem consistently outperforms state-of-the-art baselines, verifying its superiority in context-aware memory recall.

Self-supervised pre-training has emerged as a critical paradigm for learning transferable representations from unlabeled medical volumetric data. Masked autoencoder based methods have garnered significant attention, yet their application to volumetric medical image faces fundamental limitations from the discrete voxel-level reconstruction objective, which neglects comprehensive anatomical structure continuity. To address this challenge, We propose MedGMAE, a novel framework that replaces traditional voxel reconstruction with 3D Gaussian primitives reconstruction as new perspectives on representation learning. Our approach learns to predict complete sets of 3D Gaussian parameters as semantic abstractions to represent the entire 3D volume, from sparse visible image patches. MedGMAE demonstrates dual utility across medical imaging applications. For representation learning, sparse Gaussian prediction produces superior encoder representations that outperform traditional MAE baselines on downstream segmentation, classification, and registration tasks. For volumetric reconstruction, the Gaussian decoder leverages pretrained anatomical priors to accelerate 3D CT volume reconstruction convergence. Extensive experiments across multiple medical imaging datasets demonstrate that our approach achieves superior performance, establishing a new paradigm for medical image pre-training. The code will be available in https://github.com/windrise/MedGMAE.

Tables serve as a fundamental format for representing structured relational data. While current language models (LMs) excel at many text-based tasks, they still face challenges in table understanding due to the complex characteristics of tabular data, such as their structured nature. In this paper, we aim to enhance LMs for improved table understanding. We identify four key challenges: 1) difficulty in locating target data, 2) deficiency in table semantics, 3) numerical inaccuracies in textual reasoning, and 4) semantic inflexibility in symbolic reasoning. To address these issues, we propose TableMaster, a recipe and comprehensive framework that integrates multiple solutions to overcome these obstacles. TableMaster first extracts relevant table content and verbalizes it with enriched semantic context. Additionally, we introduce adaptive reasoning, a flexible approach that dynamically adjusts between textual and symbolic reasoning, tailoring the reasoning process to each query. Extensive analyses and experiments demonstrate our findings and the effectiveness of TableMaster. On the WikiTQ dataset, TableMaster achieves an accuracy of 78.13% using GPT-4o-mini, surpassing existing baselines. We hope this work will serve as a practical step toward more robust and reliable table understanding.

We introduce **EA3D**, an Event-Augmented 3D Diffusion framework for generalizable novel view synthesis from event streams and sparse RGB inputs. Existing approaches either rely solely on RGB frames for generalizable synthesis, which limits their robustness under rapid camera motion, or require per-scene optimization to exploit event data, undermining scalability. EA3D addresses these limitations by jointly leveraging the complementary strengths of asynchronous events and RGB imagery. At its core lies a learnable EA-Renderer, which constructs view-dependent 3D features within target camera frustums by fusing appearance cues from RGB frames with geometric structure extracted from adaptively sliced event voxels. These features condition a 3D-informed diffusion model, enabling high-fidelity and temporally consistent novel view generation along arbitrary camera trajectories. To further enhance scalability and generalization, we develop the Event-DL3DV dataset, a large-scale 3D benchmark pairing diverse synthetic event streams with photorealistic multi-view RGB images and depth maps. Extensive experiments on both real-world and synthetic event data demonstrate that EA3D consistently outperforms optimization-based and generalizable baselines, achieving superior fidelity and cross-scene generalization.

Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems. Through in-depth analysis of LVLM activation patterns, we reveal two key findings: 1) truthfulness and visual perception capabilities predominantly engage different subsets of attention heads within the model architecture; and 2) truthfulness steering vectors vary significantly across different semantic contexts. Based on these observations, we propose Dynamic Multimodal Activation Steering, a training-free approach for hallucination mitigation. Our method constructs a semantic-based truthfulness steering vector database and computes visual perception steering vectors, enabling context-aware interventions during inference by dynamically selecting the most relevant steering vectors based on input semantic similarity and applying them to the most influential attention heads. We conduct comprehensive experiments across multiple models and datasets, demonstrating that our approach significantly enhances model performance, outperforming existing state-of-the-art methods.

Inversion-based watermarking is a promising approach to authenticate diffusion-generated images, yet practical use is bottlenecked by inversion that is both slow and error-prone. While the primary challenge in the watermarking setting is robustness against external distortions, existing approaches over-optimize internal truncation error, and because that error scales with the sampler step size, they are inherently confined to high-NFE (number of function evaluations) regimes that cannot meet the dual demands of speed and robustness. In this work, we have two key observations: (i) the inversion trajectory has markedly lower curvature than the forward generation path does, making it highly compressible and amenable to low-NFE approximation; and (ii) in inversion for watermark verification, the trade-off between speed and truncation error is less critical, since external distortions dominate the error. A faster inverter provides a dual benefit: it is not only more efficient, but it also enables end-to-end adversarial training to directly target robustness, a task that is computationally prohibitive for the original, lengthy inversion trajectories. Building on this, we propose **FARI** (**F**ast **A**symmetric **R**obust **I**nversion), a one-step inversion framework paired with lightweight adversarial LoRA fine-tuning of the denoiser for watermark extraction. While consolidation slightly increases internal error, FARI delivers large gains in both speed and robustness: with ~20 minutes of fine-tuning on a single NVIDIA RTX A6000 GPU, it surpasses 50-step DDIM inversion on watermark-verification robustness while dramatically reducing inference time.

Despite their impressive performance on computer vision benchmarks, Deep Neural Networks (DNNs) still fall short of adequately modeling human visual behavior, as measured by error consistency and shape bias. Recent work hypothesized that behavioral alignment can be drastically improved through generative - rather than discriminative - classifiers, with far-reaching implications for models of human vision. Here, we instead show that the increased alignment of generative models can be largely explained by a seemingly innocuous resizing operation in the generative model which effectively acts as a low-pass filter. In a series of controlled experiments, we show that removing high-frequency spatial information from discriminative models like CLIP drastically increases their behavioral alignment. Simply blurring images at test-time - rather than training on blurred images - achieves a new state-of-the-art score on the model-vs-human benchmark, halving the current alignment gap between DNNs and human observers. Furthermore, low-pass filters are likely optimal, which we demonstrate by directly optimizing filters for alignment. To contextualize the performance of optimal filters, we compute the frontier of all possible pareto-optimal solutions to the benchmark, which was formerly unknown. We explain our findings by observing that the frequency spectrum of optimal Gaussian filters roughly matches the spectrum of band-pass filters implemented by the human visual system. We show that the contrast sensitivity function, describing the inverse of the contrast threshold required for humans to detect a sinusoidal grating as a function of spatiotemporal frequency, is approximated well by Gaussian filters of a specific width.

Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficiency. Instruction-related visual token compression demonstrates strong task relevance, which aligns well with MLLMs’ ultimate goal of instruction following. Previous works generally assume that visual tokens achieve better vision–language alignment in the shallow layers of LLMs, which have led to task-related token compression being primarily applied in intermediate LLM layers. In contrast, our study reveals that with proper selection, task-related token compression is feasible at the input stage of LLM with negligible performance loss. This new paradigm significantly reduces task-irrelevant visual tokens and its model-agnostic design enables application without modifying the LLM architecture. Specifically, we suggest that explainability methods for transformer-based architechtures can evaluate the global importance of each visual token with respect to the given instruction, which can effectively guide the task-related token compression for MLLMs. Furthermore, we propose to learn a mapping from the attention map of the first LLM layer to the explanation results, thereby avoiding the need for a full inference pass. Interestingly, this mapping can be learned using a simple and lightweight convolutional network, whose training is efficient and independent of MLLMs. Extensive experiments on 13 image and video benchmarks across three leading MLLMs (Qwen2-VL, LLaVA-OneVision, and VILA1.5) demonstrate the remarkable effectiveness and strong generalization of our approach. Additionally, our new compression paradigm achieves faster inference with reductions in both prefilling time and KV-cache memory.