In this paper, we present a holistic multimodal benchmark that evaluates the reasoning capabilities of MLLMs with an explicit focus on reasoning width, a complementary dimension to the more commonly studied reasoning depth. Specifically, reasoning depth measures the model's ability to carry out long-chain, sequential reasoning in which each step is tightly and rigorously linked to the next. Reasoning width tends to focus more on the model's capacity for broad trial-and-error search or multi-constrained optimization: it must systematically traverse many possible and parallelized reasoning paths, apply diverse constraints to prune unpromising branches, and identify valid solution routes for efficient iteration or backtracking. To achieve it, we carefully curate 1200+ high-quality multimodal cases spanning heterogeneous domains, and propose a fine-grained tree-of-thought evaluation protocol that jointly quantifies reasoning width and depth. We evaluate 12 major model families (over 30 advanced MLLMs) across difficulty tiers, question types, and required skills. Results show that while current models exhibit strong performance on general or common-sense VQA tasks, they still struggle to combine deep sequential thought chains with wide exploratory search to perform genuine insight-based reasoning. Finally, we analyze characteristic failure modes to provide possible directions for building MLLMs that reason not only deeper but also wider.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
Open-vocabulary human-object interaction (HOI) detection aims to localize and recognize all human-object interactions in an image, including those unseen during training. Existing approaches usually rely on the collaboration between a conventional HOI detector and a Vision-Language Model (VLM) to recognize unseen HOI categories. However, feature fusion in this paradigm is challenging due to significant gaps in cross-model representations. To address this issue, we introduce SL-HOI, a StreamLined open vocabulary HOI detection framework based solely on the powerful DINOv3 model. Our design leverages the complementary strengths of DINOv3's components: its backbone for fine-grained localization and its text-aligned vision head for open-vocabulary interaction classification. Moreover, to facilitate smooth cross-attention between the interaction queries and the vision head's output, we propose first feeding both the interaction queries and the backbone image tokens into the vision head, effectively bridging their representation gaps. All DINOv3 parameters in our approach are frozen, with only a small number of learnable parameters added, allowing a fast adaptation to the HOI detection task. Extensive experiments show that SL-HOI achieves state-of-the-art performance on both the SWiG-HOI and HICO-DET benchmarks, demonstrating the effectiveness of our streamlined model architecture. Code is available at https://github.com/MPI-Lab/SL-HOI.
Reconstructing a dynamic target moving over a large area is challenging. Standard approaches for dynamic object reconstruction require dense coverage in both the viewing space and the temporal dimension, typically relying on multi-view videos captured at each time step.However, such setups are only possible in constrained environments. In real-world scenarios, observations are often sparse over time and captured sparsely from diverse viewpoints (e.g., from security cameras), making dynamic reconstruction highly ill-posed. We present SV-GS, a framework that simultaneously estimates a deformation model and the object's motion over time under sparse observations. To initialize SV-GS, we leverage a rough skeleton graph and an initial static reconstruction as inputs to guide motion estimation. (Later, we show that this input requirement can be relaxed.) Our method optimizes a skeleton-driven deformation field composed of a coarse skeleton joint pose estimator and a module for fine-grained deformations. By making only the joint pose estimator time-dependent, our model enables smooth motion interpolation while preserving learned geometric details. Experiments on synthetic datasets show that our method outperforms existing approaches under sparse observations by up to 34% in PSNR, and achieves comparable performance to dense monocular video methods on real-world datasets despite using significantly fewer frames. Moreover, we demonstrate that the input initial static reconstruction can be replaced by a diffusion-based generative prior, making our method more practical for real-world scenarios.
Deep learning-based online mapping has emerged as a cornerstone of autonomous driving, yet these models frequently fail to generalize beyond familiar environments. We propose a framework to identify and measure the underlying failure modes by disentangling two effects: Memorization of input features and overfitting to known map topologies. We propose metrics based on evaluation subsets that control for geographical proximity and topological similarity between training and validation scenes. We introduce Frechet distance-based reconstruction statistics that capture per-element shape fidelity without threshold tuning, and define complementary failure-mode scores: an input-feature overfitting score quantifying the performance drop when geographic cues disappear, and a topology overfitting score measuring degradation as scenes become topologically novel. Beyond models, we analyze dataset biases and contribute topology-aware diagnostics: A minimum-spanning-tree (MST) diversity metric for training sets and a symmetric coverage metric to quantify topological similarity between splits. Leveraging these, we formulate an MST-based sparsification strategy that reduces redundancy and improves balancing and performance while shrinking training size. Experiments on nuScenes and Argoverse 2 across multiple state-of-the-art models yield more trustworthy assessment of generalization and show that topology-diverse and balanced training sets lead to improved performance. Our results motivate failure-mode-aware protocols and topology-centric dataset design for deployable online mapping.
CubeComposer: Spatio-Temporal Autoregressive 4K 360deg Video Generation from Perspective Video
PDF ↗Generating high-quality 360deg panoramic videos from perspective input is one of the crucial applications for virtual reality (VR), whereby high-resolution videos are especially important for immersive experience. Existing methods are constrained by computational limitations of vanilla diffusion models, only supporting <= 1K resolution native generation and relying on suboptimal post-hoc super-resolution. We introduce CubeComposer, a novel spatio-temporal autoregressive diffusion model that natively generates 4K-resolution 360deg videos. By decomposing videos into cubemap representations with six faces, CubeComposer autoregressively synthesizes content in a well-planned spatio-temporal order, reducing peak memory demands while enabling high-resolution output. Specifically, to address challenges in multi-dimensional autoregression, we propose: (1) a spatio-temporal autoregressive strategy that orchestrates 360deg video generation across cube faces and time windows for coherent synthesis; (2) a cube face context management mechanism, equipped with a sparse context attention design to improve efficiency; and (3) continuity-aware techniques, including cube-aware positional encoding, padding, and blending to eliminate boundary seams. Extensive experiments on benchmark datasets demonstrate that CubeComposer outperforms state-of-the-art methods in native resolution and visual quality, supporting practical VR application scenarios.
Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge
PDF ↗Continual learning (CL) on edge devices requires not only high accuracy but also training-time efficiency to support on-device adaptation under strict memory and computational constraints. While prompt-based continual learning (PCL) is parameter-efficient and achieves competitive accuracy, prior work has focused mainly on accuracy or inference-time performance, often overlooking the memory and computational costs of on-device training. In this paper, we propose CPS-Prompt, a critical patch-aware sparse prompting framework that explicitly targets training-time memory usage and computational cost by integrating critical patch sampling (CPS) for task-aware token reduction and decoupled prompt and classifier training (DPCT) to reduce backpropagation overhead. Experiments on three public benchmarks and real edge hardware show that CPS-Prompt improves peak memory, training time, and energy efficiency by about 1.6x over the balanced CODA-Prompt baseline, while maintaining accuracy within 2% of the state-of-the-art C-Prompt on average and remaining competitive with CODA-Prompt in accuracy. The code is available at https://github.com/laymond1/cpsprompt.
Mixture-of-Experts (MoE) has become a prevalent backbone for large vision-language models (VLMs), yet how modality-specific signals should guide expert routing remains under-explored. Existing routing strategies are either hand-crafted or modality-agnostic, relying on idealized priors that ignore the layer-dependent modality fusion patterns in MoE-VLMs and provide little guidance for expert specialization. We propose Soft Modality-guided Expert Specialization (SMoES), which consists of dynamic soft modality scores that capture layer-dependent fusion patterns, an expert binning mechanism aligned with expert-parallel deployment, and an inter-bin mutual information regularization that encourages coherent modality specialization. Our method leverages attention-based or Gaussian-statistics modality scores to optimize mutual information regularization. Experiments across four MoE-based VLMs and 16 benchmarks demonstrate improvement on both effectiveness and efficiency: 0.9% and 4.2% average gain on multimodal and language-only tasks, 56.1% reduction in EP communication overhead, and 12.3% throughput improvement under realistic deployment. These results validate that aligning routing with modality-aware expert specialization unlocks MoE-VLM capacity and efficiency.
High-quality 3D assets are critical for VR/AR, industrial design, and entertainment, driving growing interest in generative models that can create 3D content from user-provided prompts. Most existing 3D generators, however, rely on a single conditioning modality: image-conditioned models deliver high visual fidelity by exploiting pixel-aligned cues but suffer from viewpoint bias when the input view is limited or ambiguous, whereas text-conditioned models benefit from broad semantic guidance yet lack low-level visual detail. This restricts how users can express their intent and raises a natural question: can the two modalities be combined to yield more flexible and faithful 3D generation? Our diagnostic study shows that even a simple late fusion of text- and image-conditioned predictions improves over single-modality models, evidencing strong cross-modal complementarity. Building on this finding, we formalize the task of Text-Image Conditioned 3D Generation, which requires joint reasoning over a visual exemplar and a textual specification during generation. To address this task, we introduce TIGON, a minimalist dual-branch baseline that maintains separate image- and text-conditioned backbones with lightweight cross-modal fusion. Extensive experiments demonstrate that text-image conditioning yields consistent gains over single-modality methods, suggesting complementary vision-language guidance as a promising direction for future 3D generation research.
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
PDF ↗Text-to-video diffusion models have enabled open-ended video synthesis, but often struggle with generating the correct number of objects specified in a prompt. We introduce NUMINA, a training-free identify-then-guide framework for improved numerical alignment. NUMINA identifies prompt-layout inconsistencies by selecting discriminative self- and cross-attention heads to derive a countable latent layout. It then refines this layout conservatively and modulates cross-attention to guide regeneration. On the introduced CountBench, NUMINA improves counting accuracy by up to 7.4% on Wan2.1-1.3B, and by 4.9% and 5.5% on 5B and 14B models, respectively. Furthermore, CLIP alignment is improved while maintaining temporal consistency. These results demonstrate that structural guidance complements seed search and prompt enhancement, offering a practical path toward count-accurate text-to-video diffusion. The code is available at https://github.com/H-EmbodVis/NUMINA.
All-in-one Medical Image Restoration (MedIR) models offer a promising path towards generalized medical imaging intelligence but face two critical spatiotemporal challenges: 1) Spatial modality interference, where conflicting gradients from diverse modalities (e.g., MRI, CT, PET) degrade performance; and 2) a temporal static-world assumption that ignores the continual data streams in real-world clinical settings, leading to catastrophic forgetting. To address this dual challenge, we propose a novel lifelong learning framework (called Resilient On-the-fly Medical Enhancement, ROME) governed by a "disentangle-optimize-consolidate" paradigm. ROME first resolves the foundational modality conflict via the Modality-Invariant Disentanglement via Adversarial Balancing (MIDAB) module. It establishes a strategic "adversarial balance" between a "content preservation force" and a "modality erasure force" to optimize a disentangled, unified feature manifold. Building on this stable foundation, the Adaptive Feature Consolidation (AFC) module combats forgetting. AFC dynamically locates an optimal feature consolidation point via a prediction network, enforced by a novel diversity loss to ensure robust continuous learning. Experiments demonstrate that ROME not only achieves SOTA performance in static settings but also exhibits superior resilience in rigorous domain-incremental benchmarks, reducing the average catastrophic performance degradation by over 10%.
BiGMINT: Biologically-guided Hierarchical Multimodal Integration for Modeling Multiple Compound Activities in Drug Discovery
PDF ↗Compound activity modeling is critical for drug discovery, where accurate *in silico* predictions can significantly reduce reliance on expensive, time-consuming target-specific experimental assays. Traditional machine learning approaches for compound activity modeling typically rely on either chemoproteomics-centric molecular data or phenotype-centric imaging screens, limiting their ability to capture complementary biological signals. While multimodal approaches show promise, they often fail to capture the interplay between molecular mechanisms and cellular responses. In this paper, we present **BiGMINT**, a **Bi**ologically **G**uided **M**ultimodal framework that hierarchically **INT**egrates chemoproteomic and high-content imaging (HCI) data, introducing chemoproteomics-guided phenotypic aggregation, task-aware cross-modal fusion, and protein-protein interaction priors for modeling activities. On two large-scale in-house datasets, with 99K and 40K compound-HCI pairs from U2OS and iNeuron, **BiGMINT** improves mean AUCROC by up to 10.0% and 4.2%, and high-performing task coverage by up to 103% and 56% over best unimodal and multimodal methods. Thorough analysis revealed mechanistic insights, showing these gains stem from modality complementarity, and protein-protein priors enhance modeling of challenging activities.
3D Gaussian Splatting reconstructs scenes by starting from a sparse Structure-from-Motion initialization and refiningunder-reconstructed regions. This process is slow, as it requires multiple densification steps where Gaussians arerepeatedly split and adjusted, following a lengthy optimization path. Moreover, this incremental approach often yieldssuboptimal renderings in high-frequency regions. We propose a fundamentally different approach: eliminate densification with a one-step approximation of scenegeometry using triangulated pixels from dense image correspondences. This dense initialization allows us to estimatethe rough geometry of the scene while preserving rich details from input RGB images, providing each Gaussian withwell-informed color, scale, and position. As a result, we dramatically shorten the optimization path and remove theneed for densification. Unlike methods that rely on sparse keypoints, our dense initialization ensures uniform detailacross the scene, even in high-frequency regions where other methods struggle. Moreover, since all splats are initializedin parallel at the start of optimization, we remove the need to wait for densification to adjust new Gaussians.EDGS reaches LPIPS and SSIM performance of standard 3DGS significantly faster than existing efficiency-focused approaches. When trained further, it exceeds the reconstruction quality of state-of-the-art models aimed at maximizing fidelity. Our method is fully compatible with other acceleration techniques, making it a versatile and efficient solution that can be integrated with existing approaches.
TRIDENT: A Trimodal Cascade Generative Framework for Drug and RNA-Conditioned Cellular Morphology Synthesis
PDF ↗Accurately modeling the relationship between perturbations, transcriptional responses, and phenotypic changes is essential for building an AI Virtual Cell (AIVC). However, existing methods typically constrained to modeling direct associations, such as *Perturbation -> RNA* or *Perturbation -> Morphology*, overlook the crucial causal link from RNA to morphology. To bridge this gap, we propose TRIDENT, a cascade generative framework that synthesizes realistic cellular morphology by conditioning on both the perturbation and the corresponding gene expression profile. To train and evaluate this task, we construct MorphoGene, a new dataset pairing L1000 gene expression with Cell Painting images for 98 compounds. TRIDENT significantly outperforms state-of-the-art approaches, achieving up to 7-fold improvement with strong generalization to unseen compounds. In a case study on docetaxel, we validate that RNA-guided synthesis accurately produces the corresponding phenotype. An ablation study further confirms that this RNA conditioning is essential for the model's high fidelity. By explicitly modeling transcriptome-phenome mapping, TRIDENT provides a powerful in silico tool and moves us closer to a predictive virtual cell.
Shape-of-You: Fused Gromov-Wasserstein Optimal Transport for Semantic Correspondence in-the-Wild
PDF ↗Semantic correspondence is essential for handling diverse in-the-wild images lacking explicit correspondence annotations. While recent 2D foundation models offer powerful features, adapting them for unsupervised learning via nearest-neighbor pseudo-labels has key limitations: it operates locally, ignoring structural relationships, and consequently its reliance on 2D appearance fails to resolve geometric ambiguities arising from symmetries or repetitive features. In this work, we address this by reformulating pseudo-label generation as a Fused Gromov-Wasserstein (FGW) problem, which jointly optimizes inter-feature similarity and intra-structural consistency. Our framework, Shape-of-You (SoY), leverages a 3D foundation model to define this intra-structure in the geometric space, resolving abovementioned ambiguity. However, since FGW is a computationally prohibitive quadratic problem, we approximate it through anchor-based linearization. The resulting probabilistic transport plan provides a structurally consistent but noisy supervisory signal. Thus, we introduce a soft-target loss dynamically blending guidance from this plan with network predictions to build a learning framework robust to this noise. SoY achieves state-of-the-art performance on SPair-71k and AP-10k datasets, establishing a new benchmark in semantic correspondence without explicit geometric annotations. Code is available at Shape-of-You.
As a representative technique in neural architecture search, neural architecture generation aims to construct high-performance architectures for a given task directly. It is poised to replace the inefficient random exploration components of some search strategies, such as the acquisition strategies in Bayesian optimization. Despite significant research, current architecture generation techniques face problems such as low generation efficiency and insufficient constraints, leading to invalidly generated architectures. To this end, we propose Progressive Neural Architecture Generation (PNAG), which constructs architectures incrementally through coarse-to-fine evolution, enhancing generation efficiency, and incorporates step-wise refinements to ensure the validity of the generated architecture. To achieve this, PNGA involves two modules, multi-scale sub-architecture quantization (MSQ) and step-wise consistency constraint (SCC). Specifically, MSQ constructs sub-architectures using quantization decoding and progressively expands them, transitioning from simple to complex forms. This operation bypasses network inference to enhance efficiency.Complementing MSQ, SCC, implemented through a tailored regularization mechanism, introduces penalties for deviations during sub-architecture generation, guiding the process towards valid target architectures. As such, PNAG establishes a clear generation path, laying the groundwork for generating suitable architectures in downstream tasks. Extensive experiments demonstrate that PNAG not only generates superior architectures for various downstream tasks (+8.43%/+5.07%, on average) but also significantly improves generation efficiency, reducing the architecture generation time by 1300x. Furthermore, PNAG demonstrates strong extensibility by successfully generating Transformer-based architectures.
Diffusion models have become the dominant tool for high-fidelity image and video generation, yet are critically bottlenecked by their inference speed due to the numerous iterative passes of Diffusion Transformers. To reduce the exhaustive compute, recent works resort to the feature caching and reusing scheme that skips network evaluations at selected diffusion steps by using cached features in previous steps. However, their preliminary design solely relies on local approximation, causing errors to grow rapidly with large skips and leading to degraded sample quality at high speedups. In this work, we propose spectral diffusion feature forecaster (Spectrum), a training-free approach that enables global, long-range feature reuse with tightly controlled error. In particular, we view the latent features of the denoiser as functions over time and approximate them with Chebyshev polynomials. Specifically, we fit the coefficient for each basis via ridge regression, which is then leveraged to forecast features at multiple future diffusion steps. We theoretically reveal that our approach admits more favorable long-horizon behavior and yields an error bound that does not compound with the step size. Extensive experiments on various state-of-the-art image and video diffusion models consistently verify the superiority of our approach. Notably, we achieve up to 4.79x speedup on FLUX.1 and 4.67x speedup on Wan2.1-14B, while maintaining much higher sample quality compared with the baselines.
Zero-shot anomaly detection (ZSAD) requires detecting and localizing anomalies without access to target-class anomaly samples. Mainstream methods rely on vision-language models (VLMs) such as CLIP: they build hand-crafted or learned prompt sets for normal and abnormal semantics, then compute image-text similarities for open-set discrimination. While effective, this paradigm depends on a text encoder and cross-modal alignment, which can lead to training instability and parameter redundancy. This work revisits the necessity of the text branch in ZSAD and presents VisualAD, a purely visual framework built on Vision Transformers. We introduce two learnable tokens within a frozen backbone to directly encode normality and abnormality. Through multi-layer self-attention, these tokens interact with patch tokens, gradually acquiring high-level notions of normality and anomaly while guiding patches to highlight anomaly-related cues. Additionally, we incorporate a Spatial-Aware Cross-Attention (SCA) module and a lightweight Self-Alignment Function (SAF): SCA injects fine-grained spatial information into the tokens, and SAF recalibrates patch features before anomaly scoring. VisualAD achieves state-of-the-art performance on 13 zero-shot anomaly detection benchmarks spanning industrial and medical domains, and adapts seamlessly to pretrained vision backbones such as the CLIP image encoder and DINOv2. Our code is publicly available at https://github.com/7HHHHH/VisualAD.
Multimodal Large Language Models (MLLMs) have exhibited immense potential across numerous medical specialties, yet dentistry remains underexplored, in part due to limited domain-specific data, scarce dental expert annotations, insufficient modality-specific modeling, and challenges in reliability. In this paper, we present OralGPT-Omni, the first dental-specialized MLLM designed for comprehensive and trustworthy analysis across diverse dental imaging modalities and clinical tasks. To explicitly capture dentists' diagnostic reasoning, we construct TRACE-CoT, a clinically grounded chain-of-thought dataset that mirrors dental radiologists' decision-making processes. This reasoning supervision, combined with our proposed four-stage training paradigm, substantially strengthens the model's capacity for dental image understanding and analysis. In parallel, we introduce MMOral-Uni, the first unified multimodal benchmark for dental image analysis. It comprises 2,809 open-ended question-answer pairs spanning five modalities and five tasks, offering a comprehensive evaluation suite to date for MLLMs in digital dentistry. OralGPT-Omni achieves an overall score of 51.84 on the MMOral-Uni benchmark and 45.31 on the MMOral-OPG benchmark, dramatically outperforming the scores of GPT-5. Our work promotes intelligent dentistry and paves the way for future advances in dental image analysis. All code, benchmark, and models will be made publicly available.
Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference to cope with memory limits. However, this mismatch breaks long-range geometric dependencies, producing holes and fragmented components. To address this critical limitation, we introduce MeshRipple, which expands a mesh outward from an active generation frontier, akin to a ripple on a surface. MeshRipple rests on three key innovations: a frontier-aware BFS tokenization that aligns the generation order with surface topology; an expansive prediction strategy that maintains coherent, connected surface growth; and a sparse-attention global memory that provides an effectively unbounded receptive field to resolve long-range topological dependencies. This integrated design enables MeshRipple to generate meshes with high surface fidelity and topological completeness, outperforming strong recent baselines.
Love Me, Love My Label: Rethinking the Role of Labels in Prompt Retrieval for Visual In-Context Learning
PDF ↗Visual in-context learning (VICL) enables visual foundation models to handle multiple tasks by steering them with demonstrative prompts. The choice of such prompts largely influences VICL performance, standing out as a key challenge. Prior work has made substantial progress on prompt retrieval and reranking strategies, but mainly focuses on prompt images while overlooking labels. We reveal these approaches sometimes get visually similar but label-inconsistent prompts, which potentially degrade VICL performance. On the other hand, higher label consistency between query and prompts preferably indicates stronger VICL results. Motivated by these findings, we develop a framework named LaPR (Label-aware Prompt Retrieval), which highlights the role of labels in prompt selection. Our framework first designs an image-label joint representation for prompts to incorporate label cues explicitly. Besides, to handle unavailable query labels at test time, we introduce a mixture-of-expert mechanism to the dual encoders with query-adaptive routing. Each expert is expected to capture a specific label mode, while the router infers query-adaptive mixture weights and helps to learn label-aware representation. We carefully design alternative optimization for experts and router, with a VICL performance-guided contrastive loss and a label-guided contrastive loss, respectively. Extensive experiments show promising and consistent improvement of LaPR on in-context segmentation, detection, and colorization tasks. Moreover, LaPR generalizes well across feature extractors and cross-fold scenarios, suggesting the importance of label utilization in prompt retrieval for VICL. Code is available at https://github.com/luotc-why/CVPR26-LaPR.