arXiv subjects

Ming-Hsuan Yang

Publications and source records attributed to Ming-Hsuan Yang.

At least 19 recordsLinked to original sources

arXiv2026

From Models to Systems: A Comprehensive Survey of Efficient Multimodal Learning

The rapid expansion of multimodal models has surfaced formidable bottlenecks in computation, memory, and deployment, catalyzing the rise of Efficient Multimodal Learning (EML) as a pivotal research frontier. Despite intensive progress, a cohesive understanding of what, how, and where efficiency is manifested across the learning stack remains fragmented. This survey systematizes the EML landscape by introducing the first structured, model-to-system taxonomy. We distill insights from over 300 seminal works into three hierarchical levels--model, algorithm, and system--addressing architectural parsimony, execution refinement, and hardware-aware orchestration, respectively. Moving beyond a purely categorical review, we offer a methodological synthesis of the vertical synergies between these layers, elucidating how cross-layer co-design contributes to the fundamental "Efficiency-Utility-Privacy" trade-off. Through an integrative case study of Multimodal Large Language Models (MLLMs), we trace the field's evolutionary trajectory from initial structural adjustments to modern full-stack resource orchestration. Furthermore, we provide a holistic discussion and application-specific optimization blueprints for diverse domains and posit a paradigm shift toward self-regulating intelligence, where efficiency is an intrinsic, emergent property of the model's fundamental design rather than a post-hoc constraint. Finally, we present open challenges and future directions that will define the trajectory of EML research. This survey establishes a structured framework for multimodal systems that are not only high-performing and generalizable but natively efficient and ready for ubiquitous deployment. A continuously updated version is available at https://github.com/pwang322/Efficient-Multimodal-Learning-Survey.

cs.MM↗

arXiv2026

KaiNinja: Extending Native 3D Generators to the Part Level

Native 3D generators turn one image into a single mesh. TRELLIS.2 and its peers deliver high-fidelity non-watertight geometry with materials, but the output is one fused object, while downstream work such as editing, rigging and simulation operates on part-level assets. A naive idea is to run a 3D segmentation network on the fused mesh that TRELLIS.2 generates, but such pipelines are slow and bounded by the accuracy of the segmentation. We want a simple way to extend an existing native 3D generator to the part level. But we face a critical problem: the O-Voxel grid stores one sheet of surface per voxel, so a single volume cannot represent the interface where two parts touch, at any resolution. We introduce a dual-volume representation to solve this problem and put forward KaiNinja, a part-level extension of TRELLIS.2 built on a dual-volume form of its O-Voxel representation. KaiNinja keeps the generation speed and quality of TRELLIS.2 while extending it to the part level, with no mask or segmenter in the pipeline. Its training data come from sources of many kinds, including CAD models and assets authored by an LLM-driven agent; to our knowledge it is the first 3D generative model trained on agent-authored part data. Surprisingly, we also find that whole-object fidelity improves over the same backbone fine-tuned on the same dataset. Against part generation pipelines of different paradigms, it lowers whole-object Chamfer distance by 40% and raises strict part F-score by 16%.

cs.GR↗

arXiv2026

DementiaCare-Bench: A Modality-Validated Video Benchmark

Dementia affects an estimated 57 million people worldwide, and for most families the hardest part of care is not memory loss but the behavioral and psychological symptoms of dementia (BPSD): agitation, wandering, resistance to care, sundowning. Understanding these symptoms requires more than recognizing the behavior itself; it also requires knowing what happened beforehand. The same behavior may call for a different response depending on its trigger. Video-language models (VLMs) could potentially support caregivers, yet no existing benchmark evaluates this capability. To fill this gap, we present DementiaCare-Bench: 56 professionally produced caregiver training videos segmented into 94 clips across nine BPSD categories, with 2023 questions generated by a multi-agent pipeline that grounds every clinical claim in a verbatim transcript span. Each question is then probed under four visual conditions and labelled by the least it requires, so its visual demand is measured rather than assumed. Measurement contradicts intent: we wrote 77.7% of the questions to require ordered frames, and 34.8% do. Across 12 current VLMs the pattern is uniform. The best reach 85% overall, but that average is carried by questions a language model can answer from clinical knowledge alone; accuracy falls by 17 points on average on questions that require the ordered clip, and a leading open model scores at chance on judging whether a caregiver's response was appropriate. A lightweight LoRA fine-tune, DemCare-VLM, moves video dependence from -3.3 to +4.5 points, so what the benchmark exposes can be repaired and not only measured.

cs.CV↗

arXiv2026

OmniPoint: Universal Monocular Metric Pointcloud from Any Camera

Recovering metric 3D geometry from monocular images is a fundamental computer vision task, yet current methods remain heavily fragmented by fixed camera model assumptions and inflexible input schemes. We present OmniPoint, a unified framework designed to generalize metric reconstruction across diverse imaging sensors, including pinhole, fisheye, and equirectangular projections, while accommodating varying geometric priors. To overcome projection rigidity, OmniPoint abandons conventional planar depth regression. It instead adopts a decoupled ray and distance representation alongside a decoupled training objective, explicitly separating the camera projection model from the scene structure. To address the severe scarcity of training data for alternative cameras, we introduce a bidirectional augmentation strategy that explicitly bridges labeled perspective data and unlabeled omnidirectional domains in 3D space. Furthermore, to seamlessly integrate optional inputs like camera intrinsics or sparse depth without destabilizing the network through feature distribution shifts, we propose a robust information injection mechanism. This mechanism utilizes learnable input state embeddings to resolve architectural ambiguity and applies vectorized Gaussian smoothing to densify irregular measurements. Extensive experiments demonstrate that OmniPoint achieves state-of-the-art zero-shot performance across multiple benchmarks, establishing a robust new standard for unified monocular 3D reconstruction.

cs.CV↗

arXiv2026

ReCoSplat: Online Feed-Forward Gaussian Splatting via Render-and-Compare

Online novel view synthesis requires a model to reconstruct a scene causally from a stream of observations while keeping it renderable at every moment. We present ReCoSplat, an online feed-forward Gaussian Splatting model supporting both posed and unposed inputs, with or without camera intrinsics. While assembling local Gaussians with camera poses scales better than canonical-space prediction, stable training requires ground-truth poses, creating a distribution mismatch when predicted poses are used at inference. To address this, we introduce a Render-and-Compare (ReCo) module. ReCo renders the accumulated scene from the viewpoint of the incoming observation, comparing the render with the observation to produce a stable conditioning signal that helps bridge the mismatch. To support long sequences, we propose a hybrid KV-cache compression strategy combining early-layer truncation with chunk-level selective retention, reducing the KV cache size by over 90% for 100 or more frames. ReCoSplat achieves state-of-the-art performance among online methods while processing 256-view streams at an average input throughput of 45.1 FPS, with an end-of-stream throughput of 41.1 FPS on an RTX 6000 Ada GPU. Code and pretrained models are released at https://freemancheng.com/ReCoSplat .

cs.CV↗

arXiv2026

Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Models

Recent work on image content manipulation based on vision-language pre-training models has been effectively extended to text-driven 3D scene editing. However, existing schemes for 3D scene editing still have certain shortcomings, hindering their further development as interactive design tools. Such schemes typically adhere to fixed input patterns, limiting flexibility in text input. Furthermore, their editing capabilities are constrained by a single or a few 2D visual models and require intricate pipeline design to integrate these models into 3D reconstruction processes. To address the aforementioned issues, we propose the Hash-Atlas network, which reformulates 3D scene editing as operations on 2D atlas images, thereby achieving a workflow decoupling of the 2D editing and 3D reconstruction processes. Building on this foundation, we introduce a dialogue-based 3D scene editing approach, termed CE3D++, which is centered on a large language model (LLM) that allows arbitrary textual input from users and interprets their intentions, subsequently facilitating the autonomous invocation of the corresponding visual models. Additionally, we extend CE3D++ to monocular 4D scenes by imposing motion constraints on moving objects and further fine-tuning the LLM by creating a trajectory dataset related to editing tasks, which enables the smaller LLM to schedule up to 30 different visual tools accurately. Experimental results demonstrate that CE3D++ effectively integrates multiple visual models to achieve diverse visual editing effects, possessing strong scene comprehension and multi-round dialog capabilities. The source codes and trained models are available at https://github.com/Fangkang515/CE3D.

cs.CV↗

arXiv2026

Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding

Spatio-temporal video grounding (STVG) requires models to identify when a referred event occurs and localize the target entity throughout that interval. Existing multimodal large language models typically serialize dense localization trajectories autoregressively, causing decoding latency to grow with tube length and allowing localization errors to propagate across time. We introduce Parallel Tube Decoding (PTD), a generative formulation that decomposes grounding into a temporal block followed by time-conditioned spatial blocks decoded simultaneously. This removes both token-level and trajectory-level dependencies, reducing the sequential decoding depth to a fixed $1 + 1$ rounds, independent of tube length. To enable parallel spatial generation, we introduce Decoupled Block Attention, which preserves access to shared video-query context while eliminating cross-box dependencies, together with localization-aware policy optimization for temporal boundaries and spatial geometry. On VidSTG, PTD reduces Tube Completion Latency by 79x and increases spatial decoding throughput by 92x over standard autoregressive decoding, while also improving grounding accuracy. With a compact 4B backbone, our model performs favorably well on VidSTG and HC-STVG, and generalizes zero-shot to temporal grounding, grounded VideoQA, and referring video object tracking. Our results show parallel tube generation is an efficient and effective alternative to autoregressive localization in videos.

cs.CV↗

arXiv2026

Layer-Aware Video Composition via Split-then-Merge

We present Split-then-Merge (StM), a novel framework designed to enhance control in generative video composition and address its data scarcity problem. Unlike conventional methods relying on annotated datasets or handcrafted rules, StM splits a large corpus of unlabeled videos into dynamic foreground and background layers, then self-composes them to learn how dynamic subjects interact with diverse scenes. This process enables the model to learn the complex compositional dynamics required for realistic video generation. StM introduces a novel transformation-aware training pipeline that utilizes a multi-layer fusion and augmentation to achieve affordance-aware composition, alongside an identity-preservation loss that maintains foreground fidelity during blending. Experiments show StM outperforms SoTA methods in both quantitative benchmarks and in humans/VLM-based qualitative evaluations. More details are available at our project page: https://split-then-merge.github.io

cs.CV↗

arXiv2026

Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing

Open-world face anti-spoofing must address both covariate and semantic shifts: source and target domains differ in imaging conditions, while target domains contain diverse attack types absent from training. Existing prompt-based approaches often express spoofing through category semantics or language guidance, which is effective for modeling high-level concepts but is less suited to explicitly capturing the evolving fine-grained and spatially heterogeneous forensic evidence of unseen attacks. Motivated by the hypothesis that many unseen attacks can be characterized by new combinations of recurring visual cues, we propose a compositional forensic visual prompt learning framework that operates entirely in the visual feature space. Built on a frozen ViT-based vision foundation model, the framework employs patch-aware attention to refine a shared set of learnable micro-forensic primitives into localized forensic evidence units derived from image patches. Class-specific global contextual prompts then provide input-dependent routing weights that adaptively select and compose these primitives into compositional forensic visual prompts for real/spoof discrimination. The primitives are not assigned predefined semantic meanings; instead, their specialization and reuse emerge from shared parameterization and joint optimization across categories. Extensive experiments on nine open-world protocols demonstrate state-of-the-art performance, strong cross-domain generalization, and robust adaptation to unseen attacks.

cs.CV↗

arXiv2026

Dual-Grained Agent Memory and Shapley Context Attribution for Multimodal Agentic Learner

Frontier multimodal large language models (MLLMs) deliver impressive perception yet still falter on scientific and mathematical reasoning. Parameter-level adaptation is unavailable for closed-weight or on-device backbones, and stateless prompting forfeits any compounding benefit from problems already solved. We propose \textbf{DG-Mem}, a dual-grained agentic memory framework that augments a frozen MLLM with a non-parametric, externally stored memory built once from training-time rollouts and consulted read-only at test time. Motivated by the Complementary Learning Systems (CLS) account of human memory, DG-Mem factors its store into an instance-grounded exemplar memory and a category-level schema memory of IF-THEN rules, with a transient reflection store mediating their construction so that schemas are synthesized only from abstract reflections, never from exemplar text. Two design choices distinguish DG-Mem: an online concept categorizer that grows the category space incrementally during training rather than committing to a predefined taxonomy, and a Shapley context attribution procedure that decomposes correctness across the entire retrieved rule set and yields a per-rule utility that re-weights retrieval at test time. The pipeline introduces no gradient updates and is deployable on closed-weight or on-device backbones. Across MathVista, MMMU, and MMMU-Pro on four open-weight and proprietary backbones (Qwen3.5-27B, Qwen3.5-122B-A10B, GPT-5-Nano, Gemini-3-Flash), DG-Mem improves consistently over no-memory and competitive memory baselines.

cs.CV↗

arXiv2026

Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos

This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-modal large language models, which are often limited to specific modalities and tasks, Sa2VA supports a wide range of image and video tasks, including referring segmentation and conversation, with minimal single-stage instruction tuning. Sa2VA combines SAM-2, a foundation video segmentation model, with MLLM, advanced vision-language models, and unifies text, image, and video into a shared LLM token space. Using the LLM, Sa2VA generates instruction tokens that guide SAM-2 in producing precise masks, enabling a grounded, multi-modal understanding of both static and dynamic visual content. Additionally, we introduce Ref-SAV, an auto-labeled dataset containing over 72k object expressions in complex video scenes, designed to boost model performance. We also manually validate 2k video objects in the Ref-SAV datasets to benchmark referring video object segmentation in complex environments. Experiments show that Sa2VA achieves strong performance across multiple tasks, particularly in referring video object segmentation, highlighting its potential for complex real-world applications. In addition, Sa2VA can be easily extended into various MLLMs, including Qwen-VL and Intern-VL, which can be updated with rapid process in current open-sourced MLLMs. Code and models have been provided to the community.

cs.CV↗

arXiv2026

EvDiff: Event-Based Video Reconstruction using One-Step Diffusion Models

As neuromorphic sensors, event cameras asynchronously record changes in brightness as streams of sparse events with the advantages of high temporal resolution and high dynamic range. Reconstructing intensity images from events is a highly ill-posed task due to the inherent ambiguity of absolute brightness. Early methods generally follow an end-to-end regression paradigm, directly mapping events to intensity frames in a deterministic manner. While effective to some extent, these approaches often yield perceptually inferior results and struggle to scale up in model capacity and training data. In this work, we propose EvDiff, an event-based diffusion model that follows a surrogate training framework to produce high-quality videos. To reduce the high computational cost of high-frame-rate video generation, we design an event-based diffusion model that performs only a single forward diffusion step, equipped with a temporally consistent EvEncoder. Furthermore, our novel Surrogate Training Framework eliminates the dependence on paired event-image datasets, allowing the model to leverage large-scale image datasets for higher capacity. The proposed EvDiff is capable of generating high-quality colorful videos solely from monochromatic event streams. Experiments on real-world datasets demonstrate that our method strikes a sweet spot between fidelity and realism, outperforming existing approaches on both pixel-level and perceptual metrics. The code will be released publicly.

cs.CV↗

arXiv2026

So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection

Recent advances in AI-powered generative models have enabled the creation of increasingly realistic synthetic images, posing significant risks to information integrity and public trust on social media platforms. While robust detection frameworks and diverse, large-scale datasets are essential to mitigate these risks, existing academic efforts remain limited in scope: current datasets lack the diversity, scale, and realism required for social media contexts, while detection methods struggle with generalization to unseen generative technologies. To bridge this gap, we introduce So-Fake-Set, a comprehensive social media-oriented dataset with over 2 million high-quality images, diverse generative sources, and photorealistic imagery synthesized using 35 state-of-the-art generative models. To rigorously evaluate cross-domain robustness, we establish a novel and large-scale (100K) out-of-domain benchmark (So-Fake-OOD) featuring synthetic imagery from commercial models explicitly excluded from the training distribution, creating a realistic testbed for evaluating real-world performance. Leveraging these resources, we present So-Fake-R1, an advanced vision-language framework that employs reinforcement learning for highly accurate forgery detection, precise localization, and explainable inference through interpretable visual rationales. Extensive experiments show that So-Fake-R1 outperforms the second-best method, with a 1.3% gain in detection accuracy and a 4.5% increase in localization IoU. By integrating a scalable dataset, a challenging OOD benchmark, and an advanced detection framework, this work establishes a new foundation for social media-centric forgery detection research. The code, models, and datasets will be released publicly.

cs.CV↗

arXiv2026

Parameter-Efficient CLIP Adaptation for 3D Understanding via Unified Tokenization

Vision-language models, such as CLIP, encode rich semantic knowledge through large-scale image-text pretraining. Reusing these models for 3D understanding is highly desirable, because 3D-text pairs and dense point-level annotations are far scarcer and more difficult to obtain than their 2D counterparts. However, CLIP is trained on regular 2D image patches, whereas point clouds are unordered, sparse, and irregular. The primary challenge lies in constructing 3D token sequences whose geometry, position, and local relations can be interpreted by a frozen, pretrained vision transformer. Moreover, coordinate-scale variations across heterogeneous 3D domains make unified training particularly challenging. To bridge these gaps, we propose a parameter-efficient framework that learns a scale-normalized 3D tokenizer, enabling the CLIP visual encoder to be reused for point-cloud understanding. Our tokenizer, named UTok3D, estimates an input-adaptive geometric scale to calibrate sparse voxelization, coordinate normalization, token-center computation, and 3D positional encoding, and serializes the resulting tokens by Hilbert ordering. This shared geometric convention makes joint training feasible across point clouds with substantially different metric scales, including object-level shapes, indoor scenes, and outdoor LiDAR scans. The tokenizer is trained without 3D annotations through self-supervised cross-modal distillation from foundation-model features extracted from multi-view images, combining local superpoint alignment with the proposed Sinkhorn Ranked Contrastive distillation. Experiments on ShapeNetPart, ScanNetV2, S3DIS, SemanticKITTI, and nuScenes show that, when equipped with a scale-consistent and CLIP-interpretable token interface, a frozen CLIP visual backbone can be effectively reused for annotation-free 3D segmentation.

cs.CV↗

arXiv2026

ProgFormer: Hierarchical Voxel Diffusion Transformer for Longitudinal Brain MRI Prediction

Predicting future structural MRI of a brain is challenging because longitudinal changes are often subtle and confined to specific anatomical regions, while most subject-specific brain structure remains stable over time. An effective model should therefore preserve global brain structural consistency while remaining sensitive to fine-grained disease progression. Existing latent-space-based methods improve computational efficiency, but suffer from information loss during their compression-reconstruction procedure. In contrast, direct voxel-space methods avoid latent reconstruction but commonly use a unified prediction pathway to model brain structure and progression-related changes. Subtle local changes may therefore be overshadowed by the dominant stable brain structure. To address these challenges, we propose ProgFormer, a hierarchical voxel-space Diffusion Transformer for longitudinal brain MRI prediction. ProgFormer uses a coarse pathway to perform the primary volumetric prediction from 3D patch tokens. This pathway models overall brain structure and longitudinal context. The fine pathway then uses the coarse representations as spatio-temporal grounding for voxel-level refinement within individual patches. The two pathways jointly estimate a velocity field directly in voxel space through conditional flow matching, enabling end-to-end prediction without a separately learned image autoencoder. The predicted future scan is then generated from Gaussian noise by integrating the estimated velocity field over a sequence of Euler steps. Extensive experimental results on three widely used benchmarks, ADNI, AIBL, and OASIS, under both pairwise and trajectory settings demonstrate favourable performance compared against several state-of-the-art methods.

cs.CV↗

arXiv2026

Generative World Renderer at the Speed of Play

Generative world renderer AlayaRenderer receives structured world states exported from physics engines and synthesizes RGB frames. Unlike models that generate frames from text/control-hints prompts, AlayaRenderer preserves scene structure without altering the underlying world dynamics. This demonstrates an alternative path toward interactive world modeling and user-controllable play. However, the original AlayaRenderer is too computationally expensive for real-time deployment. This technical report introduces AlayaRenderer-Flash, a real-time-oriented generative forward world renderer that pushes AlayaRenderer from 0.56 FPS to 31.54 FPS, reaching the speed of play. AlayaRenderer-Flash reformulates the original renderer as a few-step autoregressive streaming model and introduces lightweight distilled codecs for efficient latent encoding and frame reconstruction. It retains the teacher model's G-buffer and text-prompt interfaces while enabling continuous rendering over input streams of unbounded length. We evaluate AlayaRenderer-Flash on G-buffer streams across content preservation, temporal consistency, cross-window stability, prompt controllability, and runtime efficiency. Our results show that AlayaRenderer-Flash substantially reduces inference cost while preserving the core rendering capabilities of the teacher model. By integrating AlayaRenderer-Flash with a physics engine, we build a fully playable generative world running at 30 FPS.

cs.CV↗

arXiv2026

DRIFT: Difficulty-aware Rectified Flows for Through-plane MRI Super-Resolution

Magnetic Resonance Imaging (MRI) is often acquired with anisotropic resolution to reduce scan time, producing stair-step artifacts along the through-plane direction. In through-plane MRI super-resolution, an efficiency-fidelity trade-off arises: feed-forward regressors are fast but oversmooth at large slice-thicknesses, while sampling-based methods improve fidelity at high inference cost. We propose DRIFT, a two-stage thickness-conditioned rectified flow framework for through-plane MRI super-resolution with continuous input slice-thickness. Stage 1 employs an Anatomical Projection Network (APN) to map low-resolution patches to a coarse high-resolution manifold, providing a deterministic anatomical initialization that shortens the residual transport of Stage 2 and stabilizes slice-wise refinement. Stage 2 refines details via rectified flow and introduces a Physics-Aware Difficulty (PAD) metric derived from slice-thickness induced through-plane bandwidth deficit to guide an Adaptive Integration Scheduler (AIS), allocating ODE steps by thickness. A Consistent Endpoint Trajectory Alignment (CETA) loss enforces thickness-consistent reconstructions. Experiments show that DRIFT outperforms super-resolution baselines while reducing inference cost. Code, models, and interactive demos are available at https://yoonseokchoi-ai.github.io/drift-eccv2026/.

cs.CV↗

arXiv2026

SeeSE3: Emergence of 3D Space in Vision Features

In this paper, we ask whether vision foundation models construct representations that reflect the intrinsic properties of 3D Euclidean space. Unlike previous works that probe 3D awareness of vision features by regressing image-centric quantities such as depth or normals, we investigate the relation between the structure of the space of visual features and the group of Euclidean transformations $SE(3)$. We propose a set of probes to evaluate this relation from both topological and geometric perspectives: a mutual neighborhood metric that measures the alignment between feature neighborhoods and spatial topology, and a Poincaré Adapter to test the linear accessibility of the geometry of camera motion from latent displacements in static scenes. We show that self-supervised vision models, which, in principle, have not been trained with direct 3D supervision or active agency, possess latent subspaces that are remarkably strongly correlated with three-dimensional Euclidean space, when probed correctly. Building on this insight we propose a new class of "Latent-Space Navigation" techniques that perform visual odometry and localization purely in the latent space, bypassing the need for explicit 3D reconstruction.

cs.CV↗