PyTorchKR Papers

최신 논문

총 16,105편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 카테고리 구독

arXiv:2611.26316v1cs.CV

C-LiTE: A Lightweight Foundation Model for Cellular feature learning in Histopathology

Characterising individual cells is fundamental to computational pathology, as cellular morphology informs tasks such as tumour grading, mitotic assessment and immune profiling. However, most pathology foundation models are trained on tissue patches and capture cellular features only implicitly, while existing cell-level models are either restricted to specific cell populations or rely on computationally expensive architectures with hundreds of millions of parameters. Applying ViTs directly to small cellular crops also presents an architectural challenge: upsampling increases computational cost without adding morphological information and may introduce interpolation artefacts. To address these limitations, we introduce C-LiTE, a lightweight foundation model for cellular representation learning in H&E-stained histopathology, with only 22 million parameters. C-LiTE employs a native-resolution tokenisation strategy tailored to cellular inputs, processing 64 x 64 px cell-centred crops using a 4 x 4 patch embedding to produce a 16 x 16 token grid without image upsampling. To transfer visual knowledge from large-scale pre-training, we adapt the patch embedding weights of a pre-trained ViT-5-S using a pseudoinverse-based transformation, enabling weight initialisation at the finer patch resolution. We further assemble a pre-training dataset of 60 million cell-centred crops from TCGA, balanced across 19 cancer types and 16 tissue types. To our knowledge, this represents the largest public dataset for self-supervised pre-training on H&E images at the cellular level. We evaluate C-LiTE on seven public datasets spanning mitotic figure recognition, nucleus and cell-type classification, and immune cell phenotyping. Under frozen-feature evaluation, C-LiTE achieves a mean macro-F1 of 0.670, approaching CytoFormer (0.682) with approximately 30x fewer parameters.

arXiv:2611.26296v1cs.LG

SKILL.PNG: Learning Agent Skills in Pixel Space

AI agents are commonly specialized for new tasks and domains using skills, i.e. natural language instructions placed in their context. However, the discrete nature of textual skills prevents continuous optimization. Gradient-based approaches such as finetuning, on the other hand, are typically model-specific, preventing skill transfer across different agents. Since many agents today are built on vision-language models (VLMs), we can address these limitations by introducing Skill.png: a method for obtaining skill-like image inputs whose pixels are optimized with gradient descent through the vision encoder of a frozen VLM. Image skills are compatible with any VLM, and a single image can be optimized jointly for an ensemble of models. We show that Skill.png significantly outperforms state-of-the-art textual skills optimized using frontier LLMs in 9 of 16 settings (across 4 VLMs and 4 benchmarks) while requiring only 64 to 256 image tokens instead of roughly 900 to 2000 text tokens at inference time. Hybrid skills, i.e. text and image skills jointly optimized, further improve agent performance. Moreover, an image optimized with an ensemble of VLMs can successfully transfer across the models in the ensemble. Skill.png thus presents the first agent skill that can be optimized with gradient descent while retaining transfer benefits of text skills. Our code is available at: https://github.com/omseeth/skill.png

arXiv:2611.26294v1cs.CV

BADAS-3.0: Real-Time Driving Perception and Planning from One Camera

We ask how far a driving model can get with one camera and real-time latency. BADAS-3.0 is a 1B-parameter video encoder with four small heads. From two seconds of one forward camera, it predicts the current speed, the metric path just driven, a collision-risk score and six candidate futures over 6.4 seconds, in under 50 ms. Given the car's current speed, BADAS-3.0 has 44% lower minADE$_6$ over five trajectory benchmarks than the 34B Alpamayo 2 Super, which reads six cameras and runs over 100x slower. The gain comes from camera rigs that neither model was trained on. On the rig they share, the two are on par. Existing benchmarks are mostly nominal driving, so we add two open-loop safety benchmarks, one of real dashcam collisions and near-misses and one of Euro NCAP scenarios. On both, BADAS-3.0 has a higher pass rate than every published planner we tested.

arXiv:2611.26269v1cs.CV

Tracking Objects Through Assembly and Decomposition

Tracking objects through transformations is essential for understanding real-world dynamics. Recent work has extended traditional object tracking to detect state changes. However, existing methods require an initial object prompt and detect only its decompositions, missing assembly events, which begin with multiple objects rather than one. We therefore introduce a prompt-free formulation of this task, where the goal is to recover all object tracks and detect both decomposition and assembly events given only a video. Our key insight is that assembly is decomposition in reverse. Building on this insight, we present Atlas, a zero-shot system that constructs and jointly reasons over forward and reverse spatiotemporal partitions to recover object tracks and their transformations. We further introduce OmniST, a benchmark with dense annotations of objects and both transformation types. On OmniST, Atlas recovers more than twice as many state changes as prior methods while remaining competitive on existing benchmarks that only evaluate decomposition.

arXiv:2611.26262v1cs.CV

Digitization of Analogue Gauges using Computer Vision

Analogue gauges remain prevalent in manufacturing industries for measuring physical quantities, yet manual monitoring by operators introduces human error and operational inefficiency. This research developed and evaluated an automated gauge reading system using computer vision and deep learning techniques. Three hybrid approaches were implemented and compared: OpenCV with Scikit-Image (traditional computer vision), OpenCV with ResNet18, and OpenCV with VGG19 (deep learning approaches). A comprehensive dataset of 1,848 pressure gauge images (0-10 BAR range) was curated through web scraping, synthetic generation, and augmentation techniques. The experimental results demonstrate that ResNet18 significantly outperforms the alternatives, achieving an accuracy of 97.3%, compared to VGG19's 64.4% and Scikit-Image's 63.8%. The study validates the effectiveness of residual learning architectures for industrial gauge digitization, providing a robust foundation for Industry 5.0 automation applications.

arXiv:2611.26254v1cs.CV

Prism: Hierarchical Text Detection with Minimalist Design

Hierarchical text detection aims to localize words, text lines, and paragraphs while parsing their structural relationships. It provides essential structural cues for visual text understanding. To maximize accuracy, existing methods typically rely on complex multi-scale feature fusion necks and heavy-weight heads, resulting in bloated architectures and low inference efficiency. In this paper, we argue that a sufficiently pre-trained backbone can effectively replace these sophisticated external modules, while simple geometric inclusion suffices for hierarchical text structural parsing. Thus, we propose Prism, a minimalist framework for hierarchical text detection. Prism performs multi-granularity detection by attaching parallel lightweight heads to a single-scale backbone feature map, covering words, text lines, and paragraphs, and reconstructs the structural hierarchy via an efficient geometric inclusion algorithm. In addition, we systematically compare representative lightweight head archetypes and show that pixel-level regression offers the best accuracy-efficiency trade-off in this setting. Experiments on multiple public benchmarks show that our significantly simplified architecture achieves state-of-the-art (SOTA) performance with remarkable efficiency. Specifically, it runs $1.7\times$ faster than LRANet on CTW1500 while achieving higher accuracy, and surpasses the current SOTA method, OmniParser V2, by over 6 PQ points on the hierarchical HierText dataset. Code will be released soon.

arXiv:2611.26249v1cs.CV

Beyond Covers and Titles: Evidence-First Ranking for Robust Cold-Start Recommendation

Short-video platforms rank new uploads before anyone has watched them, using content towers that read a video's cover, title and frames. Existing attacks on content-aware recommenders perturb pixels or features and ignore platform re-encoding, and existing defenses train against norm-bounded perturbations that neither match real edits nor preserve recommendation quality. We show with REAP, a realizable attack through {a simulated platform channel (H.264 transcoding, rescaling, cropping and JPEG)}, that packaging edits raise a cold video by 32.0 rank-percentile points in unrelated audiences. We then observe that cold-start ranking does not need the packaging at all: a tower that sees only the video body ranks cold items best. Building on this, we propose Evidence-First Ranking (EFR), which scores cold videos from their body, admits packaging only through a support-gated residual bounded by $\gamma$, and merges cold and warm rankings by rank percentile, yielding an exact certificate against any packaging edit. On MicroLens-100K, EFR cuts the attack gain by 81% and raises cold-start Recall@100 from 0.1133 to 0.170, while keeping the merged NDCG@10 within 4% of the undefended system.

arXiv:2611.26234v1cs.CV

Attention Drift Regularization with Adaptive Initialization for Domain-Robust Visual Recognition

Source-free domain adaptation (SFDA) adapts a pretrained source model to unlabeled target domains without source data access, yet two critical failure modes remain unaddressed. First, attention drift: source-learned attention maps shift toward spurious or background features under distribution shift, destabilizing feature representations. Second, domain-gap-agnostic initialization: applying a single fixed source model uniformly across all target domains ignores domain gap severity, causing premature overfitting to noisy pseudo-labels under large shifts. We propose DGA-CAFC to address both failures. The Counterfactual Attention-based Feature Consistency (CAFC) module enforces feature stability by minimizing the discrepancy between representations computed under learned attention and those under counterfactual-inspired normalized perturbations, thereby promoting domain-robust features independent of spurious attention shifts. The Domain-Gap Aware Source Model Selection (DGASS) module estimates domain gap severity via target prediction entropy and selects the source model variant whose confidence level best matches the estimated gap, reducing negative transfer and stabilizing pseudo-label quality. Crucially, CAFC transfers beyond SFDA: applied as a lightweight regularizer to standard domain generalization objectives without target data. Extensive experiments across SFDA and DG benchmarks demonstrate that our method consistently improves over recent baselines, demonstrating the effectiveness and generality of the proposed framework. Project page is available at https://visdomlab.github.io/DGA_CAFC

arXiv:2611.26218v1cs.CV

MixReact: Physics-Based Reactive Humanoid Control from Multimodal Cues via a Discrete-Continuous Mixture of Transformers

Humanoid agents in everyday environments are expected to react to diverse cues as humans do, with semantically appropriate and physically executable behaviors. Existing cue-driven reaction generation methods support only a narrow range of cue modalities and are limited to purely kinematic generation, leaving the resulting reactions susceptible to physical artifacts. To this end, we present MixReact, the first unified framework for physics-based reactive humanoid control from text, audio, and video cues, integrating a Discrete--Continuous Mixture of Transformers (DisCo-MoT) for state prediction with a History-aware Action Transformer (HAT) for physical execution. DisCo-MoT couples a discrete masked-modeling branch with a continuous autoregressive diffusion branch via one-way mixture attention within a MoT architecture. Guidance from discrete context mitigates collapse into averaged behaviors in one-to-many reaction generation, while direct prediction in continuous state space bypasses the decoding bottleneck of discrete representations. HAT then maps the predicted next state and observed execution history to executable actions, enabling robust closed-loop control in physics-based simulation. Experiments across all three modalities demonstrate consistent improvements over the baselines in fidelity, diversity, and physical consistency, while ablations validate the complementary contributions of the components. Our code will be released to facilitate future research. Project page: https://binlee26.github.io/MixReact_Page/

arXiv:2611.26211v1cs.CV

SpecWM: Turning Verification into Refinement for Streaming World Models

Recently, video world models have advanced interactive generation, with large models offering higher quality and smaller models enabling faster inference. Existing speculative methods combine their strengths through fast draft generation and selective target regeneration guided by rewards on decoded frames. However, verification covers only the external scorer's evaluation dimensions and adds decoding and scoring costs. Moreover, these scores provide no correction, requiring costly target regeneration for rejected drafts. To address these limitations, we propose Speculative World Model (SpecWM), a unified, training-free inference framework for streaming world models. It verifies draft chunks using the target's latent velocity field. Verification also yields a reusable correction; two thresholds select Accept, Refine, or Reject. Specifically, one-step refinement reuses it to improve perceptual quality, while three-step refinement strengthens camera following and trajectory consistency. These findings motivate transition-aware refinement. On WBench Navigation, SpecWM improves visual quality at 1.63$\times$ speedup over the target and raises NavScore from the draft's 75.99 to 85.63, achieving the best quality-speed-control trade-off. Additionally, our LongSpecBench shows sustained quality and control over long, multi-turn rollouts, while experiments on Hy-Nomas validate SpecWM across backbones and denoising budgets.

arXiv:2611.26201v1cs.LG

Learn, Freeze, and Transfer an Activation Function Across Architectures

Transfer learning typically reuses knowledge acquired by a source network through its learned weights. We investigate whether a learned activation function can also be transferred and remain useful in networks trained from scratch. We study this complementary form of transfer through a learn-freeze-transfer protocol, in which the activation is optimized jointly with a source network in a single training run, and is then frozen and reused in target networks trained from scratch. A pointwise activation with globally shared parameters is independent of layer dimensions and can therefore be incorporated into networks of different architectures trained from scratch. We instantiate this protocol with FAct, a five-parameter activation represented by a two-harmonic truncated Fourier series, initialized from a Fourier approximation of GELU and learned in a Vision Transformer (ViT) on ImageNet-1K. When reused in a ViT of the same architecture trained from scratch on ImageNet-1K, the frozen activation (Frozen FAct) improves top-1 accuracy by 1.46 percentage points over GELU. Across four smaller target architectures (standard ViT, Swin Transformer, linear-attention ViT, and MLP-Mixer) and four image-classification datasets, it achieves the highest mean accuracy among eleven activation functions in 15 of 16 settings under a common training configuration, with improvements of up to 1.71 percentage points over the best conventional activation. When the learning rate and weight decay are tuned separately for each activation under the same search budget, Frozen FAct still ranks first in 11 of the 16 settings, second in four, and fourth in one. These results provide empirical evidence that a learned activation function can retain its usefulness when transferred across vision architectures, independently of the weights with which it was learned.

arXiv:2611.26199v1cs.CV

Learning to Think with Images Faithfully via Adaptive Data Selection

Thinking with images (TwI) empowers vision-language models (VLMs) to overcome perceptual bottlenecks by actively cropping and zooming into fine-grained visual details, promising both higher accuracy and interpretable, region-grounded reasoning. However, our analysis shows that the improved accuracy of TwI models does not guarantee faithful tool use; they frequently invoke tools without actually relying on the zoomed region, undermining the reliability of tool-assisted reasoning. We trace this unfaithful behaviour to the training data: when questions are answerable without zooming, the model can answer correctly while ignoring the returned evidence, and this problem is exacerbated during training as the model becomes better at answering without tools. To keep zooming useful throughout training, we adapt the training data to the model's evolving capability and train on questions where correct zoomed evidence can still help the model answer correctly. This selection is supported by a data synthesis pipeline that localises small objects and constructs verifiable questions about their fine details, and complemented by an adaptiveness reward that favours tool-free answers when zooming is unnecessary. The experimental results show that our method substantially improves reasoning faithfulness and achieves state-of-the-art performance on visual search benchmarks (+11.6% on V*, +7.9% on HR-Bench 4K, and +9.4% on HR-Bench 8K). On multimodal hallucination benchmarks, our model also outperforms the compared TwI baselines. These results suggest that improving TwI faithfulness does not sacrifice accuracy and that both can be learnt from the right training data without directly supervising the reasoning process.

arXiv:2611.26195v1cs.CV

A version of the Cloude/van Zyl decomposition for full/quad pol synthetic aperture radar data

Based on the Cloude/van Zyl decomposition of reflection symmetric polarimetric SAR data we present a version for full/quad polarisation data. We demonstrate both versions on X-band F-SAR data over Vejers, Denmark. Differences between the original and our version of the decomposition occur especially for very bright man-made targets. These differences come with lower entropy for our version giving an improved focus on a more pronounced dominant scattering mechanism for these objects. Interpretation of the scattering mechanism related to the full/quad pol version of the decomposition is facilitated by means of the Cloude/Pottier $\bar{\alpha}$ angle.

arXiv:2611.26191v1cs.CV

Backbone Matters: Benchmarking Encoder-Decoder Networks for Semantic Segmentation of Driving Scenes on BDD100K

Semantic segmentation gives an autonomous vehicle a dense, pixel-level description of its surroundings and is a core part of scene understanding. Most segmentation networks consist of an encoder (the backbone) and a decoder, yet the backbone is often chosen without a systematic comparison. This work studies this choice on the BDD100K driving dataset. Four widely used decoders (U-Net, FPN, LinkNet and PSPNet) are combined with 13 backbones from six families (ResNet, VGG, DenseNet, Inception, MobileNet and EfficientNet), and all 52 models are trained with one common protocol. The best model, an FPN decoder with an EfficientNet-B4 backbone, reaches 62.6% mean intersection over union (mIoU), 89.8% accuracy and a loss of 0.092. Only two of the 52 models, both FPN with EfficientNet, exceed the 56.9% mIoU reported with the BDD100K benchmark. The effect of the backbone depends strongly on the decoder: the same EfficientNet-B4 gives 42.6% mIoU with PSPNet but 62.6% with FPN, and the gap between the best and the worst backbone ranges from 12.0 points (U-Net) to 42.5 points (FPN). The results and the scope of this study are discussed.

arXiv:2611.26187v1cs.LG

Invertible Transport Between Sample-Only Distributions via Projected Characteristic Functions

Many useful latent distributions can be sampled but do not have a tractable density. Such distributions may be represented by empirical collections of real-world observations or generated by scientific simulators and black-box generative models. These sample-only priors cannot be used directly in likelihood-based normalizing flows, which require evaluating the prior density. We propose Projected Characteristic-Function matching (PCF), a density-free framework for learning an invertible map between a data distribution and a prior specified only through samples. Our method aligns distributions using projected empirical characteristic functions, eliminating the need for density estimation, adversarial training, or paired observations. To address the non-uniqueness of the transport map, we introduce an optional transport regularizer that selects lower-displacement transformations while preserving endpoint alignment. We benchmark PCF on controlled transports, sample-efficiency studies, and high-dimensional alignment tasks. PCF matches the accuracy of kernel MMD on the controlled benchmark and on raw-pixel MNIST--USPS at a cost linear in the batch size, and it is more sample-efficient, achieving lower endpoint error than MMD in 13 of 15 paired runs across library sizes. By avoiding pairwise kernel evaluation, it reduces discrepancy memory by 29.8% and trains at batch sizes where kernel MMD exceeds GPU memory. These results show that PCF provides accurate and efficient invertible transport, particularly in sample- and memory-limited settings.

arXiv:2611.26179v1cs.CV

RegionAgent: Two-Stage Preference Optimization for Regional Image Restoration

Images under non-uniform coupled degradations require diverse restoration capabilities for different degraded regions. Existing methods employ globally uniform operations, potentially overlooking regional differences and causing incomplete restoration or even damage to image content. Moreover, a degraded region may require successive restoration actions, and earlier actions may alter residual degradation characteristics or introduce artifacts, potentially hindering subsequent restoration. To address these challenges, we propose RegionAgent, an adaptive restoration framework that trains a Vision-Language Model (VLM) through two-stage preference learning to generate a region-specific restoration action at each iteration. Specifically, we first train the VLM to select an action suited to the current region through step-level Direct Preference Optimization (DPO), using preferences derived from immediate restoration feedback to supervise only the differing component in each action pair. To account for the effects of current actions on subsequent restoration, we then apply trajectory-level DPO, using preferences derived from complete trajectory scores to supervise the sole differing action in each trajectory pair. Furthermore, as conventional image-pair datasets do not directly provide preferences over regional restoration decisions, we construct a regional restoration preference dataset comprising 10K action pairs and 20K trajectory pairs for two-stage VLM training. Experiments across multiple datasets demonstrate strong restoration performance under both mixed and single degradations. Ablation studies further validate the effectiveness of two-stage preference learning in improving restoration quality.

arXiv:2611.26178v1cs.CV

FlexVSR: Continuous-Scale Super-Resolution for Streaming Video Generation

Real-time streaming video generation has gained rapid momentum in live content creation and interactive media. Deploying such systems in practice requires flexible scaling factors to accommodate diverse source resolutions, target displays, and computational budgets. However, extending fixed-scale generative video super-resolution (VSR) to varying target scales poses two challenges: downsampling from a larger fixed scale incurs redundant cost, while re-optimizing the diffusion transformer (DiT) is costly and alters the shared generative prior. To address both, we propose FlexVSR, a decoupled framework for continuous-scale streaming generative VSR with supervision at only a few scales. Our key insight is that naively resampling fixed-scale latents onto a new target grid induces scale-dependent input mismatch, which can be effectively addressed through parameter-efficient, scale-aware adaptation of the latent interface without updating the DiT. To this end, FlexVSR introduces ReLSA (Refined Latent Scale Adaptation), a lightweight latent adapter that constructs and refines target-grid latents before they enter the DiT, enabling a shared frozen VSR prior to generalize across continuous scales with only 0.274M trainable parameters and an adaptation cost of 7.3 H100 GPU-hours, while introducing no additional temporal dependencies and preserving the native causal streaming protocol. Extensive experiments demonstrate competitive or superior reconstruction and temporal quality, lower latency than most native-scale streaming baselines and offline methods, and effective generalization to unseen continuous scales, filling the continuous-scale gap in real-time streaming generative VSR.

arXiv:2611.26177v1cs.CV

SpatialScout-V2: Can VLM Agents Actively Explore Real-World 3D Scenes and Localize Objects?

Spatial intelligence requires agents to acquire visual evidence and integrate partial observations into coherent three-dimensional representations. We introduce SpatialScout-V2, which extends SpatialScout's active mapping task from simulation to real residential scenes through three advances: real visual observations, preservation of original scene content, and interactive exploration of recorded views. Built from 100 homes in Realsee3D, the benchmark covers 3,171 target objects across 29 categories. Given a fixed target inventory, agents autonomously select recorded viewpoints and viewing directions, integrate calibrated RGB observations, and iteratively estimate and revise object centers within a fixed interaction budget. We evaluate the localization accuracy and completeness of object-center maps using mean IoU, IoU-threshold hit rates, and target coverage. Evaluating seven frontier vision-language models (VLMs), we find that six achieve an all-target mean IoU below 20\%. Even the best-performing model, Claude Opus 5.5, reaches only 22.52\%, with just 18.36\% of targets exceeding an IoU of 0.5. Further analysis shows that broad submission coverage can coexist with limited localization accuracy, while target omissions further reduce overall scores. These results highlight substantial challenges in constructing accurate and complete object-center maps through active exploration of real scenes.

arXiv:2611.26165v1cs.CV

StreamEgo: Streaming Exocentric-to-Egocentric Video Generation

Exocentric-to-egocentric (Exo2Ego) video generation transforms third-person recordings into first-person viewpoints, unlocking immersive AR/VR experiences and scalable demonstration synthesis for embodied robotics. Extending it to a streaming setting is expected to further enable live applications. However, existing methods suffer from degraded manipulation regions, overfitting and confinement to fixed-length clips with prohibitive latency. To address these limitations, we present StreamEgo, a real-time framework for unbounded, generalizable Exo2Ego video generation. To resolve intricate manipulation dynamics while supporting the streaming pipeline, a streaming dual-branch prior provides pixel-aligned guidance for translating appearance and skeletal kinematics. We also introduce a region-aware loss curriculum to improve generalization and stabilize multi-objective diffusion training. Furthermore, we distill the model into a chunk-wise autoregressive model, augmented with a region-aware corruption mechanism and a first-chunk curriculum, enabling high-quality, generalizable real-time streaming Exo2Ego generation at 24.3 FPS on a single H100 GPU.

arXiv:2611.26164v1cs.CV

MultiBinder: Preventing Multi-Subject Identity Leakage in Personalized Video Generation

Personalized video generation faces a significant scalability challenge: as the number of custom subjects increases, existing methods suffer from severe identity leakage and semantic entanglement, resulting in videos with blended attributes and incoherent narratives. We identify that this stems from a lack of explicit binding between textual entity phrases and their corresponding visual patterns prior to fusion in diffusion models. To address this, we propose MultiBinder, a novel framework built on a ``bind-then-narrate'' paradigm. Our approach introduces a two-stage conditioning process before video diffusion. First, Cross-modal Entity Binding devises an entity-aware Q-Former to extract identity-centric features from each subject's reference image and tightly align them with its unique entity phrase, yielding disentangled ``identity tokens.'' Second, a Multimodal Large Language Model (MLLM) acts as a ``narrative director'' in the Narrative-Aware Subject Arrangement stage, capturing the action of each subject from the text prompt and synthesizes contextualized subject features that encapsulate ``who is doing what'' and preserve role-specific distinctions. These features are then injected into a video diffusion model via dedicated conditioning pathways, ensuring precise attribute allocation. Extensive experiments on both general and newly curated multi-subject benchmarks show that MultiBinder significantly outperforms existing methods in multi-subject identity fidelity.