PyTorchKR Papers

“Code Generation”

총 8,452편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2410.06285

Monocular Visual Place Recognition in LiDAR Maps via Cross-Modal State Space Model and Multi-View Matching

Achieving monocular camera localization within pre-built LiDAR maps can bypass the simultaneous mapping process of visual SLAM systems, potentially reducing the computational overhead of autonomous localization. To this end, one of the key challenges is cross-modal place recognition, which involves retrieving 3D scenes (point clouds) from a LiDAR map according to online RGB images. In this paper, we introduce an efficient framework to learn descriptors for both RGB images and point clouds. It takes visual state space model (VMamba) as the backbone and employs a pixel-view-scene joint training strategy for cross-modal contrastive learning. To address the field-of-view differences, independent descriptors are generated from multiple evenly distributed viewpoints for point clouds. A visible 3D points overlap strategy is then designed to quantify the similarity between point cloud views and RGB images for multi-view supervision. Additionally, when generating descriptors from pixel-level features using NetVLAD, we compensate for the loss of geometric information, and introduce an efficient scheme for multi-view generation. Experimental results on the KITTI and KITTI-360 datasets demonstrate the effectiveness and generalization of our method. The code will be released upon acceptance.

arXiv:2410.06244

Story-Adapter: A Training-free Iterative Framework for Long Story Visualization

Story visualization, the task of generating coherent images based on a narrative, has seen significant advancements with the emergence of text-to-image models, particularly diffusion models. However, maintaining semantic consistency, generating high-quality fine-grained interactions, and ensuring computational feasibility remain challenging, especially in long story visualization (i.e., up to 100 frames). In this work, we propose a training-free and computationally efficient framework, termed Story-Adapter, to enhance the generative capability of long stories. Specifically, we propose an iterative paradigm to refine each generated image, leveraging both the text prompt and all generated images from the previous iteration. Central to our framework is a training-free global reference cross-attention module, which aggregates all generated images from the previous iteration to preserve semantic consistency across the entire story, while minimizing computational costs with global embeddings. This iterative process progressively optimizes image generation by repeatedly incorporating text constraints, resulting in more precise and fine-grained interactions. Extensive experiments validate the superiority of Story-Adapter in improving both semantic consistency and generative capability for fine-grained interactions, particularly in long story scenarios. The project page and associated code can be accessed via https://jwmao1.github.io/storyadapter .

arXiv:2411.19652공식 코드 · Papers with Code

Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing

Text-guided image generation and editing using diffusion models have achieved remarkable advancements. Among these, tuning-free methods have gained attention for their ability to perform edits without extensive model adjustments, offering simplicity and efficiency. However, existing tuning-free approaches often struggle with balancing fidelity and editing precision. Reconstruction errors in DDIM Inversion are partly attributed to the cross-attention mechanism in U-Net, which introduces misalignments during the inversion and reconstruction process. To address this, we analyze reconstruction from a structural perspective and propose a novel approach that replaces traditional cross-attention with uniform attention maps, significantly enhancing image reconstruction fidelity. Our method effectively minimizes distortions caused by varying text conditions during noise prediction. To complement this improvement, we introduce an adaptive mask-guided editing technique that integrates seamlessly with our reconstruction approach, ensuring consistency and accuracy in editing tasks. Experimental results demonstrate that our approach not only excels in achieving high-fidelity image reconstruction but also performs robustly in real image composition and editing scenarios. This study underscores the potential of uniform attention maps to enhance the fidelity and versatility of diffusion-based image processing methods. Code is available at https://github.com/Mowenyii/Uniform-Attention-Maps.

arXiv:2412.09936공식 코드 · Papers with Code

CaLoRAify: Calorie Estimation with Visual-Text Pairing and LoRA-Driven Visual Language Models

The obesity phenomenon, known as the heavy issue, is a leading cause of preventable chronic diseases worldwide. Traditional calorie estimation tools often rely on specific data formats or complex pipelines, limiting their practicality in real-world scenarios. Recently, vision-language models (VLMs) have excelled in understanding real-world contexts and enabling conversational interactions, making them ideal for downstream tasks such as ingredient analysis. However, applying VLMs to calorie estimation requires domain-specific data and alignment strategies. To this end, we curated CalData, a 330K image-text pair dataset tailored for ingredient recognition and calorie estimation, combining a large-scale recipe dataset with detailed nutritional instructions for robust vision-language training. Built upon this dataset, we present CaLoRAify, a novel VLM framework aligning ingredient recognition and calorie estimation via training with visual-text pairs. During inference, users only need a single monocular food image to estimate calories while retaining the flexibility of agent-based conversational interaction. With Low-rank Adaptation (LoRA) and Retrieve-augmented Generation (RAG) techniques, our system enhances the performance of foundational VLMs in the vertical domain of calorie estimation. Our code and data are fully open-sourced at https://github.com/KennyYao2001/16824-CaLORAify.

arXiv:2501.15151공식 코드 · Papers with Code

SpikSSD: Better Extraction and Fusion for Object Detection with Spiking Neuron Networks

As the third generation of neural networks, Spiking Neural Networks (SNNs) have gained widespread attention due to their low energy consumption and biological interpretability. Recently, SNNs have made considerable advancements in computer vision. However, efficiently conducting feature extraction and fusion under the spiking characteristics of SNNs for object detection remains a pressing challenge. To address this problem, we propose the SpikSSD, a novel Spiking Single Shot Multibox Detector. Specifically, we design a full-spiking backbone network, MDS-ResNet, which effectively adjusts the membrane synaptic input distribution at each layer, achieving better spiking feature extraction. Additionally, for spiking feature fusion, we introduce the Spiking Bi-direction Fusion Module (SBFM), which for the first time realizes bi-direction fusion of spiking features, enhancing the multi-scale detection capability of the model. Experimental results show that SpikSSD achieves 40.8% mAP on the GEN1 dataset, 76.3% and 52.4% [email omitted] on VOC 2007 and COCO 2017 datasets respectively with the lowest firing rate, outperforming existing SNN-based approaches at ultralow energy consumption. This work sets a new benchmark for future research in SNN-based object detection. Our code is publicly available in https://github.com/yimeng-fan/SpikSSD.

arXiv:2501.19393공식 코드 · Papers with Code

s1: Simple test-time scaling

Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. Recently, OpenAI's o1 model showed this capability but did not publicly share its methodology, leading to many replication efforts. We seek the simplest approach to achieve test-time scaling and strong reasoning performance. First, we curate a small dataset s1K of 1,000 questions paired with reasoning traces relying on three criteria we validate through ablations: difficulty, diversity, and quality. Second, we develop budget forcing to control test-time compute by forcefully terminating the model's thinking process or lengthening it by appending "Wait" multiple times to the model's generation when it tries to end. This can lead the model to double-check its answer, often fixing incorrect reasoning steps. After supervised finetuning the Qwen2.5-32B-Instruct language model on s1K and equipping it with budget forcing, our model s1-32B exceeds o1-preview on competition math questions by up to 27% (MATH and AIME24). Further, scaling s1-32B with budget forcing allows extrapolating beyond its performance without test-time intervention: from 50% to 57% on AIME24. Our model, data, and code are open-source at https://github.com/simplescaling/s1

arXiv:2502.08056공식 코드 · Papers with Code

Cognify: Supercharging Gen-AI Workflows With Hierarchical Autotuning

Today's gen-AI workflows that involve multiple ML model calls, tool/API calls, data retrieval, or generic code execution are often tuned manually in an ad-hoc way that is both time-consuming and error-prone. In this paper, we propose a systematic approach for automatically tuning gen-AI workflows. Our key insight is that gen-AI workflows can benefit from structure, operator, and prompt changes, but unique properties of gen-AI workflows require new optimization techniques. We propose AdaSeek, an adaptive hierarchical search algorithm for autotuning gen-AI workflows. AdaSeek organizes workflow tuning methods into different layers based on the user-specified total search budget and distributes the budget across different layers based on the complexity of each layer. During its hierarchical search, AdaSeek redistributes the search budget from less useful to more promising tuning configurations based on workflow-level evaluation results. We implement AdaSeek in a workflow autotuning framework called Cognify and evaluate Cognify using six types of workflows such as RAG-based QA and text-to-SQL transformation. Overall, Cognify improves these workflows' generation quality by up to 2.8x, reduces execution monetary cost by up to 10x, and reduces end-to-end latency by 2.7x.

arXiv:2503.00767

LLMs are everywhere: Ubiquitous Utilization of AI Models through Air Computing

We are witnessing a new era where problem-solving and cognitive tasks are being increasingly delegated to Large Language Models (LLMs) across diverse domains, ranging from code generation to holiday planning. This trend also creates a demand for the ubiquitous execution of LLM-powered applications in a wide variety of environments in which traditional terrestrial 2D networking infrastructures may prove insufficient. A promising solution in this context is to extend edge computing into a 3D setting to include aerial platforms organized in multiple layers, a paradigm we refer to as air computing, to augment local devices for running LLM and Generative AI (GenAI) applications. This approach alleviates the strain on existing infrastructure while enhancing service efficiency by offloading computational tasks to the corresponding air units such as UAVs. Furthermore, the coordinated deployment of various air units can significantly improve the Quality of Experience (QoE) by ensuring seamless, adaptive, and resilient task execution. In this study, we investigate the synergy between LLM-based applications and air computing, exploring their potential across various use cases. Additionally, we present a disaster response case study demonstrating how the collaborative utilization of LLMs and air computing can significantly improve outcomes in critical situations.

arXiv:2505.07782공식 코드 · Papers with Code

MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering

We introduce MLE-Dojo, a Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents in iterative machine learning engineering (MLE) workflows. Unlike existing benchmarks that primarily rely on static datasets or single-attempt evaluations, MLE-Dojo provides an interactive environment enabling agents to iteratively experiment, debug, and refine solutions through structured feedback loops. Built upon 200+ real-world Kaggle challenges, MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios such as data processing, architecture search, hyperparameter tuning, and code debugging. Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning, facilitating iterative experimentation, realistic data sampling, and real-time outcome verification. Extensive evaluations of eight frontier LLMs reveal that while current models achieve meaningful iterative improvements, they still exhibit significant limitations in autonomously generating long-horizon solutions and efficiently resolving complex errors. Furthermore, MLE-Dojo's flexible and extensible architecture seamlessly integrates diverse data sources, tools, and evaluation protocols, uniquely enabling model-based agent tuning and promoting interoperability, scalability, and reproducibility. We open-source our framework and benchmarks to foster community-driven innovation towards next-generation MLE agents.

arXiv:2505.10566

3D-Fixup: Advancing Photo Editing with 3D Priors

Despite significant advances in modeling image priors via diffusion models, 3D-aware image editing remains challenging, in part because the object is only specified via a single image. To tackle this challenge, we propose 3D-Fixup, a new framework for editing 2D images guided by learned 3D priors. The framework supports difficult editing situations such as object translation and 3D rotation. To achieve this, we leverage a training-based approach that harnesses the generative power of diffusion models. As video data naturally encodes real-world physical dynamics, we turn to video data for generating training data pairs, i.e., a source and a target frame. Rather than relying solely on a single trained model to infer transformations between source and target frames, we incorporate 3D guidance from an Image-to-3D model, which bridges this challenging task by explicitly projecting 2D information into 3D space. We design a data generation pipeline to ensure high-quality 3D guidance throughout training. Results show that by integrating these 3D priors, 3D-Fixup effectively supports complex, identity coherent 3D-aware edits, achieving high-quality results and advancing the application of diffusion models in realistic image manipulation. The code is provided at https://3dfixup.github.io/

arXiv:2505.17513

What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection

Recent advances in text-to-speech technologies have enabled realistic voice generation, fueling audio-based deepfake attacks such as fraud and impersonation. While audio anti-spoofing systems are critical for detecting such threats, prior work has predominantly focused on acoustic-level perturbations, leaving the impact of linguistic variation largely unexplored. In this paper, we investigate the linguistic sensitivity of both open-source and commercial anti-spoofing detectors by introducing transcript-level adversarial attacks. Our extensive evaluation reveals that even minor linguistic perturbations can significantly degrade detection accuracy: attack success rates surpass 60% on several open-source detector-voice pairs, and notably one commercial detection accuracy drops from 100% on synthetic audio to just 32%. Through a comprehensive feature attribution analysis, we identify that both linguistic complexity and model-level audio embedding similarity contribute strongly to detector vulnerability. We further demonstrate the real-world risk via a case study replicating the Brad Pitt audio deepfake scam, using transcript adversarial attacks to completely bypass commercial detectors. These results highlight the need to move beyond purely acoustic defenses and account for linguistic variation in the design of robust anti-spoofing systems. All source code will be publicly available.

arXiv:2506.01844공식 코드 · Papers with Code

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Vision-language models (VLMs) pretrained on large-scale multimodal datasets encode rich visual and linguistic knowledge, making them a strong foundation for robotics. Rather than training robotic policies from scratch, recent approaches adapt VLMs into vision-language-action (VLA) models that enable natural language-driven perception and control. However, existing VLAs are typically massive--often with billions of parameters--leading to high training costs and limited real-world deployability. Moreover, they rely on academic and industrial datasets, overlooking the growing availability of community-collected data from affordable robotic platforms. In this work, we present SmolVLA, a small, efficient, and community-driven VLA that drastically reduces both training and inference costs, while retaining competitive performance. SmolVLA is designed to be trained on a single GPU and deployed on consumer-grade GPUs or even CPUs. To further improve responsiveness, we introduce an asynchronous inference stack decoupling perception and action prediction from action execution, allowing higher control rates with chunked action generation. Despite its compact size, SmolVLA achieves performance comparable to VLAs that are 10x larger. We evaluate SmolVLA on a range of both simulated as well as real-world robotic benchmarks and release all code, pretrained models, and training data.

arXiv:1805.03973

Active User Detection of Uplink Grant-Free SCMA in Frequency Selective Channel

Massive machine type communication (mMTC) is one of the three fifth generation mobile networking (5G) key usage scenarios, which is characterized by a very large number of connected devices typically transmitting a relatively low volume of non-delay sensitive data. To support the mMTC communication, an uplink (UL) grant-free sparse code multiple access (SCMA) system has been proposed. In this system, the knowledge of user equipments' (UEs') status should be obtained before decoding the data by a message passing algorithm (MPA). An existing solution is to use the compressive sensing (CS) theory to detect active UEs under the assumed condition of flat fading channel. But the assumed condition is not suitable for the frequency selective channel and will decrease the accuracy of active UEs detection. This paper proposes a new simple module named refined active UE detector (RAUD), which is based on frequency selective channel gain analyzing. By making full use of the channel gain and analyzing the difference between characteristic values of the two status of UEs, RAUD module can enhance the active UEs detection accuracy. Meanwhile, the addition of the proposed module has a negligible effect on the complexity of UL grant-free SCMA receiver.

arXiv:2012.10974

High-Fidelity Neural Human Motion Transfer from Monocular Video

Video-based human motion transfer creates video animations of humans following a source motion. Current methods show remarkable results for tightly-clad subjects. However, the lack of temporally consistent handling of plausible clothing dynamics, including fine and high-frequency details, significantly limits the attainable visual quality. We address these limitations for the first time in the literature and present a new framework which performs high-fidelity and temporally-consistent human motion transfer with natural pose-dependent non-rigid deformations, for several types of loose garments. In contrast to the previous techniques, we perform image generation in three subsequent stages, synthesizing human shape, structure, and appearance. Given a monocular RGB video of an actor, we train a stack of recurrent deep neural networks that generate these intermediate representations from 2D poses and their temporal derivatives. Splitting the difficult motion transfer problem into subtasks that are aware of the temporal motion context helps us to synthesize results with plausible dynamics and pose-dependent detail. It also allows artistic control of results by manipulation of individual framework stages. In the experimental results, we significantly outperform the state-of-the-art in terms of video realism. Our code and data will be made publicly available.

arXiv:2012.08106

Hybrid NOMA for Future Radio Access: Design, Potentials and Limitations

Next-generation internet of things (IoT) applications need trillions of low-powered wireless mobile devices to connect with each other having ultra-reliability and low-latency. Non-orthogonal multiple access (NOMA) is a promising technology to address massive connectivity for 5G and beyond by accommodating several users within the same orthogonal resource block. Therefore, this article explores hybrid NOMA (HNOMA) for massive multiple access in the uplink scenarios due to its higher spectral efficiency. The HNOMA includes both power domain and code domain NOMA method due to diverse channel conditions in practice. We highlight that polar coded based data transmission can achieve higher reliability and lower latency in HNOMA-based wireless networks. Further, at the base station (BS), channel state information (CSI) of each link is not perfectly available or very complex to estimate due to non-orthogonal links. Therefore, we analyze and review the performance of uplink based system involving HNOMA transmission in the presence of imperfect CSI. Furthermore, we summarize some key technical challenges as well as their potential solutions in futuristic IoT applications using HNOMA transmission. Finally, we offer some design guidelines for HNOMA-based systems using deep learning approach to implement adaptive and efficient wireless networks.

arXiv:2108.01682공식 코드 · Papers with Code

Exploiting BERT For Multimodal Target Sentiment Classification Through Input Space Translation

Multimodal target/aspect sentiment classification combines multimodal sentiment analysis and aspect/target sentiment classification. The goal of the task is to combine vision and language to understand the sentiment towards a target entity in a sentence. Twitter is an ideal setting for the task because it is inherently multimodal, highly emotional, and affects real world events. However, multimodal tweets are short and accompanied by complex, possibly irrelevant images. We introduce a two-stream model that translates images in input space using an object-aware transformer followed by a single-pass non-autoregressive text generation approach. We then leverage the translation to construct an auxiliary sentence that provides multimodal information to a language model. Our approach increases the amount of text available to the language model and distills the object-level information in complex images. We achieve state-of-the-art performance on two multimodal Twitter datasets without modifying the internals of the language model to accept multimodal data, demonstrating the effectiveness of our translation. In addition, we explain a failure mode of a popular approach for aspect sentiment analysis when applied to tweets. Our code is available at \textcolor{blue}{\url{https://github.com/codezakh/exploiting-BERT-thru-translation}}.

arXiv:2110.00966공식 코드 · Papers with Code

Translating Images into Maps

We approach instantaneous mapping, converting images to a top-down view of the world, as a translation problem. We show how a novel form of transformer network can be used to map from images and video directly to an overhead map or bird's-eye-view (BEV) of the world, in a single end-to-end network. We assume a 1-1 correspondence between a vertical scanline in the image, and rays passing through the camera location in an overhead map. This lets us formulate map generation from an image as a set of sequence-to-sequence translations. Posing the problem as translation allows the network to use the context of the image when interpreting the role of each pixel. This constrained formulation, based upon a strong physical grounding of the problem, leads to a restricted transformer network that is convolutional in the horizontal direction only. The structure allows us to make efficient use of data when training, and obtains state-of-the-art results for instantaneous mapping of three large-scale datasets, including a 15% and 30% relative gain against existing best performing methods on the nuScenes and Argoverse datasets, respectively. We make our code available on https://github.com/avishkarsaha/translating-images-into-maps.

arXiv:2111.12853공식 코드 · Papers with Code

Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains

Domain generalization (DG) is a difficult transfer learning problem aiming to learn a generalizable model for unseen domains. Recent foundation models (FMs) are robust to many distribution shifts and, therefore, should substantially improve the performance of DG. In this work, we study generic ways to adopt CLIP, a Visual-Language Foundation Model, for DG problems in image classification. While ERM greatly improves the accuracy with bigger backbones and training datasets using standard DG benchmarks, fine-tuning FMs is not practical in many real-world situations. We propose Domain Prompt Learning (DPL) as a novel approach for domain inference in the form of conditional prompt generation. DPL achieved a significant accuracy improvement with only training a lightweight prompt generator (a three-layer MLP), whose parameter is of equivalent scale to the classification projector in the previous DG literature. Combining \dplshort~with CLIP provides surprising performance, raising the accuracy of zero-shot CLIP from 73.7% to 79.3% on several standard datasets, namely PACS, VLCS, OfficeHome, and TerraIncognita. We hope the simplicity and success of our approach lead to broader adoption and analysis of foundation models in the domain generalization field. Our code is available at https://github.com/shogi880/DPLCLIP.

arXiv:2207.07818공식 코드 · Papers with Code

Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization

Classification activation map (CAM), utilizing the classification structure to generate pixel-wise localization maps, is a crucial mechanism for weakly supervised object localization (WSOL). However, CAM directly uses the classifier trained on image-level features to locate objects, making it prefers to discern global discriminative factors rather than regional object cues. Thus only the discriminative locations are activated when feeding pixel-level features into this classifier. To solve this issue, this paper elaborates a plug-and-play mechanism called BagCAMs to better project a well-trained classifier for the localization task without refining or re-training the baseline structure. Our BagCAMs adopts a proposed regional localizer generation (RLG) strategy to define a set of regional localizers and then derive them from a well-trained classifier. These regional localizers can be viewed as the base learner that only discerns region-wise object factors for localization tasks, and their results can be effectively weighted by our BagCAMs to form the final localization map. Experiments indicate that adopting our proposed BagCAMs can improve the performance of baseline WSOL methods to a great extent and obtains state-of-the-art performance on three WSOL benchmarks. Code are released at https://github.com/zh460045050/BagCAMs.

arXiv:2211.01184

Joint Data and Feature Augmentation for Self-Supervised Representation Learning on Point Clouds

To deal with the exhausting annotations, self-supervised representation learning from unlabeled point clouds has drawn much attention, especially centered on augmentation-based contrastive methods. However, specific augmentations hardly produce sufficient transferability to high-level tasks on different datasets. Besides, augmentations on point clouds may also change underlying semantics. To address the issues, we propose a simple but efficient augmentation fusion contrastive learning framework to combine data augmentations in Euclidean space and feature augmentations in feature space. In particular, we propose a data augmentation method based on sampling and graph generation. Meanwhile, we design a data augmentation network to enable a correspondence of representations by maximizing consistency between augmented graph pairs. We further design a feature augmentation network that encourages the model to learn representations invariant to the perturbations using an encoder perturbation. We comprehensively conduct extensive object classification experiments and object part segmentation experiments to validate the transferability of the proposed framework. Experimental results demonstrate that the proposed framework is effective to learn the point cloud representation in a self-supervised manner, and yields state-of-the-art results in the community. The source code is publicly available at: https://zhiyongsu.github.io/Project/AFSRL.html.