{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/object/papers/41","list_of":"/task/object","task":"Object","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":41,"pages_in_order":107,"rows_per_page":100,"rows":[4001,4100],"of":10696,"counts":{"archive_papers_tagged":10696,"with_a_code_link":3979,"where_syntology_ran_a_sample":1043,"not_listed_spam_title":0,"listed":10696,"listed_where_code_ran":1043,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":919,"every_run_a_failure_of_syntologys_instrument":124,"listed_with_a_run_with_no_instrument_failure":919,"listed_every_run_a_failure_of_syntologys_instrument":124,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/object","prev":"/task/object/papers/40","next":"/task/object/papers/42","papers":[{"url":null,"slug":"particle-grid-neural-dynamics-for-learning","title":"Particle-Grid Neural Dynamics for Learning Deformable Object Models from RGB-D Videos","date":"2025-06-18","arxiv_id":"2506.15680","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrospective-memory-for-camouflaged-object","title":"Retrospective Memory for Camouflaged Object Detection","date":"2025-06-18","arxiv_id":"2506.15244","repositories_listed":0,"syntology":null},{"url":null,"slug":"foam-a-general-frequency-optimized-anti","title":"FOAM: A General Frequency-Optimized Anti-Overlapping Framework for Overlapping Object Perception","date":"2025-06-16","arxiv_id":"2506.13501","repositories_listed":0,"syntology":null},{"url":null,"slug":"jenga-object-selection-and-pose-estimation","title":"JENGA: Object selection and pose estimation for robotic grasping from a stack","date":"2025-06-16","arxiv_id":"2506.13425","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-convolutional-recurrent-learning-for","title":"Sparse Convolutional Recurrent Learning for Efficient Event-based Neuromorphic Object Detection","date":"2025-06-16","arxiv_id":"2506.13440","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-4d-scene-gaussian-splatting-with","title":"Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors","date":"2025-06-15","arxiv_id":"2506.12716","repositories_listed":0,"syntology":null},{"url":null,"slug":"idit-hoi-inpainting-based-hand-object","title":"iDiT-HOI: Inpainting-based Hand Object Interaction Reenactment via Video Diffusion Transformer","date":"2025-06-15","arxiv_id":"2506.12847","repositories_listed":0,"syntology":null},{"url":null,"slug":"splatart-articulated-gaussian-splatting-with","title":"SPLATART: Articulated Gaussian Splatting with Estimated Object Structure","date":"2025-06-13","arxiv_id":"2506.12184","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-based-lifting-of-2d-object-detections","title":"Vision-based Lifting of 2D Object Detections for Automated Driving","date":"2025-06-13","arxiv_id":"2506.11839","repositories_listed":0,"syntology":null},{"url":null,"slug":"vitascope-visuo-tactile-implicit","title":"ViTaSCOPE: Visuo-tactile Implicit Representation for In-hand Pose and Extrinsic Contact Estimation","date":"2025-06-13","arxiv_id":"2506.12239","repositories_listed":0,"syntology":null},{"url":null,"slug":"occlusion-aware-3d-hand-object-pose","title":"Occlusion-Aware 3D Hand-Object Pose Estimation with Masked AutoEncoders","date":"2025-06-12","arxiv_id":"2506.10816","repositories_listed":0,"syntology":null},{"url":null,"slug":"scoop-and-toss-dynamic-object-collection-for","title":"Scoop-and-Toss: Dynamic Object Collection for Quadrupedal Systems","date":"2025-06-11","arxiv_id":"2506.09406","repositories_listed":0,"syntology":null},{"url":null,"slug":"adam-autonomous-discovery-and-annotation","title":"ADAM: Autonomous Discovery and Annotation Model using LLMs for Context-Aware Annotations","date":"2025-06-10","arxiv_id":"2506.08968","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-augmentation-for-small-object-using-fast","title":"Data Augmentation For Small Object using Fast AutoAugment","date":"2025-06-10","arxiv_id":"2506.08956","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizable-articulated-object","title":"Generalizable Articulated Object Reconstruction from Casually Captured RGBD Videos","date":"2025-06-10","arxiv_id":"2506.08334","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-neural-collapse-detection","title":"Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detection","date":"2025-06-10","arxiv_id":"2506.08562","repositories_listed":0,"syntology":null},{"url":null,"slug":"orida-object-centric-real-world-image-1","title":"ORIDa: Object-centric Real-world Image Composition Dataset","date":"2025-06-10","arxiv_id":"2506.08964","repositories_listed":0,"syntology":null},{"url":null,"slug":"orientation-matters-making-3d-generative","title":"Orientation Matters: Making 3D Generative Models Orientation-Aligned","date":"2025-06-10","arxiv_id":"2506.08640","repositories_listed":0,"syntology":null},{"url":null,"slug":"uad-unsupervised-affordance-distillation-for","title":"UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation","date":"2025-06-10","arxiv_id":"2506.09284","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapbert-bitwise-masked-modeling-for-real-time","title":"MapBERT: Bitwise Masked Modeling for Real-Time Semantic Mapping Generation","date":"2025-06-09","arxiv_id":"2506.07350","repositories_listed":0,"syntology":null},{"url":null,"slug":"r3d2-realistic-3d-asset-insertion-via","title":"R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation","date":"2025-06-09","arxiv_id":"2506.07826","repositories_listed":0,"syntology":null},{"url":null,"slug":"sam2auto-auto-annotation-using-flash","title":"SAM2Auto: Auto Annotation Using FLASH","date":"2025-06-09","arxiv_id":"2506.07850","repositories_listed":0,"syntology":null},{"url":null,"slug":"ua-pose-uncertainty-aware-6d-object-pose-1","title":"UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References","date":"2025-06-09","arxiv_id":"2506.07996","repositories_listed":0,"syntology":null},{"url":null,"slug":"hoi-page-zero-shot-human-object-interaction","title":"HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance","date":"2025-06-08","arxiv_id":"2506.07209","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-navigation-with-structure-semantic","title":"Object Navigation with Structure-Semantic Reasoning-Based Multi-level Map and Multimodal Decision-Making LLM","date":"2025-06-06","arxiv_id":"2506.05896","repositories_listed":0,"syntology":null},{"url":null,"slug":"civet-systematic-evaluation-of-understanding","title":"CIVET: Systematic Evaluation of Understanding in VLMs","date":"2025-06-05","arxiv_id":"2506.05146","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-numerical-layout-generation-for-3d","title":"Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning","date":"2025-06-05","arxiv_id":"2506.05341","repositories_listed":0,"syntology":null},{"url":null,"slug":"eoc-bench-can-mllms-identify-recall-and","title":"EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?","date":"2025-06-05","arxiv_id":"2506.05287","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-based-lie-group-transformer-for-real","title":"Feature-Based Lie Group Transformer for Real-World Applications","date":"2025-06-05","arxiv_id":"2506.04668","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-objects-to-anywhere-a-holistic-benchmark","title":"From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes","date":"2025-06-05","arxiv_id":"2506.04897","repositories_listed":0,"syntology":null},{"url":null,"slug":"gen-n-val-agentic-image-data-generation-and","title":"Gen-n-Val: Agentic Image Data Generation and Validation","date":"2025-06-05","arxiv_id":"2506.04676","repositories_listed":0,"syntology":null},{"url":null,"slug":"light-and-3d-a-methodological-exploration-of","title":"Light and 3D: a methodological exploration of digitisation techniques adapted to a selection of objects from the Mus{é}e d'Arch{é}ologie Nationale","date":"2025-06-05","arxiv_id":"2506.04925","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-x-learning-to-reconstruct-multi-modal","title":"Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations","date":"2025-06-05","arxiv_id":"2506.04789","repositories_listed":0,"syntology":null},{"url":null,"slug":"rayst3r-predicting-novel-depth-maps-for-zero","title":"RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion","date":"2025-06-05","arxiv_id":"2506.05285","repositories_listed":0,"syntology":null},{"url":null,"slug":"mambanext-yolo-a-hybrid-state-space-model-for","title":"MambaNeXt-YOLO: A Hybrid State Space Model for Real-time Object Detection","date":"2025-06-04","arxiv_id":"2506.03654","repositories_listed":0,"syntology":null},{"url":null,"slug":"rex-thinker-grounded-object-referring-via","title":"Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning","date":"2025-06-04","arxiv_id":"2506.04034","repositories_listed":0,"syntology":null},{"url":null,"slug":"semnav-a-model-based-planner-for-zero-shot","title":"SemNav: A Model-Based Planner for Zero-Shot Object Goal Navigation Using Vision-Foundation Models","date":"2025-06-04","arxiv_id":"2506.03516","repositories_listed":0,"syntology":null},{"url":null,"slug":"sounding-that-object-interactive-object-aware","title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation","date":"2025-06-04","arxiv_id":"2506.04214","repositories_listed":0,"syntology":null},{"url":null,"slug":"interrvos-interaction-aware-referring-video","title":"InterRVOS: Interaction-aware Referring Video Object Segmentation","date":"2025-06-03","arxiv_id":"2506.02356","repositories_listed":0,"syntology":null},{"url":null,"slug":"respace-text-driven-3d-scene-synthesis-and","title":"ReSpace: Text-Driven 3D Scene Synthesis and Editing with Preference Alignment","date":"2025-06-03","arxiv_id":"2506.02459","repositories_listed":0,"syntology":null},{"url":null,"slug":"tru-pomdp-task-planning-under-uncertainty-via","title":"Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs","date":"2025-06-03","arxiv_id":"2506.02860","repositories_listed":0,"syntology":null},{"url":null,"slug":"womap-world-models-for-embodied-open","title":"WoMAP: World Models For Embodied Open-Vocabulary Object Localization","date":"2025-06-02","arxiv_id":"2506.01600","repositories_listed":0,"syntology":null},{"url":null,"slug":"composeanything-composite-object-priors-for","title":"ComposeAnything: Composite Object Priors for Text-to-Image Generation","date":"2025-05-30","arxiv_id":"2505.24086","repositories_listed":0,"syntology":null},{"url":null,"slug":"dexmachina-functional-retargeting-for","title":"DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation","date":"2025-05-30","arxiv_id":"2505.24853","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactanything-zero-shot-human-object","title":"InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing","date":"2025-05-30","arxiv_id":"2505.24315","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-concept-bottlenecks","title":"Object Centric Concept Bottlenecks","date":"2025-05-30","arxiv_id":"2505.24492","repositories_listed":0,"syntology":null},{"url":null,"slug":"out-of-sight-not-out-of-context-egocentric","title":"Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames","date":"2025-05-30","arxiv_id":"2505.24257","repositories_listed":0,"syntology":null},{"url":null,"slug":"conformal-object-detection-by-sequential-risk","title":"Conformal Object Detection by Sequential Risk Control","date":"2025-05-29","arxiv_id":"2505.24038","repositories_listed":0,"syntology":null},{"url":null,"slug":"disrupting-vision-language-model-driven","title":"Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion","date":"2025-05-29","arxiv_id":"2505.23266","repositories_listed":0,"syntology":null},{"url":null,"slug":"fmg-det-foundation-model-guided-robust-object","title":"FMG-Det: Foundation Model Guided Robust Object Detection","date":"2025-05-29","arxiv_id":"2505.23726","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-guided-learning-for-object-detection","title":"Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images","date":"2025-05-29","arxiv_id":"2505.23193","repositories_listed":0,"syntology":null},{"url":null,"slug":"movi-training-free-text-conditioned-multi","title":"MOVi: Training-free Text-conditioned Multi-Object Video Generation","date":"2025-05-29","arxiv_id":"2505.22980","repositories_listed":0,"syntology":null},{"url":null,"slug":"rooms-from-motion-un-posed-indoor-3d-object","title":"Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping","date":"2025-05-29","arxiv_id":"2505.23756","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-meeseeks-mesh-spatially-consistent-3d","title":"The Meeseeks Mesh: Spatially Consistent 3D Adversarial Objects for BEV Detector","date":"2025-05-28","arxiv_id":"2505.22499","repositories_listed":0,"syntology":null},{"url":null,"slug":"coda-coordinated-diffusion-noise-optimization","title":"CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects","date":"2025-05-27","arxiv_id":"2505.21437","repositories_listed":0,"syntology":null},{"url":null,"slug":"partinstruct-part-level-instruction-following","title":"PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulation","date":"2025-05-27","arxiv_id":"2505.21652","repositories_listed":0,"syntology":null},{"url":null,"slug":"right-side-up-disentangling-orientation","title":"Right Side Up? Disentangling Orientation Understanding in MLLMs with Fine-grained Multi-axis Perception Tasks","date":"2025-05-27","arxiv_id":"2505.21649","repositories_listed":0,"syntology":null},{"url":null,"slug":"category-agnostic-neural-object-rigging","title":"Category-Agnostic Neural Object Rigging","date":"2025-05-26","arxiv_id":"2505.20283","repositories_listed":0,"syntology":null},{"url":null,"slug":"next-multi-grained-mixture-of-experts-via","title":"NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-ID","date":"2025-05-26","arxiv_id":"2505.20001","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-scaling-visual-object-tracking","title":"Progressive Scaling Visual Object Tracking","date":"2025-05-26","arxiv_id":"2505.19990","repositories_listed":0,"syntology":null},{"url":null,"slug":"maskedmanipulator-versatile-whole-body","title":"MaskedManipulator: Versatile Whole-Body Control for Loco-Manipulation","date":"2025-05-25","arxiv_id":"2505.19086","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusiontrack-end-to-end-multi-object-tracking","title":"FusionTrack: End-to-End Multi-Object Tracking in Arbitrary Multi-View Environment","date":"2025-05-24","arxiv_id":"2505.18727","repositories_listed":0,"syntology":null},{"url":null,"slug":"sd-ovon-a-semantics-aware-dataset-and","title":"SD-OVON: A Semantics-aware Dataset and Benchmark Generation Pipeline for Open-Vocabulary Object Navigation in Dynamic Scenes","date":"2025-05-24","arxiv_id":"2505.18881","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-sam-2-for-visual-object-tracking-1st","title":"Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-Modal Tracking","date":"2025-05-23","arxiv_id":"2505.18111","repositories_listed":0,"syntology":null},{"url":null,"slug":"rqr3d-reparametrizing-the-regression-targets","title":"RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection","date":"2025-05-23","arxiv_id":"2505.17732","repositories_listed":0,"syntology":null},{"url":null,"slug":"sampling-strategies-for-efficient-training-of","title":"Sampling Strategies for Efficient Training of Deep Learning Object Detection Algorithms","date":"2025-05-23","arxiv_id":"2505.18302","repositories_listed":0,"syntology":null},{"url":"/paper/embodied-agents-meet-personalization","slug":"embodied-agents-meet-personalization","title":"Embodied Agents Meet Personalization: Exploring Memory Utilization for Personalized Assistance","date":"2025-05-22","arxiv_id":"2505.16348","repositories_listed":0,"syntology":{"n":6,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/embodied-agents-meet-personalization#ran","syntology_url":"https://syntology.ai/paper/2505.16348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16348"}},"official":null}},{"url":null,"slug":"investigating-fine-and-coarse-grained","title":"Investigating Fine- and Coarse-grained Structural Correspondences Between Deep Neural Networks and Human Object Image Similarity Judgments Using Unsupervised Alignment","date":"2025-05-22","arxiv_id":"2505.16419","repositories_listed":0,"syntology":null},{"url":null,"slug":"mafe-r-cnn-selecting-more-samples-to-learn","title":"MAFE R-CNN: Selecting More Samples to Learn Category-aware Features for Small Object Detection","date":"2025-05-22","arxiv_id":"2505.16442","repositories_listed":0,"syntology":null},{"url":null,"slug":"megohand-multimodal-egocentric-hand-object","title":"MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation","date":"2025-05-22","arxiv_id":"2505.16602","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-compression-of-3d-objects-for-open","title":"Semantic Compression of 3D Objects for Open and Collaborative Virtual Worlds","date":"2025-05-22","arxiv_id":"2505.16679","repositories_listed":0,"syntology":null},{"url":null,"slug":"texturesam-towards-a-texture-aware-foundation","title":"TextureSAM: Towards a Texture Aware Foundation Model for Segmentation","date":"2025-05-22","arxiv_id":"2505.16540","repositories_listed":0,"syntology":null},{"url":null,"slug":"expanding-zero-shot-object-counting-with-rich","title":"Expanding Zero-Shot Object Counting with Rich Prompts","date":"2025-05-21","arxiv_id":"2505.15398","repositories_listed":0,"syntology":null},{"url":null,"slug":"gen2seg-generative-models-enable","title":"gen2seg: Generative Models Enable Generalizable Instance Segmentation","date":"2025-05-21","arxiv_id":"2505.15263","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-focus-actor-for-data-efficient-robot","title":"Object-Focus Actor for Data-efficient Robot Generalization Dexterous Manipulation","date":"2025-05-21","arxiv_id":"2505.15098","repositories_listed":0,"syntology":null},{"url":null,"slug":"razer-robust-accelerated-zero-shot-3d-open","title":"RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabulary Panoptic Reconstruction with Spatio-Temporal Aggregation","date":"2025-05-21","arxiv_id":"2505.15373","repositories_listed":0,"syntology":null},{"url":null,"slug":"lidar-mot-detr-a-lidar-based-two-stage","title":"LiDAR MOT-DETR: A LiDAR-based Two-Stage Transformer for 3D Multiple Object Tracking","date":"2025-05-19","arxiv_id":"2505.12753","repositories_listed":0,"syntology":null},{"url":null,"slug":"opa-pack-object-property-aware-robotic-bin","title":"OPA-Pack: Object-Property-Aware Robotic Bin Packing","date":"2025-05-19","arxiv_id":"2505.13339","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-retrieval-augmented-generation-for","title":"Optimizing Retrieval Augmented Generation for Object Constraint Language","date":"2025-05-19","arxiv_id":"2505.13129","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergent-active-perception-and-dexterity-of","title":"Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learning","date":"2025-05-18","arxiv_id":"2505.12278","repositories_listed":0,"syntology":null},{"url":null,"slug":"gtr-gaussian-splatting-tracking-and","title":"GTR: Gaussian Splatting Tracking and Reconstruction of Unknown Objects Based on Appearance and Geometric Complexity","date":"2025-05-17","arxiv_id":"2505.11905","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-10825","title":"A High-Performance Thermal Infrared Object Detection Framework with Centralized Regulation","date":"2025-05-16","arxiv_id":"2505.10825","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-10841","title":"RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects","date":"2025-05-16","arxiv_id":"2505.10841","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11232","title":"AW-GATCN: Adaptive Weighted Graph Attention Convolutional Network for Event Camera Data Joint Denoising and Object Recognition","date":"2025-05-16","arxiv_id":"2505.11232","repositories_listed":0,"syntology":null},{"url":null,"slug":"feasibility-with-language-models-for-open","title":"Feasibility with Language Models for Open-World Compositional Zero-Shot Learning","date":"2025-05-16","arxiv_id":"2505.11181","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-10604","title":"MIRAGE: A Multi-modal Benchmark for Spatial Perception, Reasoning, and Intelligence","date":"2025-05-15","arxiv_id":"2505.10604","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-general-prompts-automated-prompt","title":"Beyond General Prompts: Automated Prompt Refinement using Contrastive Class Alignment Scores for Disambiguating Objects in Vision-Language Models","date":"2025-05-14","arxiv_id":"2505.09139","repositories_listed":0,"syntology":null},{"url":null,"slug":"manipbench-benchmarking-vision-language","title":"ManipBench: Benchmarking Vision-Language Models for Low-Level Robot Manipulation","date":"2025-05-14","arxiv_id":"2505.09698","repositories_listed":0,"syntology":null},{"url":null,"slug":"moral-motion-aware-multi-frame-4d-radar-and","title":"MoRAL: Motion-aware Multi-Frame 4D Radar and LiDAR Fusion for Robust 3D Object Detection","date":"2025-05-14","arxiv_id":"2505.09422","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-multi-modal-information-to-enhance","title":"Leveraging Multi-Modal Information to Enhance Dataset Distillation","date":"2025-05-13","arxiv_id":"2505.08605","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-detection-in-adverse-weather","title":"Object detection in adverse weather conditions for autonomous vehicles using Instruct Pix2Pix","date":"2025-05-13","arxiv_id":"2505.08228","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustness-analysis-against-adversarial-patch","title":"Robustness Analysis against Adversarial Patch Attacks in Fully Unmanned Stores","date":"2025-05-13","arxiv_id":"2505.08835","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-autonomous-uav-visual-object-search","title":"Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology","date":"2025-05-13","arxiv_id":"2505.08765","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-spiking-vision-transformer-for-object","title":"Hybrid Spiking Vision Transformer for Object Detection with Event Cameras","date":"2025-05-12","arxiv_id":"2505.07715","repositories_listed":0,"syntology":null},{"url":"/paper/towards-accurate-state-estimation-kalman","slug":"towards-accurate-state-estimation-kalman","title":"Towards Accurate State Estimation: Kalman Filter Incorporating Motion Dynamics for 3D Multi-Object Tracking","date":"2025-05-12","arxiv_id":"2505.07254","repositories_listed":0,"syntology":null},{"url":null,"slug":"underwater-object-detection-in-sonar-imagery","title":"Underwater object detection in sonar imagery with detection transformer and Zero-shot neural architecture search","date":"2025-05-10","arxiv_id":"2505.06694","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-edge-ai-solution-for-space-object","title":"An Edge AI Solution for Space Object Detection","date":"2025-05-08","arxiv_id":"2505.13468","repositories_listed":0,"syntology":null},{"url":null,"slug":"mde-edit-masked-dual-editing-for-multi-object","title":"MDE-Edit: Masked Dual-Editing for Multi-Object Image Editing via Diffusion Models","date":"2025-05-08","arxiv_id":"2505.05101","repositories_listed":0,"syntology":null},{"url":null,"slug":"panicar-securing-the-perception-of-advanced","title":"PaniCar: Securing the Perception of Advanced Driving Assistance Systems Against Emergency Vehicle Lighting","date":"2025-05-08","arxiv_id":"2505.05183","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-affordances-enabling-robots-to","title":"Visual Affordances: Enabling Robots to Understand Object Functionality","date":"2025-05-08","arxiv_id":"2505.05074","repositories_listed":0,"syntology":null}],"record_sha256":"245ef1485614d8e36d9736ec1ed567875662c52273d920ca3a1d9290761c7f98","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}