{"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/9","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":9,"pages_in_order":107,"rows_per_page":100,"rows":[801,900],"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/8","next":"/task/object/papers/10","papers":[{"url":"/paper/towards-reliable-detection-of-empty-space","slug":"towards-reliable-detection-of-empty-space","title":"Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object Detection","date":"2025-06-26","arxiv_id":"2506.21486","repositories_listed":1,"syntology":null},{"url":"/paper/consensus-driven-uncertainty-for-robotic","slug":"consensus-driven-uncertainty-for-robotic","title":"Consensus-Driven Uncertainty for Robotic Grasping based on RGB Perception","date":"2025-06-24","arxiv_id":"2506.20045","repositories_listed":1,"syntology":null},{"url":"/paper/rgbtrack-fast-robust-depth-free-6d-pose","slug":"rgbtrack-fast-robust-depth-free-6d-pose","title":"RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking","date":"2025-06-20","arxiv_id":"2506.17119","repositories_listed":1,"syntology":null},{"url":"/paper/object-centric-neuro-argumentative-learning","slug":"object-centric-neuro-argumentative-learning","title":"Object-Centric Neuro-Argumentative Learning","date":"2025-06-17","arxiv_id":"2506.14577","repositories_listed":1,"syntology":null},{"url":"/paper/m-3-vos-multi-phase-multi-transition-and-1","slug":"m-3-vos-multi-phase-multi-transition-and-1","title":"M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation","date":"2025-06-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/slotpi-physics-informed-object-centric","slug":"slotpi-physics-informed-object-centric","title":"SlotPi: Physics-informed Object-centric Reasoning Models","date":"2025-06-12","arxiv_id":"2506.10778","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/slotpi-physics-informed-object-centric#ran","syntology_url":"https://syntology.ai/paper/2506.10778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.10778"}},"official":{"repos":["intell-sci-comput/slotpi"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-part-level-3d-object-generation-via","slug":"efficient-part-level-3d-object-generation-via","title":"Efficient Part-level 3D Object Generation via Dual Volume Packing","date":"2025-06-11","arxiv_id":"2506.09980","repositories_listed":1,"syntology":null},{"url":"/paper/domain-randomization-for-object-detection-in","slug":"domain-randomization-for-object-detection-in","title":"Domain Randomization for Object Detection in Manufacturing Applications using Synthetic Data: A Comprehensive Study","date":"2025-06-09","arxiv_id":"2506.07539","repositories_listed":1,"syntology":null},{"url":"/paper/multiple-object-stitching-for-unsupervised","slug":"multiple-object-stitching-for-unsupervised","title":"Multiple Object Stitching for Unsupervised Representation Learning","date":"2025-06-09","arxiv_id":"2506.07364","repositories_listed":1,"syntology":null},{"url":"/paper/edge-enabled-collaborative-object-detection","slug":"edge-enabled-collaborative-object-detection","title":"Edge-Enabled Collaborative Object Detection for Real-Time Multi-Vehicle Perception","date":"2025-06-06","arxiv_id":"2506.06474","repositories_listed":1,"syntology":null},{"url":"/paper/unmore-unsupervised-multi-object-segmentation","slug":"unmore-unsupervised-multi-object-segmentation","title":"unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning","date":"2025-06-02","arxiv_id":"2506.01778","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/unmore-unsupervised-multi-object-segmentation#ran","syntology_url":"https://syntology.ai/paper/2506.01778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.01778"}},"official":{"repos":["vlar-group/unmore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sorce-small-object-retrieval-in-complex","slug":"sorce-small-object-retrieval-in-complex","title":"SORCE: Small Object Retrieval in Complex Environments","date":"2025-05-30","arxiv_id":"2505.24441","repositories_listed":1,"syntology":null},{"url":"/paper/lpoi-listwise-preference-optimization-for","slug":"lpoi-listwise-preference-optimization-for","title":"LPOI: Listwise Preference Optimization for Vision Language Models","date":"2025-05-27","arxiv_id":"2505.21061","repositories_listed":1,"syntology":null},{"url":"/paper/causal-llava-causal-disentanglement-for","slug":"causal-llava-causal-disentanglement-for","title":"Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models","date":"2025-05-26","arxiv_id":"2505.19474","repositories_listed":1,"syntology":{"n":19,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":11,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/causal-llava-causal-disentanglement-for#ran","syntology_url":"https://syntology.ai/paper/2505.19474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19474"}},"official":{"repos":["ignisavium/causal-llava"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/locality-aware-zero-shot-human-object","slug":"locality-aware-zero-shot-human-object","title":"Locality-Aware Zero-Shot Human-Object Interaction Detection","date":"2025-05-26","arxiv_id":"2505.19503","repositories_listed":1,"syntology":null},{"url":"/paper/reamot-a-benchmark-and-framework-for","slug":"reamot-a-benchmark-and-framework-for","title":"ReaMOT: A Benchmark and Framework for Reasoning-based Multi-Object Tracking","date":"2025-05-26","arxiv_id":"2505.20381","repositories_listed":1,"syntology":null},{"url":"/paper/eotnet-deep-memory-aided-bayesian-filter-for","slug":"eotnet-deep-memory-aided-bayesian-filter-for","title":"EOTNet: Deep Memory Aided Bayesian Filter for Extended Object Tracking","date":"2025-05-24","arxiv_id":"2505.18684","repositories_listed":1,"syntology":null},{"url":"/paper/thinkvideo-high-quality-reasoning-video","slug":"thinkvideo-high-quality-reasoning-video","title":"ThinkVideo: High-Quality Reasoning Video Segmentation with Chain of Thoughts","date":"2025-05-24","arxiv_id":"2505.18561","repositories_listed":1,"syntology":null},{"url":"/paper/object-level-cross-view-geo-localization-with","slug":"object-level-cross-view-geo-localization-with","title":"Object-level Cross-view Geo-localization with Location Enhancement and Multi-Head Cross Attention","date":"2025-05-23","arxiv_id":"2505.17911","repositories_listed":1,"syntology":null},{"url":"/paper/prompttad-object-prompt-enhanced-traffic","slug":"prompttad-object-prompt-enhanced-traffic","title":"PromptTAD: Object-Prompt Enhanced Traffic Anomaly Detection","date":"2025-05-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/instructsam-a-training-free-framework-for","slug":"instructsam-a-training-free-framework-for","title":"InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition","date":"2025-05-21","arxiv_id":"2505.15818","repositories_listed":1,"syntology":null},{"url":"/paper/multispectral-detection-transformer-with","slug":"multispectral-detection-transformer-with","title":"Multispectral Detection Transformer with Infrared-Centric Sensor Fusion","date":"2025-05-21","arxiv_id":"2505.15137","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-graph-induced-contour-aware-heat","slug":"dynamic-graph-induced-contour-aware-heat","title":"Dynamic Graph Induced Contour-aware Heat Conduction Network for Event-based Object Detection","date":"2025-05-19","arxiv_id":"2505.12908","repositories_listed":1,"syntology":null},{"url":"/paper/parsec-preference-adaptation-for-robotic","slug":"parsec-preference-adaptation-for-robotic","title":"PARSEC: Preference Adaptation for Robotic Object Rearrangement from Scene Context","date":"2025-05-16","arxiv_id":"2505.11108","repositories_listed":1,"syntology":null},{"url":"/paper/storyreasoning-dataset-using-chain-of-thought","slug":"storyreasoning-dataset-using-chain-of-thought","title":"StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation","date":"2025-05-15","arxiv_id":"2505.10292","repositories_listed":1,"syntology":null},{"url":"/paper/camera-only-3d-panoptic-scene-completion-for","slug":"camera-only-3d-panoptic-scene-completion-for","title":"Camera-Only 3D Panoptic Scene Completion for Autonomous Driving through Differentiable Object Shapes","date":"2025-05-14","arxiv_id":"2505.09562","repositories_listed":1,"syntology":null},{"url":"/paper/hmpnet-a-feature-aggregation-architecture-for","slug":"hmpnet-a-feature-aggregation-architecture-for","title":"HMPNet: A Feature Aggregation Architecture for Maritime Object Detection from a Shipborne Perspective","date":"2025-05-13","arxiv_id":"2505.08231","repositories_listed":1,"syntology":null},{"url":"/paper/improving-unsupervised-task-driven-models-of","slug":"improving-unsupervised-task-driven-models-of","title":"Improving Unsupervised Task-driven Models of Ventral Visual Stream via Relative Position Predictivity","date":"2025-05-13","arxiv_id":"2505.08316","repositories_listed":1,"syntology":null},{"url":"/paper/asynchronous-multi-object-tracking-with-an","slug":"asynchronous-multi-object-tracking-with-an","title":"Asynchronous Multi-Object Tracking with an Event Camera","date":"2025-05-12","arxiv_id":"2505.08126","repositories_listed":1,"syntology":null},{"url":"/paper/metor-a-unified-framework-for-mutual","slug":"metor-a-unified-framework-for-mutual","title":"METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection","date":"2025-05-10","arxiv_id":"2505.06663","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-detector-with-frame-dynamics-is-a","slug":"a-simple-detector-with-frame-dynamics-is-a","title":"A Simple Detector with Frame Dynamics is a Strong Tracker","date":"2025-05-08","arxiv_id":"2505.04917","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-satellite-object-localization-with","slug":"enhancing-satellite-object-localization-with","title":"Enhancing Satellite Object Localization with Dilated Convolutions and Attention-aided Spatial Pooling","date":"2025-05-08","arxiv_id":"2505.05599","repositories_listed":1,"syntology":null},{"url":"/paper/as3d-2d-assisted-cross-modal-understanding","slug":"as3d-2d-assisted-cross-modal-understanding","title":"AS3D: 2D-Assisted Cross-Modal Understanding with Semantic-Spatial Scene Graphs for 3D Visual Grounding","date":"2025-05-07","arxiv_id":"2505.04058","repositories_listed":1,"syntology":null},{"url":"/paper/sim2real-transfer-for-vision-based-grasp","slug":"sim2real-transfer-for-vision-based-grasp","title":"Sim2Real Transfer for Vision-Based Grasp Verification","date":"2025-05-05","arxiv_id":"2505.03046","repositories_listed":1,"syntology":null},{"url":"/paper/cdformer-cross-domain-few-shot-object","slug":"cdformer-cross-domain-few-shot-object","title":"CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion","date":"2025-05-02","arxiv_id":"2505.00938","repositories_listed":1,"syntology":null},{"url":"/paper/llm-empowered-embodied-agent-for-memory","slug":"llm-empowered-embodied-agent-for-memory","title":"LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics","date":"2025-04-30","arxiv_id":"2504.21716","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llm-empowered-embodied-agent-for-memory#ran","syntology_url":"https://syntology.ai/paper/2504.21716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21716"}},"official":{"repos":["marc1198/chat-hsr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-context-learning-of-object","slug":"hierarchical-context-learning-of-object","title":"Hierarchical Context Learning of object components for unsupervised semantic segmentation","date":"2025-04-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-referring-video-single-and-multi","slug":"few-shot-referring-video-single-and-multi","title":"Few-Shot Referring Video Single- and Multi-Object Segmentation via Cross-Modal Affinity with Instance Sequence Matching","date":"2025-04-18","arxiv_id":"2504.13710","repositories_listed":1,"syntology":null},{"url":"/paper/grabs-generative-embodied-agent-for-3d-object","slug":"grabs-generative-embodied-agent-for-3d-object","title":"GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision","date":"2025-04-16","arxiv_id":"2504.11754","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/grabs-generative-embodied-agent-for-3d-object#ran","syntology_url":"https://syntology.ai/paper/2504.11754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11754"}},"official":{"repos":["vlar-group/grabs"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/masseg-2nd-technical-report-for-4th-pvuw-mose","slug":"masseg-2nd-technical-report-for-4th-pvuw-mose","title":"MASSeg : 2nd Technical Report for 4th PVUW MOSE Track","date":"2025-04-14","arxiv_id":"2504.10254","repositories_listed":1,"syntology":null},{"url":"/paper/monodiff9d-monocular-category-level-9d-object","slug":"monodiff9d-monocular-category-level-9d-object","title":"MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model","date":"2025-04-14","arxiv_id":"2504.10433","repositories_listed":1,"syntology":null},{"url":"/paper/cut-and-splat-leveraging-gaussian-splatting","slug":"cut-and-splat-leveraging-gaussian-splatting","title":"Cut-and-Splat: Leveraging Gaussian Splatting for Synthetic Data Generation","date":"2025-04-11","arxiv_id":"2504.08473","repositories_listed":1,"syntology":null},{"url":"/paper/are-we-done-with-object-centric-learning","slug":"are-we-done-with-object-centric-learning","title":"Are We Done with Object-Centric Learning?","date":"2025-04-09","arxiv_id":"2504.07092","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/are-we-done-with-object-centric-learning#ran","syntology_url":"https://syntology.ai/paper/2504.07092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07092"}},"official":{"repos":["alexanderrubinstein/occam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/objaverse-curated-3d-object-dataset-with","slug":"objaverse-curated-3d-object-dataset-with","title":"Objaverse++: Curated 3D Object Dataset with Quality Annotations","date":"2025-04-09","arxiv_id":"2504.07334","repositories_listed":1,"syntology":null},{"url":"/paper/caption-anything-in-video-fine-grained-object","slug":"caption-anything-in-video-fine-grained-object","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","date":"2025-04-07","arxiv_id":"2504.05541","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/caption-anything-in-video-fine-grained-object#ran","syntology_url":"https://syntology.ai/paper/2504.05541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.05541"}},"official":{"repos":["yunlong10/CAT-V"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/interactvlm-3d-interaction-reasoning-from-2d","slug":"interactvlm-3d-interaction-reasoning-from-2d","title":"InteractVLM: 3D Interaction Reasoning from 2D Foundational Models","date":"2025-04-07","arxiv_id":"2504.05303","repositories_listed":1,"syntology":null},{"url":"/paper/playing-non-embedded-card-based-games-with","slug":"playing-non-embedded-card-based-games-with","title":"Playing Non-Embedded Card-Based Games with Reinforcement Learning","date":"2025-04-07","arxiv_id":"2504.04783","repositories_listed":1,"syntology":null},{"url":"/paper/sam2mot-a-novel-paradigm-of-multi-object","slug":"sam2mot-a-novel-paradigm-of-multi-object","title":"SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation","date":"2025-04-06","arxiv_id":"2504.04519","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-via-object","slug":"deep-reinforcement-learning-via-object","title":"Deep Reinforcement Learning via Object-Centric Attention","date":"2025-04-03","arxiv_id":"2504.03024","repositories_listed":1,"syntology":null},{"url":"/paper/picopose-progressive-pixel-to-pixel","slug":"picopose-progressive-pixel-to-pixel","title":"PicoPose: Progressive Pixel-to-Pixel Correspondence Learning for Novel Object Pose Estimation","date":"2025-04-03","arxiv_id":"2504.02617","repositories_listed":1,"syntology":null},{"url":"/paper/cost-contrastive-one-stage-transformer-for","slug":"cost-contrastive-one-stage-transformer-for","title":"COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking","date":"2025-04-02","arxiv_id":"2504.01321","repositories_listed":1,"syntology":null},{"url":"/paper/v-clr-view-consistent-learning-for-open-world","slug":"v-clr-view-consistent-learning-for-open-world","title":"v-CLR: View-Consistent Learning for Open-World Instance Segmentation","date":"2025-04-02","arxiv_id":"2504.01383","repositories_listed":1,"syntology":null},{"url":"/paper/mb-ores-a-multi-branch-object-reasoner-for","slug":"mb-ores-a-multi-branch-object-reasoner-for","title":"MB-ORES: A Multi-Branch Object Reasoner for Visual Grounding in Remote Sensing","date":"2025-03-31","arxiv_id":"2503.24219","repositories_listed":1,"syntology":null},{"url":"/paper/dash-detection-and-assessment-of-systematic","slug":"dash-detection-and-assessment-of-systematic","title":"DASH: Detection and Assessment of Systematic Hallucinations of VLMs","date":"2025-03-30","arxiv_id":"2503.23573","repositories_listed":1,"syntology":null},{"url":"/paper/eaglevision-object-level-attribute-multimodal","slug":"eaglevision-object-level-attribute-multimodal","title":"EagleVision: Object-level Attribute Multimodal LLM for Remote Sensing","date":"2025-03-30","arxiv_id":"2503.23330","repositories_listed":1,"syntology":null},{"url":"/paper/referdino-plus-2nd-solution-for-4th-pvuw","slug":"referdino-plus-2nd-solution-for-4th-pvuw","title":"ReferDINO-Plus: 2nd Solution for 4th PVUW MeViS Challenge at CVPR 2025","date":"2025-03-30","arxiv_id":"2503.23509","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-explicit-joint-level-interaction","slug":"efficient-explicit-joint-level-interaction","title":"Efficient Explicit Joint-level Interaction Modeling with Mamba for Text-guided HOI Generation","date":"2025-03-29","arxiv_id":"2503.23121","repositories_listed":1,"syntology":null},{"url":"/paper/agile-a-diffusion-based-attention-guided","slug":"agile-a-diffusion-based-attention-guided","title":"AGILE: A Diffusion-Based Attention-Guided Image and Label Translation for Efficient Cross-Domain Plant Trait Identification","date":"2025-03-27","arxiv_id":"2503.22019","repositories_listed":1,"syntology":null},{"url":"/paper/bootplace-bootstrapped-object-placement-with","slug":"bootplace-bootstrapped-object-placement-with","title":"BOOTPLACE: Bootstrapped Object Placement with Detection Transformers","date":"2025-03-27","arxiv_id":"2503.21991","repositories_listed":1,"syntology":null},{"url":"/paper/learning-class-prototypes-for-unified-sparse","slug":"learning-class-prototypes-for-unified-sparse","title":"Learning Class Prototypes for Unified Sparse Supervised 3D Object Detection","date":"2025-03-27","arxiv_id":"2503.21099","repositories_listed":1,"syntology":null},{"url":"/paper/camsam2-segment-anything-accurately-in","slug":"camsam2-segment-anything-accurately-in","title":"CamSAM2: Segment Anything Accurately in Camouflaged Videos","date":"2025-03-25","arxiv_id":"2503.19730","repositories_listed":1,"syntology":null},{"url":"/paper/cob-gs-clear-object-boundaries-in-3dgs","slug":"cob-gs-clear-object-boundaries-in-3dgs","title":"COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian Splitting","date":"2025-03-25","arxiv_id":"2503.19443","repositories_listed":1,"syntology":null},{"url":"/paper/dynopets-a-versatile-benchmark-for-dynamic","slug":"dynopets-a-versatile-benchmark-for-dynamic","title":"DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera Scenarios","date":"2025-03-25","arxiv_id":"2503.19625","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-object-detectors-under-real-1","slug":"benchmarking-object-detectors-under-real-1","title":"Benchmarking Object Detectors under Real-World Distribution Shifts in Satellite Imagery","date":"2025-03-24","arxiv_id":"2503.19202","repositories_listed":1,"syntology":null},{"url":"/paper/cq-dino-mitigating-gradient-dilution-via","slug":"cq-dino-mitigating-gradient-dilution-via","title":"CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection","date":"2025-03-24","arxiv_id":"2503.18430","repositories_listed":1,"syntology":null},{"url":"/paper/global-local-tree-search-for-language-guided","slug":"global-local-tree-search-for-language-guided","title":"Global-Local Tree Search in VLMs for 3D Indoor Scene Generation","date":"2025-03-24","arxiv_id":"2503.18476","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/global-local-tree-search-for-language-guided#ran","syntology_url":"https://syntology.ai/paper/2503.18476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18476"}},"official":{"repos":["dw-dengwei/treesearchgen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/4d-bench-benchmarking-multi-modal-large","slug":"4d-bench-benchmarking-multi-modal-large","title":"4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding","date":"2025-03-22","arxiv_id":"2503.17827","repositories_listed":1,"syntology":null},{"url":"/paper/goal-global-local-object-alignment-learning","slug":"goal-global-local-object-alignment-learning","title":"GOAL: Global-local Object Alignment Learning","date":"2025-03-22","arxiv_id":"2503.17782","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/goal-global-local-object-alignment-learning#ran","syntology_url":"https://syntology.ai/paper/2503.17782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.17782"}},"official":{"repos":["perceptualai-lab/goal"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/givepose-gradual-intra-class-variation","slug":"givepose-gradual-intra-class-variation","title":"GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation","date":"2025-03-19","arxiv_id":"2503.15110","repositories_listed":1,"syntology":null},{"url":"/paper/ultraflwr-an-efficient-federated-medical-and","slug":"ultraflwr-an-efficient-federated-medical-and","title":"UltraFlwr -- An Efficient Federated Medical and Surgical Object Detection Framework","date":"2025-03-19","arxiv_id":"2503.15161","repositories_listed":1,"syntology":null},{"url":"/paper/hsod-bit-v2-a-new-challenging-benchmarkfor","slug":"hsod-bit-v2-a-new-challenging-benchmarkfor","title":"HSOD-BIT-V2: A New Challenging Benchmarkfor Hyperspectral Salient Object Detection","date":"2025-03-18","arxiv_id":"2503.13906","repositories_listed":1,"syntology":null},{"url":"/paper/led-llm-enhanced-open-vocabulary-object","slug":"led-llm-enhanced-open-vocabulary-object","title":"LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data Generation","date":"2025-03-18","arxiv_id":"2503.13794","repositories_listed":1,"syntology":null},{"url":"/paper/mmr-a-large-scale-benchmark-dataset-for-multi","slug":"mmr-a-large-scale-benchmark-dataset-for-multi","title":"MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation","date":"2025-03-18","arxiv_id":"2503.13881","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/mmr-a-large-scale-benchmark-dataset-for-multi#ran","syntology_url":"https://syntology.ai/paper/2503.13881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13881"}},"official":{"repos":["jdg900/mmr"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/rethinking-end-to-end-2d-to-3d-scene","slug":"rethinking-end-to-end-2d-to-3d-scene","title":"Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting","date":"2025-03-18","arxiv_id":"2503.14029","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/rethinking-end-to-end-2d-to-3d-scene#ran","syntology_url":"https://syntology.ai/paper/2503.14029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14029"}},"official":{"repos":["runsong123/unified-lift"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/history-aware-transformation-of-reid-features","slug":"history-aware-transformation-of-reid-features","title":"History-Aware Transformation of ReID Features for Multiple Object Tracking","date":"2025-03-16","arxiv_id":"2503.12562","repositories_listed":1,"syntology":null},{"url":"/paper/4d-langsplat-4d-language-gaussian-splatting","slug":"4d-langsplat-4d-language-gaussian-splatting","title":"4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models","date":"2025-03-13","arxiv_id":"2503.10437","repositories_listed":1,"syntology":null},{"url":"/paper/moedit-on-learning-quantity-perception-for","slug":"moedit-on-learning-quantity-perception-for","title":"MoEdit: On Learning Quantity Perception for Multi-object Image Editing","date":"2025-03-13","arxiv_id":"2503.10112","repositories_listed":1,"syntology":null},{"url":"/paper/omnistvg-toward-spatio-temporal-omni-object","slug":"omnistvg-toward-spatio-temporal-omni-object","title":"OmniSTVG: Toward Spatio-Temporal Omni-Object Video Grounding","date":"2025-03-13","arxiv_id":"2503.10500","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-detect-objects-from-multi-agent","slug":"learning-to-detect-objects-from-multi-agent","title":"Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels","date":"2025-03-11","arxiv_id":"2503.08421","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 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) · 1 unverified","sample_list":"/paper/learning-to-detect-objects-from-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2503.08421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08421"}},"official":{"repos":["xmuqimingxia/dota"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-data-centric-revisit-of-pre-trained-vision","slug":"a-data-centric-revisit-of-pre-trained-vision","title":"A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning","date":"2025-03-10","arxiv_id":"2503.06960","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-data-centric-revisit-of-pre-trained-vision#ran","syntology_url":"https://syntology.ai/paper/2503.06960","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06960"}},"official":{"repos":["cvmi-lab/slotmim"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/large-model-enhanced-computational-ghost","slug":"large-model-enhanced-computational-ghost","title":"Large model enhanced computational ghost imaging","date":"2025-03-10","arxiv_id":"2503.08710","repositories_listed":1,"syntology":null},{"url":"/paper/simrod-a-simple-baseline-for-raw-object","slug":"simrod-a-simple-baseline-for-raw-object","title":"SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancements","date":"2025-03-10","arxiv_id":"2503.07101","repositories_listed":1,"syntology":null},{"url":"/paper/omnidirectional-multi-object-tracking","slug":"omnidirectional-multi-object-tracking","title":"Omnidirectional Multi-Object Tracking","date":"2025-03-06","arxiv_id":"2503.04565","repositories_listed":1,"syntology":null},{"url":"/paper/reynoldsflow-exquisite-flow-estimation-via","slug":"reynoldsflow-exquisite-flow-estimation-via","title":"ReynoldsFlow: Exquisite Flow Estimation via Reynolds Transport Theorem","date":"2025-03-06","arxiv_id":"2503.04500","repositories_listed":1,"syntology":null},{"url":"/paper/4d-radar-ground-truth-augmentation-with-lidar","slug":"4d-radar-ground-truth-augmentation-with-lidar","title":"L2RDaS: Synthesizing 4D Radar Tensors for Model Generalization via Dataset Expansion","date":"2025-03-05","arxiv_id":"2503.03637","repositories_listed":1,"syntology":null},{"url":"/paper/find-first-track-next-decoupling","slug":"find-first-track-next-decoupling","title":"Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation","date":"2025-03-05","arxiv_id":"2503.03492","repositories_listed":1,"syntology":null},{"url":"/paper/simulation-based-performance-evaluation-of-3d","slug":"simulation-based-performance-evaluation-of-3d","title":"Simulation-Based Performance Evaluation of 3D Object Detection Methods with Deep Learning for a LiDAR Point Cloud Dataset in a SOTIF-related Use Case","date":"2025-03-05","arxiv_id":"2503.03548","repositories_listed":1,"syntology":null},{"url":"/paper/dqo-map-dual-quadrics-multi-object-mapping","slug":"dqo-map-dual-quadrics-multi-object-mapping","title":"DQO-MAP: Dual Quadrics Multi-Object mapping with Gaussian Splatting","date":"2025-03-04","arxiv_id":"2503.02223","repositories_listed":1,"syntology":null},{"url":"/paper/ai-driven-relocation-tracking-in-dynamic","slug":"ai-driven-relocation-tracking-in-dynamic","title":"AI-Driven Relocation Tracking in Dynamic Kitchen Environments","date":"2025-03-03","arxiv_id":"2503.01547","repositories_listed":1,"syntology":null},{"url":"/paper/convex-hull-based-algebraic-constraint-for","slug":"convex-hull-based-algebraic-constraint-for","title":"Convex Hull-based Algebraic Constraint for Visual Quadric SLAM","date":"2025-03-03","arxiv_id":"2503.01254","repositories_listed":1,"syntology":null},{"url":"/paper/visual-rft-visual-reinforcement-fine-tuning","slug":"visual-rft-visual-reinforcement-fine-tuning","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","date":"2025-03-03","arxiv_id":"2503.01785","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/visual-rft-visual-reinforcement-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2503.01785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01785"}},"official":{"repos":["liuziyu77/visual-rft"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/modeling-fine-grained-hand-object-dynamics","slug":"modeling-fine-grained-hand-object-dynamics","title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","date":"2025-03-02","arxiv_id":"2503.00986","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/modeling-fine-grained-hand-object-dynamics#ran","syntology_url":"https://syntology.ai/paper/2503.00986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00986"}},"official":{"repos":["openrobotlab/egohod"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-markov-blanket-detection-for","slug":"dynamic-markov-blanket-detection-for","title":"Dynamic Markov Blanket Detection for Macroscopic Physics Discovery","date":"2025-02-28","arxiv_id":"2502.21217","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-hallucinations-in-large-vision-4","slug":"mitigating-hallucinations-in-large-vision-4","title":"Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow","date":"2025-02-28","arxiv_id":"2502.20750","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mitigating-hallucinations-in-large-vision-4#ran","syntology_url":"https://syntology.ai/paper/2502.20750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20750"}},"official":{"repos":["jiaqi5598/adavib"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/c-drag-chain-of-thought-driven-motion","slug":"c-drag-chain-of-thought-driven-motion","title":"C-Drag: Chain-of-Thought Driven Motion Controller for Video Generation","date":"2025-02-27","arxiv_id":"2502.19868","repositories_listed":1,"syntology":null},{"url":"/paper/clip-under-the-microscope-a-fine-grained","slug":"clip-under-the-microscope-a-fine-grained","title":"CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation","date":"2025-02-27","arxiv_id":"2502.19842","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clip-under-the-microscope-a-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2502.19842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19842"}},"official":{"repos":["clip-oscope/clip-oscope"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/intermimic-towards-universal-whole-body","slug":"intermimic-towards-universal-whole-body","title":"InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions","date":"2025-02-27","arxiv_id":"2502.20390","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/intermimic-towards-universal-whole-body#ran","syntology_url":"https://syntology.ai/paper/2502.20390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20390"}},"official":{"repos":["Sirui-Xu/InterMimic"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vector-quantized-vision-foundation-models-for","slug":"vector-quantized-vision-foundation-models-for","title":"Vector-Quantized Vision Foundation Models for Object-Centric Learning","date":"2025-02-27","arxiv_id":"2502.20263","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vector-quantized-vision-foundation-models-for#ran","syntology_url":"https://syntology.ai/paper/2502.20263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20263"}},"official":{"repos":["Genera1Z/VQ-VFM-OCL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-encoders-already-know-what-they-see","slug":"vision-encoders-already-know-what-they-see","title":"Vision-Encoders (Already) Know What They See: Mitigating Object Hallucination via Simple Fine-Grained CLIPScore","date":"2025-02-27","arxiv_id":"2502.20034","repositories_listed":1,"syntology":null},{"url":"/paper/ev-3dod-pushing-the-temporal-boundaries-of-3d","slug":"ev-3dod-pushing-the-temporal-boundaries-of-3d","title":"Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras","date":"2025-02-26","arxiv_id":"2502.19630","repositories_listed":1,"syntology":null}],"record_sha256":"2d3807056c9ed9ed3302f3423c8972b8b8cfd16be3f562a93576079b34ed7707","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}