{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/elu-feature-map","entry":"elu_feature_map","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":14,"n_papers_ran":13,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":4,"n_samples_ran":3,"n_samples_fingerprinted":3,"n_places":16,"n_places_pointer_only":4,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":1},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2501.09688","paper":"/paper/fine-grained-image-text-correspondence-with","title":"Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation","date":"2025-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaist-cvml/part-catseg","path":"baselines/modeling/transformer/obj_part_cat_seg_model.py","file_url":"https://github.com/kaist-cvml/part-catseg/blob/HEAD/baselines/modeling/transformer/obj_part_cat_seg_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d5505bd782b4a89","mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"arxiv_id":"2409.19720","paper":"/paper/fast-a-dual-tier-few-shot-learning-paradigm","title":"FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification","date":"2024-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fukexue/FAST","path":"models/linear_attention.py","file_url":"https://github.com/fukexue/FAST/blob/HEAD/models/linear_attention.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d5505bd782b4a89","mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"arxiv_id":"2409.19720","paper":"/paper/fast-a-dual-tier-few-shot-learning-paradigm","title":"FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification","date":"2024-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fukexue/FAST","path":"FAST_CAMELYON_CLIP_Train.py","file_url":"https://github.com/fukexue/FAST/blob/HEAD/FAST_CAMELYON_CLIP_Train.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"da63f97238fd433d","mcp_get_code":{"code_sha256":"da63f97238fd433d"}},{"arxiv_id":"2409.19720","paper":"/paper/fast-a-dual-tier-few-shot-learning-paradigm","title":"FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification","date":"2024-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fukexue/FAST","path":"FAST_TCGA_RENAL_CLIP_Train.py","file_url":"https://github.com/fukexue/FAST/blob/HEAD/FAST_TCGA_RENAL_CLIP_Train.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"660bb1c1cfb15688","mcp_get_code":{"code_sha256":"660bb1c1cfb15688"}},{"arxiv_id":"2403.00592","paper":"/paper/rethinking-few-shot-3d-point-cloud-semantic","title":"Rethinking Few-shot 3D Point Cloud Semantic Segmentation","date":"2024-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhaochongAn/COSeg","path":"model/common.py","file_url":"https://github.com/ZhaochongAn/COSeg/blob/HEAD/model/common.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d5505bd782b4a89","mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"arxiv_id":"2311.15537","paper":"/paper/sed-a-simple-encoder-decoder-for-open","title":"SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation","date":"2023-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xb534/sed","path":"sed/modeling/transformer/model.py","file_url":"https://github.com/xb534/sed/blob/HEAD/sed/modeling/transformer/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0d5505bd782b4a89","mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"arxiv_id":"2303.11797","paper":"/paper/cat-seg-cost-aggregation-for-open-vocabulary","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","date":"2023-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KU-CVLAB/CAT-Seg","path":"cat_seg/modeling/transformer/model.py","file_url":"https://github.com/KU-CVLAB/CAT-Seg/blob/HEAD/cat_seg/modeling/transformer/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d5505bd782b4a89","mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"arxiv_id":"2204.10144","paper":"/paper/a-case-for-using-rotation-invariant-features","title":"A case for using rotation invariant features in state of the art feature matchers","date":"2022-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"georg-bn/se2-loftr","path":"src/loftr/loftr_module/linear_attention.py","file_url":"https://github.com/georg-bn/se2-loftr/blob/HEAD/src/loftr/loftr_module/linear_attention.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0d5505bd782b4a89","mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"arxiv_id":"2203.10981","paper":"/paper/monodtr-monocular-3d-object-detection-with","title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","date":"2022-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kuanchihhuang/monodtr","path":"visualDet3D/networks/detectors/dtr.py","file_url":"https://github.com/kuanchihhuang/monodtr/blob/HEAD/visualDet3D/networks/detectors/dtr.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d5505bd782b4a89","mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"arxiv_id":"2203.09645","paper":"/paper/matchformer-interleaving-attention-in","title":"MatchFormer: Interleaving Attention in Transformers for Feature Matching","date":"2022-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jamycheung/matchformer","path":"model/backbone/match_LA_large.py","file_url":"https://github.com/jamycheung/matchformer/blob/HEAD/model/backbone/match_LA_large.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0d5505bd782b4a89","mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"arxiv_id":"2104.00680","paper":"/paper/loftr-detector-free-local-feature-matching","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","date":"2021-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kolkir/coarse_loftr_trt","path":"loftr/loftr.py","file_url":"https://github.com/kolkir/coarse_loftr_trt/blob/HEAD/loftr/loftr.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0d5505bd782b4a89","mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"arxiv_id":"aaai_25158","paper":null,"title":"arXiv:aaai_25158","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"transvcl/TransVCL","path":"transvcl/models/linear_attention.py","file_url":"https://github.com/transvcl/TransVCL/blob/HEAD/transvcl/models/linear_attention.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d5505bd782b4a89","mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"arxiv_id":"Zhu_SkySense-O_Towards_Open-World_Remote_Sensing_Interpretation_with_Vision-Centric_Visual-Language_Modeling_CVPR_2025_paper","paper":null,"title":"arXiv:Zhu_SkySense-O_Towards_Open-World_Remote_Sensing_Interpretation_with_Vision-Centric_Visual-Language_Modeling_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zqcrafts/SkySense-O","path":"skysense_o/modeling/heads/visual_decoder.py","file_url":"https://github.com/zqcrafts/SkySense-O/blob/HEAD/skysense_o/modeling/heads/visual_decoder.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0d5505bd782b4a89","mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"arxiv_id":"Zhang_DeMatch_Deep_Decomposition_of_Motion_Field_for_Two-View_Correspondence_Learning_CVPR_2024_paper","paper":null,"title":"arXiv:Zhang_DeMatch_Deep_Decomposition_of_Motion_Field_for_Two-View_Correspondence_Learning_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SuhZhang/DeMatch","path":"core/dematch.py","file_url":"https://github.com/SuhZhang/DeMatch/blob/HEAD/core/dematch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2b010ac2650d7557","mcp_get_code":{"code_sha256":"2b010ac2650d7557"}},{"arxiv_id":"Xie_SED_A_Simple_Encoder-Decoder_for_Open-Vocabulary_Semantic_Segmentation_CVPR_2024_paper","paper":null,"title":"arXiv:Xie_SED_A_Simple_Encoder-Decoder_for_Open-Vocabulary_Semantic_Segmentation_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"xb534/SED","path":"sed/modeling/transformer/model.py","file_url":"https://github.com/xb534/SED/blob/HEAD/sed/modeling/transformer/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0d5505bd782b4a89","mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"arxiv_id":"Ren_VolRecon_Volume_Rendering_of_Signed_Ray_Distance_Functions_for_Generalizable_CVPR_2023_paper","paper":null,"title":"arXiv:Ren_VolRecon_Volume_Rendering_of_Signed_Ray_Distance_Functions_for_Generalizable_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"IVRL/VolRecon","path":"code/attention/linear_attention.py","file_url":"https://github.com/IVRL/VolRecon/blob/HEAD/code/attention/linear_attention.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d5505bd782b4a89","mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}}]}