{"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":"/method/bpe/papers/129","list_of":"/method/bpe","method":"BPE","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":129,"pages_in_order":190,"rows_per_page":100,"rows":[12801,12900],"of":18975,"counts":{"archive_papers_tagged":18975,"with_a_code_link":8675,"where_syntology_ran_a_sample":2895,"not_listed_spam_title":0,"listed":18975,"listed_where_code_ran":2895,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2443,"every_run_a_failure_of_syntologys_instrument":452,"listed_with_a_run_with_no_instrument_failure":2443,"listed_every_run_a_failure_of_syntologys_instrument":452,"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":"/method/bpe","prev":"/method/bpe/papers/128","next":"/method/bpe/papers/130","papers":[{"paper":null,"slug":"recommending-root-cause-and-mitigation-steps","title":"Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models","date":"2023-01-10","arxiv_id":"2301.03797","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-laws-for-generative-mixed-modal","title":"Scaling Laws for Generative Mixed-Modal Language Models","date":"2023-01-10","arxiv_id":"2301.03728","n_code_links":0,"syntology":null},{"paper":null,"slug":"streaming-punctuation-a-novel-punctuation","title":"Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition","date":"2023-01-10","arxiv_id":"2301.03819","n_code_links":0,"syntology":null},{"paper":"/paper/there-is-no-big-brother-or-small-brother","slug":"there-is-no-big-brother-or-small-brother","title":"There is No Big Brother or Small Brother: Knowledge Infusion in Language Models for Link Prediction and Question Answering","date":"2023-01-10","arxiv_id":"2301.04013","n_code_links":2,"syntology":null},{"paper":"/paper/unsupervised-mandarin-cantonese-machine","slug":"unsupervised-mandarin-cantonese-machine","title":"Unsupervised Mandarin-Cantonese Machine Translation","date":"2023-01-10","arxiv_id":"2301.03971","n_code_links":1,"syntology":null},{"paper":"/paper/a-study-on-the-generality-of-neural-network","slug":"a-study-on-the-generality-of-neural-network","title":"A Study on the Generality of Neural Network Structures for Monocular Depth Estimation","date":"2023-01-09","arxiv_id":"2301.03169","n_code_links":1,"syntology":null},{"paper":"/paper/advances-in-medical-image-analysis-with","slug":"advances-in-medical-image-analysis-with","title":"Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review","date":"2023-01-09","arxiv_id":"2301.03505","n_code_links":1,"syntology":null},{"paper":"/paper/an-impartial-transformer-for-story","slug":"an-impartial-transformer-for-story","title":"An Impartial Transformer for Story Visualization","date":"2023-01-09","arxiv_id":"2301.03563","n_code_links":0,"syntology":null},{"paper":"/paper/demt-deformable-mixer-transformer-for-multi","slug":"demt-deformable-mixer-transformer-for-multi","title":"DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense Prediction","date":"2023-01-09","arxiv_id":"2301.03461","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":6,"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) · 3 unverified","official":{"repos":["yangyangxu0/demt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"logically-at-factify-2023-a-multi-modal-fact","title":"Logically at Factify 2: A Multi-Modal Fact Checking System Based on Evidence Retrieval techniques and Transformer Encoder Architecture","date":"2023-01-09","arxiv_id":"2301.03127","n_code_links":0,"syntology":null},{"paper":null,"slug":"universal-multimodal-representation-for","title":"Universal Multimodal Representation for Language Understanding","date":"2023-01-09","arxiv_id":"2301.03344","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-generation-of-german-drama-texts","title":"Automatic Generation of German Drama Texts Using Fine Tuned GPT-2 Models","date":"2023-01-08","arxiv_id":"2301.03119","n_code_links":0,"syntology":null},{"paper":"/paper/deepmatcher-a-deep-transformer-based-network","slug":"deepmatcher-a-deep-transformer-based-network","title":"DeepMatcher: A Deep Transformer-based Network for Robust and Accurate Local Feature Matching","date":"2023-01-08","arxiv_id":"2301.02993","n_code_links":1,"syntology":null},{"paper":"/paper/hrtransnet-hrformer-driven-two-modality","slug":"hrtransnet-hrformer-driven-two-modality","title":"HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection","date":"2023-01-08","arxiv_id":"2301.03036","n_code_links":1,"syntology":null},{"paper":"/paper/codetalker-speech-driven-3d-facial-animation","slug":"codetalker-speech-driven-3d-facial-animation","title":"CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior","date":"2023-01-06","arxiv_id":"2301.02379","n_code_links":1,"syntology":{"ran":8,"of":13,"n_ran_checked":8,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["Doubiiu/CodeTalker"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"conditional-generation-of-paired-antibody","title":"Generative Antibody Design for Complementary Chain Pairing Sequences through Encoder-Decoder Language Model","date":"2023-01-06","arxiv_id":"2301.02748","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-compressing-activations-help-model","title":"Does compressing activations help model parallel training?","date":"2023-01-06","arxiv_id":"2301.02654","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-efficient-few-shot-adaptation-for","slug":"exploring-efficient-few-shot-adaptation-for","title":"Exploring Efficient Few-shot Adaptation for Vision Transformers","date":"2023-01-06","arxiv_id":"2301.02419","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-genre-music-transformer-composing-full","title":"Multi-Genre Music Transformer -- Composing Full Length Musical Piece","date":"2023-01-06","arxiv_id":"2301.02385","n_code_links":0,"syntology":null},{"paper":null,"slug":"systems-for-parallel-and-distributed-large","title":"Systems for Parallel and Distributed Large-Model Deep Learning Training","date":"2023-01-06","arxiv_id":"2301.02691","n_code_links":0,"syntology":null},{"paper":null,"slug":"task-aware-feature-extraction-framework-for","title":"Adaptive Pattern Extraction Multi-Task Learning for Multi-Step Conversion Estimations","date":"2023-01-06","arxiv_id":"2301.02494","n_code_links":0,"syntology":null},{"paper":"/paper/adaptively-clustering-neighbor-elements-for","slug":"adaptively-clustering-neighbor-elements-for","title":"Adaptively Clustering Neighbor Elements for Image-Text Generation","date":"2023-01-05","arxiv_id":"2301.01955","n_code_links":1,"syntology":null},{"paper":null,"slug":"cat-localization-and-identification-cascade-1","title":"CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection","date":"2023-01-05","arxiv_id":"2301.01970","n_code_links":0,"syntology":null},{"paper":"/paper/critical-perspectives-a-benchmark-revealing","slug":"critical-perspectives-a-benchmark-revealing","title":"Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI","date":"2023-01-05","arxiv_id":"2301.01874","n_code_links":1,"syntology":null},{"paper":"/paper/learning-feature-recovery-transformer-for","slug":"learning-feature-recovery-transformer-for","title":"Learning Feature Recovery Transformer for Occluded Person Re-identification","date":"2023-01-05","arxiv_id":"2301.01879","n_code_links":1,"syntology":null},{"paper":null,"slug":"scalable-communication-for-multi-agent","title":"Scalable Communication for Multi-Agent Reinforcement Learning via Transformer-Based Email Mechanism","date":"2023-01-05","arxiv_id":"2301.01919","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequentially-controlled-text-generation-1","title":"Sequentially Controlled Text Generation","date":"2023-01-05","arxiv_id":"2301.02299","n_code_links":0,"syntology":null},{"paper":"/paper/towards-autoformalization-of-mathematics-and","slug":"towards-autoformalization-of-mathematics-and","title":"Towards Autoformalization of Mathematics and Code Correctness: Experiments with Elementary Proofs","date":"2023-01-05","arxiv_id":"2301.02195","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["gc974517/autoformalization"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-long-term-time-series-forecasting","slug":"towards-long-term-time-series-forecasting","title":"Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution","date":"2023-01-05","arxiv_id":"2301.02068","n_code_links":1,"syntology":null},{"paper":"/paper/extending-source-code-pre-trained-language","slug":"extending-source-code-pre-trained-language","title":"Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries","date":"2023-01-04","arxiv_id":"2301.01701","n_code_links":1,"syntology":null},{"paper":null,"slug":"infomaxformer-maximum-entropy-transformer-for","title":"Infomaxformer: Maximum Entropy Transformer for Long Time-Series Forecasting Problem","date":"2023-01-04","arxiv_id":"2301.01772","n_code_links":0,"syntology":null},{"paper":"/paper/inpars-v2-large-language-models-as-efficient","slug":"inpars-v2-large-language-models-as-efficient","title":"InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval","date":"2023-01-04","arxiv_id":"2301.01820","n_code_links":1,"syntology":null},{"paper":"/paper/multi-aspect-explainable-inductive-relation","slug":"multi-aspect-explainable-inductive-relation","title":"Multi-Aspect Explainable Inductive Relation Prediction by Sentence Transformer","date":"2023-01-04","arxiv_id":"2301.01664","n_code_links":1,"syntology":null},{"paper":null,"slug":"semi-mae-masked-autoencoders-for-semi","title":"Semi-MAE: Masked Autoencoders for Semi-supervised Vision Transformers","date":"2023-01-04","arxiv_id":"2301.01431","n_code_links":0,"syntology":null},{"paper":"/paper/spts-v2-single-point-scene-text-spotting","slug":"spts-v2-single-point-scene-text-spotting","title":"SPTS v2: Single-Point Scene Text Spotting","date":"2023-01-04","arxiv_id":"2301.01635","n_code_links":3,"syntology":{"ran":15,"of":16,"n_ran_checked":11,"n_instrument":4,"unverified":1,"pointer_only":3,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bytedance/sptsv2","yuliang-liu/sptsv2","shannanyinxiang/spts"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/unihd-at-tsar-2022-shared-task-is-compute-all","slug":"unihd-at-tsar-2022-shared-task-is-compute-all","title":"UniHD at TSAR-2022 Shared Task: Is Compute All We Need for Lexical Simplification?","date":"2023-01-04","arxiv_id":"2301.01764","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-new-perspective-to-boost-vision-transformer","title":"A New Perspective to Boost Vision Transformer for Medical Image Classification","date":"2023-01-03","arxiv_id":"2301.00989","n_code_links":0,"syntology":null},{"paper":"/paper/cross-modal-transformer-via-coordinates","slug":"cross-modal-transformer-via-coordinates","title":"Cross Modal Transformer: Towards Fast and Robust 3D Object Detection","date":"2023-01-03","arxiv_id":"2301.01283","n_code_links":2,"syntology":null},{"paper":"/paper/large-language-models-as-corporate-lobbyists","slug":"large-language-models-as-corporate-lobbyists","title":"Large Language Models as Corporate Lobbyists","date":"2023-01-03","arxiv_id":"2301.01181","n_code_links":1,"syntology":null},{"paper":"/paper/medical-image-segmentation-via-cascaded","slug":"medical-image-segmentation-via-cascaded","title":"Medical Image Segmentation via Cascaded Attention Decoding","date":"2023-01-03","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"modeling-the-rhythm-from-lyrics-for-melody","title":"Modeling the Rhythm from Lyrics for Melody Generation of Pop Song","date":"2023-01-03","arxiv_id":"2301.01361","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-mobile-block-for-efficient-neural","slug":"rethinking-mobile-block-for-efficient-neural","title":"Rethinking Mobile Block for Efficient Attention-based Models","date":"2023-01-03","arxiv_id":"2301.01146","n_code_links":1,"syntology":null},{"paper":"/paper/tinymim-an-empirical-study-of-distilling-mim","slug":"tinymim-an-empirical-study-of-distilling-mim","title":"TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models","date":"2023-01-03","arxiv_id":"2301.01296","n_code_links":2,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"pointer_only":11,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["oliverrensu/tinymim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/betrayed-by-captions-joint-caption-grounding","slug":"betrayed-by-captions-joint-caption-grounding","title":"Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation","date":"2023-01-02","arxiv_id":"2301.00805","n_code_links":2,"syntology":null},{"paper":"/paper/maud-an-expert-annotated-legal-nlp-dataset","slug":"maud-an-expert-annotated-legal-nlp-dataset","title":"MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understanding","date":"2023-01-02","arxiv_id":"2301.00876","n_code_links":2,"syntology":null},{"paper":null,"slug":"multi-stage-spatio-temporal-aggregation","title":"Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification","date":"2023-01-02","arxiv_id":"2301.00531","n_code_links":0,"syntology":null},{"paper":"/paper/muse-text-to-image-generation-via-masked","slug":"muse-text-to-image-generation-via-masked","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","date":"2023-01-02","arxiv_id":"2301.00704","n_code_links":5,"syntology":{"ran":19,"of":21,"n_ran_checked":8,"n_instrument":11,"unverified":2,"pointer_only":11,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 5 violated, 1 with no contract checked; 11 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"transformer-based-geocoding","title":"Transformer Based Geocoding","date":"2023-01-02","arxiv_id":"2301.01170","n_code_links":0,"syntology":null},{"paper":"/paper/3dppe-3d-point-positional-encoding-for","slug":"3dppe-3d-point-positional-encoding-for","title":"3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-large-scale-robustness-analysis-of-video","title":"A Large-Scale Robustness Analysis of Video Action Recognition Models","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"aunet-learning-relations-between-action-units","title":"AUNet: Learning Relations Between Action Units for Face Forgery Detection","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-knowledge-distillation-via-monte","title":"Automated Knowledge Distillation via Monte Carlo Tree Search","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bit-shrinking-limiting-instantaneous","title":"Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-whole-slide-image-classification","title":"Boosting Whole Slide Image Classification from the Perspectives of Distribution, Correlation and Magnification","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"building-vision-transformers-with-hierarchy","title":"Building Vision Transformers with Hierarchy Aware Feature Aggregation","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bus-efficient-and-effective-vision-language-1","title":"BUS: Efficient and Effective Vision-Language Pre-Training with Bottom-Up Patch Summarization.","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"clipping-distilling-clip-based-models-with-a","title":"CLIPPING: Distilling CLIP-Based Models With a Student Base for Video-Language Retrieval","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"co-pilot-dynamic-top-down-point-cloud-with","title":"CO-PILOT: Dynamic Top-Down Point Cloud with Conditional Neighborhood Aggregation for Multi-Gigapixel Histopathology Image Representation","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/comprehensive-and-delicate-an-efficient","slug":"comprehensive-and-delicate-an-efficient","title":"Comprehensive and Delicate: An Efficient Transformer for Image Restoration","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/detr-does-not-need-multi-scale-or-locality","slug":"detr-does-not-need-multi-scale-or-locality","title":"DETR Does Not Need Multi-Scale or Locality Design","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"dkt-diverse-knowledge-transfer-transformer","title":"DKT: Diverse Knowledge Transfer Transformer for Class Incremental Learning","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dropkey-for-vision-transformer","title":"DropKey for Vision Transformer","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"few-shot-video-classification-via","title":"Few-Shot Video Classification via Representation Fusion and Promotion Learning","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/focal-network-for-image-restoration","slug":"focal-network-for-image-restoration","title":"Focal Network for Image Restoration","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"foreground-background-distribution-modeling","title":"Foreground-Background Distribution Modeling Transformer for Visual Object Tracking","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/fusing-pre-trained-language-models-with","slug":"fusing-pre-trained-language-models-with","title":"Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-human-motion-from-textual","title":"Generating Human Motion From Textual Descriptions With Discrete Representations","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/geometrized-transformer-for-self-supervised","slug":"geometrized-transformer-for-self-supervised","title":"Geometrized Transformer for Self-Supervised Homography Estimation","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/goal-guided-transformer-enabled-reinforcement","slug":"goal-guided-transformer-enabled-reinforcement","title":"Goal-Guided Transformer-Enabled Reinforcement Learning for Efficient Autonomous Navigation","date":"2023-01-01","arxiv_id":"2301.00362","n_code_links":1,"syntology":null},{"paper":null,"slug":"heat-diffusion-based-multi-scale-and","title":"Heat Diffusion Based Multi-Scale and Geometric Structure-Aware Transformer for Mesh Segmentation","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hgnet-learning-hierarchical-geometry-from","title":"HGNet: Learning Hierarchical Geometry From Points, Edges, and Surfaces","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hsr-diff-hyperspectral-image-super-resolution-1","title":"HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"image-to-tree-with-recursive-prompting","title":"Image To Tree with Recursive Prompting","date":"2023-01-01","arxiv_id":"2301.00447","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-word-segmentation-necessary-for-vietnamese","title":"Is word segmentation necessary for Vietnamese sentiment classification?","date":"2023-01-01","arxiv_id":"2301.00418","n_code_links":0,"syntology":null},{"paper":"/paper/lape-layer-adaptive-position-embedding-for","slug":"lape-layer-adaptive-position-embedding-for","title":"LaPE: Layer-adaptive Position Embedding for Vision Transformers with Independent Layer Normalization","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-long-range-information-with-dual","title":"Learning Long-Range Information with Dual-Scale Transformers for Indoor Scene Completion","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lite-detr-an-interleaved-multi-scale-encoder-1","title":"Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lnpl-mil-learning-from-noisy-pseudo-labels","title":"LNPL-MIL: Learning from Noisy Pseudo Labels for Promoting Multiple Instance Learning in Whole Slide Image","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/masked-auto-encoders-meet-generative","slug":"masked-auto-encoders-meet-generative","title":"Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"msra-sr-image-super-resolution-transformer","title":"MSRA-SR: Image Super-resolution Transformer with Multi-scale Shared Representation Acquisition","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/peal-prior-embedded-explicit-attention","slug":"peal-prior-embedded-explicit-attention","title":"PEAL: Prior-Embedded Explicit Attention Learning for Low-Overlap Point Cloud Registration","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/pointclustering-unsupervised-point-cloud-pre","slug":"pointclustering-unsupervised-point-cloud-pre","title":"PointClustering: Unsupervised Point Cloud Pre-Training Using Transformation Invariance in Clustering","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"pointlistnet-deep-learning-on-3d-point-lists","title":"PointListNet: Deep Learning on 3D Point Lists","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"polarized-color-image-denoising","title":"Polarized Color Image Denoising","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"promptcap-prompt-guided-image-captioning-for","title":"PromptCap: Prompt-Guided Image Captioning for VQA with GPT-3","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/query-refinement-transformer-for-3d-instance","slug":"query-refinement-transformer-for-3d-instance","title":"Query Refinement Transformer for 3D Instance Segmentation","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-point-cloud-registration-as","slug":"rethinking-point-cloud-registration-as","title":"Rethinking Point Cloud Registration as Masking and Reconstruction","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/segment-every-reference-object-in-spatial-and","slug":"segment-every-reference-object-in-spatial-and","title":"Segment Every Reference Object in Spatial and Temporal Spaces","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"semicvt-semi-supervised-convolutional-vision","title":"SemiCVT: Semi-Supervised Convolutional Vision Transformer for Semantic Segmentation","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"single-image-deblurring-with-row-dependent","title":"Single Image Deblurring with Row-dependent Blur Magnitude","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/skeletr-towards-skeleton-based-action","slug":"skeletr-towards-skeleton-based-action","title":"SkeleTR: Towards Skeleton-based Action Recognition in the Wild","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/skit-a-fast-key-information-video-transformer","slug":"skit-a-fast-key-information-video-transformer","title":"SKiT: a Fast Key Information Video Transformer for Online Surgical Phase Recognition","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"sparse-multi-modal-graph-transformer-with","title":"Sparse Multi-Modal Graph Transformer With Shared-Context Processing for Representation Learning of Giga-Pixel Images","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/swinlstm-improving-spatiotemporal-prediction-1","slug":"swinlstm-improving-spatiotemporal-prediction-1","title":"SwinLSTM: Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/thinking-image-color-aesthetics-assessment","slug":"thinking-image-color-aesthetics-assessment","title":"Thinking Image Color Aesthetics Assessment: Models, Datasets and Benchmarks","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/tokenhpe-learning-orientation-tokens-for","slug":"tokenhpe-learning-orientation-tokens-for","title":"TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"translating-images-to-road-network-a-non","title":"Translating Images to Road Network: A Non-Autoregressive Sequence-to-Sequence Approach","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/uni-3d-a-universal-model-for-panoptic-3d","slug":"uni-3d-a-universal-model-for-panoptic-3d","title":"Uni-3D: A Universal Model for Panoptic 3D Scene Reconstruction","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"weakly-supervised-referring-image","title":"Weakly Supervised Referring Image Segmentation with Intra-Chunk and Inter-Chunk Consistency","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-rotation-invariance-with-point","title":"Rethinking Rotation Invariance with Point Cloud Registration","date":"2022-12-31","arxiv_id":"2301.00149","n_code_links":0,"syntology":null}],"record_sha256":"682e0f75a7b5a8f5e541f5b526a973f7a55fdec029faccfaf4df24a083dc0f65","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}