{"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/transformer/papers/12","list_of":"/method/transformer","method":"Transformer","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":12,"pages_in_order":140,"rows_per_page":100,"rows":[1101,1200],"of":13999,"counts":{"archive_papers_tagged":13999,"with_a_code_link":6572,"where_syntology_ran_a_sample":2248,"not_listed_spam_title":0,"listed":13999,"listed_where_code_ran":2248,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1919,"every_run_a_failure_of_syntologys_instrument":329,"listed_with_a_run_with_no_instrument_failure":1919,"listed_every_run_a_failure_of_syntologys_instrument":329,"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/transformer","prev":"/method/transformer/papers/11","next":"/method/transformer/papers/13","papers":[{"paper":null,"slug":"from-knowledge-generation-to-knowledge","title":"From Knowledge Generation to Knowledge Verification: Examining the BioMedical Generative Capabilities of ChatGPT","date":"2025-02-20","arxiv_id":"2502.14714","n_code_links":0,"syntology":null},{"paper":null,"slug":"full-step-dpo-self-supervised-preference","title":"Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning","date":"2025-02-20","arxiv_id":"2502.14356","n_code_links":0,"syntology":null},{"paper":null,"slug":"hardware-friendly-static-quantization-method","title":"Hardware-Friendly Static Quantization Method for Video Diffusion Transformers","date":"2025-02-20","arxiv_id":"2502.15077","n_code_links":0,"syntology":null},{"paper":null,"slug":"kitab-bench-a-comprehensive-multi-domain","title":"KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding","date":"2025-02-20","arxiv_id":"2502.14949","n_code_links":0,"syntology":null},{"paper":"/paper/multiscale-byte-language-models-a","slug":"multiscale-byte-language-models-a","title":"Multiscale Byte Language Models -- A Hierarchical Architecture for Causal Million-Length Sequence Modeling","date":"2025-02-20","arxiv_id":"2502.14553","n_code_links":1,"syntology":null},{"paper":null,"slug":"paperhelper-knowledge-based-llm-qa-paper","title":"PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant","date":"2025-02-20","arxiv_id":"2502.14271","n_code_links":0,"syntology":null},{"paper":null,"slug":"relactrl-relevance-guided-efficient-control","title":"RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers","date":"2025-02-20","arxiv_id":"2502.14377","n_code_links":0,"syntology":null},{"paper":null,"slug":"tabular-embeddings-for-tables-with-bi","title":"Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nesting","date":"2025-02-20","arxiv_id":"2502.15819","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-large-language-models-for-time","title":"Adapting Large Language Models for Time Series Modeling via a Novel Parameter-efficient Adaptation Method","date":"2025-02-19","arxiv_id":"2502.13725","n_code_links":0,"syntology":null},{"paper":"/paper/building-age-estimation-a-new-multi-modal","slug":"building-age-estimation-a-new-multi-modal","title":"Building Age Estimation: A New Multi-Modal Benchmark Dataset and Community Challenge","date":"2025-02-19","arxiv_id":"2502.13818","n_code_links":1,"syntology":null},{"paper":null,"slug":"capturing-rich-behavior-representations-a","title":"Capturing Rich Behavior Representations: A Dynamic Action Semantic-Aware Graph Transformer for Video Captioning","date":"2025-02-19","arxiv_id":"2502.13754","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-social-connections-from-finnish","title":"Extracting Social Connections from Finnish Karelian Refugee Interviews Using LLMs","date":"2025-02-19","arxiv_id":"2502.13566","n_code_links":0,"syntology":null},{"paper":null,"slug":"fairkv-balancing-per-head-kv-cache-for-fast","title":"FairKV: Balancing Per-Head KV Cache for Fast Multi-GPU Inference","date":"2025-02-19","arxiv_id":"2502.15804","n_code_links":0,"syntology":null},{"paper":null,"slug":"flextok-resampling-images-into-1d-token","title":"FlexTok: Resampling Images into 1D Token Sequences of Flexible Length","date":"2025-02-19","arxiv_id":"2502.13967","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-correctness-to-comprehension-ai-agents","title":"From Correctness to Comprehension: AI Agents for Personalized Error Diagnosis in Education","date":"2025-02-19","arxiv_id":"2502.13789","n_code_links":0,"syntology":null},{"paper":null,"slug":"inner-thinking-transformer-leveraging-dynamic","title":"Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking","date":"2025-02-19","arxiv_id":"2502.13842","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-novel-transformer-architecture-for","title":"Learning Novel Transformer Architecture for Time-series Forecasting","date":"2025-02-19","arxiv_id":"2502.13721","n_code_links":0,"syntology":null},{"paper":"/paper/medical-image-classification-with-kan","slug":"medical-image-classification-with-kan","title":"Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attention","date":"2025-02-19","arxiv_id":"2502.13693","n_code_links":1,"syntology":null},{"paper":"/paper/mom-linear-sequence-modeling-with-mixture-of","slug":"mom-linear-sequence-modeling-with-mixture-of","title":"MoM: Linear Sequence Modeling with Mixture-of-Memories","date":"2025-02-19","arxiv_id":"2502.13685","n_code_links":2,"syntology":{"ran":1,"of":4,"n_ran_checked":0,"n_instrument":1,"unverified":3,"pointer_only":0,"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) · 3 unverified","official":{"repos":["opensparsellms/linear-moe","opensparsellms/mom"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/qwen2-5-vl-technical-report","slug":"qwen2-5-vl-technical-report","title":"Qwen2.5-VL Technical Report","date":"2025-02-19","arxiv_id":"2502.13923","n_code_links":4,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"raptor-refined-approach-for-product-table","title":"RAPTOR: Refined Approach for Product Table Object Recognition","date":"2025-02-19","arxiv_id":"2502.14918","n_code_links":0,"syntology":null},{"paper":"/paper/spiking-point-transformer-for-point-cloud","slug":"spiking-point-transformer-for-point-cloud","title":"Spiking Point Transformer for Point Cloud Classification","date":"2025-02-19","arxiv_id":"2502.15811","n_code_links":1,"syntology":null},{"paper":null,"slug":"star-sql-self-taught-reasoner-for-text-to-sql","title":"STaR-SQL: Self-Taught Reasoner for Text-to-SQL","date":"2025-02-19","arxiv_id":"2502.13550","n_code_links":0,"syntology":null},{"paper":"/paper/token-adaptation-via-side-graph-convolution","slug":"token-adaptation-via-side-graph-convolution","title":"Token Adaptation via Side Graph Convolution for Temporally and Spatially Efficient Fine-tuning of 3D Point Cloud Transformers","date":"2025-02-19","arxiv_id":"2502.14142","n_code_links":1,"syntology":null},{"paper":"/paper/deepresonance-enhancing-multimodal-music","slug":"deepresonance-enhancing-multimodal-music","title":"DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning","date":"2025-02-18","arxiv_id":"2502.12623","n_code_links":0,"syntology":{"ran":7,"of":12,"n_ran_checked":4,"n_instrument":3,"unverified":5,"pointer_only":0,"phrase":"7 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; 3 where Syntology's instrument failed) · 5 unverified","official":null}},{"paper":null,"slug":"language-barriers-evaluating-cross-lingual","title":"Language Barriers: Evaluating Cross-Lingual Performance of CNN and Transformer Architectures for Speech Quality Estimation","date":"2025-02-18","arxiv_id":"2502.13004","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-are-few-shot-graders","title":"Language Models are Few-Shot Graders","date":"2025-02-18","arxiv_id":"2502.13337","n_code_links":0,"syntology":null},{"paper":null,"slug":"matterchat-a-multi-modal-llm-for-material","title":"MatterChat: A Multi-Modal LLM for Material Science","date":"2025-02-18","arxiv_id":"2502.13107","n_code_links":0,"syntology":null},{"paper":"/paper/multi-view-contrastive-network-mcnet-for","slug":"multi-view-contrastive-network-mcnet-for","title":"MVCNet: Multi-View Contrastive Network for Motor Imagery Classification","date":"2025-02-18","arxiv_id":"2502.17482","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-mamba-decoder-only-multimodal","slug":"multimodal-mamba-decoder-only-multimodal","title":"Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation","date":"2025-02-18","arxiv_id":"2502.13145","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-sleep-stage-and-sleep-apnea","title":"Multimodal Sleep Stage and Sleep Apnea Classification Using Vision Transformer: A Multitask Explainable Learning Approach","date":"2025-02-18","arxiv_id":"2502.17486","n_code_links":0,"syntology":null},{"paper":"/paper/myna-masking-based-contrastive-learning-of","slug":"myna-masking-based-contrastive-learning-of","title":"Myna: Masking-Based Contrastive Learning of Musical Representations","date":"2025-02-18","arxiv_id":"2502.12511","n_code_links":1,"syntology":null},{"paper":null,"slug":"ringformer-rethinking-recurrent-transformer","title":"RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signals","date":"2025-02-18","arxiv_id":"2502.13181","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-transformers-as-iterative","title":"Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction","date":"2025-02-18","arxiv_id":"2502.15794","n_code_links":0,"syntology":null},{"paper":"/paper/testing-prompt-engineering-methods-for","slug":"testing-prompt-engineering-methods-for","title":"Testing Prompt Engineering Methods for Knowledge Extraction from Text","date":"2025-02-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/when-segmentation-meets-hyperspectral-image","slug":"when-segmentation-meets-hyperspectral-image","title":"When Segmentation Meets Hyperspectral Image: New Paradigm for Hyperspectral Image Classification","date":"2025-02-18","arxiv_id":"2502.12541","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-bridging-eeg-signals-and","title":"A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyond","date":"2025-02-17","arxiv_id":"2502.12048","n_code_links":0,"syntology":null},{"paper":null,"slug":"cmqcic-bench-a-chinese-benchmark-for","title":"CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation","date":"2025-02-17","arxiv_id":"2502.11703","n_code_links":0,"syntology":null},{"paper":null,"slug":"gltw-joint-improved-graph-transformer-and-llm","title":"GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion","date":"2025-02-17","arxiv_id":"2502.11471","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-graph-topic-modeling-with-topic","title":"Hierarchical Graph Topic Modeling with Topic Tree-based Transformer","date":"2025-02-17","arxiv_id":"2502.11345","n_code_links":0,"syntology":null},{"paper":null,"slug":"hyperspherical-energy-transformer-with","title":"Hyperspherical Energy Transformer with Recurrent Depth","date":"2025-02-17","arxiv_id":"2502.11646","n_code_links":0,"syntology":null},{"paper":"/paper/if-attention-serves-as-a-cognitive-model-of","slug":"if-attention-serves-as-a-cognitive-model-of","title":"If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation?","date":"2025-02-17","arxiv_id":"2502.11469","n_code_links":0,"syntology":{"ran":6,"of":8,"n_ran_checked":5,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/maskgwm-a-generalizable-driving-world-model","slug":"maskgwm-a-generalizable-driving-world-model","title":"MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction","date":"2025-02-17","arxiv_id":"2502.11663","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":2,"n_instrument":2,"unverified":4,"pointer_only":1,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["sensetime-fvg/opendwm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/musc-improving-complex-instruction-following","slug":"musc-improving-complex-instruction-following","title":"MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training","date":"2025-02-17","arxiv_id":"2502.11541","n_code_links":1,"syntology":null},{"paper":null,"slug":"oct-data-is-all-you-need-how-vision","title":"OCT Data is All You Need: How Vision Transformers with and without Pre-training Benefit Imaging","date":"2025-02-17","arxiv_id":"2502.12379","n_code_links":0,"syntology":null},{"paper":null,"slug":"s2tx-cross-attention-multi-scale-state-space","title":"S2TX: Cross-Attention Multi-Scale State-Space Transformer for Time Series Forecasting","date":"2025-02-17","arxiv_id":"2502.11340","n_code_links":0,"syntology":null},{"paper":null,"slug":"smartllm-smart-contract-auditing-using-custom","title":"SmartLLM: Smart Contract Auditing using Custom Generative AI","date":"2025-02-17","arxiv_id":"2502.13167","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-geometry-of-bert","title":"The geometry of BERT","date":"2025-02-17","arxiv_id":"2502.12033","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-efficient-pre-training-exploring-fp4","title":"Towards Efficient Pre-training: Exploring FP4 Precision in Large Language Models","date":"2025-02-17","arxiv_id":"2502.11458","n_code_links":0,"syntology":null},{"paper":"/paper/towards-mechanistic-interpretability-of-graph","slug":"towards-mechanistic-interpretability-of-graph","title":"Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs","date":"2025-02-17","arxiv_id":"2502.12352","n_code_links":1,"syntology":null},{"paper":"/paper/x-il-exploring-the-design-space-of-imitation","slug":"x-il-exploring-the-design-space-of-imitation","title":"X-IL: Exploring the Design Space of Imitation Learning Policies","date":"2025-02-17","arxiv_id":"2502.12330","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":{"repos":["ALRhub/X_IL"],"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"]}}},{"paper":null,"slug":"zero-token-driven-deep-thinking-in-llms","title":"Zero Token-Driven Deep Thinking in LLMs: Unlocking the Full Potential of Existing Parameters via Cyclic Refinement","date":"2025-02-17","arxiv_id":"2502.12214","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-recurrent-vision-transformer-shows","title":"A recurrent vision transformer shows signatures of primate visual attention","date":"2025-02-16","arxiv_id":"2502.10955","n_code_links":0,"syntology":null},{"paper":null,"slug":"anyrefill-a-unified-data-efficient-framework","title":"AnyRefill: A Unified, Data-Efficient Framework for Left-Prompt-Guided Vision Tasks","date":"2025-02-16","arxiv_id":"2502.11158","n_code_links":0,"syntology":null},{"paper":"/paper/davimnet-ssms-based-domain-adaptive-object","slug":"davimnet-ssms-based-domain-adaptive-object","title":"DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object Detection","date":"2025-02-16","arxiv_id":"2502.11178","n_code_links":2,"syntology":null},{"paper":null,"slug":"empirical-evaluation-of-llms-in-predicting","title":"Empirical evaluation of LLMs in predicting fixes of Configuration bugs in Smart Home System","date":"2025-02-16","arxiv_id":"2502.10953","n_code_links":0,"syntology":null},{"paper":"/paper/exposing-numeracy-gaps-a-benchmark-to","slug":"exposing-numeracy-gaps-a-benchmark-to","title":"Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models","date":"2025-02-16","arxiv_id":"2502.11075","n_code_links":1,"syntology":null},{"paper":"/paper/knowing-your-target-target-aware-transformer","slug":"knowing-your-target-target-aware-transformer","title":"Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding","date":"2025-02-16","arxiv_id":"2502.11168","n_code_links":1,"syntology":null},{"paper":null,"slug":"performance-review-on-llm-for-solving","title":"Performance Review on LLM for solving leetcode problems","date":"2025-02-16","arxiv_id":"2502.15770","n_code_links":0,"syntology":null},{"paper":"/paper/rt-demt-a-hybrid-real-time-acupoint-detection","slug":"rt-demt-a-hybrid-real-time-acupoint-detection","title":"RT-DEMT: A hybrid real-time acupoint detection model combining mamba and transformer","date":"2025-02-16","arxiv_id":"2502.11179","n_code_links":1,"syntology":null},{"paper":null,"slug":"vendi-rag-adaptively-trading-off-diversity","title":"Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs","date":"2025-02-16","arxiv_id":"2502.11228","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-quality-assessment-of-first","title":"Automatic Quality Assessment of First Trimester Crown-Rump-Length Ultrasound Images","date":"2025-02-15","arxiv_id":"2502.10908","n_code_links":0,"syntology":null},{"paper":null,"slug":"clockdistill-consistent-location-and-context","title":"CLoCKDistill: Consistent Location-and-Context-aware Knowledge Distillation for DETRs","date":"2025-02-15","arxiv_id":"2502.10683","n_code_links":0,"syntology":null},{"paper":null,"slug":"e2cb2former-effecitve-and-explainable","title":"E2CB2former: Effecitve and Explainable Transformer for CB2 Receptor Ligand Activity Prediction","date":"2025-02-15","arxiv_id":"2502.12186","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-deepfake-image-detection-a","title":"CAE-Net: Generalized Deepfake Image Detection using Convolution and Attention Mechanisms with Spatial and Frequency Domain Features","date":"2025-02-15","arxiv_id":"2502.10682","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-action-segmentation-via-explicit","title":"Improving action segmentation via explicit similarity measurement","date":"2025-02-15","arxiv_id":"2502.10713","n_code_links":0,"syntology":null},{"paper":null,"slug":"neuroamp-a-novel-end-to-end-general-purpose","title":"NeuroAMP: A Novel End-to-end General Purpose Deep Neural Amplifier for Personalized Hearing Aids","date":"2025-02-15","arxiv_id":"2502.10822","n_code_links":0,"syntology":null},{"paper":null,"slug":"occlusion-aware-text-image-point-cloud","title":"Occlusion-aware Text-Image-Point Cloud Pretraining for Open-World 3D Object Recognition","date":"2025-02-15","arxiv_id":"2502.10674","n_code_links":0,"syntology":null},{"paper":null,"slug":"resicomp-loss-resilient-image-compression-via","title":"ResiComp: Loss-Resilient Image Compression via Dual-Functional Masked Visual Token Modeling","date":"2025-02-15","arxiv_id":"2502.10812","n_code_links":0,"syntology":null},{"paper":"/paper/skyreels-a1-expressive-portrait-animation-in","slug":"skyreels-a1-expressive-portrait-animation-in","title":"SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers","date":"2025-02-15","arxiv_id":"2502.10841","n_code_links":1,"syntology":null},{"paper":"/paper/spatio-temporal-collaborative-multiple-stream","slug":"spatio-temporal-collaborative-multiple-stream","title":"Spatio-temporal collaborative multiple-stream transformer network for liver lesion classification on multiple-sequence magnetic resonance imaging","date":"2025-02-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/the-underlying-structures-of-self-attention","slug":"the-underlying-structures-of-self-attention","title":"The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training","date":"2025-02-15","arxiv_id":"2502.10927","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-efficient-large-recommendation-model","title":"An Efficient Large Recommendation Model: Towards a Resource-Optimal Scaling Law","date":"2025-02-14","arxiv_id":"2502.09888","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-innovative-next-activity-prediction","title":"An Innovative Next Activity Prediction Approach Using Process Entropy and DAW-Transformer","date":"2025-02-14","arxiv_id":"2502.10573","n_code_links":0,"syntology":null},{"paper":"/paper/compress-image-to-patches-for-vision","slug":"compress-image-to-patches-for-vision","title":"Compress image to patches for Vision Transformer","date":"2025-02-14","arxiv_id":"2502.10120","n_code_links":1,"syntology":null},{"paper":null,"slug":"generalized-attention-flow-feature","title":"Generalized Attention Flow: Feature Attribution for Transformer Models via Maximum Flow","date":"2025-02-14","arxiv_id":"2502.15765","n_code_links":0,"syntology":null},{"paper":null,"slug":"janus-collaborative-vision-transformer-under","title":"Janus: Collaborative Vision Transformer Under Dynamic Network Environment","date":"2025-02-14","arxiv_id":"2502.10047","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-diffusion-models","slug":"large-language-diffusion-models","title":"Large Language Diffusion Models","date":"2025-02-14","arxiv_id":"2502.09992","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":1,"n_instrument":5,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/qmaxvit-unet-a-query-based-maxvit-unet-with","slug":"qmaxvit-unet-a-query-based-maxvit-unet-with","title":"QMaxViT-Unet+: A Query-Based MaxViT-Unet with Edge Enhancement for Scribble-Supervised Segmentation of Medical Images","date":"2025-02-14","arxiv_id":"2502.10294","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-hybrid-transformer-model-for-fake-news","title":"A Hybrid Transformer Model for Fake News Detection: Leveraging Bayesian Optimization and Bidirectional Recurrent Unit","date":"2025-02-13","arxiv_id":"2502.09097","n_code_links":0,"syntology":null},{"paper":"/paper/a-physics-informed-deep-learning-model-for","slug":"a-physics-informed-deep-learning-model-for","title":"A Physics-Informed Deep Learning Model for MRI Brain Motion Correction","date":"2025-02-13","arxiv_id":"2502.09296","n_code_links":1,"syntology":null},{"paper":"/paper/application-of-tabular-transformer","slug":"application-of-tabular-transformer","title":"Application of Tabular Transformer Architectures for Operating System Fingerprinting","date":"2025-02-13","arxiv_id":"2502.09084","n_code_links":1,"syntology":null},{"paper":"/paper/biologically-plausible-brain-graph","slug":"biologically-plausible-brain-graph","title":"Biologically Plausible Brain Graph Transformer","date":"2025-02-13","arxiv_id":"2502.08958","n_code_links":1,"syntology":{"ran":3,"of":8,"n_ran_checked":1,"n_instrument":2,"unverified":5,"pointer_only":8,"phrase":"3 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; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["pcyyyy/BioBGT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"can-uniform-meaning-representation-help-gpt-4","title":"Can Uniform Meaning Representation Help GPT-4 Translate from Indigenous Languages?","date":"2025-02-13","arxiv_id":"2502.08900","n_code_links":0,"syntology":null},{"paper":null,"slug":"channel-dependence-limited-lookback-windows","title":"Channel Dependence, Limited Lookback Windows, and the Simplicity of Datasets: How Biased is Time Series Forecasting?","date":"2025-02-13","arxiv_id":"2502.09683","n_code_links":0,"syntology":null},{"paper":null,"slug":"diverse-transformer-decoding-for-offline","title":"Diverse Transformer Decoding for Offline Reinforcement Learning Using Financial Algorithmic Approaches","date":"2025-02-13","arxiv_id":"2502.10473","n_code_links":0,"syntology":null},{"paper":null,"slug":"e-md3c-taming-masked-diffusion-transformers","title":"E-MD3C: Taming Masked Diffusion Transformers for Efficient Zero-Shot Object Customization","date":"2025-02-13","arxiv_id":"2502.09164","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-vision-transformer-with","title":"Hierarchical Vision Transformer with Prototypes for Interpretable Medical Image Classification","date":"2025-02-13","arxiv_id":"2502.08997","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-tcm-question-answering-through-tree","title":"Improving TCM Question Answering through Tree-Organized Self-Reflective Retrieval with LLMs","date":"2025-02-13","arxiv_id":"2502.09156","n_code_links":0,"syntology":null},{"paper":"/paper/mc2sleepnet-multi-modal-cross-masking-with","slug":"mc2sleepnet-multi-modal-cross-masking-with","title":"MC2SleepNet: Multi-modal Cross-masking with Contrastive Learning for Sleep Stage Classification","date":"2025-02-13","arxiv_id":"2502.17470","n_code_links":1,"syntology":null},{"paper":"/paper/residual-transformer-fusion-network-for-salt-1","slug":"residual-transformer-fusion-network-for-salt-1","title":"Residual Transformer Fusion Network for Salt and Pepper Image Denoising","date":"2025-02-13","arxiv_id":"2502.09000","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-evaluation-metrics-for-grammatical","slug":"rethinking-evaluation-metrics-for-grammatical","title":"Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human?","date":"2025-02-13","arxiv_id":"2502.09416","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["gotutiyan/gec-metrics"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/what-exactly-has-tabpfn-learned-to-do","slug":"what-exactly-has-tabpfn-learned-to-do","title":"What exactly has TabPFN learned to do?","date":"2025-02-13","arxiv_id":"2502.08978","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-image-quality-assessment-insights","title":"A Survey on Image Quality Assessment: Insights, Analysis, and Future Outlook","date":"2025-02-12","arxiv_id":"2502.08540","n_code_links":0,"syntology":null},{"paper":null,"slug":"coast-intelligent-time-adaptive-neural","title":"TANTE: Time-Adaptive Operator Learning via Neural Taylor Expansion","date":"2025-02-12","arxiv_id":"2502.08574","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-auto-regressive-chain-of-thought","title":"Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning","date":"2025-02-12","arxiv_id":"2502.08482","n_code_links":0,"syntology":null},{"paper":"/paper/fino1-on-the-transferability-of-reasoning","slug":"fino1-on-the-transferability-of-reasoning","title":"Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance","date":"2025-02-12","arxiv_id":"2502.08127","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["the-finai/fino1"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/hdt-hierarchical-discrete-transformer-for","slug":"hdt-hierarchical-discrete-transformer-for","title":"HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting","date":"2025-02-12","arxiv_id":"2502.08302","n_code_links":1,"syntology":null},{"paper":"/paper/hi-end-mae-hierarchical-encoder-driven-masked","slug":"hi-end-mae-hierarchical-encoder-driven-masked","title":"Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation","date":"2025-02-12","arxiv_id":"2502.08347","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-tokenized-graph-transformers-for","title":"Rethinking Tokenized Graph Transformers for Node Classification","date":"2025-02-12","arxiv_id":"2502.08101","n_code_links":0,"syntology":null}],"record_sha256":"c995f92211bce4cd4a3f2797162e10b1ff4531011c465189c027d829d5302222","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}