{"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/residual-connection/papers/109","list_of":"/method/residual-connection","method":"Residual Connection","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":109,"pages_in_order":285,"rows_per_page":100,"rows":[10801,10900],"of":28401,"counts":{"archive_papers_tagged":28401,"with_a_code_link":12847,"where_syntology_ran_a_sample":3897,"not_listed_spam_title":0,"listed":28401,"listed_where_code_ran":3897,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3291,"every_run_a_failure_of_syntologys_instrument":606,"listed_with_a_run_with_no_instrument_failure":3291,"listed_every_run_a_failure_of_syntologys_instrument":606,"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/residual-connection","prev":"/method/residual-connection/papers/108","next":"/method/residual-connection/papers/110","papers":[{"paper":null,"slug":"you-only-forward-once-prediction-and","title":"You Only Forward Once: Prediction and Rationalization in A Single Forward Pass","date":"2023-11-04","arxiv_id":"2311.02344","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-benchmarking-chinese","title":"An Empirical Study of Benchmarking Chinese Aspect Sentiment Quad Prediction","date":"2023-11-03","arxiv_id":"2311.01713","n_code_links":0,"syntology":null},{"paper":"/paper/automating-governing-knowledge-commons-and","slug":"automating-governing-knowledge-commons-and","title":"Automating Governing Knowledge Commons and Contextual Integrity (GKC-CI) Privacy Policy Annotations with Large Language Models","date":"2023-11-03","arxiv_id":"2311.02192","n_code_links":1,"syntology":null},{"paper":null,"slug":"capturing-local-and-global-features-in","title":"Capturing Local and Global Features in Medical Images by Using Ensemble CNN-Transformer","date":"2023-11-03","arxiv_id":"2311.01731","n_code_links":0,"syntology":null},{"paper":null,"slug":"cosmic-data-efficient-instruction-tuning-for","title":"COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning","date":"2023-11-03","arxiv_id":"2311.02248","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-free-distillation-of-language-model-by","title":"Data-Free Distillation of Language Model by Text-to-Text Transfer","date":"2023-11-03","arxiv_id":"2311.01689","n_code_links":0,"syntology":null},{"paper":null,"slug":"depth-guided-free-space-segmentation-for-a","title":"Depth-guided Free-space Segmentation for a Mobile Robot","date":"2023-11-03","arxiv_id":"2311.01966","n_code_links":0,"syntology":null},{"paper":"/paper/dialogbench-evaluating-llms-as-human-like","slug":"dialogbench-evaluating-llms-as-human-like","title":"DialogBench: Evaluating LLMs as Human-like Dialogue Systems","date":"2023-11-03","arxiv_id":"2311.01677","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-black-box-adversarial-attacks-on","slug":"efficient-black-box-adversarial-attacks-on","title":"Efficient Black-Box Adversarial Attacks on Neural Text Detectors","date":"2023-11-03","arxiv_id":"2311.01873","n_code_links":1,"syntology":null},{"paper":null,"slug":"emergence-of-abstract-state-representations","title":"Emergence of Abstract State Representations in Embodied Sequence Modeling","date":"2023-11-03","arxiv_id":"2311.02171","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-numerical-reasoning","title":"Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data","date":"2023-11-03","arxiv_id":"2311.02216","n_code_links":0,"syntology":null},{"paper":"/paper/famesumm-investigating-and-improving","slug":"famesumm-investigating-and-improving","title":"FaMeSumm: Investigating and Improving Faithfulness of Medical Summarization","date":"2023-11-03","arxiv_id":"2311.02271","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["psunlpgroup/famesumm"],"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":"/paper/gateloop-fully-data-controlled-linear","slug":"gateloop-fully-data-controlled-linear","title":"GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling","date":"2023-11-03","arxiv_id":"2311.01927","n_code_links":3,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["tobiaskatsch/GateLoop"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/indo-lego-absa-a-multitask-generative-aspect","slug":"indo-lego-absa-a-multitask-generative-aspect","title":"Indo LEGO-ABSA: A Multitask Generative Aspect Based Sentiment Analysis for Indonesian Language","date":"2023-11-03","arxiv_id":"2311.01757","n_code_links":1,"syntology":null},{"paper":"/paper/minesegsat-an-automated-system-to-evaluate","slug":"minesegsat-an-automated-system-to-evaluate","title":"MineSegSAT: An automated system to evaluate mining disturbed area extents from Sentinel-2 imagery","date":"2023-11-03","arxiv_id":"2311.01676","n_code_links":1,"syntology":null},{"paper":"/paper/multi-scale-time-stepping-of-partial","slug":"multi-scale-time-stepping-of-partial","title":"Multi-scale Time-stepping of Partial Differential Equations with Transformers","date":"2023-11-03","arxiv_id":"2311.02225","n_code_links":1,"syntology":null},{"paper":"/paper/pptc-benchmark-evaluating-large-language","slug":"pptc-benchmark-evaluating-large-language","title":"PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion","date":"2023-11-03","arxiv_id":"2311.01767","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":13,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["gydpku/pptc"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pros-facial-omni-representation-learning-via","title":"ProS: Facial Omni-Representation Learning via Prototype-based Self-Distillation","date":"2023-11-03","arxiv_id":"2311.01929","n_code_links":0,"syntology":null},{"paper":"/paper/simplifying-transformer-blocks","slug":"simplifying-transformer-blocks","title":"Simplifying Transformer Blocks","date":"2023-11-03","arxiv_id":"2311.01906","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-potential-of-wearable-sensors-for","title":"The Potential of Wearable Sensors for Assessing Patient Acuity in Intensive Care Unit (ICU)","date":"2023-11-03","arxiv_id":"2311.02251","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-risks-of-risk-based-ai-regulation-taking","title":"The risks of risk-based AI regulation: taking liability seriously","date":"2023-11-03","arxiv_id":"2311.14684","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-unified-transformer-based-framework","title":"Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection","date":"2023-11-03","arxiv_id":"2311.01755","n_code_links":0,"syntology":null},{"paper":null,"slug":"atgnn-audio-tagging-graph-neural-network","title":"ATGNN: Audio Tagging Graph Neural Network","date":"2023-11-02","arxiv_id":"2311.01526","n_code_links":0,"syntology":null},{"paper":"/paper/better-together-enhancing-generative","slug":"better-together-enhancing-generative","title":"Better Together: Enhancing Generative Knowledge Graph Completion with Language Models and Neighborhood Information","date":"2023-11-02","arxiv_id":"2311.01326","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-double-descent-for-time-series","title":"Deep Double Descent for Time Series Forecasting: Avoiding Undertrained Models","date":"2023-11-02","arxiv_id":"2311.01442","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-knowledge-from-cnn-transformer","title":"Distilling Knowledge from CNN-Transformer Models for Enhanced Human Action Recognition","date":"2023-11-02","arxiv_id":"2311.01283","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-vision-transformer-for-accurate","title":"Efficient Vision Transformer for Accurate Traffic Sign Detection","date":"2023-11-02","arxiv_id":"2311.01429","n_code_links":0,"syntology":null},{"paper":null,"slug":"enriching-phrases-with-coupled-pixel-and","title":"Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding","date":"2023-11-02","arxiv_id":"2311.01091","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-input-towards-next-generation","title":"Generative Input: Towards Next-Generation Input Methods Paradigm","date":"2023-11-02","arxiv_id":"2311.01166","n_code_links":0,"syntology":null},{"paper":"/paper/hybrid-fusion-transformer-for-multisequence","slug":"hybrid-fusion-transformer-for-multisequence","title":"Hybrid-Fusion Transformer for Multisequence MRI","date":"2023-11-02","arxiv_id":"2311.01308","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-defect-prediction-from-unrealistic","title":"Learning Defect Prediction from Unrealistic Data","date":"2023-11-02","arxiv_id":"2311.00931","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-unsupervised-world-models-for","title":"Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion","date":"2023-11-02","arxiv_id":"2311.01017","n_code_links":0,"syntology":null},{"paper":"/paper/long-story-short-a-summarize-then-search","slug":"long-story-short-a-summarize-then-search","title":"Long Story Short: a Summarize-then-Search Method for Long Video Question Answering","date":"2023-11-02","arxiv_id":"2311.01233","n_code_links":1,"syntology":null},{"paper":"/paper/m-m3d-multi-dataset-training-and-efficient","slug":"m-m3d-multi-dataset-training-and-efficient","title":"M&M3D: Multi-Dataset Training and Efficient Network for Multi-view 3D Object Detection","date":"2023-11-02","arxiv_id":"2311.00986","n_code_links":1,"syntology":null},{"paper":null,"slug":"maaig-motion-analysis-and-instruction","title":"MAAIG: Motion Analysis And Instruction Generation","date":"2023-11-02","arxiv_id":"2311.00980","n_code_links":0,"syntology":null},{"paper":null,"slug":"measuring-five-accountable-talk-moves-to","title":"Measuring Five Accountable Talk Moves to Improve Instruction at Scale","date":"2023-11-02","arxiv_id":"2311.10749","n_code_links":0,"syntology":null},{"paper":null,"slug":"novel-view-synthesis-from-a-single-rgbd-image","title":"Novel View Synthesis from a Single RGBD Image for Indoor Scenes","date":"2023-11-02","arxiv_id":"2311.01065","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-convergence-of-encoder-only-shallow","title":"On the Convergence of Encoder-only Shallow Transformers","date":"2023-11-02","arxiv_id":"2311.01575","n_code_links":0,"syntology":null},{"paper":null,"slug":"scattering-vision-transformer-spectral-mixing","title":"Scattering Vision Transformer: Spectral Mixing Matters","date":"2023-11-02","arxiv_id":"2311.01310","n_code_links":0,"syntology":null},{"paper":null,"slug":"server-side-rescoring-of-spoken-entity","title":"Server-side Rescoring of Spoken Entity-centric Knowledge Queries for Virtual Assistants","date":"2023-11-02","arxiv_id":"2311.01398","n_code_links":0,"syntology":null},{"paper":"/paper/video2music-suitable-music-generation-from","slug":"video2music-suitable-music-generation-from","title":"Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model","date":"2023-11-02","arxiv_id":"2311.00968","n_code_links":1,"syntology":{"ran":1,"of":5,"n_ran_checked":0,"n_instrument":1,"unverified":4,"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) · 4 unverified","official":{"repos":["amaai-lab/video2music"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"1dformer-learning-1d-landmark-representations","title":"1DFormer: a Transformer Architecture Learning 1D Landmark Representations for Facial Landmark Tracking","date":"2023-11-01","arxiv_id":"2311.00241","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-spatial-temporal-transformer-based","title":"A Spatial-Temporal Transformer based Framework For Human Pose Assessment And Correction in Education Scenarios","date":"2023-11-01","arxiv_id":"2311.00401","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-improved-transformer-based-model-for","title":"An Improved Transformer-based Model for Detecting Phishing, Spam, and Ham: A Large Language Model Approach","date":"2023-11-01","arxiv_id":"2311.04913","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-reliable-judges-a","title":"Are Large Language Models Reliable Judges? A Study on the Factuality Evaluation Capabilities of LLMs","date":"2023-11-01","arxiv_id":"2311.00681","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-alignment-and-flexible-positional","title":"Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation","date":"2023-11-01","arxiv_id":"2311.00684","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-models-capture-public","title":"Can Large Language Models Capture Public Opinion about Global Warming? An Empirical Assessment of Algorithmic Fidelity and Bias","date":"2023-11-01","arxiv_id":"2311.00217","n_code_links":0,"syntology":null},{"paper":null,"slug":"continuous-training-and-fine-tuning-for","title":"Continuous Training and Fine-tuning for Domain-Specific Language Models in Medical Question Answering","date":"2023-11-01","arxiv_id":"2311.00204","n_code_links":0,"syntology":null},{"paper":"/paper/costar-improved-temporal-counterfactual","slug":"costar-improved-temporal-counterfactual","title":"COSTAR: Improved Temporal Counterfactual Estimation with Self-Supervised Learning","date":"2023-11-01","arxiv_id":"2311.00886","n_code_links":1,"syntology":null},{"paper":"/paper/data-augmentation-for-code-translation-with","slug":"data-augmentation-for-code-translation-with","title":"Data Augmentation for Code Translation with Comparable Corpora and Multiple References","date":"2023-11-01","arxiv_id":"2311.00317","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":6,"n_instrument":0,"unverified":6,"pointer_only":12,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["veronicium/cmtrans"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"detecting-visual-cues-in-the-intensive-care","title":"Detecting Visual Cues in the Intensive Care Unit and Association with Patient Clinical Status","date":"2023-11-01","arxiv_id":"2311.00565","n_code_links":0,"syntology":null},{"paper":null,"slug":"entity-alignment-method-of-science-and","title":"Entity Alignment Method of Science and Technology Patent based on Graph Convolution Network and Information Fusion","date":"2023-11-01","arxiv_id":"2311.00300","n_code_links":0,"syntology":null},{"paper":"/paper/feature-oriented-deep-learning-framework-for","slug":"feature-oriented-deep-learning-framework-for","title":"Feature-oriented Deep Learning Framework for Pulmonary Cone-beam CT (CBCT) Enhancement with Multi-task Customized Perceptual Loss","date":"2023-11-01","arxiv_id":"2311.00412","n_code_links":1,"syntology":null},{"paper":"/paper/from-text-to-structure-using-large-language","slug":"from-text-to-structure-using-large-language","title":"From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems","date":"2023-11-01","arxiv_id":"2311.04911","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-robustness-for-vision-transformer","title":"Improving Robustness for Vision Transformer with a Simple Dynamic Scanning Augmentation","date":"2023-11-01","arxiv_id":"2311.00441","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-gpt-powerful-enough-to-analyze-the","title":"Is GPT Powerful Enough to Analyze the Emotions of Memes?","date":"2023-11-01","arxiv_id":"2311.00223","n_code_links":0,"syntology":null},{"paper":null,"slug":"kronecker-factored-approximate-curvature-for","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","date":"2023-11-01","arxiv_id":"2311.00636","n_code_links":0,"syntology":null},{"paper":null,"slug":"patch-based-deep-unsupervised-image","title":"Patch-Based Deep Unsupervised Image Segmentation using Graph Cuts","date":"2023-11-01","arxiv_id":"2311.01475","n_code_links":0,"syntology":null},{"paper":null,"slug":"progressive-recurrent-network-for-shadow","title":"Progressive Recurrent Network for Shadow Removal","date":"2023-11-01","arxiv_id":"2311.00455","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-decision-transformer-via","title":"Rethinking Decision Transformer via Hierarchical Reinforcement Learning","date":"2023-11-01","arxiv_id":"2311.00267","n_code_links":0,"syntology":null},{"paper":"/paper/syntactic-inductive-bias-in-transformer","slug":"syntactic-inductive-bias-in-transformer","title":"Syntactic Inductive Bias in Transformer Language Models: Especially Helpful for Low-Resource Languages?","date":"2023-11-01","arxiv_id":"2311.00268","n_code_links":1,"syntology":null},{"paper":"/paper/the-development-of-llms-for-embodied","slug":"the-development-of-llms-for-embodied","title":"Advances in Embodied Navigation Using Large Language Models: A Survey","date":"2023-11-01","arxiv_id":"2311.00530","n_code_links":1,"syntology":null},{"paper":null,"slug":"tipping-points-of-evolving-epidemiological","title":"Tipping Points of Evolving Epidemiological Networks: Machine Learning-Assisted, Data-Driven Effective Modeling","date":"2023-11-01","arxiv_id":"2311.00797","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-lexical-simplification-with","slug":"unsupervised-lexical-simplification-with","title":"Unsupervised Lexical Simplification with Context Augmentation","date":"2023-11-01","arxiv_id":"2311.00310","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-systematic-review-for-transformer-based","title":"A Systematic Review for Transformer-based Long-term Series Forecasting","date":"2023-10-31","arxiv_id":"2310.20218","n_code_links":0,"syntology":null},{"paper":null,"slug":"addressing-limitations-of-state-aware","title":"Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving","date":"2023-10-31","arxiv_id":"2310.20650","n_code_links":0,"syntology":null},{"paper":null,"slug":"bertwich-extending-bert-s-capabilities-to","title":"BERTwich: Extending BERT's Capabilities to Model Dialectal and Noisy Text","date":"2023-10-31","arxiv_id":"2311.00116","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-the-token-barrier-chunking-and","title":"Breaking the Token Barrier: Chunking and Convolution for Efficient Long Text Classification with BERT","date":"2023-10-31","arxiv_id":"2310.20558","n_code_links":0,"syntology":null},{"paper":null,"slug":"breathing-life-into-faces-speech-driven-3d","title":"Breathing Life into Faces: Speech-driven 3D Facial Animation with Natural Head Pose and Detailed Shape","date":"2023-10-31","arxiv_id":"2310.20240","n_code_links":0,"syntology":null},{"paper":"/paper/causal-interpretation-of-self-attention-in","slug":"causal-interpretation-of-self-attention-in","title":"Causal Interpretation of Self-Attention in Pre-Trained Transformers","date":"2023-10-31","arxiv_id":"2310.20307","n_code_links":1,"syntology":null},{"paper":null,"slug":"chipnemo-domain-adapted-llms-for-chip-design","title":"ChipNeMo: Domain-Adapted LLMs for Chip Design","date":"2023-10-31","arxiv_id":"2311.00176","n_code_links":0,"syntology":null},{"paper":null,"slug":"diversified-node-sampling-based-hierarchical","title":"Diversified Node Sampling based Hierarchical Transformer Pooling for Graph Representation Learning","date":"2023-10-31","arxiv_id":"2310.20250","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-large-language-models-solve-verbal","title":"Do large language models solve verbal analogies like children do?","date":"2023-10-31","arxiv_id":"2310.20384","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-gpt-4-pass-the-turing-test","title":"Does GPT-4 pass the Turing test?","date":"2023-10-31","arxiv_id":"2310.20216","n_code_links":0,"syntology":null},{"paper":null,"slug":"eelbert-tiny-models-through-dynamic","title":"EELBERT: Tiny Models through Dynamic Embeddings","date":"2023-10-31","arxiv_id":"2310.20144","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-classification-of-student-help","title":"Efficient Classification of Student Help Requests in Programming Courses Using Large Language Models","date":"2023-10-31","arxiv_id":"2310.20105","n_code_links":0,"syntology":null},{"paper":null,"slug":"fa-team-at-the-ntcir-17-ufo-task","title":"FA Team at the NTCIR-17 UFO Task","date":"2023-10-31","arxiv_id":"2310.20322","n_code_links":0,"syntology":null},{"paper":null,"slug":"gar-meets-rag-paradigm-for-zero-shot","title":"GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval","date":"2023-10-31","arxiv_id":"2310.20158","n_code_links":0,"syntology":null},{"paper":"/paper/generate-what-you-prefer-reshaping-sequential","slug":"generate-what-you-prefer-reshaping-sequential","title":"Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion","date":"2023-10-31","arxiv_id":"2310.20453","n_code_links":1,"syntology":null},{"paper":null,"slug":"global-transformer-architecture-for-indoor","title":"Global Transformer Architecture for Indoor Room Temperature Forecasting","date":"2023-10-31","arxiv_id":"2310.20476","n_code_links":0,"syntology":null},{"paper":null,"slug":"graphtransformers-for-geospatial-forecasting","title":"GraphTransformers for Geospatial Forecasting of Hurricane Trajectories","date":"2023-10-31","arxiv_id":"2310.20174","n_code_links":0,"syntology":null},{"paper":null,"slug":"importance-estimation-with-random-gradient","title":"Importance Estimation with Random Gradient for Neural Network Pruning","date":"2023-10-31","arxiv_id":"2310.20203","n_code_links":0,"syntology":null},{"paper":"/paper/in-search-of-lost-online-test-time-adaptation","slug":"in-search-of-lost-online-test-time-adaptation","title":"In Search of Lost Online Test-time Adaptation: A Survey","date":"2023-10-31","arxiv_id":"2310.20199","n_code_links":1,"syntology":{"ran":14,"of":17,"n_ran_checked":9,"n_instrument":5,"unverified":3,"pointer_only":7,"phrase":"14 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; 5 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jo-wang/otta_vit_survey"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/increasing-the-performance-of-cognitively","slug":"increasing-the-performance-of-cognitively","title":"Increasing The Performance of Cognitively Inspired Data-Efficient Language Models via Implicit Structure Building","date":"2023-10-31","arxiv_id":"2310.20589","n_code_links":1,"syntology":null},{"paper":null,"slug":"interactive-multi-fidelity-learning-for-cost","title":"Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision","date":"2023-10-31","arxiv_id":"2310.20153","n_code_links":0,"syntology":null},{"paper":"/paper/learning-from-mistakes-makes-llm-better","slug":"learning-from-mistakes-makes-llm-better","title":"Learning From Mistakes Makes LLM Better Reasoner","date":"2023-10-31","arxiv_id":"2310.20689","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/lema"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"machine-learning-refinement-of-in-situ-images","title":"Machine learning refinement of in situ images acquired by low electron dose LC-TEM","date":"2023-10-31","arxiv_id":"2310.20279","n_code_links":0,"syntology":null},{"paper":"/paper/psycot-psychological-questionnaire-as","slug":"psycot-psychological-questionnaire-as","title":"PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection","date":"2023-10-31","arxiv_id":"2310.20256","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-serotonergic-psychedelic-n-n","title":"The serotonergic psychedelic N,N-dipropyltryptamine alters information-processing dynamics in cortical neural circuits","date":"2023-10-31","arxiv_id":"2310.20582","n_code_links":0,"syntology":null},{"paper":null,"slug":"theory-of-mind-in-large-language-models","title":"Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests","date":"2023-10-31","arxiv_id":"2310.20320","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-a-whole-slide-image-can-tell-subtype","title":"What a Whole Slide Image Can Tell? Subtype-guided Masked Transformer for Pathological Image Captioning","date":"2023-10-31","arxiv_id":"2310.20607","n_code_links":0,"syntology":null},{"paper":null,"slug":"bioinstruct-instruction-tuning-of-large","title":"BioInstruct: Instruction Tuning of Large Language Models for Biomedical Natural Language Processing","date":"2023-10-30","arxiv_id":"2310.19975","n_code_links":0,"syntology":null},{"paper":"/paper/btrec-bert-based-trajectory-recommendation","slug":"btrec-bert-based-trajectory-recommendation","title":"BTRec: BERT-Based Trajectory Recommendation for Personalized Tours","date":"2023-10-30","arxiv_id":"2310.19886","n_code_links":1,"syntology":null},{"paper":null,"slug":"building-real-world-meeting-summarization","title":"Building Real-World Meeting Summarization Systems using Large Language Models: A Practical Perspective","date":"2023-10-30","arxiv_id":"2310.19233","n_code_links":0,"syntology":null},{"paper":null,"slug":"constituency-parsing-using-llms","title":"Constituency Parsing using LLMs","date":"2023-10-30","arxiv_id":"2310.19462","n_code_links":0,"syntology":null},{"paper":"/paper/dynamics-of-instruction-tuning-each-ability","slug":"dynamics-of-instruction-tuning-each-ability","title":"Dynamics of Instruction Tuning: Each Ability of Large Language Models Has Its Own Growth Pace","date":"2023-10-30","arxiv_id":"2310.19651","n_code_links":1,"syntology":null},{"paper":"/paper/exploiting-image-related-inductive-biases-in","slug":"exploiting-image-related-inductive-biases-in","title":"AViTMP: A Tracking-Specific Transformer for Single-Branch Visual Tracking","date":"2023-10-30","arxiv_id":"2310.19542","n_code_links":1,"syntology":null},{"paper":null,"slug":"fusing-temporal-graphs-into-transformers-for","title":"Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering","date":"2023-10-30","arxiv_id":"2310.19292","n_code_links":0,"syntology":null},{"paper":"/paper/generating-medical-instructions-with","slug":"generating-medical-instructions-with","title":"Generating Medical Prescriptions with Conditional Transformer","date":"2023-10-30","arxiv_id":"2310.19727","n_code_links":1,"syntology":{"ran":10,"of":14,"n_ran_checked":7,"n_instrument":3,"unverified":4,"pointer_only":14,"phrase":"10 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["hecta-uom/label-to-text-transformer"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":4,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/grokking-tickets-lottery-tickets-accelerate","slug":"grokking-tickets-lottery-tickets-accelerate","title":"Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks","date":"2023-10-30","arxiv_id":"2310.19470","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":5,"phrase":"3 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["gouki510/grokking-tickets"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"c9921aaa7a32d4ee523e926b2579e9f8964b36186f3ffab74c5dd03707b03d86","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}