{"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/34","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":34,"pages_in_order":285,"rows_per_page":100,"rows":[3301,3400],"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/33","next":"/method/residual-connection/papers/35","papers":[{"paper":"/paper/druggen-advancing-drug-discovery-with-large","slug":"druggen-advancing-drug-discovery-with-large","title":"DrugGen: Advancing Drug Discovery with Large Language Models and Reinforcement Learning Feedback","date":"2024-11-20","arxiv_id":"2411.14157","n_code_links":4,"syntology":null},{"paper":null,"slug":"exploring-large-language-models-for-climate","title":"Exploring Large Language Models for Climate Forecasting","date":"2024-11-20","arxiv_id":"2411.13724","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-large-language-model-for-wheat","title":"Multimodal large language model for wheat breeding: a new exploration of smart breeding","date":"2024-11-20","arxiv_id":"2411.15203","n_code_links":0,"syntology":null},{"paper":null,"slug":"multipath-mitigation-technology-integrated","title":"Multipath Mitigation Technology-integrated GNSS Direct Position Estimation Plug-in Module","date":"2024-11-20","arxiv_id":"2411.13339","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-way-to-llm-personalization-learning-to","title":"On the Way to LLM Personalization: Learning to Remember User Conversations","date":"2024-11-20","arxiv_id":"2411.13405","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantum-attention-for-vision-transformers-in","title":"Quantum Attention for Vision Transformers in High Energy Physics","date":"2024-11-20","arxiv_id":"2411.13520","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-for-domain-1","title":"Retrieval-Augmented Generation for Domain-Specific Question Answering: A Case Study on Pittsburgh and CMU","date":"2024-11-20","arxiv_id":"2411.13691","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-laws-for-online-advertisement","title":"Scaling Laws for Online Advertisement Retrieval","date":"2024-11-20","arxiv_id":"2411.13322","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impossible-test-a-2024-unsolvable-dataset","title":"The Impossible Test: A 2024 Unsolvable Dataset and A Chance for an AGI Quiz","date":"2024-11-20","arxiv_id":"2411.14486","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-with-sparse-attention-for","title":"Transformers with Sparse Attention for Granger Causality","date":"2024-11-20","arxiv_id":"2411.13264","n_code_links":0,"syntology":null},{"paper":null,"slug":"unlocking-historical-clinical-trial-data-with","title":"Unlocking Historical Clinical Trial Data with ALIGN: A Compositional Large Language Model System for Medical Coding","date":"2024-11-20","arxiv_id":"2411.13163","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-combined-encoder-and-transformer-approach","title":"A Combined Encoder and Transformer Approach for Coherent and High-Quality Text Generation","date":"2024-11-19","arxiv_id":"2411.12157","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-prior-and-learned-time","title":"Comparing Prior and Learned Time Representations in Transformer Models of Timeseries","date":"2024-11-19","arxiv_id":"2411.12476","n_code_links":0,"syntology":null},{"paper":"/paper/dlbacktrace-a-model-agnostic-explainability","slug":"dlbacktrace-a-model-agnostic-explainability","title":"DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models","date":"2024-11-19","arxiv_id":"2411.12643","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-multi-class-disease-classification","title":"Enhancing Multi-Class Disease Classification: Neoplasms, Cardiovascular, Nervous System, and Digestive Disorders Using Advanced LLMs","date":"2024-11-19","arxiv_id":"2411.12712","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-tokenizer-performance-of-large","title":"Evaluating Tokenizer Performance of Large Language Models Across Official Indian Languages","date":"2024-11-19","arxiv_id":"2411.12240","n_code_links":0,"syntology":null},{"paper":null,"slug":"faster-multi-gpu-training-with-ppll-a","title":"Faster Multi-GPU Training with PPLL: A Pipeline Parallelism Framework Leveraging Local Learning","date":"2024-11-19","arxiv_id":"2411.12780","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-virtual-reality-and-ai-tutoring","title":"Leveraging Virtual Reality and AI Tutoring for Language Learning: A Case Study of a Virtual Campus Environment with OpenAI GPT Integration with Unity 3D","date":"2024-11-19","arxiv_id":"2411.12619","n_code_links":0,"syntology":null},{"paper":"/paper/multi-grained-preference-enhanced-transformer","slug":"multi-grained-preference-enhanced-transformer","title":"Multi-Grained Preference Enhanced Transformer for Multi-Behavior Sequential Recommendation","date":"2024-11-19","arxiv_id":"2411.12179","n_code_links":1,"syntology":null},{"paper":null,"slug":"residual-vision-transformer-resvit-based-self","title":"Residual Vision Transformer (ResViT) Based Self-Supervised Learning Model for Brain Tumor Classification","date":"2024-11-19","arxiv_id":"2411.12874","n_code_links":0,"syntology":null},{"paper":null,"slug":"strengthening-fake-news-detection-leveraging","title":"Strengthening Fake News Detection: Leveraging SVM and Sophisticated Text Vectorization Techniques. Defying BERT?","date":"2024-11-19","arxiv_id":"2411.12703","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-neural-processes-kernel","title":"Transformer Neural Processes -- Kernel Regression","date":"2024-11-19","arxiv_id":"2411.12502","n_code_links":0,"syntology":null},{"paper":null,"slug":"ultra-sparse-memory-network","title":"Ultra-Sparse Memory Network","date":"2024-11-19","arxiv_id":"2411.12364","n_code_links":0,"syntology":null},{"paper":"/paper/advacheck-at-genai-detection-task-1-ai","slug":"advacheck-at-genai-detection-task-1-ai","title":"Advacheck at GenAI Detection Task 1: AI Detection Powered by Domain-Aware Multi-Tasking","date":"2024-11-18","arxiv_id":"2411.11736","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-open-source-llms-enhance-data","title":"Can Open-source LLMs Enhance Data Synthesis for Toxic Detection?: An Experimental Study","date":"2024-11-18","arxiv_id":"2411.15175","n_code_links":0,"syntology":null},{"paper":null,"slug":"chapter-7-review-of-data-driven-generative-ai","title":"Chapter 7 Review of Data-Driven Generative AI Models for Knowledge Extraction from Scientific Literature in Healthcare","date":"2024-11-18","arxiv_id":"2411.11635","n_code_links":0,"syntology":null},{"paper":"/paper/cnmbert-a-model-for-hanyu-pinyin-abbreviation","slug":"cnmbert-a-model-for-hanyu-pinyin-abbreviation","title":"CNMBERT: A Model for Converting Hanyu Pinyin Abbreviations to Chinese Characters","date":"2024-11-18","arxiv_id":"2411.11770","n_code_links":1,"syntology":null},{"paper":null,"slug":"deforhmr-vision-transformer-with-deformable","title":"DeforHMR: Vision Transformer with Deformable Cross-Attention for 3D Human Mesh Recovery","date":"2024-11-18","arxiv_id":"2411.11214","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-decision-transformer-with-diffusion","title":"Enhancing Decision Transformer with Diffusion-Based Trajectory Branch Generation","date":"2024-11-18","arxiv_id":"2411.11327","n_code_links":0,"syntology":null},{"paper":null,"slug":"fcc-fully-connected-correlation-for-few-shot","title":"FCC: Fully Connected Correlation for Few-Shot Segmentation","date":"2024-11-18","arxiv_id":"2411.11917","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-situ-melt-pool-characterization-via","title":"In-Situ Melt Pool Characterization via Thermal Imaging for Defect Detection in Directed Energy Deposition Using Vision Transformers","date":"2024-11-18","arxiv_id":"2411.12028","n_code_links":0,"syntology":null},{"paper":null,"slug":"lavin-dit-large-vision-diffusion-transformer","title":"LaVin-DiT: Large Vision Diffusion Transformer","date":"2024-11-18","arxiv_id":"2411.11505","n_code_links":0,"syntology":null},{"paper":null,"slug":"litformer-efficient-modeling-and-analysis-of","title":"LiTformer: Efficient Modeling and Analysis of High-Speed Link Transmitters Using Non-Autoregressive Transformer","date":"2024-11-18","arxiv_id":"2411.11699","n_code_links":0,"syntology":null},{"paper":"/paper/perfcodegen-improving-performance-of-llm","slug":"perfcodegen-improving-performance-of-llm","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","date":"2024-11-18","arxiv_id":"2412.03578","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["SalesforceAIResearch/perfcodegen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"popular-llms-amplify-race-and-gender","title":"Popular LLMs Amplify Race and Gender Disparities in Human Mobility","date":"2024-11-18","arxiv_id":"2411.14469","n_code_links":0,"syntology":null},{"paper":null,"slug":"st-tree-with-interpretability-for","title":"ST-Tree with Interpretability for Multivariate Time Series Classification","date":"2024-11-18","arxiv_id":"2411.11620","n_code_links":0,"syntology":null},{"paper":null,"slug":"suicide-risk-assessment-on-social-media-with","title":"Suicide Risk Assessment on Social Media with Semi-Supervised Learning","date":"2024-11-18","arxiv_id":"2411.12767","n_code_links":0,"syntology":null},{"paper":"/paper/timeformer-capturing-temporal-relationships","slug":"timeformer-capturing-temporal-relationships","title":"TimeFormer: Capturing Temporal Relationships of Deformable 3D Gaussians for Robust Reconstruction","date":"2024-11-18","arxiv_id":"2411.11941","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-student-sentiment-on-mental","title":"Understanding Student Sentiment on Mental Health Support in Colleges Using Large Language Models","date":"2024-11-18","arxiv_id":"2412.04326","n_code_links":0,"syntology":null},{"paper":"/paper/unveiling-the-inflexibility-of-adaptive","slug":"unveiling-the-inflexibility-of-adaptive","title":"Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting","date":"2024-11-18","arxiv_id":"2411.11448","n_code_links":1,"syntology":null},{"paper":"/paper/versatune-fine-tuning-multi-ability-llms","slug":"versatune-fine-tuning-multi-ability-llms","title":"VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs","date":"2024-11-18","arxiv_id":"2411.11266","n_code_links":1,"syntology":null},{"paper":"/paper/exploiting-vlm-localizability-and-semantics","slug":"exploiting-vlm-localizability-and-semantics","title":"Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection","date":"2024-11-17","arxiv_id":"2411.10922","n_code_links":1,"syntology":null},{"paper":null,"slug":"ive-enhanced-probabilistic-forecasting-of","title":"IVE: Enhanced Probabilistic Forecasting of Intraday Volume Ratio with Transformers","date":"2024-11-17","arxiv_id":"2411.10956","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-enhanced-transformer-for","title":"Knowledge-enhanced Transformer for Multivariate Long Sequence Time-series Forecasting","date":"2024-11-17","arxiv_id":"2411.11046","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-adaptive-hybrid-focal-entropy-loss","title":"A Novel Adaptive Hybrid Focal-Entropy Loss for Enhancing Diabetic Retinopathy Detection Using Convolutional Neural Networks","date":"2024-11-16","arxiv_id":"2411.10843","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-approach-to-eliminating","title":"A Novel Approach to Eliminating Hallucinations in Large Language Model-Assisted Causal Discovery","date":"2024-11-16","arxiv_id":"2411.12759","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-wearable-gait-monitoring-system-for-17-gait","title":"A Wearable Gait Monitoring System for 17 Gait Parameters Based on Computer Vision","date":"2024-11-16","arxiv_id":"2411.10739","n_code_links":0,"syntology":null},{"paper":null,"slug":"allrestorer-all-in-one-transformer-for-image","title":"AllRestorer: All-in-One Transformer for Image Restoration under Composite Degradations","date":"2024-11-16","arxiv_id":"2411.10708","n_code_links":0,"syntology":null},{"paper":"/paper/bag-of-design-choices-for-inference-of-high","slug":"bag-of-design-choices-for-inference-of-high","title":"Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer","date":"2024-11-16","arxiv_id":"2411.10781","n_code_links":1,"syntology":null},{"paper":null,"slug":"intentgpt-few-shot-intent-discovery-with","title":"IntentGPT: Few-shot Intent Discovery with Large Language Models","date":"2024-11-16","arxiv_id":"2411.10670","n_code_links":0,"syntology":null},{"paper":"/paper/metala-unified-optimal-linear-approximation","slug":"metala-unified-optimal-linear-approximation","title":"MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map","date":"2024-11-16","arxiv_id":"2411.10741","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"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":["BICLab/MetaLA"],"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/mpoxvlm-a-vision-language-model-for","slug":"mpoxvlm-a-vision-language-model-for","title":"MpoxVLM: A Vision-Language Model for Diagnosing Skin Lesions from Mpox Virus Infection","date":"2024-11-16","arxiv_id":"2411.10888","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-scale-spatial-temporal-network-for","title":"A Multi-Scale Spatial-Temporal Network for Wireless Video Transmission","date":"2024-11-15","arxiv_id":"2411.09936","n_code_links":0,"syntology":null},{"paper":null,"slug":"building-6g-radio-foundation-models-with","title":"Building 6G Radio Foundation Models with Transformer Architectures","date":"2024-11-15","arxiv_id":"2411.09996","n_code_links":0,"syntology":null},{"paper":null,"slug":"cmath-cross-modality-augmented-transformer","title":"CMATH: Cross-Modality Augmented Transformer with Hierarchical Variational Distillation for Multimodal Emotion Recognition in Conversation","date":"2024-11-15","arxiv_id":"2411.10060","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-machine-learning-7","title":"Comparative Analysis of Machine Learning Approaches for Bone Age Assessment: A Comprehensive Study on Three Distinct Models","date":"2024-11-15","arxiv_id":"2411.10345","n_code_links":0,"syntology":null},{"paper":null,"slug":"debias-clr-a-contrastive-learning-based","title":"Debias-CLR: A Contrastive Learning Based Debiasing Method for Algorithmic Fairness in Healthcare Applications","date":"2024-11-15","arxiv_id":"2411.10544","n_code_links":0,"syntology":null},{"paper":null,"slug":"dimodif-discourse-modality-information","title":"DiMoDif: Discourse Modality-information Differentiation for Audio-visual Deepfake Detection and Localization","date":"2024-11-15","arxiv_id":"2411.10193","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-prompt-formatting-have-any-impact-on-llm","title":"Does Prompt Formatting Have Any Impact on LLM Performance?","date":"2024-11-15","arxiv_id":"2411.10541","n_code_links":0,"syntology":null},{"paper":null,"slug":"evidential-federated-learning-for-skin-lesion","title":"Evidential Federated Learning for Skin Lesion Image Classification","date":"2024-11-15","arxiv_id":"2411.10071","n_code_links":0,"syntology":null},{"paper":"/paper/hysteresis-activation-function-for-efficient","slug":"hysteresis-activation-function-for-efficient","title":"Hysteresis Activation Function for Efficient Inference","date":"2024-11-15","arxiv_id":"2411.10573","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["idankdev/helu"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/information-extraction-from-clinical-notes","slug":"information-extraction-from-clinical-notes","title":"Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models?","date":"2024-11-15","arxiv_id":"2411.10020","n_code_links":1,"syntology":null},{"paper":null,"slug":"lora-litee-a-computationally-efficient","title":"LoRA-LiteE: A Computationally Efficient Framework for Chatbot Preference-Tuning","date":"2024-11-15","arxiv_id":"2411.09947","n_code_links":0,"syntology":null},{"paper":"/paper/mars-unleashing-the-power-of-variance","slug":"mars-unleashing-the-power-of-variance","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","date":"2024-11-15","arxiv_id":"2411.10438","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["AGI-Arena/MARS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"probabilistic-prior-driven-attention","title":"Probabilistic Prior Driven Attention Mechanism Based on Diffusion Model for Imaging Through Atmospheric Turbulence","date":"2024-11-15","arxiv_id":"2411.10321","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompting-and-fine-tuning-large-language","title":"Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation","date":"2024-11-15","arxiv_id":"2411.10129","n_code_links":0,"syntology":null},{"paper":"/paper/retr-multi-view-radar-detection-transformer","slug":"retr-multi-view-radar-detection-transformer","title":"RETR: Multi-View Radar Detection Transformer for Indoor Perception","date":"2024-11-15","arxiv_id":"2411.10293","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["merlresearch/radar-detection-transformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"scaling-law-for-post-training-after-model","title":"P$^2$ Law: Scaling Law for Post-Training After Model Pruning","date":"2024-11-15","arxiv_id":"2411.10272","n_code_links":0,"syntology":null},{"paper":null,"slug":"softlms-efficient-adaptive-low-rank","title":"SoftLMs: Efficient Adaptive Low-Rank Approximation of Language Models using Soft-Thresholding Mechanism","date":"2024-11-15","arxiv_id":"2411.10543","n_code_links":0,"syntology":null},{"paper":null,"slug":"take-package-as-language-anomaly-detection","title":"Take Package as Language: Anomaly Detection Using Transformer","date":"2024-11-15","arxiv_id":"2412.04473","n_code_links":0,"syntology":null},{"paper":null,"slug":"ultra-unveiling-latent-token-interpretability","title":"ULTra: Unveiling Latent Token Interpretability in Transformer Based Understanding","date":"2024-11-15","arxiv_id":"2411.12589","n_code_links":0,"syntology":null},{"paper":null,"slug":"adopting-rag-for-llm-aided-future-vehicle","title":"Adopting RAG for LLM-Aided Future Vehicle Design","date":"2024-11-14","arxiv_id":"2411.09590","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-performance-of-the-dinov2-self","title":"Assessing the Performance of the DINOv2 Self-supervised Learning Vision Transformer Model for the Segmentation of the Left Atrium from MRI Images","date":"2024-11-14","arxiv_id":"2411.09598","n_code_links":0,"syntology":null},{"paper":null,"slug":"automating-autograding-large-language-models","title":"Automating Autograding: Large Language Models as Test Suite Generators for Introductory Programming","date":"2024-11-14","arxiv_id":"2411.09261","n_code_links":0,"syntology":null},{"paper":null,"slug":"babylm-challenge-exploring-the-effect-of","title":"BabyLM Challenge: Exploring the Effect of Variation Sets on Language Model Training Efficiency","date":"2024-11-14","arxiv_id":"2411.09587","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-static-tools-evaluating-large-language","title":"Beyond Static Tools: Evaluating Large Language Models for Cryptographic Misuse Detection","date":"2024-11-14","arxiv_id":"2411.09772","n_code_links":0,"syntology":null},{"paper":null,"slug":"comprehensive-and-practical-evaluation-of","title":"Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering","date":"2024-11-14","arxiv_id":"2411.09213","n_code_links":0,"syntology":null},{"paper":null,"slug":"dscformer-a-dual-branch-network-integrating","title":"DSCformer: A Dual-Branch Network Integrating Enhanced Dynamic Snake Convolution and SegFormer for Crack Segmentation","date":"2024-11-14","arxiv_id":"2411.09371","n_code_links":0,"syntology":null},{"paper":null,"slug":"dt-jrd-deep-transformer-based-just","title":"DT-JRD: Deep Transformer based Just Recognizable Difference Prediction Model for Video Coding for Machines","date":"2024-11-14","arxiv_id":"2411.09308","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-gender-bias-in-large-language-1","title":"Evaluating Gender Bias in Large Language Models","date":"2024-11-14","arxiv_id":"2411.09826","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-vision-foundation-models-for-high","slug":"harnessing-vision-foundation-models-for-high","title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation","date":"2024-11-14","arxiv_id":"2411.09219","n_code_links":1,"syntology":null},{"paper":null,"slug":"hategpt-unleashing-gpt-3-5-turbo-to-combat","title":"HateGPT: Unleashing GPT-3.5 Turbo to Combat Hate Speech on X","date":"2024-11-14","arxiv_id":"2411.09214","n_code_links":0,"syntology":null},{"paper":"/paper/initial-nugget-evaluation-results-for-the","slug":"initial-nugget-evaluation-results-for-the","title":"Initial Nugget Evaluation Results for the TREC 2024 RAG Track with the AutoNuggetizer Framework","date":"2024-11-14","arxiv_id":"2411.09607","n_code_links":2,"syntology":null},{"paper":"/paper/learning-parameter-sharing-with-tensor","slug":"learning-parameter-sharing-with-tensor","title":"Learning Parameter Sharing with Tensor Decompositions and Sparsity","date":"2024-11-14","arxiv_id":"2411.09816","n_code_links":1,"syntology":null},{"paper":null,"slug":"local-deployment-of-large-scale-music-ai","title":"Local deployment of large-scale music AI models on commodity hardware","date":"2024-11-14","arxiv_id":"2411.09625","n_code_links":0,"syntology":null},{"paper":"/paper/mm-eval-a-hierarchical-benchmark-for-modern","slug":"mm-eval-a-hierarchical-benchmark-for-modern","title":"MM-Eval: A Hierarchical Benchmark for Modern Mongolian Evaluation in LLMs","date":"2024-11-14","arxiv_id":"2411.09492","n_code_links":1,"syntology":null},{"paper":"/paper/opengemm-a-high-utilization-gemm-accelerator","slug":"opengemm-a-high-utilization-gemm-accelerator","title":"OpenGeMM: A High-Utilization GeMM Accelerator Generator with Lightweight RISC-V Control and Tight Memory Coupling","date":"2024-11-14","arxiv_id":"2411.09543","n_code_links":1,"syntology":null},{"paper":null,"slug":"partial-multi-view-clustering-via-meta","title":"Partial Multi-View Clustering via Meta-Learning and Contrastive Feature Alignment","date":"2024-11-14","arxiv_id":"2411.09758","n_code_links":0,"syntology":null},{"paper":null,"slug":"re-parameterization-of-lightweight","title":"Re-Parameterization of Lightweight Transformer for On-Device Speech Emotion Recognition","date":"2024-11-14","arxiv_id":"2411.09339","n_code_links":0,"syntology":null},{"paper":"/paper/sag-vit-a-scale-aware-high-fidelity-patching","slug":"sag-vit-a-scale-aware-high-fidelity-patching","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","date":"2024-11-14","arxiv_id":"2411.09420","n_code_links":1,"syntology":null},{"paper":"/paper/a-large-scale-study-of-relevance-assessments","slug":"a-large-scale-study-of-relevance-assessments","title":"A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look","date":"2024-11-13","arxiv_id":"2411.08275","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-transformer-based-visual-piano","title":"A Transformer-Based Visual Piano Transcription Algorithm","date":"2024-11-13","arxiv_id":"2411.09037","n_code_links":0,"syntology":null},{"paper":null,"slug":"ad-dino-attention-dynamic-dino-for-distance","title":"AD-DINO: Attention-Dynamic DINO for Distance-Aware Embodied Reference Understanding","date":"2024-11-13","arxiv_id":"2411.08451","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyst-reports-and-stock-performance","title":"Analyst Reports and Stock Performance: Evidence from the Chinese Market","date":"2024-11-13","arxiv_id":"2411.08726","n_code_links":0,"syntology":null},{"paper":null,"slug":"camembert-2-0-a-smarter-french-language-model","title":"CamemBERT 2.0: A Smarter French Language Model Aged to Perfection","date":"2024-11-13","arxiv_id":"2411.08868","n_code_links":0,"syntology":null},{"paper":null,"slug":"continuous-gnn-based-anomaly-detection-on","title":"Continuous GNN-based Anomaly Detection on Edge using Efficient Adaptive Knowledge Graph Learning","date":"2024-11-13","arxiv_id":"2411.09072","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-world-models-with-llm-for-decision","title":"Evaluating World Models with LLM for Decision Making","date":"2024-11-13","arxiv_id":"2411.08794","n_code_links":0,"syntology":null},{"paper":null,"slug":"llmstinger-jailbreaking-llms-using-rl-fine","title":"LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs","date":"2024-11-13","arxiv_id":"2411.08862","n_code_links":0,"syntology":null},{"paper":"/paper/logllm-log-based-anomaly-detection-using","slug":"logllm-log-based-anomaly-detection-using","title":"LogLLM: Log-based Anomaly Detection Using Large Language Models","date":"2024-11-13","arxiv_id":"2411.08561","n_code_links":1,"syntology":null},{"paper":null,"slug":"oblique-bayesian-additive-regression-trees","title":"Oblique Bayesian additive regression trees","date":"2024-11-13","arxiv_id":"2411.08849","n_code_links":0,"syntology":null}],"record_sha256":"32332661e7f5bfe7bfd492a8e74f29fd89007d393b7cc6434d2cfcb5e2453d8f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}