{"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/27","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":27,"pages_in_order":285,"rows_per_page":100,"rows":[2601,2700],"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/26","next":"/method/residual-connection/papers/28","papers":[{"paper":null,"slug":"position-information-emerges-in-causal","title":"Position Information Emerges in Causal Transformers Without Positional Encodings via Similarity of Nearby Embeddings","date":"2024-12-30","arxiv_id":"2501.00073","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-classification-neural-networks-vs","title":"Text Classification: Neural Networks VS Machine Learning Models VS Pre-trained Models","date":"2024-12-30","arxiv_id":"2412.21022","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-performance-of-advanced-nlp","title":"Comparative Performance of Advanced NLP Models and LLMs in Multilingual Geo-Entity Detection","date":"2024-12-29","arxiv_id":"2412.20414","n_code_links":0,"syntology":null},{"paper":"/paper/electra-and-gpt-4o-cost-effective-partners","slug":"electra-and-gpt-4o-cost-effective-partners","title":"ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis","date":"2024-12-29","arxiv_id":"2501.00062","n_code_links":1,"syntology":null},{"paper":"/paper/freqmixformerv2-lightweight-frequency-aware","slug":"freqmixformerv2-lightweight-frequency-aware","title":"FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition","date":"2024-12-29","arxiv_id":"2412.20621","n_code_links":1,"syntology":null},{"paper":null,"slug":"matey-multiscale-adaptive-foundation-models","title":"MATEY: multiscale adaptive foundation models for spatiotemporal physical systems","date":"2024-12-29","arxiv_id":"2412.20601","n_code_links":0,"syntology":null},{"paper":null,"slug":"nlp-based-regulatory-compliance-using-gpt-4-0","title":"NLP-based Regulatory Compliance -- Using GPT 4.0 to Decode Regulatory Documents","date":"2024-12-29","arxiv_id":"2412.20602","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-adversarial-robustness-of-language-models","title":"On Adversarial Robustness of Language Models in Transfer Learning","date":"2024-12-29","arxiv_id":"2501.00066","n_code_links":0,"syntology":null},{"paper":"/paper/open-sora-democratizing-efficient-video","slug":"open-sora-democratizing-efficient-video","title":"Open-Sora: Democratizing Efficient Video Production for All","date":"2024-12-29","arxiv_id":"2412.20404","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["hpcaitech/open-sora"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/understanding-the-impact-of-confidence-in","slug":"understanding-the-impact-of-confidence-in","title":"Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical Domain","date":"2024-12-29","arxiv_id":"2412.20309","n_code_links":1,"syntology":null},{"paper":"/paper/a-fuzzy-rank-based-ensemble-of-cnn-models-for-1","slug":"a-fuzzy-rank-based-ensemble-of-cnn-models-for-1","title":"A fuzzy rank-based ensemble of CNN models for MRI segmentation","date":"2024-12-28","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-robustness-for-deep-learning","title":"Adversarial Robustness for Deep Learning-based Wildfire Prediction Models","date":"2024-12-28","arxiv_id":"2412.20006","n_code_links":0,"syntology":null},{"paper":null,"slug":"ddd-gendt-dynamic-data-driven-generative","title":"DDD-GenDT: Dynamic Data-driven Generative Digital Twin Framework","date":"2024-12-28","arxiv_id":"2501.00051","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilled-transformers-with-locally-enhanced","title":"Distilled Transformers with Locally Enhanced Global Representations for Face Forgery Detection","date":"2024-12-28","arxiv_id":"2412.20156","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-multi-agent-collaboration-with-tool","title":"Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering","date":"2024-12-28","arxiv_id":"2412.20145","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-transfer-learning-for-medical-image","title":"Enhancing Transfer Learning for Medical Image Classification with SMOTE: A Comparative Study","date":"2024-12-28","arxiv_id":"2412.20235","n_code_links":0,"syntology":null},{"paper":null,"slug":"real-time-calibration-model-for-low-cost","title":"Real-time Calibration Model for Low-cost Sensor in Fine-grained Time series","date":"2024-12-28","arxiv_id":"2412.20170","n_code_links":0,"syntology":null},{"paper":"/paper/segkan-high-resolution-medical-image","slug":"segkan-high-resolution-medical-image","title":"SegKAN: High-Resolution Medical Image Segmentation with Long-Distance Dependencies","date":"2024-12-28","arxiv_id":"2412.19990","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-ideal-temporal-graph-neural-networks","title":"Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours","date":"2024-12-28","arxiv_id":"2412.20256","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-contrastive-meta-learning","title":"Transformer-Based Contrastive Meta-Learning For Low-Resource Generalizable Activity Recognition","date":"2024-12-28","arxiv_id":"2412.20290","n_code_links":0,"syntology":null},{"paper":"/paper/velora-a-low-rank-adaptation-approach-for","slug":"velora-a-low-rank-adaptation-approach-for","title":"VELoRA: A Low-Rank Adaptation Approach for Efficient RGB-Event based Recognition","date":"2024-12-28","arxiv_id":"2412.20064","n_code_links":1,"syntology":null},{"paper":"/paper/vistabnet-adapting-vision-transformers-for","slug":"vistabnet-adapting-vision-transformers-for","title":"VisTabNet: Adapting Vision Transformers for Tabular Data","date":"2024-12-28","arxiv_id":"2501.00057","n_code_links":1,"syntology":null},{"paper":"/paper/yad-leveraging-t5-for-improved-automatic","slug":"yad-leveraging-t5-for-improved-automatic","title":"YAD: Leveraging T5 for Improved Automatic Diacritization of Yorùbá Text","date":"2024-12-28","arxiv_id":"2412.20218","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-text-classification-methods-for","title":"Assessing Text Classification Methods for Cyberbullying Detection on Social Media Platforms","date":"2024-12-27","arxiv_id":"2412.19928","n_code_links":0,"syntology":null},{"paper":"/paper/drivingworld-constructingworld-model-for","slug":"drivingworld-constructingworld-model-for","title":"DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT","date":"2024-12-27","arxiv_id":"2412.19505","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yvanyin/drivingworld"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"feature-alignment-based-knowledge","title":"Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models","date":"2024-12-27","arxiv_id":"2412.19449","n_code_links":0,"syntology":null},{"paper":"/paper/generative-pretrained-embedding-and","slug":"generative-pretrained-embedding-and","title":"Generative Pretrained Embedding and Hierarchical Irregular Time Series Representation for Daily Living Activity Recognition","date":"2024-12-27","arxiv_id":"2412.19732","n_code_links":1,"syntology":null},{"paper":"/paper/gradient-weight-normalized-low-rank","slug":"gradient-weight-normalized-low-rank","title":"Gradient Weight-normalized Low-rank Projection for Efficient LLM Training","date":"2024-12-27","arxiv_id":"2412.19616","n_code_links":1,"syntology":null},{"paper":null,"slug":"hidformer-transformer-style-neural-network-in","title":"Hidformer: Transformer-Style Neural Network in Stock Price Forecasting","date":"2024-12-27","arxiv_id":"2412.19932","n_code_links":0,"syntology":null},{"paper":"/paper/long-context-vs-rag-for-llms-an-evaluation","slug":"long-context-vs-rag-for-llms-an-evaluation","title":"Long Context vs. RAG for LLMs: An Evaluation and Revisits","date":"2024-12-27","arxiv_id":"2501.01880","n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-local-global-dependencies-for","slug":"optimizing-local-global-dependencies-for","title":"Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimation","date":"2024-12-27","arxiv_id":"2412.19676","n_code_links":1,"syntology":null},{"paper":null,"slug":"residual-feature-reutilization-inception","title":"Residual Feature-Reutilization Inception Network for Image Classification","date":"2024-12-27","arxiv_id":"2412.19433","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-pca-for-time-series-reduction-in","slug":"revisiting-pca-for-time-series-reduction-in","title":"Revisiting PCA for time series reduction in temporal dimension","date":"2024-12-27","arxiv_id":"2412.19423","n_code_links":1,"syntology":null},{"paper":null,"slug":"text2insight-transform-natural-language-text","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","date":"2024-12-27","arxiv_id":"2412.19718","n_code_links":0,"syntology":null},{"paper":"/paper/toward-adaptive-reasoning-in-large-language-1","slug":"toward-adaptive-reasoning-in-large-language-1","title":"Toward Adaptive Reasoning in Large Language Models with Thought Rollback","date":"2024-12-27","arxiv_id":"2412.19707","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["iQua/llmpebase"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/context-aware-deep-learning-for-multi-modal","slug":"context-aware-deep-learning-for-multi-modal","title":"Context-Aware Deep Learning for Multi Modal Depression Detection","date":"2024-12-26","arxiv_id":"2412.19209","n_code_links":1,"syntology":null},{"paper":"/paper/dapointr-domain-adaptive-point-transformer","slug":"dapointr-domain-adaptive-point-transformer","title":"DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion","date":"2024-12-26","arxiv_id":"2412.19062","n_code_links":1,"syntology":null},{"paper":null,"slug":"dual-channel-multi-attention-in-vit-for","title":"Dual Channel Multi-Attention in ViT for Biometric Authentication using Forehead Subcutaneous Vein Pattern and Periocular Pattern","date":"2024-12-26","arxiv_id":"2412.19160","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-convolutional-neural-networks-for","title":"Evaluating Convolutional Neural Networks for COVID-19 classification in chest X-ray images","date":"2024-12-26","arxiv_id":"2412.19362","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-the-network-traffic-classification","title":"Improving the network traffic classification using the Packet Vision approach","date":"2024-12-26","arxiv_id":"2412.19360","n_code_links":0,"syntology":null},{"paper":null,"slug":"indonesian-english-code-switching-speech","title":"Indonesian-English Code-Switching Speech Synthesizer Utilizing Multilingual STEN-TTS and Bert LID","date":"2024-12-26","arxiv_id":"2412.19043","n_code_links":0,"syntology":null},{"paper":"/paper/medec-a-benchmark-for-medical-error-detection","slug":"medec-a-benchmark-for-medical-error-detection","title":"MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes","date":"2024-12-26","arxiv_id":"2412.19260","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-expressiveness-and-length","slug":"on-the-expressiveness-and-length","title":"On the Expressiveness and Length Generalization of Selective State-Space Models on Regular Languages","date":"2024-12-26","arxiv_id":"2412.19350","n_code_links":1,"syntology":null},{"paper":"/paper/rag-with-differential-privacy","slug":"rag-with-differential-privacy","title":"RAG with Differential Privacy","date":"2024-12-26","arxiv_id":"2412.19291","n_code_links":1,"syntology":null},{"paper":"/paper/reversed-in-time-a-novel-temporal-emphasized","slug":"reversed-in-time-a-novel-temporal-emphasized","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","date":"2024-12-26","arxiv_id":"2412.19178","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-trading-with-large-language-models","title":"Sentiment trading with large language models","date":"2024-12-26","arxiv_id":"2412.19245","n_code_links":0,"syntology":null},{"paper":"/paper/spectralkd-understanding-and-optimizing","slug":"spectralkd-understanding-and-optimizing","title":"SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral Analysis","date":"2024-12-26","arxiv_id":"2412.19055","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-based-wireless-capsule-endoscopy","slug":"transformer-based-wireless-capsule-endoscopy","title":"Transformer-Based Wireless Capsule Endoscopy Bleeding Tissue Detection and Classification","date":"2024-12-26","arxiv_id":"2412.19218","n_code_links":1,"syntology":null},{"paper":null,"slug":"adopting-trustworthy-ai-for-sleep-disorder","title":"Adopting Trustworthy AI for Sleep Disorder Prediction: Deep Time Series Analysis with Temporal Attention Mechanism and Counterfactual Explanations","date":"2024-12-25","arxiv_id":"2412.18971","n_code_links":0,"syntology":null},{"paper":"/paper/dcis-efficient-length-extrapolation-of-llms","slug":"dcis-efficient-length-extrapolation-of-llms","title":"DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor Search","date":"2024-12-25","arxiv_id":"2412.18811","n_code_links":1,"syntology":null},{"paper":"/paper/distortion-aware-adversarial-attacks-on","slug":"distortion-aware-adversarial-attacks-on","title":"Distortion-Aware Adversarial Attacks on Bounding Boxes of Object Detectors","date":"2024-12-25","arxiv_id":"2412.18815","n_code_links":1,"syntology":null},{"paper":null,"slug":"ec-diffuser-multi-object-manipulation-via","title":"EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation","date":"2024-12-25","arxiv_id":"2412.18907","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-adversarial-robustness-of-3","title":"Evaluating the Adversarial Robustness of Detection Transformers","date":"2024-12-25","arxiv_id":"2412.18718","n_code_links":0,"syntology":null},{"paper":null,"slug":"hand-hierarchical-attention-network-for-multi","title":"HAND: Hierarchical Attention Network for Multi-Scale Handwritten Document Recognition and Layout Analysis","date":"2024-12-25","arxiv_id":"2412.18981","n_code_links":0,"syntology":null},{"paper":null,"slug":"injecting-bias-into-text-classification","title":"Injecting Bias into Text Classification Models using Backdoor Attacks","date":"2024-12-25","arxiv_id":"2412.18975","n_code_links":0,"syntology":null},{"paper":null,"slug":"ister-inverted-seasonal-trend-decomposition","title":"Ister: Inverted Seasonal-Trend Decomposition Transformer for Explainable Multivariate Time Series Forecasting","date":"2024-12-25","arxiv_id":"2412.18798","n_code_links":0,"syntology":null},{"paper":"/paper/mtcae-dfer-multi-task-cascaded-autoencoder","slug":"mtcae-dfer-multi-task-cascaded-autoencoder","title":"MTCAE-DFER: Multi-Task Cascaded Autoencoder for Dynamic Facial Expression Recognition","date":"2024-12-25","arxiv_id":"2412.18988","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimizing-large-language-models-with-an","title":"Optimizing Large Language Models with an Enhanced LoRA Fine-Tuning Algorithm for Efficiency and Robustness in NLP Tasks","date":"2024-12-25","arxiv_id":"2412.18729","n_code_links":0,"syntology":null},{"paper":null,"slug":"position-aware-graph-transformer-for","title":"Position-aware Graph Transformer for Recommendation","date":"2024-12-25","arxiv_id":"2412.18731","n_code_links":0,"syntology":null},{"paper":null,"slug":"resource-efficient-transformer-architecture","title":"Resource-Efficient Transformer Architecture: Optimizing Memory and Execution Time for Real-Time Applications","date":"2024-12-25","arxiv_id":"2501.00042","n_code_links":0,"syntology":null},{"paper":null,"slug":"saflite-fuzzing-autonomous-systems-via-large","title":"SAFLITE: Fuzzing Autonomous Systems via Large Language Models","date":"2024-12-25","arxiv_id":"2412.18727","n_code_links":0,"syntology":null},{"paper":null,"slug":"unic-adapter-unified-image-instruction","title":"UNIC-Adapter: Unified Image-instruction Adapter with Multi-modal Transformer for Image Generation","date":"2024-12-25","arxiv_id":"2412.18928","n_code_links":0,"syntology":null},{"paper":null,"slug":"unified-local-and-global-attention","title":"Unified Local and Global Attention Interaction Modeling for Vision Transformers","date":"2024-12-25","arxiv_id":"2412.18778","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-for-automated","title":"Using Large Language Models for Automated Grading of Student Writing about Science","date":"2024-12-25","arxiv_id":"2412.18719","n_code_links":0,"syntology":null},{"paper":null,"slug":"whose-morality-do-they-speak-unraveling","title":"Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Models","date":"2024-12-25","arxiv_id":"2412.18863","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-explainability-in-neural-machine","title":"Advancing Explainability in Neural Machine Translation: Analytical Metrics for Attention and Alignment Consistency","date":"2024-12-24","arxiv_id":"2412.18669","n_code_links":0,"syntology":null},{"paper":null,"slug":"autosculpt-a-pattern-based-model-auto-pruning","title":"AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learning","date":"2024-12-24","arxiv_id":"2412.18091","n_code_links":0,"syntology":null},{"paper":"/paper/comprehensive-assessment-of-bert-based","slug":"comprehensive-assessment-of-bert-based","title":"Comprehensive Assessment of BERT-Based Methods for Predicting Antimicrobial Peptides","date":"2024-12-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/decentralized-intelligence-in-gamefi-embodied","slug":"decentralized-intelligence-in-gamefi-embodied","title":"Decentralized Intelligence in GameFi: Embodied AI Agents and the Convergence of DeFi and Virtual Ecosystems","date":"2024-12-24","arxiv_id":"2412.18601","n_code_links":1,"syntology":null},{"paper":"/paper/ditctrl-exploring-attention-control-in-multi","slug":"ditctrl-exploring-attention-control-in-multi","title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation","date":"2024-12-24","arxiv_id":"2412.18597","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["tencentarc/ditctrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"do-language-models-understand-the-cognitive","title":"Do Language Models Understand the Cognitive Tasks Given to Them? Investigations with the N-Back Paradigm","date":"2024-12-24","arxiv_id":"2412.18120","n_code_links":0,"syntology":null},{"paper":"/paper/ervd-an-efficient-and-robust-vit-based","slug":"ervd-an-efficient-and-robust-vit-based","title":"ERVD: An Efficient and Robust ViT-Based Distillation Framework for Remote Sensing Image Retrieval","date":"2024-12-24","arxiv_id":"2412.18136","n_code_links":1,"syntology":null},{"paper":null,"slug":"evopat-a-multi-llm-based-patents","title":"EvoPat: A Multi-LLM-based Patents Summarization and Analysis Agent","date":"2024-12-24","arxiv_id":"2412.18100","n_code_links":0,"syntology":null},{"paper":null,"slug":"gear-graph-enhanced-agent-for-retrieval","title":"GeAR: Graph-enhanced Agent for Retrieval-augmented Generation","date":"2024-12-24","arxiv_id":"2412.18431","n_code_links":0,"syntology":null},{"paper":null,"slug":"htr-jand-handwritten-text-recognition-with","title":"HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge Distillation","date":"2024-12-24","arxiv_id":"2412.18524","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-factuality-with-explicit-working","title":"Improving Factuality with Explicit Working Memory","date":"2024-12-24","arxiv_id":"2412.18069","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-convolutional-neural-network","title":"Leveraging Convolutional Neural Network-Transformer Synergy for Predictive Modeling in Risk-Based Applications","date":"2024-12-24","arxiv_id":"2412.18222","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-deep-learning-with-multi-head","title":"Leveraging Deep Learning with Multi-Head Attention for Accurate Extraction of Medicine from Handwritten Prescriptions","date":"2024-12-24","arxiv_id":"2412.18199","n_code_links":0,"syntology":null},{"paper":null,"slug":"molly-making-large-language-model-agents","title":"Molly: Making Large Language Model Agents Solve Python Problem More Logically","date":"2024-12-24","arxiv_id":"2412.18093","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-mathematical-reasoning-advancing","slug":"multilingual-mathematical-reasoning-advancing","title":"Multilingual Mathematical Reasoning: Advancing Open-Source LLMs in Hindi and English","date":"2024-12-24","arxiv_id":"2412.18415","n_code_links":1,"syntology":null},{"paper":null,"slug":"pirates-of-the-rag-adaptively-attacking-llms","title":"Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases","date":"2024-12-24","arxiv_id":"2412.18295","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-the-proximity-relationships-of","title":"Research on the Proximity Relationships of Psychosomatic Disease Knowledge Graph Modules Extracted by Large Language Models","date":"2024-12-24","arxiv_id":"2412.18419","n_code_links":0,"syntology":null},{"paper":"/paper/segment-based-attention-masking-for-gpts","slug":"segment-based-attention-masking-for-gpts","title":"Segment-Based Attention Masking for GPTs","date":"2024-12-24","arxiv_id":"2412.18487","n_code_links":1,"syntology":null},{"paper":"/paper/tab-transformer-attention-bottlenecks-enable","slug":"tab-transformer-attention-bottlenecks-enable","title":"TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models","date":"2024-12-24","arxiv_id":"2412.18675","n_code_links":1,"syntology":null},{"paper":null,"slug":"timelyllm-segmented-llm-serving-system-for","title":"TimelyLLM: Segmented LLM Serving System for Time-sensitive Robotic Applications","date":"2024-12-24","arxiv_id":"2412.18695","n_code_links":0,"syntology":null},{"paper":null,"slug":"unlocking-the-potential-of-multiple-bert","title":"Unlocking the Potential of Multiple BERT Models for Bangla Question Answering in NCTB Textbooks","date":"2024-12-24","arxiv_id":"2412.18440","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-of-query-optimization-in-large","title":"A Survey of Query Optimization in Large Language Models","date":"2024-12-23","arxiv_id":"2412.17558","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-temporal-convolutional-network-based","title":"A Temporal Convolutional Network-based Approach for Network Intrusion Detection","date":"2024-12-23","arxiv_id":"2412.17452","n_code_links":0,"syntology":null},{"paper":"/paper/citebart-learning-to-generate-citations-for","slug":"citebart-learning-to-generate-citations-for","title":"CiteBART: Learning to Generate Citations for Local Citation Recommendation","date":"2024-12-23","arxiv_id":"2412.17534","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":12,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["eyclk/citationrecommendation"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"collaborative-optimization-in-financial-data","title":"Collaborative Optimization in Financial Data Mining Through Deep Learning and ResNeXt","date":"2024-12-23","arxiv_id":"2412.17314","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-document-level","title":"Comparative Analysis of Document-Level Embedding Methods for Similarity Scoring on Shakespeare Sonnets and Taylor Swift Lyrics","date":"2024-12-23","arxiv_id":"2412.17552","n_code_links":0,"syntology":null},{"paper":"/paper/comprehensive-multi-modal-prototypes-are","slug":"comprehensive-multi-modal-prototypes-are","title":"Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection","date":"2024-12-23","arxiv_id":"2412.17800","n_code_links":1,"syntology":null},{"paper":"/paper/diffformer-a-differential-spatial-spectral","slug":"diffformer-a-differential-spatial-spectral","title":"DiffFormer: a Differential Spatial-Spectral Transformer for Hyperspectral Image Classification","date":"2024-12-23","arxiv_id":"2412.17350","n_code_links":1,"syntology":null},{"paper":null,"slug":"edge-ai-for-agriculture-lightweight-vision","title":"Edge-AI for Agriculture: Lightweight Vision Models for Disease Detection in Resource-Limited Settings","date":"2024-12-23","arxiv_id":"2412.18635","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-fine-tuning-methodology-of-text","slug":"efficient-fine-tuning-methodology-of-text","title":"Efficient fine-tuning methodology of text embedding models for information retrieval: contrastive learning penalty (clp)","date":"2024-12-23","arxiv_id":"2412.17364","n_code_links":1,"syntology":null},{"paper":null,"slug":"fast-gradient-computation-for-rope-attention","title":"Fast Gradient Computation for RoPE Attention in Almost Linear Time","date":"2024-12-23","arxiv_id":"2412.17316","n_code_links":0,"syntology":null},{"paper":"/paper/layerdropback-a-universally-applicable","slug":"layerdropback-a-universally-applicable","title":"LayerDropBack: A Universally Applicable Approach for Accelerating Training of Deep Networks","date":"2024-12-23","arxiv_id":"2412.18027","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-preference-data-synthetic","slug":"multimodal-preference-data-synthetic","title":"Multimodal Preference Data Synthetic Alignment with Reward Model","date":"2024-12-23","arxiv_id":"2412.17417","n_code_links":1,"syntology":null},{"paper":"/paper/steinformer-spatial-temporal-interaction","slug":"steinformer-spatial-temporal-interaction","title":"STeInFormer: Spatial-Temporal Interaction Transformer Architecture for Remote Sensing Change Detection","date":"2024-12-23","arxiv_id":"2412.17247","n_code_links":1,"syntology":null},{"paper":null,"slug":"theoretical-constraints-on-the-expressive","title":"Theoretical Constraints on the Expressive Power of $\\mathsf{RoPE}$-based Tensor Attention Transformers","date":"2024-12-23","arxiv_id":"2412.18040","n_code_links":0,"syntology":null}],"record_sha256":"3455d216fc185a4678ad2eb0b15c5187813de4b31f513ddcdc71e7e926be3b0f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}