{"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/multi-head-attention/papers/80","list_of":"/method/multi-head-attention","method":"Multi-Head Attention","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":80,"pages_in_order":249,"rows_per_page":100,"rows":[7901,8000],"of":24855,"counts":{"archive_papers_tagged":24855,"with_a_code_link":11214,"where_syntology_ran_a_sample":3454,"not_listed_spam_title":0,"listed":24855,"listed_where_code_ran":3454,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2916,"every_run_a_failure_of_syntologys_instrument":538,"listed_with_a_run_with_no_instrument_failure":2916,"listed_every_run_a_failure_of_syntologys_instrument":538,"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/multi-head-attention","prev":"/method/multi-head-attention/papers/79","next":"/method/multi-head-attention/papers/81","papers":[{"paper":null,"slug":"revealing-trends-in-datasets-from-the-2022","title":"Revealing Trends in Datasets from the 2022 ACL and EMNLP Conferences","date":"2024-03-31","arxiv_id":"2404.08666","n_code_links":0,"syntology":null},{"paper":"/paper/rq-rag-learning-to-refine-queries-for","slug":"rq-rag-learning-to-refine-queries-for","title":"RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation","date":"2024-03-31","arxiv_id":"2404.00610","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-free-semantic-segmentation-via-llm","title":"Training-Free Semantic Segmentation via LLM-Supervision","date":"2024-03-31","arxiv_id":"2404.00701","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-pluralistic-image","slug":"transformer-based-pluralistic-image","title":"Transformer based Pluralistic Image Completion with Reduced Information Loss","date":"2024-03-31","arxiv_id":"2404.00513","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comprehensive-study-on-nlp-data","title":"A Comprehensive Study on NLP Data Augmentation for Hate Speech Detection: Legacy Methods, BERT, and LLMs","date":"2024-03-30","arxiv_id":"2404.00303","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-feature-map-enhancement-technique","title":"A Novel Feature Map Enhancement Technique Integrating Residual CNN and Transformer for Alzheimer Diseases Diagnosis","date":"2024-03-30","arxiv_id":"2405.12986","n_code_links":0,"syntology":null},{"paper":"/paper/can-llms-master-math-investigating-large","slug":"can-llms-master-math-investigating-large","title":"Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange","date":"2024-03-30","arxiv_id":"2404.00344","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["gipplab/llm-investig-mathstackexchange"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dependability-evaluation-of-stable-diffusion","title":"Dependability Evaluation of Stable Diffusion with Soft Errors on the Model Parameters","date":"2024-03-30","arxiv_id":"2404.00352","n_code_links":0,"syntology":null},{"paper":"/paper/edinburgh-clinical-nlp-at-semeval-2024-task-2","slug":"edinburgh-clinical-nlp-at-semeval-2024-task-2","title":"Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4","date":"2024-03-30","arxiv_id":"2404.00484","n_code_links":1,"syntology":null},{"paper":null,"slug":"injecting-new-knowledge-into-large-language","title":"Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning","date":"2024-03-30","arxiv_id":"2404.00213","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-pre-trained-and-transformer","title":"Leveraging Pre-trained and Transformer-derived Embeddings from EHRs to Characterize Heterogeneity Across Alzheimer's Disease and Related Dementias","date":"2024-03-30","arxiv_id":"2404.00464","n_code_links":0,"syntology":null},{"paper":"/paper/small-language-models-learn-enhanced","slug":"small-language-models-learn-enhanced","title":"Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks","date":"2024-03-30","arxiv_id":"2404.00376","n_code_links":0,"syntology":null},{"paper":null,"slug":"spread-your-wings-a-radial-strip-transformer","title":"Spread Your Wings: A Radial Strip Transformer for Image Deblurring","date":"2024-03-30","arxiv_id":"2404.00358","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-parallel-attention-network-for-cattle-face","title":"A Parallel Attention Network for Cattle Face Recognition","date":"2024-03-29","arxiv_id":"2403.19980","n_code_links":0,"syntology":null},{"paper":"/paper/agileformer-spatially-agile-transformer-unet","slug":"agileformer-spatially-agile-transformer-unet","title":"AgileFormer: Spatially Agile Transformer UNet for Medical Image Segmentation","date":"2024-03-29","arxiv_id":"2404.00122","n_code_links":1,"syntology":null},{"paper":null,"slug":"chatgpt-v-s-media-bias-a-comparative-study-of","title":"ChatGPT v.s. Media Bias: A Comparative Study of GPT-3.5 and Fine-tuned Language Models","date":"2024-03-29","arxiv_id":"2403.20158","n_code_links":0,"syntology":null},{"paper":"/paper/classifying-conspiratorial-narratives-at","slug":"classifying-conspiratorial-narratives-at","title":"Classifying Conspiratorial Narratives At Scale: False Alarms and Erroneous Connections","date":"2024-03-29","arxiv_id":"2404.00141","n_code_links":1,"syntology":null},{"paper":null,"slug":"dataagent-evaluating-large-language-models","title":"DataAgent: Evaluating Large Language Models' Ability to Answer Zero-Shot, Natural Language Queries","date":"2024-03-29","arxiv_id":"2404.00188","n_code_links":0,"syntology":null},{"paper":"/paper/decision-mamba-reinforcement-learning-via","slug":"decision-mamba-reinforcement-learning-via","title":"Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces","date":"2024-03-29","arxiv_id":"2403.19925","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["toshihiro-ota/decision-mamba"],"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"]}}},{"paper":"/paper/dijiang-efficient-large-language-models","slug":"dijiang-efficient-large-language-models","title":"DiJiang: Efficient Large Language Models through Compact Kernelization","date":"2024-03-29","arxiv_id":"2403.19928","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":6,"phrase":"6 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yuchuantian/dijiang"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/enhancing-the-general-agent-capabilities-of","slug":"enhancing-the-general-agent-capabilities-of","title":"Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning","date":"2024-03-29","arxiv_id":"2403.19962","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":4,"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) · 3 unverified","official":{"repos":["haiv-lab/llm-tmbr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/explainable-deep-learning-a-visual-analytics","slug":"explainable-deep-learning-a-visual-analytics","title":"Explainable Deep Learning: A Visual Analytics Approach with Transition Matrices","date":"2024-03-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/latxa-an-open-language-model-and-evaluation","slug":"latxa-an-open-language-model-and-evaluation","title":"Latxa: An Open Language Model and Evaluation Suite for Basque","date":"2024-03-29","arxiv_id":"2403.20266","n_code_links":1,"syntology":null},{"paper":null,"slug":"layernorm-a-key-component-in-parameter","title":"LayerNorm: A key component in parameter-efficient fine-tuning","date":"2024-03-29","arxiv_id":"2403.20284","n_code_links":0,"syntology":null},{"paper":"/paper/localising-the-seizure-onset-zone-from-single","slug":"localising-the-seizure-onset-zone-from-single","title":"Localising the Seizure Onset Zone from Single-Pulse Electrical Stimulation Responses with a CNN Transformer","date":"2024-03-29","arxiv_id":"2403.20324","n_code_links":1,"syntology":null},{"paper":"/paper/mango-a-benchmark-for-evaluating-mapping-and","slug":"mango-a-benchmark-for-evaluating-mapping-and","title":"MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models","date":"2024-03-29","arxiv_id":"2403.19913","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["oaklight/mango"],"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"]}}},{"paper":"/paper/on-the-fly-definition-augmentation-of-llms","slug":"on-the-fly-definition-augmentation-of-llms","title":"On-the-fly Definition Augmentation of LLMs for Biomedical NER","date":"2024-03-29","arxiv_id":"2404.00152","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["allenai/beacon"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"realm-reference-resolution-as-language","title":"ReALM: Reference Resolution As Language Modeling","date":"2024-03-29","arxiv_id":"2403.20329","n_code_links":0,"syntology":null},{"paper":"/paper/scenetracker-long-term-scene-flow-estimation","slug":"scenetracker-long-term-scene-flow-estimation","title":"SceneTracker: Long-term Scene Flow Estimation Network","date":"2024-03-29","arxiv_id":"2403.19924","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["wwsource/scenetracker"],"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"]}}},{"paper":"/paper/shallow-cross-encoders-for-low-latency","slug":"shallow-cross-encoders-for-low-latency","title":"Shallow Cross-Encoders for Low-Latency Retrieval","date":"2024-03-29","arxiv_id":"2403.20222","n_code_links":1,"syntology":null},{"paper":null,"slug":"tdanet-a-novel-temporal-denoise-convolutional","title":"TDANet: A Novel Temporal Denoise Convolutional Neural Network With Attention for Fault Diagnosis","date":"2024-03-29","arxiv_id":"2403.19943","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-stochastic-transformer-based-approach","title":"A Novel Stochastic Transformer-based Approach for Post-Traumatic Stress Disorder Detection using Audio Recording of Clinical Interviews","date":"2024-03-28","arxiv_id":"2403.19441","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-review-of-multi-modal-large-language-and","title":"A Review of Multi-Modal Large Language and Vision Models","date":"2024-03-28","arxiv_id":"2404.01322","n_code_links":0,"syntology":null},{"paper":"/paper/aapmt-agi-assessment-through-prompt-and","slug":"aapmt-agi-assessment-through-prompt-and","title":"AAPMT: AGI Assessment Through Prompt and Metric Transformer","date":"2024-03-28","arxiv_id":"2403.19101","n_code_links":1,"syntology":null},{"paper":null,"slug":"alloybert-alloy-property-prediction-with","title":"AlloyBERT: Alloy Property Prediction with Large Language Models","date":"2024-03-28","arxiv_id":"2403.19783","n_code_links":0,"syntology":null},{"paper":"/paper/are-large-language-models-good-at-utility","slug":"are-large-language-models-good-at-utility","title":"Are Large Language Models Good at Utility Judgments?","date":"2024-03-28","arxiv_id":"2403.19216","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":7,"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) · 4 unverified","official":{"repos":["ict-bigdatalab/utility_judgments"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"checkpoint-merging-via-bayesian-optimization","title":"Checkpoint Merging via Bayesian Optimization in LLM Pretraining","date":"2024-03-28","arxiv_id":"2403.19390","n_code_links":0,"syntology":null},{"paper":null,"slug":"code-comparison-tuning-for-code-large","title":"Code Comparison Tuning for Code Large Language Models","date":"2024-03-28","arxiv_id":"2403.19121","n_code_links":0,"syntology":null},{"paper":"/paper/densenets-reloaded-paradigm-shift-beyond","slug":"densenets-reloaded-paradigm-shift-beyond","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","date":"2024-03-28","arxiv_id":"2403.19588","n_code_links":3,"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: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["huggingface/pytorch-image-models","naver-ai/rdnet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-efficiency-in-vision-transformer","title":"Enhancing Efficiency in Vision Transformer Networks: Design Techniques and Insights","date":"2024-03-28","arxiv_id":"2403.19882","n_code_links":0,"syntology":null},{"paper":null,"slug":"factoid-factual-entailment-for-hallucination","title":"FACTOID: FACtual enTailment fOr hallucInation Detection","date":"2024-03-28","arxiv_id":"2403.19113","n_code_links":0,"syntology":null},{"paper":null,"slug":"generate-then-retrieve-conversational","title":"Generating Multi-Aspect Queries for Conversational Search","date":"2024-03-28","arxiv_id":"2403.19302","n_code_links":0,"syntology":null},{"paper":"/paper/genetic-quantization-aware-approximation-for","slug":"genetic-quantization-aware-approximation-for","title":"Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers","date":"2024-03-28","arxiv_id":"2403.19591","n_code_links":1,"syntology":null},{"paper":null,"slug":"intelligent-classification-and-personalized","title":"Intelligent Classification and Personalized Recommendation of E-commerce Products Based on Machine Learning","date":"2024-03-28","arxiv_id":"2403.19345","n_code_links":0,"syntology":null},{"paper":"/paper/interpreting-key-mechanisms-of-factual-recall","slug":"interpreting-key-mechanisms-of-factual-recall","title":"Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models","date":"2024-03-28","arxiv_id":"2403.19521","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":12,"n_instrument":0,"unverified":2,"pointer_only":14,"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) · 2 unverified","official":{"repos":["trestad/factual-recall-mechanism"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/jamba-a-hybrid-transformer-mamba-language","slug":"jamba-a-hybrid-transformer-mamba-language","title":"Jamba: A Hybrid Transformer-Mamba Language Model","date":"2024-03-28","arxiv_id":"2403.19887","n_code_links":3,"syntology":null},{"paper":null,"slug":"just-dna-seq-open-source-personal-genomics","title":"Just-DNA-Seq, open-source personal genomics platform: longevity science for everyone","date":"2024-03-28","arxiv_id":"2403.19087","n_code_links":0,"syntology":null},{"paper":null,"slug":"keypoint-action-tokens-enable-in-context","title":"Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics","date":"2024-03-28","arxiv_id":"2403.19578","n_code_links":0,"syntology":null},{"paper":"/paper/mateval-a-multi-agent-discussion-framework","slug":"mateval-a-multi-agent-discussion-framework","title":"MATEval: A Multi-Agent Discussion Framework for Advancing Open-Ended Text Evaluation","date":"2024-03-28","arxiv_id":"2403.19305","n_code_links":1,"syntology":null},{"paper":"/paper/mitigating-misleading-chain-of-thought","slug":"mitigating-misleading-chain-of-thought","title":"Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering","date":"2024-03-28","arxiv_id":"2403.19167","n_code_links":1,"syntology":null},{"paper":null,"slug":"patch-spatio-temporal-relation-prediction-for","title":"Patch Spatio-Temporal Relation Prediction for Video Anomaly Detection","date":"2024-03-28","arxiv_id":"2403.19111","n_code_links":0,"syntology":null},{"paper":null,"slug":"risk-prediction-of-pathological-gambling-on","title":"Risk prediction of pathological gambling on social media","date":"2024-03-28","arxiv_id":"2403.19358","n_code_links":0,"syntology":null},{"paper":"/paper/siamese-vision-transformers-are-scalable","slug":"siamese-vision-transformers-are-scalable","title":"Siamese Vision Transformers are Scalable Audio-visual Learners","date":"2024-03-28","arxiv_id":"2403.19638","n_code_links":1,"syntology":{"ran":15,"of":19,"n_ran_checked":15,"n_instrument":0,"unverified":4,"pointer_only":19,"phrase":"15 ran (of which 3 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["genjib/avsiam"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":3,"n_ran_no_instrument_failure":15,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"single-shared-network-with-prior-inspired","title":"Single-Shared Network with Prior-Inspired Loss for Parameter-Efficient Multi-Modal Imaging Skin Lesion Classification","date":"2024-03-28","arxiv_id":"2403.19203","n_code_links":0,"syntology":null},{"paper":"/paper/a-novel-corpus-of-annotated-medical-imaging","slug":"a-novel-corpus-of-annotated-medical-imaging","title":"A Novel Corpus of Annotated Medical Imaging Reports and Information Extraction Results Using BERT-based Language Models","date":"2024-03-27","arxiv_id":"2403.18975","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-large-language-models-from","title":"A Survey on Large Language Models from Concept to Implementation","date":"2024-03-27","arxiv_id":"2403.18969","n_code_links":0,"syntology":null},{"paper":null,"slug":"acted-automatic-acquisition-of-typical-event","title":"AcTED: Automatic Acquisition of Typical Event Duration for Semi-supervised Temporal Commonsense QA","date":"2024-03-27","arxiv_id":"2403.18504","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-aware-semantic-relevance-predicting","title":"Attention-aware semantic relevance predicting Chinese sentence reading","date":"2024-03-27","arxiv_id":"2403.18542","n_code_links":0,"syntology":null},{"paper":"/paper/biomedlm-a-2-7b-parameter-language-model","slug":"biomedlm-a-2-7b-parameter-language-model","title":"BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text","date":"2024-03-27","arxiv_id":"2403.18421","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"3 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["stanford-crfm/biomedlm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"blade-enhancing-black-box-large-language","title":"BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models","date":"2024-03-27","arxiv_id":"2403.18365","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-conversational-question-answering","title":"Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Check","date":"2024-03-27","arxiv_id":"2403.18243","n_code_links":0,"syntology":null},{"paper":null,"slug":"cpr-retrieval-augmented-generation-for","title":"CPR: Retrieval Augmented Generation for Copyright Protection","date":"2024-03-27","arxiv_id":"2403.18920","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-domain-fiber-cluster-shape-analysis-for","title":"Cross-domain Fiber Cluster Shape Analysis for Language Performance Cognitive Score Prediction","date":"2024-03-27","arxiv_id":"2403.19001","n_code_links":0,"syntology":null},{"paper":"/paper/ecodepth-effective-conditioning-of-diffusion","slug":"ecodepth-effective-conditioning-of-diffusion","title":"ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation","date":"2024-03-27","arxiv_id":"2403.18807","n_code_links":1,"syntology":{"ran":11,"of":15,"n_ran_checked":6,"n_instrument":5,"unverified":4,"pointer_only":15,"phrase":"11 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","official":{"repos":["aradhye2002/ecodepth"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":1,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluating-large-language-models-for-health-1","title":"Evaluating Large Language Models for Health-Related Text Classification Tasks with Public Social Media Data","date":"2024-03-27","arxiv_id":"2403.19031","n_code_links":0,"syntology":null},{"paper":"/paper/faster-convergence-for-transformer-fine","slug":"faster-convergence-for-transformer-fine","title":"Faster Convergence for Transformer Fine-tuning with Line Search Methods","date":"2024-03-27","arxiv_id":"2403.18506","n_code_links":1,"syntology":null},{"paper":null,"slug":"few-shot-cross-system-anomaly-trace","title":"Cross-System Categorization of Abnormal Traces in Microservice-Based Systems via Meta-Learning","date":"2024-03-27","arxiv_id":"2403.18998","n_code_links":0,"syntology":null},{"paper":null,"slug":"fourier-or-wavelet-bases-as-counterpart-self","title":"Fourier or Wavelet bases as counterpart self-attention in spikformer for efficient visual classification","date":"2024-03-27","arxiv_id":"2403.18228","n_code_links":0,"syntology":null},{"paper":null,"slug":"fusion-approaches-for-emotion-recognition","title":"Fusion approaches for emotion recognition from speech using acoustic and text-based features","date":"2024-03-27","arxiv_id":"2403.18635","n_code_links":0,"syntology":null},{"paper":null,"slug":"illicit-object-detection-in-x-ray-images","title":"Illicit object detection in X-ray images using Vision Transformers","date":"2024-03-27","arxiv_id":"2403.19043","n_code_links":0,"syntology":null},{"paper":null,"slug":"lift3d-zero-shot-lifting-of-any-2d-vision","title":"Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D","date":"2024-03-27","arxiv_id":"2403.18922","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-in-hci-data-work-bridging-the-gap","title":"LLMs in HCI Data Work: Bridging the Gap Between Information Retrieval and Responsible Research Practices","date":"2024-03-27","arxiv_id":"2403.18173","n_code_links":0,"syntology":null},{"paper":"/paper/long-form-factuality-in-large-language-models","slug":"long-form-factuality-in-large-language-models","title":"Long-form factuality in large language models","date":"2024-03-27","arxiv_id":"2403.18802","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-deepmind/long-form-factuality"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"malbert-is-a-compact-multilingual-bert-model","title":"mALBERT: Is a Compact Multilingual BERT Model Still Worth It?","date":"2024-03-27","arxiv_id":"2403.18338","n_code_links":0,"syntology":null},{"paper":"/paper/mini-gemini-mining-the-potential-of-multi","slug":"mini-gemini-mining-the-potential-of-multi","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","date":"2024-03-27","arxiv_id":"2403.18814","n_code_links":2,"syntology":{"ran":8,"of":8,"n_ran_checked":5,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dvlab-research/minigemini"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-layer-dense-attention-decoder-for-polyp","slug":"multi-layer-dense-attention-decoder-for-polyp","title":"Multi-Layer Dense Attention Decoder for Polyp Segmentation","date":"2024-03-27","arxiv_id":"2403.18180","n_code_links":1,"syntology":null},{"paper":"/paper/parco-part-coordinating-text-to-motion","slug":"parco-part-coordinating-text-to-motion","title":"ParCo: Part-Coordinating Text-to-Motion Synthesis","date":"2024-03-27","arxiv_id":"2403.18512","n_code_links":1,"syntology":null},{"paper":"/paper/rankmamba-benchmarking-mamba-s-document","slug":"rankmamba-benchmarking-mamba-s-document","title":"RankMamba: Benchmarking Mamba's Document Ranking Performance in the Era of Transformers","date":"2024-03-27","arxiv_id":"2403.18276","n_code_links":1,"syntology":null},{"paper":"/paper/reshaping-free-text-radiology-notes-into","slug":"reshaping-free-text-radiology-notes-into","title":"Reshaping Free-Text Radiology Notes Into Structured Reports With Generative Transformers","date":"2024-03-27","arxiv_id":"2403.18938","n_code_links":1,"syntology":null},{"paper":"/paper/semrode-macro-adversarial-training-to-learn","slug":"semrode-macro-adversarial-training-to-learn","title":"SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks","date":"2024-03-27","arxiv_id":"2403.18423","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["aniloid2/semrode-macroadversarialtraining"],"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":"vitar-vision-transformer-with-any-resolution","title":"ViTAR: Vision Transformer with Any Resolution","date":"2024-03-27","arxiv_id":"2403.18361","n_code_links":0,"syntology":null},{"paper":"/paper/vulnerability-detection-with-code-language","slug":"vulnerability-detection-with-code-language","title":"Vulnerability Detection with Code Language Models: How Far Are We?","date":"2024-03-27","arxiv_id":"2403.18624","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":0,"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) · 4 unverified","official":{"repos":["dlvuldet/primevul"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/accuracy-enhancement-method-for-speech","slug":"accuracy-enhancement-method-for-speech","title":"Accuracy enhancement method for speech emotion recognition from spectrogram using temporal frequency correlation and positional information learning through knowledge transfer","date":"2024-03-26","arxiv_id":"2403.17327","n_code_links":1,"syntology":null},{"paper":null,"slug":"alisa-accelerating-large-language-model","title":"ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching","date":"2024-03-26","arxiv_id":"2403.17312","n_code_links":0,"syntology":null},{"paper":"/paper/are-compressed-language-models-less-subgroup","slug":"are-compressed-language-models-less-subgroup","title":"Are Compressed Language Models Less Subgroup Robust?","date":"2024-03-26","arxiv_id":"2403.17811","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-report-generation-for-lung","title":"Automated Report Generation for Lung Cytological Images Using a CNN Vision Classifier and Multiple-Transformer Text Decoders: Preliminary Study","date":"2024-03-26","arxiv_id":"2403.18151","n_code_links":0,"syntology":null},{"paper":null,"slug":"ccdsreformer-traffic-flow-prediction-with-a","title":"CCDSReFormer: Traffic Flow Prediction with a Criss-Crossed Dual-Stream Enhanced Rectified Transformer Model","date":"2024-03-26","arxiv_id":"2403.17753","n_code_links":0,"syntology":null},{"paper":"/paper/constructions-are-so-difficult-that-even","slug":"constructions-are-so-difficult-that-even","title":"Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons","date":"2024-03-26","arxiv_id":"2403.17760","n_code_links":1,"syntology":null},{"paper":null,"slug":"decoding-probing-revealing-internal","title":"Decoding Probing: Revealing Internal Linguistic Structures in Neural Language Models using Minimal Pairs","date":"2024-03-26","arxiv_id":"2403.17299","n_code_links":0,"syntology":null},{"paper":null,"slug":"disambiguate-entity-matching-through-relation","title":"Disambiguate Entity Matching using Large Language Models through Relation Discovery","date":"2024-03-26","arxiv_id":"2403.17344","n_code_links":0,"syntology":null},{"paper":"/paper/don-t-trust-verify-grounding-llm-quantitative","slug":"don-t-trust-verify-grounding-llm-quantitative","title":"Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization","date":"2024-03-26","arxiv_id":"2403.18120","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":2,"n_instrument":8,"unverified":2,"pointer_only":0,"phrase":"10 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; 8 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jinpz/dtv"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/egoposeformer-a-simple-baseline-for","slug":"egoposeformer-a-simple-baseline-for","title":"EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimation","date":"2024-03-26","arxiv_id":"2403.18080","n_code_links":1,"syntology":null},{"paper":"/paper/ellen-extremely-lightly-supervised-learning","slug":"ellen-extremely-lightly-supervised-learning","title":"ELLEN: Extremely Lightly Supervised Learning For Efficient Named Entity Recognition","date":"2024-03-26","arxiv_id":"2403.17385","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-legal-document-retrieval-a-multi","title":"Enhancing Legal Document Retrieval: A Multi-Phase Approach with Large Language Models","date":"2024-03-26","arxiv_id":"2403.18093","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-efficacy-of-prompt-engineered","title":"Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models Versus Fine-Tuned Vision Transformers in Image-Based Security Applications","date":"2024-03-26","arxiv_id":"2403.17787","n_code_links":0,"syntology":null},{"paper":"/paper/fingerprinting-web-servers-through","slug":"fingerprinting-web-servers-through","title":"Fingerprinting web servers through Transformer-encoded HTTP response headers","date":"2024-03-26","arxiv_id":"2404.00056","n_code_links":1,"syntology":null},{"paper":"/paper/hierarchical-light-transformer-ensembles-for","slug":"hierarchical-light-transformer-ensembles-for","title":"Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecasting","date":"2024-03-26","arxiv_id":"2403.17678","n_code_links":1,"syntology":null},{"paper":null,"slug":"hierarchical-multi-label-classification-for","title":"Hierarchical Multi-label Classification for Fine-level Event Extraction from Aviation Accident Reports","date":"2024-03-26","arxiv_id":"2403.17914","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrative-graph-transformer-framework-for","title":"Integrative Graph-Transformer Framework for Histopathology Whole Slide Image Representation and Classification","date":"2024-03-26","arxiv_id":"2403.18134","n_code_links":0,"syntology":null},{"paper":"/paper/internlm2-technical-report","slug":"internlm2-technical-report","title":"InternLM2 Technical Report","date":"2024-03-26","arxiv_id":"2403.17297","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":null}}],"record_sha256":"442ec011c9e9dfeca7d0c9dd715d7e042ec4e6f06427b741bc978154adb4eb2c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}