{"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/position-wise-feed-forward-layer/papers/47","list_of":"/method/position-wise-feed-forward-layer","method":"Position-Wise Feed-Forward Layer","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":47,"pages_in_order":139,"rows_per_page":100,"rows":[4601,4700],"of":13895,"counts":{"archive_papers_tagged":13895,"with_a_code_link":6514,"where_syntology_ran_a_sample":2229,"not_listed_spam_title":0,"listed":13895,"listed_where_code_ran":2229,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1902,"every_run_a_failure_of_syntologys_instrument":327,"listed_with_a_run_with_no_instrument_failure":1902,"listed_every_run_a_failure_of_syntologys_instrument":327,"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/position-wise-feed-forward-layer","prev":"/method/position-wise-feed-forward-layer/papers/46","next":"/method/position-wise-feed-forward-layer/papers/48","papers":[{"paper":"/paper/dmssn-distilled-mixed-spectral-spatial","slug":"dmssn-distilled-mixed-spectral-spatial","title":"DMSSN: Distilled Mixed Spectral-Spatial Network for Hyperspectral Salient Object Detection","date":"2024-03-31","arxiv_id":"2404.00694","n_code_links":1,"syntology":null},{"paper":"/paper/drct-saving-image-super-resolution-away-from","slug":"drct-saving-image-super-resolution-away-from","title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","date":"2024-03-31","arxiv_id":"2404.00722","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ming053l/drct"],"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":"/paper/dual-detrs-for-multi-label-temporal-action","slug":"dual-detrs-for-multi-label-temporal-action","title":"Dual DETRs for Multi-Label Temporal Action Detection","date":"2024-03-31","arxiv_id":"2404.00653","n_code_links":0,"syntology":null},{"paper":"/paper/evocodebench-an-evolving-code-generation","slug":"evocodebench-an-evolving-code-generation","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","date":"2024-03-31","arxiv_id":"2404.00599","n_code_links":1,"syntology":{"ran":15,"of":15,"n_ran_checked":14,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["seketeam/evocodebench"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/extracting-social-determinants-of-health-from","slug":"extracting-social-determinants-of-health-from","title":"Extracting Social Determinants of Health from Pediatric Patient Notes Using Large Language Models: Novel Corpus and Methods","date":"2024-03-31","arxiv_id":"2404.00826","n_code_links":1,"syntology":null},{"paper":"/paper/how-much-are-llms-contaminated-a","slug":"how-much-are-llms-contaminated-a","title":"How Much are Large Language Models Contaminated? A Comprehensive Survey and the LLMSanitize Library","date":"2024-03-31","arxiv_id":"2404.00699","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ntunlp/llmsanitize"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/ktpformer-kinematics-and-trajectory-prior","slug":"ktpformer-kinematics-and-trajectory-prior","title":"KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation","date":"2024-03-31","arxiv_id":"2404.00658","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":5,"n_instrument":1,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["JihuaPeng/KTPFormer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mugennet-a-novel-combined-convolution-neural","title":"MugenNet: A Novel Combined Convolution Neural Network and Transformer Network with its Application for Colonic Polyp Image Segmentation","date":"2024-03-31","arxiv_id":"2404.00726","n_code_links":0,"syntology":null},{"paper":"/paper/on-difficulties-of-attention-factorization","slug":"on-difficulties-of-attention-factorization","title":"On Difficulties of Attention Factorization through Shared Memory","date":"2024-03-31","arxiv_id":"2404.00798","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":0,"n_instrument":3,"unverified":3,"pointer_only":6,"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) · 3 unverified","official":{"repos":["vladyorsh/lra_efficient_transformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/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-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":"/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/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":"/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":"/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":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":"/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":"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":"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":"/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":"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":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":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":"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":"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":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":"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":"/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":"/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/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":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":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":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":"/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/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":"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}},{"paper":null,"slug":"large-language-models-are-state-of-the-art-2","title":"Large Language Models Are State-of-the-Art Evaluator for Grammatical Error Correction","date":"2024-03-26","arxiv_id":"2403.17540","n_code_links":0,"syntology":null},{"paper":null,"slug":"magis-llm-based-multi-agent-framework-for","title":"MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution","date":"2024-03-26","arxiv_id":"2403.17927","n_code_links":0,"syntology":null},{"paper":"/paper/mechanistic-design-and-scaling-of-hybrid","slug":"mechanistic-design-and-scaling-of-hybrid","title":"Mechanistic Design and Scaling of Hybrid Architectures","date":"2024-03-26","arxiv_id":"2403.17844","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["athms/mad-lab"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"rotate-to-scan-unet-like-mamba-with-triplet","title":"Rotate to Scan: UNet-like Mamba with Triplet SSM Module for Medical Image Segmentation","date":"2024-03-26","arxiv_id":"2403.17701","n_code_links":0,"syntology":null},{"paper":"/paper/sghormer-an-energy-saving-graph-transformer","slug":"sghormer-an-energy-saving-graph-transformer","title":"SGHormer: An Energy-Saving Graph Transformer Driven by Spikes","date":"2024-03-26","arxiv_id":"2403.17656","n_code_links":1,"syntology":null},{"paper":"/paper/sledge-synthesizing-simulation-environments","slug":"sledge-synthesizing-simulation-environments","title":"SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic","date":"2024-03-26","arxiv_id":"2403.17933","n_code_links":1,"syntology":null},{"paper":null,"slug":"supervisory-prompt-training","title":"Supervisory Prompt Training","date":"2024-03-26","arxiv_id":"2403.18051","n_code_links":0,"syntology":null},{"paper":null,"slug":"verbing-weirds-language-models-evaluation-of","title":"Verbing Weirds Language (Models): Evaluation of English Zero-Derivation in Five LLMs","date":"2024-03-26","arxiv_id":"2403.17856","n_code_links":0,"syntology":null},{"paper":"/paper/3d-effivitcaps-3d-efficient-vision","slug":"3d-effivitcaps-3d-efficient-vision","title":"3D-EffiViTCaps: 3D Efficient Vision Transformer with Capsule for Medical Image Segmentation","date":"2024-03-25","arxiv_id":"2403.16350","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comparative-analysis-of-embedding-models","title":"A comparative analysis of embedding models for patent similarity","date":"2024-03-25","arxiv_id":"2403.16630","n_code_links":0,"syntology":null},{"paper":"/paper/a-comparison-of-human-gpt-3-5-and-gpt-4","slug":"a-comparison-of-human-gpt-3-5-and-gpt-4","title":"A comparison of Human, GPT-3.5, and GPT-4 Performance in a University-Level Coding Course","date":"2024-03-25","arxiv_id":"2403.16977","n_code_links":1,"syntology":null},{"paper":"/paper/an-end-to-end-structure-with-novel-position","slug":"an-end-to-end-structure-with-novel-position","title":"An End-to-End Structure with Novel Position Mechanism and Improved EMD for Stock Forecasting","date":"2024-03-25","arxiv_id":"2404.07969","n_code_links":1,"syntology":null},{"paper":null,"slug":"chebmixer-efficient-graph-representation","title":"ChebMixer: Efficient Graph Representation Learning with MLP Mixer","date":"2024-03-25","arxiv_id":"2403.16358","n_code_links":0,"syntology":null},{"paper":"/paper/ct-bound-fast-boundary-estimation-from-noisy","slug":"ct-bound-fast-boundary-estimation-from-noisy","title":"CT-Bound: Robust Boundary Detection From Noisy Images Via Hybrid Convolution and Transformer Neural Networks","date":"2024-03-25","arxiv_id":"2403.16494","n_code_links":1,"syntology":null},{"paper":null,"slug":"cvt-xrf-contrastive-in-voxel-transformer-for","title":"CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs","date":"2024-03-25","arxiv_id":"2403.16885","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-llm-agents-have-regret-a-case-study-in","title":"Do LLM Agents Have Regret? A Case Study in Online Learning and Games","date":"2024-03-25","arxiv_id":"2403.16843","n_code_links":0,"syntology":null},{"paper":"/paper/doctr-disentangled-object-centric-transformer","slug":"doctr-disentangled-object-centric-transformer","title":"DOCTR: Disentangled Object-Centric Transformer for Point Scene Understanding","date":"2024-03-25","arxiv_id":"2403.16431","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-4-understands-discourse-at-least-as-well","title":"Text Understanding in GPT-4 vs Humans","date":"2024-03-25","arxiv_id":"2403.17196","n_code_links":0,"syntology":null},{"paper":"/paper/linear-cross-document-event-coreference","slug":"linear-cross-document-event-coreference","title":"Linear Cross-document Event Coreference Resolution with X-AMR","date":"2024-03-25","arxiv_id":"2404.08656","n_code_links":1,"syntology":null},{"paper":"/paper/lsttn-a-long-short-term-transformer-based","slug":"lsttn-a-long-short-term-transformer-based","title":"LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting","date":"2024-03-25","arxiv_id":"2403.16495","n_code_links":1,"syntology":null},{"paper":"/paper/modetv2-gpu-accelerated-motion-decomposition","slug":"modetv2-gpu-accelerated-motion-decomposition","title":"ModeTv2: GPU-accelerated Motion Decomposition Transformer for Pairwise Optimization in Medical Image Registration","date":"2024-03-25","arxiv_id":"2403.16526","n_code_links":2,"syntology":null},{"paper":"/paper/qkformer-hierarchical-spiking-transformer","slug":"qkformer-hierarchical-spiking-transformer","title":"QKFormer: Hierarchical Spiking Transformer using Q-K Attention","date":"2024-03-25","arxiv_id":"2403.16552","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhouchenlin2096/qkformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/residual-dense-swin-transformer-for","slug":"residual-dense-swin-transformer-for","title":"Residual Dense Swin Transformer for Continuous Depth-Independent Ultrasound Imaging","date":"2024-03-25","arxiv_id":"2403.16384","n_code_links":1,"syntology":null},{"paper":null,"slug":"sd-dit-unleashing-the-power-of-self","title":"SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer","date":"2024-03-25","arxiv_id":"2403.17004","n_code_links":0,"syntology":null},{"paper":"/paper/sesame-a-framework-to-simulate-self-reported","slug":"sesame-a-framework-to-simulate-self-reported","title":"SeSaMe: A Framework to Simulate Self-Reported Ground Truth for Mental Health Sensing Studies","date":"2024-03-25","arxiv_id":"2403.17219","n_code_links":1,"syntology":null},{"paper":"/paper/state-space-models-as-foundation-models-a","slug":"state-space-models-as-foundation-models-a","title":"State Space Models as Foundation Models: A Control Theoretic Overview","date":"2024-03-25","arxiv_id":"2403.16899","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":5,"n_instrument":1,"unverified":3,"pointer_only":7,"phrase":"6 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jsie7/ssm-benchmark"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/voicecraft-zero-shot-speech-editing-and-text","slug":"voicecraft-zero-shot-speech-editing-and-text","title":"VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild","date":"2024-03-25","arxiv_id":"2403.16973","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jasonppy/voicecraft"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-transformer-approach-for-electricity-price","slug":"a-transformer-approach-for-electricity-price","title":"A Transformer approach for Electricity Price Forecasting","date":"2024-03-24","arxiv_id":"2403.16108","n_code_links":2,"syntology":null},{"paper":null,"slug":"alora-allocating-low-rank-adaptation-for-fine","title":"ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models","date":"2024-03-24","arxiv_id":"2403.16187","n_code_links":0,"syntology":null},{"paper":"/paper/cfat-unleashing-triangularwindows-for-image","slug":"cfat-unleashing-triangularwindows-for-image","title":"CFAT: Unleashing TriangularWindows for Image Super-resolution","date":"2024-03-24","arxiv_id":"2403.16143","n_code_links":1,"syntology":null},{"paper":"/paper/dtf-at-decoupled-time-frequency-audio","slug":"dtf-at-decoupled-time-frequency-audio","title":"DTF-AT: Decoupled Time-Frequency Audio Transformer for Event Classification","date":"2024-03-24","arxiv_id":null,"n_code_links":1,"syntology":null}],"record_sha256":"85b51361f242e960b42d52d9e5143ff1dd9754da58f4a7718cda6e3e3bf292d2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}