{"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/53","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":53,"pages_in_order":139,"rows_per_page":100,"rows":[5201,5300],"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/52","next":"/method/position-wise-feed-forward-layer/papers/54","papers":[{"paper":null,"slug":"ploutos-towards-interpretable-stock-movement","title":"Ploutos: Towards interpretable stock movement prediction with financial large language model","date":"2024-02-18","arxiv_id":"2403.00782","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-flan-scaling-human-labeled-tasks-in","title":"Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning","date":"2024-02-18","arxiv_id":"2402.11690","n_code_links":0,"syntology":null},{"paper":"/paper/boosting-of-thoughts-trial-and-error-problem","slug":"boosting-of-thoughts-trial-and-error-problem","title":"Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models","date":"2024-02-17","arxiv_id":"2402.11140","n_code_links":2,"syntology":null},{"paper":null,"slug":"detecting-a-proxy-for-potential-comorbid-adhd","title":"Detecting a Proxy for Potential Comorbid ADHD in People Reporting Anxiety Symptoms from Social Media Data","date":"2024-02-17","arxiv_id":"2403.05561","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-chatgpt-for-next-generation","title":"Exploring ChatGPT for Next-generation Information Retrieval: Opportunities and Challenges","date":"2024-02-17","arxiv_id":"2402.11203","n_code_links":0,"syntology":null},{"paper":null,"slug":"gendec-a-robust-generative-question","title":"GenDec: A robust generative Question-decomposition method for Multi-hop reasoning","date":"2024-02-17","arxiv_id":"2402.11166","n_code_links":0,"syntology":null},{"paper":null,"slug":"reasoning-before-comparison-llm-enhanced","title":"Reasoning before Comparison: LLM-Enhanced Semantic Similarity Metrics for Domain Specialized Text Analysis","date":"2024-02-17","arxiv_id":"2402.11398","n_code_links":0,"syntology":null},{"paper":"/paper/revit-enhancing-vision-transformers-with","slug":"revit-enhancing-vision-transformers-with","title":"ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections","date":"2024-02-17","arxiv_id":"2402.11301","n_code_links":1,"syntology":{"ran":22,"of":24,"n_ran_checked":20,"n_instrument":2,"unverified":2,"pointer_only":1,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["adiko1997/revit"],"state":"official (archive's flag): 22 ran","n_ran":22,"n_constructed":0,"n_ran_no_instrument_failure":20,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/zerog-investigating-cross-dataset-zero-shot","slug":"zerog-investigating-cross-dataset-zero-shot","title":"ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs","date":"2024-02-17","arxiv_id":"2402.11235","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["nineabyss/zerog"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"assessing-the-reasoning-abilities-of-chatgpt","title":"Assessing the Reasoning Abilities of ChatGPT in the Context of Claim Verification","date":"2024-02-16","arxiv_id":"2402.10735","n_code_links":0,"syntology":null},{"paper":"/paper/can-llms-speak-for-diverse-people-tuning-llms","slug":"can-llms-speak-for-diverse-people-tuning-llms","title":"Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements","date":"2024-02-16","arxiv_id":"2402.10614","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":["tianyi-lab/debatune"],"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":"can-separators-improve-chain-of-thought","title":"Can Separators Improve Chain-of-Thought Prompting?","date":"2024-02-16","arxiv_id":"2402.10645","n_code_links":0,"syntology":null},{"paper":"/paper/contiformer-continuous-time-transformer-for-1","slug":"contiformer-continuous-time-transformer-for-1","title":"ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling","date":"2024-02-16","arxiv_id":"2402.10635","n_code_links":1,"syntology":{"ran":8,"of":12,"n_ran_checked":8,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["microsoft/SeqML"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/dynamic-patch-aware-enrichment-transformer","slug":"dynamic-patch-aware-enrichment-transformer","title":"Dynamic Patch-aware Enrichment Transformer for Occluded Person Re-Identification","date":"2024-02-16","arxiv_id":"2402.10435","n_code_links":0,"syntology":null},{"paper":null,"slug":"emoji-driven-crypto-assets-market-reactions","title":"Emoji Driven Crypto Assets Market Reactions","date":"2024-02-16","arxiv_id":"2402.10481","n_code_links":0,"syntology":null},{"paper":null,"slug":"fintral-a-family-of-gpt-4-level-multimodal","title":"FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models","date":"2024-02-16","arxiv_id":"2402.10986","n_code_links":0,"syntology":null},{"paper":"/paper/german-text-simplification-finetuning-large","slug":"german-text-simplification-finetuning-large","title":"German Text Simplification: Finetuning Large Language Models with Semi-Synthetic Data","date":"2024-02-16","arxiv_id":"2402.10675","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-reliable-are-automatic-evaluation-methods","title":"How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs?","date":"2024-02-16","arxiv_id":"2402.10770","n_code_links":0,"syntology":null},{"paper":"/paper/in-search-of-needles-in-a-10m-haystack","slug":"in-search-of-needles-in-a-10m-haystack","title":"In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Miss","date":"2024-02-16","arxiv_id":"2402.10790","n_code_links":2,"syntology":null},{"paper":"/paper/jailbreaking-proprietary-large-language","slug":"jailbreaking-proprietary-large-language","title":"When \"Competency\" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers","date":"2024-02-16","arxiv_id":"2402.10601","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":["divijh/jailbreak_cryptography"],"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/large-language-models-as-zero-shot-dialogue","slug":"large-language-models-as-zero-shot-dialogue","title":"Large Language Models as Zero-shot Dialogue State Tracker through Function Calling","date":"2024-02-16","arxiv_id":"2402.10466","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["facebookresearch/fnctod"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"large-language-models-fall-short","title":"Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives","date":"2024-02-16","arxiv_id":"2402.11051","n_code_links":0,"syntology":null},{"paper":"/paper/linear-transformers-with-learnable-kernel","slug":"linear-transformers-with-learnable-kernel","title":"Linear Transformers with Learnable Kernel Functions are Better In-Context Models","date":"2024-02-16","arxiv_id":"2402.10644","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["sustcsonglin/flash-linear-attention","corl-team/rebased"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/linkner-linking-local-named-entity","slug":"linkner-linking-local-named-entity","title":"LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using Uncertainty","date":"2024-02-16","arxiv_id":"2402.10573","n_code_links":1,"syntology":null},{"paper":"/paper/toolsword-unveiling-safety-issues-of-large","slug":"toolsword-unveiling-safety-issues-of-large","title":"ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages","date":"2024-02-16","arxiv_id":"2402.10753","n_code_links":1,"syntology":null},{"paper":"/paper/weak-mamba-unet-visual-mamba-makes-cnn-and","slug":"weak-mamba-unet-visual-mamba-makes-cnn-and","title":"Weak-Mamba-UNet: Visual Mamba Makes CNN and ViT Work Better for Scribble-based Medical Image Segmentation","date":"2024-02-16","arxiv_id":"2402.10887","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":2,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ziyangwang007/mamba-unet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/a-strongreject-for-empty-jailbreaks","slug":"a-strongreject-for-empty-jailbreaks","title":"A StrongREJECT for Empty Jailbreaks","date":"2024-02-15","arxiv_id":"2402.10260","n_code_links":2,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"0 ran · 4 unverified","official":{"repos":["alexandrasouly/strongreject"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"an-analysis-of-langauge-frequency-and-error","title":"An Analysis of Language Frequency and Error Correction for Esperanto","date":"2024-02-15","arxiv_id":"2402.09696","n_code_links":0,"syntology":null},{"paper":null,"slug":"camouflage-is-all-you-need-evaluating-and","title":"Camouflage is all you need: Evaluating and Enhancing Language Model Robustness Against Camouflage Adversarial Attacks","date":"2024-02-15","arxiv_id":"2402.09874","n_code_links":0,"syntology":null},{"paper":"/paper/data-engineering-for-scaling-language-models","slug":"data-engineering-for-scaling-language-models","title":"Data Engineering for Scaling Language Models to 128K Context","date":"2024-02-15","arxiv_id":"2402.10171","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":["franxyao/long-context-data-engineering"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fine-tuning-large-language-model-llm","title":"Fine-tuning Large Language Model (LLM) Artificial Intelligence Chatbots in Ophthalmology and LLM-based evaluation using GPT-4","date":"2024-02-15","arxiv_id":"2402.10083","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-s-assessment-of-its-performance-in-a","title":"GPT-4's assessment of its performance in a USMLE-based case study","date":"2024-02-15","arxiv_id":"2402.09654","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-non-autoregressive-machine","title":"Improving Non-autoregressive Machine Translation with Error Exposure and Consistency Regularization","date":"2024-02-15","arxiv_id":"2402.09725","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-forecasting-and","title":"Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review","date":"2024-02-15","arxiv_id":"2402.10350","n_code_links":0,"syntology":null},{"paper":null,"slug":"nyctale-neuro-evidence-transformer-for","title":"NYCTALE: Neuro-Evidence Transformer for Adaptive and Personalized Lung Nodule Invasiveness Prediction","date":"2024-02-15","arxiv_id":"2402.10066","n_code_links":0,"syntology":null},{"paper":"/paper/openmathinstruct-1-a-1-8-million-math","slug":"openmathinstruct-1-a-1-8-million-math","title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","date":"2024-02-15","arxiv_id":"2402.10176","n_code_links":1,"syntology":null},{"paper":null,"slug":"prompt-based-bias-calibration-for-better-zero","title":"Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models","date":"2024-02-15","arxiv_id":"2402.10353","n_code_links":0,"syntology":null},{"paper":null,"slug":"protchatgpt-towards-understanding-proteins","title":"ProtChatGPT: Towards Understanding Proteins with Large Language Models","date":"2024-02-15","arxiv_id":"2402.09649","n_code_links":0,"syntology":null},{"paper":"/paper/spike-driven-transformer-v2-meta-spiking","slug":"spike-driven-transformer-v2-meta-spiking","title":"Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips","date":"2024-02-15","arxiv_id":"2404.03663","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["biclab/spike-driven-transformer-v2"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/unlocking-structure-measuring-introducing-pdd","slug":"unlocking-structure-measuring-introducing-pdd","title":"Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence","date":"2024-02-15","arxiv_id":"2402.10175","n_code_links":1,"syntology":null},{"paper":null,"slug":"x-lifecycle-learning-for-cloud-incident","title":"X-lifecycle Learning for Cloud Incident Management using LLMs","date":"2024-02-15","arxiv_id":"2404.03662","n_code_links":0,"syntology":null},{"paper":"/paper/api-pack-a-massive-multilingual-dataset-for","slug":"api-pack-a-massive-multilingual-dataset-for","title":"API Pack: A Massive Multi-Programming Language Dataset for API Call Generation","date":"2024-02-14","arxiv_id":"2402.09615","n_code_links":1,"syntology":null},{"paper":"/paper/aqa-bench-an-interactive-benchmark-for","slug":"aqa-bench-an-interactive-benchmark-for","title":"AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability","date":"2024-02-14","arxiv_id":"2402.09404","n_code_links":1,"syntology":null},{"paper":"/paper/bidirectional-generative-pre-training-for","slug":"bidirectional-generative-pre-training-for","title":"Bidirectional Generative Pre-training for Improving Healthcare Time-series Representation Learning","date":"2024-02-14","arxiv_id":"2402.09558","n_code_links":1,"syntology":null},{"paper":null,"slug":"changes-by-butterflies-farsighted-forecasting","title":"Changes by Butterflies: Farsighted Forecasting with Group Reservoir Transformer","date":"2024-02-14","arxiv_id":"2402.09573","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-composing-for-full-line-code","title":"Context Composing for Full Line Code Completion","date":"2024-02-14","arxiv_id":"2402.09230","n_code_links":0,"syntology":null},{"paper":null,"slug":"fgeo-tp-a-language-model-enhanced-solver-for","title":"FGeo-TP: A Language Model-Enhanced Solver for Geometry Problems","date":"2024-02-14","arxiv_id":"2402.09047","n_code_links":0,"syntology":null},{"paper":null,"slug":"heal-vit-vision-transformers-on-a-spherical","title":"HEAL-ViT: Vision Transformers on a spherical mesh for medium-range weather forecasting","date":"2024-02-14","arxiv_id":"2403.17016","n_code_links":0,"syntology":null},{"paper":null,"slug":"l3go-language-agents-with-chain-of-3d","title":"L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects","date":"2024-02-14","arxiv_id":"2402.09052","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-enhanced-1","title":"Leveraging Large Language Models for Enhanced NLP Task Performance through Knowledge Distillation and Optimized Training Strategies","date":"2024-02-14","arxiv_id":"2402.09282","n_code_links":0,"syntology":null},{"paper":"/paper/llasmol-advancing-large-language-models-for","slug":"llasmol-advancing-large-language-models-for","title":"LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset","date":"2024-02-14","arxiv_id":"2402.09391","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["osu-nlp-group/llm4chem"],"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/pyramid-attention-network-for-medical-image","slug":"pyramid-attention-network-for-medical-image","title":"Pyramid Attention Network for Medical Image Registration","date":"2024-02-14","arxiv_id":"2402.09016","n_code_links":1,"syntology":null},{"paper":null,"slug":"research-and-application-of-transformer-based","title":"Research and application of Transformer based anomaly detection model: A literature review","date":"2024-02-14","arxiv_id":"2402.08975","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-the-authoring-of-autotutors-with","slug":"scaling-the-authoring-of-autotutors-with","title":"AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails","date":"2024-02-14","arxiv_id":"2402.09216","n_code_links":1,"syntology":{"ran":4,"of":10,"n_ran_checked":4,"n_instrument":0,"unverified":6,"pointer_only":10,"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) · 6 unverified","official":{"repos":["eth-lre/mwptutor"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"stochastic-spiking-attention-accelerating","title":"Stochastic Spiking Attention: Accelerating Attention with Stochastic Computing in Spiking Networks","date":"2024-02-14","arxiv_id":"2402.09109","n_code_links":0,"syntology":null},{"paper":"/paper/tdvit-temporal-dilated-video-transformer-for","slug":"tdvit-temporal-dilated-video-transformer-for","title":"TDViT: Temporal Dilated Video Transformer for Dense Video Tasks","date":"2024-02-14","arxiv_id":"2402.09257","n_code_links":1,"syntology":null},{"paper":"/paper/towards-next-level-post-training-quantization","slug":"towards-next-level-post-training-quantization","title":"Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers","date":"2024-02-14","arxiv_id":"2402.08958","n_code_links":0,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"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) · 0 unverified","official":null}},{"paper":"/paper/bbox-adapter-lightweight-adapting-for-black","slug":"bbox-adapter-lightweight-adapting-for-black","title":"BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models","date":"2024-02-13","arxiv_id":"2402.08219","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"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":["haotiansun14/bbox-adapter"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/befunet-a-hybrid-cnn-transformer-architecture","slug":"befunet-a-hybrid-cnn-transformer-architecture","title":"BEFUnet: A Hybrid CNN-Transformer Architecture for Precise Medical Image Segmentation","date":"2024-02-13","arxiv_id":"2402.08793","n_code_links":1,"syntology":null},{"paper":null,"slug":"combining-insights-from-multiple-large","title":"Combining Insights From Multiple Large Language Models Improves Diagnostic Accuracy","date":"2024-02-13","arxiv_id":"2402.08806","n_code_links":0,"syntology":null},{"paper":"/paper/ecellm-generalizing-large-language-models-for","slug":"ecellm-generalizing-large-language-models-for","title":"eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data","date":"2024-02-13","arxiv_id":"2402.08831","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ninglab/ecellm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/instructgraph-boosting-large-language-models","slug":"instructgraph-boosting-large-language-models","title":"InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment","date":"2024-02-13","arxiv_id":"2402.08785","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-for-the-automated","slug":"large-language-models-for-the-automated","title":"Large Language Models for the Automated Analysis of Optimization Algorithms","date":"2024-02-13","arxiv_id":"2402.08472","n_code_links":1,"syntology":null},{"paper":"/paper/llaga-large-language-and-graph-assistant","slug":"llaga-large-language-and-graph-assistant","title":"LLaGA: Large Language and Graph Assistant","date":"2024-02-13","arxiv_id":"2402.08170","n_code_links":2,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["chenrunjin/llaga","vita-group/llaga"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"metatra-meta-learning-for-generalized","title":"MetaTra: Meta-Learning for Generalized Trajectory Prediction in Unseen Domain","date":"2024-02-13","arxiv_id":"2402.08221","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-limitations-of-the-transformer","title":"On Limitations of the Transformer Architecture","date":"2024-02-13","arxiv_id":"2402.08164","n_code_links":0,"syntology":null},{"paper":"/paper/optimized-information-flow-for-transformer","slug":"optimized-information-flow-for-transformer","title":"Optimized Information Flow for Transformer Tracking","date":"2024-02-13","arxiv_id":"2402.08195","n_code_links":1,"syntology":null},{"paper":"/paper/prompt-optimization-in-multi-step-tasks","slug":"prompt-optimization-in-multi-step-tasks","title":"PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling","date":"2024-02-13","arxiv_id":"2402.08702","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["yongchao98/promst"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-last-jitai-the-unreasonable-effectiveness","title":"The Last JITAI? Exploring Large Language Models for Issuing Just-in-Time Adaptive Interventions: Fostering Physical Activity in a Conceptual Cardiac Rehabilitation Setting","date":"2024-02-13","arxiv_id":"2402.08658","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-mechanisms-mimic-frontostriatal","title":"Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Tasks","date":"2024-02-13","arxiv_id":"2402.08211","n_code_links":0,"syntology":null},{"paper":"/paper/translating-images-to-road-network-a-non-1","slug":"translating-images-to-road-network-a-non-1","title":"Translating Images to Road Network: A Sequence-to-Sequence Perspective","date":"2024-02-13","arxiv_id":"2402.08207","n_code_links":3,"syntology":null},{"paper":"/paper/addressing-cognitive-bias-in-medical-language","slug":"addressing-cognitive-bias-in-medical-language","title":"Addressing cognitive bias in medical language models","date":"2024-02-12","arxiv_id":"2402.08113","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":6,"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) · 1 unverified","official":{"repos":["carlwharris/cog-bias-med-llms"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/air-bench-benchmarking-large-audio-language","slug":"air-bench-benchmarking-large-audio-language","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","date":"2024-02-12","arxiv_id":"2402.07729","n_code_links":1,"syntology":null},{"paper":"/paper/aydiv-adaptable-yielding-3d-object-detection","slug":"aydiv-adaptable-yielding-3d-object-detection","title":"AYDIV: Adaptable Yielding 3D Object Detection via Integrated Contextual Vision Transformer","date":"2024-02-12","arxiv_id":"2402.07680","n_code_links":1,"syntology":null},{"paper":null,"slug":"base-tts-lessons-from-building-a-billion","title":"BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data","date":"2024-02-12","arxiv_id":"2402.08093","n_code_links":0,"syntology":null},{"paper":"/paper/clustertabnet-supervised-clustering-method","slug":"clustertabnet-supervised-clustering-method","title":"ClusterTabNet: Supervised clustering method for table detection and table structure recognition","date":"2024-02-12","arxiv_id":"2402.07502","n_code_links":1,"syntology":{"ran":16,"of":16,"n_ran_checked":13,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sap-samples/clustertabnet"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/dolares-or-dollars-unraveling-the-bilingual","slug":"dolares-or-dollars-unraveling-the-bilingual","title":"Dólares or Dollars? Unraveling the Bilingual Prowess of Financial LLMs Between Spanish and English","date":"2024-02-12","arxiv_id":"2402.07405","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-multi-criteria-decision-analysis","title":"Enhancing Multi-Criteria Decision Analysis with AI: Integrating Analytic Hierarchy Process and GPT-4 for Automated Decision Support","date":"2024-02-12","arxiv_id":"2402.07404","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-programming-error-messages-in-real","title":"Enhancing Programming Error Messages in Real Time with Generative AI","date":"2024-02-12","arxiv_id":"2402.08072","n_code_links":0,"syntology":null},{"paper":null,"slug":"fourier-circuits-in-neural-networks-unlocking","title":"Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs","date":"2024-02-12","arxiv_id":"2402.09469","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-ad-referendum-how-good","title":"Large Language Models \"Ad Referendum\": How Good Are They at Machine Translation in the Legal Domain?","date":"2024-02-12","arxiv_id":"2402.07681","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-few-shot-generators","slug":"large-language-models-are-few-shot-generators","title":"Large Language Models are Few-shot Generators: Proposing Hybrid Prompt Algorithm To Generate Webshell Escape Samples","date":"2024-02-12","arxiv_id":"2402.07408","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-ai-to-advance-science-and","title":"Leveraging AI to Advance Science and Computing Education across Africa: Challenges, Progress and Opportunities","date":"2024-02-12","arxiv_id":"2402.07397","n_code_links":0,"syntology":null},{"paper":null,"slug":"message-detouring-a-simple-yet-effective","title":"Message Detouring: A Simple Yet Effective Cycle Representation for Expressive Graph Learning","date":"2024-02-12","arxiv_id":"2402.08085","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-self-verification-limitations-of-large","title":"On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks","date":"2024-02-12","arxiv_id":"2402.08115","n_code_links":0,"syntology":null},{"paper":"/paper/only-the-curve-shape-matters-training","slug":"only-the-curve-shape-matters-training","title":"Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction","date":"2024-02-12","arxiv_id":"2402.07570","n_code_links":0,"syntology":null},{"paper":null,"slug":"secret-collusion-among-generative-ai-agents","title":"Secret Collusion among Generative AI Agents: Multi-Agent Deception via Steganography","date":"2024-02-12","arxiv_id":"2402.07510","n_code_links":0,"syntology":null},{"paper":"/paper/sheet-music-transformer-end-to-end-optical","slug":"sheet-music-transformer-end-to-end-optical","title":"Sheet Music Transformer: End-To-End Optical Music Recognition Beyond Monophonic Transcription","date":"2024-02-12","arxiv_id":"2402.07596","n_code_links":1,"syntology":null},{"paper":null,"slug":"suppressing-pink-elephants-with-direct","title":"Suppressing Pink Elephants with Direct Principle Feedback","date":"2024-02-12","arxiv_id":"2402.07896","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-i-o-complexity-of-attention-or-how","title":"The I/O Complexity of Attention, or How Optimal is Flash Attention?","date":"2024-02-12","arxiv_id":"2402.07443","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-an-understanding-of-stepwise","title":"Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model","date":"2024-02-12","arxiv_id":"2402.07757","n_code_links":0,"syntology":null},{"paper":null,"slug":"transaxx-efficient-transformers-with","title":"TransAxx: Efficient Transformers with Approximate Computing","date":"2024-02-12","arxiv_id":"2402.07545","n_code_links":0,"syntology":null},{"paper":"/paper/vcr-video-representation-for-contextual","slug":"vcr-video-representation-for-contextual","title":"VCR: Video representation for Contextual Retrieval","date":"2024-02-12","arxiv_id":"2402.07466","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-do-large-language-models-navigate","title":"How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?","date":"2024-02-11","arxiv_id":"2402.07282","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-model-empowered-dose-volume","title":"Large-Language-Model Empowered Dose Volume Histogram Prediction for Intensity Modulated Radiotherapy","date":"2024-02-11","arxiv_id":"2402.07167","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-modal-emotion-recognition-by-text","title":"Multi-Modal Emotion Recognition by Text, Speech and Video Using Pretrained Transformers","date":"2024-02-11","arxiv_id":"2402.07327","n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-reinforcement-learning","title":"Natural Language Reinforcement Learning","date":"2024-02-11","arxiv_id":"2402.07157","n_code_links":0,"syntology":null},{"paper":"/paper/semi-mamba-unet-pixel-level-contrastive-cross","slug":"semi-mamba-unet-pixel-level-contrastive-cross","title":"Semi-Mamba-UNet: Pixel-Level Contrastive and Pixel-Level Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image Segmentation","date":"2024-02-11","arxiv_id":"2402.07245","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ziyangwang007/mamba-unet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/chemllm-a-chemical-large-language-model","slug":"chemllm-a-chemical-large-language-model","title":"ChemLLM: A Chemical Large Language Model","date":"2024-02-10","arxiv_id":"2402.06852","n_code_links":1,"syntology":null},{"paper":"/paper/gemini-goes-to-med-school-exploring-the","slug":"gemini-goes-to-med-school-exploring-the","title":"Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations","date":"2024-02-10","arxiv_id":"2402.07023","n_code_links":1,"syntology":null}],"record_sha256":"491445d4e8c3c705c8d1e6ead678705cff33f769f9bf86224bf50d385ab0da79","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}