{"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/38","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":38,"pages_in_order":139,"rows_per_page":100,"rows":[3701,3800],"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/37","next":"/method/position-wise-feed-forward-layer/papers/39","papers":[{"paper":"/paper/husky-a-unified-open-source-language-agent","slug":"husky-a-unified-open-source-language-agent","title":"Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning","date":"2024-06-10","arxiv_id":"2406.06469","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: 1 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["agent-husky/husky-v1"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/in-context-learning-and-fine-tuning-gpt-for","slug":"in-context-learning-and-fine-tuning-gpt-for","title":"In-Context Learning and Fine-Tuning GPT for Argument Mining","date":"2024-06-10","arxiv_id":"2406.06699","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-physical-simulation-with-message","title":"Learning Physical Simulation with Message Passing Transformer","date":"2024-06-10","arxiv_id":"2406.06060","n_code_links":0,"syntology":null},{"paper":null,"slug":"pointabm-integrating-bidirectional-state","title":"PointABM:Integrating Bidirectional State Space Model with Multi-Head Self-Attention for Point Cloud Analysis","date":"2024-06-10","arxiv_id":"2406.06069","n_code_links":0,"syntology":null},{"paper":null,"slug":"securenet-a-comparative-study-of-deberta-and","title":"SecureNet: A Comparative Study of DeBERTa and Large Language Models for Phishing Detection","date":"2024-06-10","arxiv_id":"2406.06663","n_code_links":0,"syntology":null},{"paper":"/paper/separate-and-reconstruct-asymmetric-encoder","slug":"separate-and-reconstruct-asymmetric-encoder","title":"Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation","date":"2024-06-10","arxiv_id":"2406.05983","n_code_links":1,"syntology":null},{"paper":null,"slug":"symmetric-dot-product-attention-for-efficient","title":"Symmetric Dot-Product Attention for Efficient Training of BERT Language Models","date":"2024-06-10","arxiv_id":"2406.06366","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-knowledge-component-based-methodology-for","title":"A Knowledge-Component-Based Methodology for Evaluating AI Assistants","date":"2024-06-09","arxiv_id":"2406.05603","n_code_links":0,"syntology":null},{"paper":"/paper/are-large-language-models-actually-good-at","slug":"are-large-language-models-actually-good-at","title":"Are Large Language Models Actually Good at Text Style Transfer?","date":"2024-06-09","arxiv_id":"2406.05885","n_code_links":1,"syntology":null},{"paper":"/paper/convolution-and-attention-free-mamba-based","slug":"convolution-and-attention-free-mamba-based","title":"CAMS: Convolution and Attention-Free Mamba-based Cardiac Image Segmentation","date":"2024-06-09","arxiv_id":"2406.05786","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-efficacy-of-large-language-1","title":"Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering","date":"2024-06-09","arxiv_id":"2406.06637","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-memorize-sensor","title":"Large Language Models Memorize Sensor Datasets! Implications on Human Activity Recognition Research","date":"2024-06-09","arxiv_id":"2406.05900","n_code_links":0,"syntology":null},{"paper":null,"slug":"od-detr-online-distillation-for-stabilizing","title":"OD-DETR: Online Distillation for Stabilizing Training of Detection Transformer","date":"2024-06-09","arxiv_id":"2406.05791","n_code_links":0,"syntology":null},{"paper":"/paper/sinklora-enhanced-efficiency-and-chat","slug":"sinklora-enhanced-efficiency-and-chat","title":"SinkLoRA: Enhanced Efficiency and Chat Capabilities for Long-Context Large Language Models","date":"2024-06-09","arxiv_id":"2406.05678","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":["dexter-gt-86/sinklora"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/smiles2dock-an-open-large-scale-multi-task","slug":"smiles2dock-an-open-large-scale-multi-task","title":"Smiles2Dock: an open large-scale multi-task dataset for ML-based molecular docking","date":"2024-06-09","arxiv_id":"2406.05738","n_code_links":1,"syntology":null},{"paper":null,"slug":"text2vp-generative-ai-for-visual-programming","title":"Text2VP: Generative AI for Visual Programming and Parametric Modeling","date":"2024-06-09","arxiv_id":"2407.07732","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-mamba-cutting-edge-classification-of","title":"Vision Mamba: Cutting-Edge Classification of Alzheimer's Disease with 3D MRI Scans","date":"2024-06-09","arxiv_id":"2406.05757","n_code_links":0,"syntology":null},{"paper":"/paper/a-fine-tuning-dataset-and-benchmark-for-large","slug":"a-fine-tuning-dataset-and-benchmark-for-large","title":"A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding","date":"2024-06-08","arxiv_id":"2406.05540","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["tsynbio/proteinlmdataset"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/automata-extraction-from-transformers","slug":"automata-extraction-from-transformers","title":"Automata Extraction from Transformers","date":"2024-06-08","arxiv_id":"2406.05564","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmarking-neural-decoding-backbones","title":"Benchmarking Neural Decoding Backbones towards Enhanced On-edge iBCI Applications","date":"2024-06-08","arxiv_id":"2406.06626","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-llms-recognize-me-when-i-is-not-me","title":"Do LLMs Recognize me, When I is not me: Assessment of LLMs Understanding of Turkish Indexical Pronouns in Indexical Shift Contexts","date":"2024-06-08","arxiv_id":"2406.05569","n_code_links":0,"syntology":null},{"paper":null,"slug":"g-transformer-counterfactual-outcome","title":"G-Transformer: Counterfactual Outcome Prediction under Dynamic and Time-varying Treatment Regimes","date":"2024-06-08","arxiv_id":"2406.05504","n_code_links":0,"syntology":null},{"paper":null,"slug":"selfdefend-llms-can-defend-themselves-against","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","date":"2024-06-08","arxiv_id":"2406.05498","n_code_links":0,"syntology":null},{"paper":null,"slug":"teaching-assistant-in-the-loop-improving","title":"Teaching-Assistant-in-the-Loop: Improving Knowledge Distillation from Imperfect Teacher Models in Low-Budget Scenarios","date":"2024-06-08","arxiv_id":"2406.05322","n_code_links":0,"syntology":null},{"paper":"/paper/toward-reliable-ad-hoc-scientific-information","slug":"toward-reliable-ad-hoc-scientific-information","title":"Toward Reliable Ad-hoc Scientific Information Extraction: A Case Study on Two Materials Datasets","date":"2024-06-08","arxiv_id":"2406.05348","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-conformal-prediction-for-time","slug":"transformer-conformal-prediction-for-time","title":"Transformer Conformal Prediction for Time Series","date":"2024-06-08","arxiv_id":"2406.05332","n_code_links":1,"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":{"repos":["Jayaos/TCPTS"],"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":"/paper/u-net-ensemble-for-enhanced-semantic","slug":"u-net-ensemble-for-enhanced-semantic","title":"U-Net Ensemble for Enhanced Semantic Segmentation in Remote Sensing Imagery","date":"2024-06-08","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-more-empathetic","title":"Are Large Language Models More Empathetic than Humans?","date":"2024-06-07","arxiv_id":"2406.05063","n_code_links":0,"syntology":null},{"paper":null,"slug":"cdefuse-continuous-decomposition-for-infrared","title":"Conti-Fuse: A Novel Continuous Decomposition-based Fusion Framework for Infrared and Visible Images","date":"2024-06-07","arxiv_id":"2406.04689","n_code_links":0,"syntology":null},{"paper":"/paper/diving-deep-into-the-motion-representation-of","slug":"diving-deep-into-the-motion-representation-of","title":"Diving Deep into the Motion Representation of Video-Text Models","date":"2024-06-07","arxiv_id":"2406.05075","n_code_links":1,"syntology":null},{"paper":"/paper/gamebench-evaluating-strategic-reasoning","slug":"gamebench-evaluating-strategic-reasoning","title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents","date":"2024-06-07","arxiv_id":"2406.06613","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Joshuaclymer/GameBench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hints-in-browser-benchmarking-language-models","title":"Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation","date":"2024-06-07","arxiv_id":"2406.05053","n_code_links":0,"syntology":null},{"paper":"/paper/improving-logits-based-detector-without","slug":"improving-logits-based-detector-without","title":"DALD: Improving Logits-based Detector without Logits from Black-box LLMs","date":"2024-06-07","arxiv_id":"2406.05232","n_code_links":1,"syntology":null},{"paper":"/paper/llavaguard-vlm-based-safeguards-for-vision","slug":"llavaguard-vlm-based-safeguards-for-vision","title":"LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models","date":"2024-06-07","arxiv_id":"2406.05113","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":["ml-research/llavaguard"],"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":"/paper/llms-are-not-intelligent-thinkers-introducing","slug":"llms-are-not-intelligent-thinkers-introducing","title":"LLMs Are Not Intelligent Thinkers: Introducing Mathematical Topic Tree Benchmark for Comprehensive Evaluation of LLMs","date":"2024-06-07","arxiv_id":"2406.05194","n_code_links":1,"syntology":null},{"paper":null,"slug":"logic-synthesis-with-generative-deep-neural","title":"Logic Synthesis with Generative Deep Neural Networks","date":"2024-06-07","arxiv_id":"2406.04699","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-resource-cross-lingual-summarization","title":"Low-Resource Cross-Lingual Summarization through Few-Shot Learning with Large Language Models","date":"2024-06-07","arxiv_id":"2406.04630","n_code_links":0,"syntology":null},{"paper":"/paper/mixture-of-agents-enhances-large-language","slug":"mixture-of-agents-enhances-large-language","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","date":"2024-06-07","arxiv_id":"2406.04692","n_code_links":3,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"multiplane-prior-guided-few-shot-aerial-scene","title":"Multiplane Prior Guided Few-Shot Aerial Scene Rendering","date":"2024-06-07","arxiv_id":"2406.04961","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-interpretable-deep-local-learning","title":"Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation","date":"2024-06-07","arxiv_id":"2406.05222","n_code_links":0,"syntology":null},{"paper":null,"slug":"unitst-effectively-modeling-inter-series-and","title":"UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting","date":"2024-06-07","arxiv_id":"2406.04975","n_code_links":0,"syntology":null},{"paper":"/paper/are-graphs-and-gcns-necessary-for-short-term","slug":"are-graphs-and-gcns-necessary-for-short-term","title":"Are Graphs and GCNs necessary for short-term metro ridership forecasting?","date":"2024-06-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmark-data-contamination-of-large","title":"Benchmark Data Contamination of Large Language Models: A Survey","date":"2024-06-06","arxiv_id":"2406.04244","n_code_links":0,"syntology":null},{"paper":"/paper/characterizing-similarities-and-divergences","slug":"characterizing-similarities-and-divergences","title":"Characterizing Similarities and Divergences in Conversational Tones in Humans and LLMs by Sampling with People","date":"2024-06-06","arxiv_id":"2406.04278","n_code_links":1,"syntology":null},{"paper":null,"slug":"credit-card-fraud-detection-using-advanced","title":"Credit Card Fraud Detection Using Advanced Transformer Model","date":"2024-06-06","arxiv_id":"2406.03733","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-variable-linear-integrated-enhanced","title":"Cross-variable Linear Integrated ENhanced Transformer for Photovoltaic power forecasting","date":"2024-06-06","arxiv_id":"2406.03808","n_code_links":0,"syntology":null},{"paper":"/paper/decoder-only-streaming-transformer-for","slug":"decoder-only-streaming-transformer-for","title":"Decoder-only Streaming Transformer for Simultaneous Translation","date":"2024-06-06","arxiv_id":"2406.03878","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["ictnlp/DST"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/enhancing-in-context-learning-performance","slug":"enhancing-in-context-learning-performance","title":"Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective","date":"2024-06-06","arxiv_id":"2406.03768","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":["chen123ctrls/enhancingicl_svdpruning"],"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":"exploring-the-latest-llms-for-leaderboard","title":"Exploring the Latest LLMs for Leaderboard Extraction","date":"2024-06-06","arxiv_id":"2406.04383","n_code_links":0,"syntology":null},{"paper":"/paper/generalization-enhanced-code-vulnerability","slug":"generalization-enhanced-code-vulnerability","title":"Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning","date":"2024-06-06","arxiv_id":"2406.03718","n_code_links":1,"syntology":null},{"paper":null,"slug":"glint-ru-gated-lightweight-intelligent","title":"GLINT-RU: Gated Lightweight Intelligent Recurrent Units for Sequential Recommender Systems","date":"2024-06-06","arxiv_id":"2406.10244","n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-plan-benchmarking-llms-on-natural","title":"NATURAL PLAN: Benchmarking LLMs on Natural Language Planning","date":"2024-06-06","arxiv_id":"2406.04520","n_code_links":0,"syntology":null},{"paper":null,"slug":"proactive-detection-of-physical-inter-rule","title":"Proactive Detection of Physical Inter-rule Vulnerabilities in IoT Services Using a Deep Learning Approach","date":"2024-06-06","arxiv_id":"2406.03836","n_code_links":0,"syntology":null},{"paper":null,"slug":"robocoder-robotic-learning-from-basic-skills","title":"RoboCoder: Robotic Learning from Basic Skills to General Tasks with Large Language Models","date":"2024-06-06","arxiv_id":"2406.03757","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-and-evaluating-sparse-autoencoders","slug":"scaling-and-evaluating-sparse-autoencoders","title":"Scaling and evaluating sparse autoencoders","date":"2024-06-06","arxiv_id":"2406.04093","n_code_links":5,"syntology":{"ran":7,"of":10,"n_ran_checked":5,"n_instrument":2,"unverified":3,"pointer_only":4,"phrase":"7 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["openai/sparse_autoencoder"],"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":["listed","official"]}}},{"paper":"/paper/tool-planner-dynamic-solution-tree-planning","slug":"tool-planner-dynamic-solution-tree-planning","title":"Tool-Planner: Task Planning with Clusters across Multiple Tools","date":"2024-06-06","arxiv_id":"2406.03807","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":1,"n_instrument":6,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["OceannTwT/Tool-Planner"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transformers-need-glasses-information-over","title":"Transformers need glasses! Information over-squashing in language tasks","date":"2024-06-06","arxiv_id":"2406.04267","n_code_links":0,"syntology":null},{"paper":null,"slug":"twins-revisiting-non-stationarity-in","title":"TwinS: Revisiting Non-Stationarity in Multivariate Time Series Forecasting","date":"2024-06-06","arxiv_id":"2406.03710","n_code_links":0,"syntology":null},{"paper":"/paper/ultramedical-building-specialized-generalists","slug":"ultramedical-building-specialized-generalists","title":"UltraMedical: Building Specialized Generalists in Biomedicine","date":"2024-06-06","arxiv_id":"2406.03949","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"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":["tsinghuac3i/ultramedical"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"what-languages-are-easy-to-language-model-a","title":"What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages","date":"2024-06-06","arxiv_id":"2406.04289","n_code_links":0,"syntology":null},{"paper":"/paper/aligning-transformers-with-weisfeiler-leman","slug":"aligning-transformers-with-weisfeiler-leman","title":"Aligning Transformers with Weisfeiler-Leman","date":"2024-06-05","arxiv_id":"2406.03148","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["luis-mueller/wl-transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"paper":null,"slug":"analyzing-llm-behavior-in-dialogue","title":"Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trends","date":"2024-06-05","arxiv_id":"2406.03487","n_code_links":0,"syntology":null},{"paper":null,"slug":"biped-pedagogically-informed-tutoring-system","title":"BIPED: Pedagogically Informed Tutoring System for ESL Education","date":"2024-06-05","arxiv_id":"2406.03486","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-3d-lane-detection-and-topology","slug":"enhancing-3d-lane-detection-and-topology","title":"Enhancing 3D Lane Detection and Topology Reasoning with 2D Lane Priors","date":"2024-06-05","arxiv_id":"2406.03105","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-efficacy-of-large-language","title":"Evaluating the Efficacy of Large Language Models in Detecting Fake News: A Comparative Analysis","date":"2024-06-05","arxiv_id":"2406.06584","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-tarzan-to-tolkien-controlling-the","title":"From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation","date":"2024-06-05","arxiv_id":"2406.03030","n_code_links":0,"syntology":null},{"paper":null,"slug":"get-a-generative-eeg-transformer-for","title":"GET: A Generative EEG Transformer for Continuous Context-Based Neural Signals","date":"2024-06-05","arxiv_id":"2406.03115","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-truncating-weights-improves-reasoning-in","title":"How Truncating Weights Improves Reasoning in Language Models","date":"2024-06-05","arxiv_id":"2406.03068","n_code_links":0,"syntology":null},{"paper":"/paper/learning-long-range-dependencies-on-graphs","slug":"learning-long-range-dependencies-on-graphs","title":"Learning Long Range Dependencies on Graphs via Random Walks","date":"2024-06-05","arxiv_id":"2406.03386","n_code_links":1,"syntology":{"ran":13,"of":13,"n_ran_checked":10,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["borgwardtlab/neuralwalker"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/lw-detr-a-transformer-replacement-to-yolo-for","slug":"lw-detr-a-transformer-replacement-to-yolo-for","title":"LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection","date":"2024-06-05","arxiv_id":"2406.03459","n_code_links":2,"syntology":{"ran":13,"of":16,"n_ran_checked":10,"n_instrument":3,"unverified":3,"pointer_only":4,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["atten4vis/lw-detr"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/mmcl-boosting-deformable-detr-based-detectors","slug":"mmcl-boosting-deformable-detr-based-detectors","title":"MMCL: Boosting Deformable DETR-Based Detectors with Multi-Class Min-Margin Contrastive Learning for Superior Prohibited Item Detection","date":"2024-06-05","arxiv_id":"2406.03176","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-microphone-speech-emotion-recognition","title":"Multi-Microphone Speech Emotion Recognition using the Hierarchical Token-semantic Audio Transformer Architecture","date":"2024-06-05","arxiv_id":"2406.03272","n_code_links":0,"syntology":null},{"paper":"/paper/population-transformer-learning-population","slug":"population-transformer-learning-population","title":"Population Transformer: Learning Population-level Representations of Neural Activity","date":"2024-06-05","arxiv_id":"2406.03044","n_code_links":1,"syntology":{"ran":4,"of":9,"n_ran_checked":4,"n_instrument":0,"unverified":5,"pointer_only":9,"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) · 5 unverified","official":{"repos":["czlwang/populationtransformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/predicting-genetic-mutation-from-whole-slide","slug":"predicting-genetic-mutation-from-whole-slide","title":"Predicting Genetic Mutation from Whole Slide Images via Biomedical-Linguistic Knowledge Enhanced Multi-label Classification","date":"2024-06-05","arxiv_id":"2406.02990","n_code_links":1,"syntology":null},{"paper":"/paper/puzzle-pieces-picker-deciphering-ancient","slug":"puzzle-pieces-picker-deciphering-ancient","title":"Puzzle Pieces Picker: Deciphering Ancient Chinese Characters with Radical Reconstruction","date":"2024-06-05","arxiv_id":"2406.03019","n_code_links":1,"syntology":null},{"paper":"/paper/streamspeech-simultaneous-speech-to-speech","slug":"streamspeech-simultaneous-speech-to-speech","title":"StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning","date":"2024-06-05","arxiv_id":"2406.03049","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["ictnlp/streamspeech"],"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":["official"]}}},{"paper":"/paper/superformer-volumetric-transformer","slug":"superformer-volumetric-transformer","title":"SuperFormer: Volumetric Transformer Architectures for MRI Super-Resolution","date":"2024-06-05","arxiv_id":"2406.03359","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-good-the-bad-and-the-hulk-like-gpt","title":"The Good, the Bad, and the Hulk-like GPT: Analyzing Emotional Decisions of Large Language Models in Cooperation and Bargaining Games","date":"2024-06-05","arxiv_id":"2406.03299","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-is-the-best-way-for-chatgpt-to-translate","title":"What is the Best Way for ChatGPT to Translate Poetry?","date":"2024-06-05","arxiv_id":"2406.03450","n_code_links":0,"syntology":null},{"paper":"/paper/a-temporal-kolmogorov-arnold-transformer-for","slug":"a-temporal-kolmogorov-arnold-transformer-for","title":"A Temporal Kolmogorov-Arnold Transformer for Time Series Forecasting","date":"2024-06-04","arxiv_id":"2406.02486","n_code_links":1,"syntology":null},{"paper":"/paper/audio-mamba-selective-state-spaces-for-self","slug":"audio-mamba-selective-state-spaces-for-self","title":"Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations","date":"2024-06-04","arxiv_id":"2406.02178","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["SarthakYadav/audio-mamba-official"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/block-transformer-global-to-local-language","slug":"block-transformer-global-to-local-language","title":"Block Transformer: Global-to-Local Language Modeling for Fast Inference","date":"2024-06-04","arxiv_id":"2406.02657","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":["itsnamgyu/block-transformer"],"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":"contextual-dynamic-pricing-algorithms","title":"Contextual Dynamic Pricing: Algorithms, Optimality, and Local Differential Privacy Constraints","date":"2024-06-04","arxiv_id":"2406.02424","n_code_links":0,"syntology":null},{"paper":null,"slug":"dishonesty-in-helpful-and-harmless-alignment","title":"Dishonesty in Helpful and Harmless Alignment","date":"2024-06-04","arxiv_id":"2406.01931","n_code_links":0,"syntology":null},{"paper":null,"slug":"eliciting-the-priors-of-large-language-models","title":"Eliciting the Priors of Large Language Models using Iterated In-Context Learning","date":"2024-06-04","arxiv_id":"2406.01860","n_code_links":0,"syntology":null},{"paper":null,"slug":"explicitly-encoding-structural-symmetry-is","title":"Explicitly Encoding Structural Symmetry is Key to Length Generalization in Arithmetic Tasks","date":"2024-06-04","arxiv_id":"2406.01895","n_code_links":0,"syntology":null},{"paper":"/paper/grootvl-tree-topology-is-all-you-need-in","slug":"grootvl-tree-topology-is-all-you-need-in","title":"GrootVL: Tree Topology is All You Need in State Space Model","date":"2024-06-04","arxiv_id":"2406.02395","n_code_links":2,"syntology":{"ran":9,"of":14,"n_ran_checked":8,"n_instrument":1,"unverified":5,"pointer_only":14,"phrase":"9 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; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["easonxiao-888/grootvl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improved-context-sensitive-transformer-model","title":"Improved context-sensitive transformer model for inland vessel trajectory prediction","date":"2024-06-04","arxiv_id":"2406.02771","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-model-enabled-multi-agent","title":"Large Language Model-Enabled Multi-Agent Manufacturing Systems","date":"2024-06-04","arxiv_id":"2406.01893","n_code_links":0,"syntology":null},{"paper":"/paper/mamba-as-decision-maker-exploring-multi-scale","slug":"mamba-as-decision-maker-exploring-multi-scale","title":"Mamba as Decision Maker: Exploring Multi-scale Sequence Modeling in Offline Reinforcement Learning","date":"2024-06-04","arxiv_id":"2406.02013","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-layer-learnable-attention-mask-for","title":"Multi-layer Learnable Attention Mask for Multimodal Tasks","date":"2024-06-04","arxiv_id":"2406.02761","n_code_links":0,"syntology":null},{"paper":"/paper/multiple-choice-questions-and-large-languages","slug":"multiple-choice-questions-and-large-languages","title":"Multiple Choice Questions and Large Languages Models: A Case Study with Fictional Medical Data","date":"2024-06-04","arxiv_id":"2406.02394","n_code_links":1,"syntology":null},{"paper":null,"slug":"spatial-and-social-situation-aware","title":"Spatial and social situation-aware transformer-based trajectory prediction of autonomous systems","date":"2024-06-04","arxiv_id":"2406.02767","n_code_links":0,"syntology":null},{"paper":"/paper/stable-pose-leveraging-transformers-for-pose","slug":"stable-pose-leveraging-transformers-for-pose","title":"Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation","date":"2024-06-04","arxiv_id":"2406.02485","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":11,"n_instrument":1,"unverified":1,"pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 4 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ai-med/stablepose"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"technical-language-processing-for","title":"Technical Language Processing for Telecommunications Specifications","date":"2024-06-04","arxiv_id":"2406.02325","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-auditory-evoked-brain-signal","title":"Understanding Auditory Evoked Brain Signal via Physics-informed Embedding Network with Multi-Task Transformer","date":"2024-06-04","arxiv_id":"2406.02014","n_code_links":0,"syntology":null},{"paper":"/paper/vidit-q-efficient-and-accurate-quantization","slug":"vidit-q-efficient-and-accurate-quantization","title":"ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation","date":"2024-06-04","arxiv_id":"2406.02540","n_code_links":1,"syntology":{"ran":3,"of":10,"n_ran_checked":3,"n_instrument":0,"unverified":7,"pointer_only":10,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["a-suozhang/vidit-q"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"what-improves-the-generalization-of-graph","title":"What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding","date":"2024-06-04","arxiv_id":"2406.01977","n_code_links":0,"syntology":null},{"paper":null,"slug":"badrag-identifying-vulnerabilities-in","title":"BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models","date":"2024-06-03","arxiv_id":"2406.00083","n_code_links":0,"syntology":null},{"paper":null,"slug":"compute-efficient-medical-image","title":"Compute-Efficient Medical Image Classification with Softmax-Free Transformers and Sequence Normalization","date":"2024-06-03","arxiv_id":"2406.01314","n_code_links":0,"syntology":null}],"record_sha256":"d5a14f26df967a0da7f7cdf790a2f9494fe64d317f597be0f29689be5d3f9a33","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}