{"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/40","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":40,"pages_in_order":139,"rows_per_page":100,"rows":[3901,4000],"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/39","next":"/method/position-wise-feed-forward-layer/papers/41","papers":[{"paper":"/paper/harmodt-harmony-multi-task-decision","slug":"harmodt-harmony-multi-task-decision","title":"HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning","date":"2024-05-28","arxiv_id":"2405.18080","n_code_links":1,"syntology":null},{"paper":null,"slug":"iapt-instruction-aware-prompt-tuning-for","title":"IAPT: Instruction-Aware Prompt Tuning for Large Language Models","date":"2024-05-28","arxiv_id":"2405.18203","n_code_links":0,"syntology":null},{"paper":"/paper/ldmol-text-conditioned-molecule-diffusion","slug":"ldmol-text-conditioned-molecule-diffusion","title":"LDMol: Text-to-Molecule Diffusion Model with Structurally Informative Latent Space","date":"2024-05-28","arxiv_id":"2405.17829","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":5,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jinhojsk515/ldmol"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"lstm-cox-model-a-concise-and-efficient-deep","title":"Modeling Long Sequences in Bladder Cancer Recurrence: A Comparative Evaluation of LSTM,Transformer,and Mamba","date":"2024-05-28","arxiv_id":"2405.18518","n_code_links":0,"syntology":null},{"paper":null,"slug":"mindformer-a-transformer-architecture-for","title":"MindFormer: Semantic Alignment of Multi-Subject fMRI for Brain Decoding","date":"2024-05-28","arxiv_id":"2405.17720","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-objective-representation-for-numbers-in","title":"Multi-objective Representation for Numbers in Clinical Narratives: A CamemBERT-Bio-Based Alternative to Large-Scale LLMs","date":"2024-05-28","arxiv_id":"2405.18448","n_code_links":0,"syntology":null},{"paper":null,"slug":"notes-on-applicability-of-gpt-4-to-document","title":"Notes on Applicability of GPT-4 to Document Understanding","date":"2024-05-28","arxiv_id":"2405.18433","n_code_links":0,"syntology":null},{"paper":"/paper/orlm-training-large-language-models-for","slug":"orlm-training-large-language-models-for","title":"ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling","date":"2024-05-28","arxiv_id":"2405.17743","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"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) · 2 unverified","official":{"repos":["cardinal-operations/orlm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/ov-dquo-open-vocabulary-detr-with-denoising","slug":"ov-dquo-open-vocabulary-detr-with-denoising","title":"OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision","date":"2024-05-28","arxiv_id":"2405.17913","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":7,"n_instrument":2,"unverified":2,"pointer_only":2,"phrase":"9 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["xiaomoguhz/ov-dquo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/peering-into-the-mind-of-language-models-an","slug":"peering-into-the-mind-of-language-models-an","title":"Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering","date":"2024-05-28","arxiv_id":"2405.17980","n_code_links":1,"syntology":null},{"paper":null,"slug":"proof-of-quality-a-costless-paradigm-for","title":"Proof of Quality: A Costless Paradigm for Trustless Generative AI Model Inference on Blockchains","date":"2024-05-28","arxiv_id":"2405.17934","n_code_links":0,"syntology":null},{"paper":null,"slug":"realitysummary-on-demand-mixed-reality","title":"RealitySummary: Exploring On-Demand Mixed Reality Text Summarization and Question Answering using Large Language Models","date":"2024-05-28","arxiv_id":"2405.18620","n_code_links":0,"syntology":null},{"paper":"/paper/thai-winograd-schemas-a-benchmark-for-thai","slug":"thai-winograd-schemas-a-benchmark-for-thai","title":"Thai Winograd Schemas: A Benchmark for Thai Commonsense Reasoning","date":"2024-05-28","arxiv_id":"2405.18375","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-battle-of-llms-a-comparative-study-in","title":"The Battle of LLMs: A Comparative Study in Conversational QA Tasks","date":"2024-05-28","arxiv_id":"2405.18344","n_code_links":0,"syntology":null},{"paper":"/paper/vig-linear-complexity-visual-sequence","slug":"vig-linear-complexity-visual-sequence","title":"ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention","date":"2024-05-28","arxiv_id":"2405.18425","n_code_links":1,"syntology":null},{"paper":"/paper/visual-anchors-are-strong-information","slug":"visual-anchors-are-strong-information","title":"Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model","date":"2024-05-28","arxiv_id":"2405.17815","n_code_links":1,"syntology":null},{"paper":null,"slug":"viton-dit-learning-in-the-wild-video-try-on","title":"VITON-DiT: Learning In-the-Wild Video Try-On from Human Dance Videos via Diffusion Transformers","date":"2024-05-28","arxiv_id":"2405.18326","n_code_links":0,"syntology":null},{"paper":null,"slug":"wavelet-based-image-tokenizer-for-vision","title":"Wavelet-Based Image Tokenizer for Vision Transformers","date":"2024-05-28","arxiv_id":"2405.18616","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-one-layer-decoder-only-transformer-is-a-two","title":"A One-Layer Decoder-Only Transformer is a Two-Layer RNN: With an Application to Certified Robustness","date":"2024-05-27","arxiv_id":"2405.17361","n_code_links":0,"syntology":null},{"paper":"/paper/advanced-language-model-based-translator-for","slug":"advanced-language-model-based-translator-for","title":"Advanced Language Model-based Translator for English-Vietnamese Translation","date":"2024-05-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/are-self-attentions-effective-for-time-series","slug":"are-self-attentions-effective-for-time-series","title":"Are Self-Attentions Effective for Time Series Forecasting?","date":"2024-05-27","arxiv_id":"2405.16877","n_code_links":1,"syntology":{"ran":5,"of":13,"n_ran_checked":5,"n_instrument":0,"unverified":8,"pointer_only":3,"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) · 8 unverified","official":{"repos":["dongbeank/cats"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/autoformalizing-euclidean-geometry","slug":"autoformalizing-euclidean-geometry","title":"Autoformalizing Euclidean Geometry","date":"2024-05-27","arxiv_id":"2405.17216","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":4,"n_instrument":5,"unverified":4,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","official":{"repos":["loganrjmurphy/leaneuclid"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"automatic-domain-adaptation-by-transformers","title":"Automatic Domain Adaptation by Transformers in In-Context Learning","date":"2024-05-27","arxiv_id":"2405.16819","n_code_links":0,"syntology":null},{"paper":null,"slug":"behaviorgpt-smart-agent-simulation-for","title":"BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction","date":"2024-05-27","arxiv_id":"2405.17372","n_code_links":0,"syntology":null},{"paper":"/paper/chess-contextual-harnessing-for-efficient-sql","slug":"chess-contextual-harnessing-for-efficient-sql","title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","date":"2024-05-27","arxiv_id":"2405.16755","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":["shayantalaei/chess"],"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":null,"slug":"cost-efficient-knowledge-based-question","title":"Cost-efficient Knowledge-based Question Answering with Large Language Models","date":"2024-05-27","arxiv_id":"2405.17337","n_code_links":0,"syntology":null},{"paper":"/paper/deciphering-movement-unified-trajectory","slug":"deciphering-movement-unified-trajectory","title":"Deciphering Movement: Unified Trajectory Generation Model for Multi-Agent","date":"2024-05-27","arxiv_id":"2405.17680","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":["colorfulfuture/unitraj-pytorch"],"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":null,"slug":"galaxy-a-resource-efficient-collaborative","title":"Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference","date":"2024-05-27","arxiv_id":"2405.17245","n_code_links":0,"syntology":null},{"paper":"/paper/generation-and-human-expert-evaluation-of","slug":"generation-and-human-expert-evaluation-of","title":"Interesting Scientific Idea Generation using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders","date":"2024-05-27","arxiv_id":"2405.17044","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-does-perfect-fitting-affect","title":"How Do the Architecture and Optimizer Affect Representation Learning? On the Training Dynamics of Representations in Deep Neural Networks","date":"2024-05-27","arxiv_id":"2405.17377","n_code_links":0,"syntology":null},{"paper":"/paper/lcm-locally-constrained-compact-point-cloud","slug":"lcm-locally-constrained-compact-point-cloud","title":"LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling","date":"2024-05-27","arxiv_id":"2405.17149","n_code_links":1,"syntology":{"ran":12,"of":12,"n_ran_checked":5,"n_instrument":7,"unverified":0,"pointer_only":10,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zyh16143998882/lcm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"paper":null,"slug":"llm-based-cooperative-agents-using","title":"REVECA: Adaptive Planning and Trajectory-based Validation in Cooperative Language Agents using Information Relevance and Relative Proximity","date":"2024-05-27","arxiv_id":"2405.16751","n_code_links":0,"syntology":null},{"paper":"/paper/loretrack-efficient-and-accurate-low","slug":"loretrack-efficient-and-accurate-low","title":"LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking","date":"2024-05-27","arxiv_id":"2405.17660","n_code_links":1,"syntology":null},{"paper":"/paper/motionllm-multimodal-motion-language-learning","slug":"motionllm-multimodal-motion-language-learning","title":"Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs","date":"2024-05-27","arxiv_id":"2405.17013","n_code_links":1,"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":["szqwu/Motion-Agent"],"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":null,"slug":"novel-approaches-for-ml-assisted-particle","title":"Novel Approaches for ML-Assisted Particle Track Reconstruction and Hit Clustering","date":"2024-05-27","arxiv_id":"2405.17325","n_code_links":0,"syntology":null},{"paper":null,"slug":"pivotmesh-generic-3d-mesh-generation-via","title":"PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance","date":"2024-05-27","arxiv_id":"2405.16890","n_code_links":0,"syntology":null},{"paper":"/paper/q-value-regularized-transformer-for-offline","slug":"q-value-regularized-transformer-for-offline","title":"Q-value Regularized Transformer for Offline Reinforcement Learning","date":"2024-05-27","arxiv_id":"2405.17098","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":5,"n_instrument":1,"unverified":2,"pointer_only":3,"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) · 2 unverified","official":null}},{"paper":"/paper/reflectioncoder-learning-from-reflection","slug":"reflectioncoder-learning-from-reflection","title":"ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation","date":"2024-05-27","arxiv_id":"2405.17057","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["sensellm/reflectioncoder"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/rethinking-transformers-in-solving-pomdps","slug":"rethinking-transformers-in-solving-pomdps","title":"Rethinking Transformers in Solving POMDPs","date":"2024-05-27","arxiv_id":"2405.17358","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["ctp314/tfporl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/rtl-repo-a-benchmark-for-evaluating-llms-on","slug":"rtl-repo-a-benchmark-for-evaluating-llms-on","title":"RTL-Repo: A Benchmark for Evaluating LLMs on Large-Scale RTL Design Projects","date":"2024-05-27","arxiv_id":"2405.17378","n_code_links":1,"syntology":null},{"paper":"/paper/safe-lora-the-silver-lining-of-reducing","slug":"safe-lora-the-silver-lining-of-reducing","title":"Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models","date":"2024-05-27","arxiv_id":"2405.16833","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["ibm/safelora"],"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":"supervised-batch-normalization","title":"Supervised Batch Normalization","date":"2024-05-27","arxiv_id":"2405.17027","n_code_links":0,"syntology":null},{"paper":null,"slug":"swat-scalable-and-efficient-window-attention","title":"SWAT: Scalable and Efficient Window Attention-based Transformers Acceleration on FPGAs","date":"2024-05-27","arxiv_id":"2405.17025","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-scaling-law-in-stellar-light-curves","title":"The Scaling Law in Stellar Light Curves","date":"2024-05-27","arxiv_id":"2405.17156","n_code_links":0,"syntology":null},{"paper":"/paper/thread-thinking-deeper-with-recursive","slug":"thread-thinking-deeper-with-recursive","title":"THREAD: Thinking Deeper with Recursive Spawning","date":"2024-05-27","arxiv_id":"2405.17402","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":11,"phrase":"7 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; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["philipmit/thread"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transformer-in-context-learning-for","title":"On Understanding Attention-Based In-Context Learning for Categorical Data","date":"2024-05-27","arxiv_id":"2405.17248","n_code_links":0,"syntology":null},{"paper":null,"slug":"uit-darkcow-team-at-imageclefmedical-caption","title":"UIT-DarkCow team at ImageCLEFmedical Caption 2024: Diagnostic Captioning for Radiology Images Efficiency with Transformer Models","date":"2024-05-27","arxiv_id":"2405.17002","n_code_links":0,"syntology":null},{"paper":"/paper/unisolver-pde-conditional-transformers-are","slug":"unisolver-pde-conditional-transformers-are","title":"Unisolver: PDE-Conditional Transformers Are Universal PDE Solvers","date":"2024-05-27","arxiv_id":"2405.17527","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"5 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; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"vision-and-language-navigation-generative","title":"Vision-and-Language Navigation Generative Pretrained Transformer","date":"2024-05-27","arxiv_id":"2405.16994","n_code_links":0,"syntology":null},{"paper":"/paper/a-unified-implicit-attention-formulation-for","slug":"a-unified-implicit-attention-formulation-for","title":"Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation","date":"2024-05-26","arxiv_id":"2405.16504","n_code_links":1,"syntology":null},{"paper":"/paper/darijabanking-a-new-resource-for-overcoming","slug":"darijabanking-a-new-resource-for-overcoming","title":"DarijaBanking: A New Resource for Overcoming Language Barriers in Banking Intent Detection for Moroccan Arabic Speakers","date":"2024-05-26","arxiv_id":"2405.16482","n_code_links":1,"syntology":null},{"paper":"/paper/demystify-mamba-in-vision-a-linear-attention","slug":"demystify-mamba-in-vision-a-linear-attention","title":"Demystify Mamba in Vision: A Linear Attention Perspective","date":"2024-05-26","arxiv_id":"2405.16605","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 6 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) · 2 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","official":{"repos":["LeapLabTHU/MLLA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/disentangling-and-integrating-relational-and","slug":"disentangling-and-integrating-relational-and","title":"Disentangling and Integrating Relational and Sensory Information in Transformer Architectures","date":"2024-05-26","arxiv_id":"2405.16727","n_code_links":2,"syntology":{"ran":14,"of":21,"n_ran_checked":10,"n_instrument":4,"unverified":7,"pointer_only":0,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","official":{"repos":["awni00/dual-attention"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/mambats-improved-selective-state-space-models","slug":"mambats-improved-selective-state-space-models","title":"MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting","date":"2024-05-26","arxiv_id":"2405.16440","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":4,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["XiudingCai/MambaTS-pytorch"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/meta-task-planning-for-language-agents","slug":"meta-task-planning-for-language-agents","title":"Planning with Multi-Constraints via Collaborative Language Agents","date":"2024-05-26","arxiv_id":"2405.16510","n_code_links":1,"syntology":null},{"paper":null,"slug":"scalable-numerical-embeddings-for","title":"Scalable Numerical Embeddings for Multivariate Time Series: Enhancing Healthcare Data Representation Learning","date":"2024-05-26","arxiv_id":"2405.16557","n_code_links":0,"syntology":null},{"paper":"/paper/spinquant-llm-quantization-with-learned","slug":"spinquant-llm-quantization-with-learned","title":"SpinQuant: LLM quantization with learned rotations","date":"2024-05-26","arxiv_id":"2405.16406","n_code_links":3,"syntology":{"ran":10,"of":10,"n_ran_checked":7,"n_instrument":3,"unverified":0,"pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/accelerating-transformers-with-spectrum-1","slug":"accelerating-transformers-with-spectrum-1","title":"Accelerating Transformers with Spectrum-Preserving Token Merging","date":"2024-05-25","arxiv_id":"2405.16148","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":2,"n_instrument":4,"unverified":1,"pointer_only":7,"phrase":"6 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; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hchautran/PiToMe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"comparative-analysis-of-open-source-language","title":"Comparative Analysis of Open-Source Language Models in Summarizing Medical Text Data","date":"2024-05-25","arxiv_id":"2405.16295","n_code_links":0,"syntology":null},{"paper":"/paper/confidence-under-the-hood-an-investigation","slug":"confidence-under-the-hood-an-investigation","title":"Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models","date":"2024-05-25","arxiv_id":"2405.16282","n_code_links":1,"syntology":{"ran":1,"of":6,"n_ran_checked":1,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 5 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["akkeshav/confidence_probability_alignment"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dynamic-inhomogeneous-quantum-resource","title":"Dynamic Inhomogeneous Quantum Resource Scheduling with Reinforcement Learning","date":"2024-05-25","arxiv_id":"2405.16380","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-temporal-action-segmentation-via","slug":"efficient-temporal-action-segmentation-via","title":"Efficient Temporal Action Segmentation via Boundary-aware Query Voting","date":"2024-05-25","arxiv_id":"2405.15995","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-deep-learning-methods-applied-to","slug":"evaluating-deep-learning-methods-applied-to","title":"Evaluating deep learning methods applied to Landsat time series subsequences to detect and classify boreal forest disturbances events: The challenge of partial and progressive disturbances","date":"2024-05-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"geneagent-self-verification-language-agent","title":"GeneAgent: Self-verification Language Agent for Gene Set Knowledge Discovery using Domain Databases","date":"2024-05-25","arxiv_id":"2405.16205","n_code_links":0,"syntology":null},{"paper":null,"slug":"hethub-a-heterogeneous-distributed-hybrid","title":"HETHUB: A Distributed Training System with Heterogeneous Cluster for Large-Scale Models","date":"2024-05-25","arxiv_id":"2405.16256","n_code_links":0,"syntology":null},{"paper":"/paper/lateralization-mlp-a-simple-brain-inspired","slug":"lateralization-mlp-a-simple-brain-inspired","title":"Lateralization MLP: A Simple Brain-inspired Architecture for Diffusion","date":"2024-05-25","arxiv_id":"2405.16098","n_code_links":1,"syntology":null},{"paper":"/paper/moeut-mixture-of-experts-universal","slug":"moeut-mixture-of-experts-universal","title":"MoEUT: Mixture-of-Experts Universal Transformers","date":"2024-05-25","arxiv_id":"2405.16039","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":5,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"8 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["robertcsordas/moeut"],"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":null,"slug":"picturing-ambiguity-a-visual-twist-on-the","title":"Picturing Ambiguity: A Visual Twist on the Winograd Schema Challenge","date":"2024-05-25","arxiv_id":"2405.16277","n_code_links":0,"syntology":null},{"paper":"/paper/stride-a-tool-assisted-llm-agent-framework","slug":"stride-a-tool-assisted-llm-agent-framework","title":"STRIDE: A Tool-Assisted LLM Agent Framework for Strategic and Interactive Decision-Making","date":"2024-05-25","arxiv_id":"2405.16376","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["cyrilli/stride"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-black-box-membership-inference-attack","title":"Towards Black-Box Membership Inference Attack for Diffusion Models","date":"2024-05-25","arxiv_id":"2405.20771","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-meets-gated-residual-networks-to","title":"Transformer Meets Gated Residual Networks To Enhance Photoplethysmogram Artifact Detection Informed by Mutual Information Neural Estimation","date":"2024-05-25","arxiv_id":"2405.16177","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-evaluation-of-estimative-uncertainty-in","title":"An Evaluation of Estimative Uncertainty in Large Language Models","date":"2024-05-24","arxiv_id":"2405.15185","n_code_links":0,"syntology":null},{"paper":"/paper/before-generation-align-it-a-novel-and","slug":"before-generation-align-it-a-novel-and","title":"Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation","date":"2024-05-24","arxiv_id":"2405.15307","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":7,"n_instrument":1,"unverified":2,"pointer_only":10,"phrase":"8 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["quge2023/TA-SQL"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"benchmarking-hierarchical-image-pyramid","title":"Benchmarking Hierarchical Image Pyramid Transformer for the classification of colon biopsies and polyps in histopathology images","date":"2024-05-24","arxiv_id":"2405.15127","n_code_links":0,"syntology":null},{"paper":"/paper/continuously-learning-adapting-and-improving","slug":"continuously-learning-adapting-and-improving","title":"Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving","date":"2024-05-24","arxiv_id":"2405.15324","n_code_links":1,"syntology":null},{"paper":"/paper/convllava-hierarchical-backbones-as-visual","slug":"convllava-hierarchical-backbones-as-visual","title":"ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models","date":"2024-05-24","arxiv_id":"2405.15738","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":5,"n_instrument":3,"unverified":2,"pointer_only":1,"phrase":"8 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alibaba/conv-llava"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/culturepark-boosting-cross-cultural","slug":"culturepark-boosting-cross-cultural","title":"CulturePark: Boosting Cross-cultural Understanding in Large Language Models","date":"2024-05-24","arxiv_id":"2405.15145","n_code_links":1,"syntology":{"ran":0,"of":7,"n_ran_checked":0,"n_instrument":0,"unverified":7,"pointer_only":7,"phrase":"0 ran · 7 unverified","official":{"repos":["scarelette/culturepark"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":[]}}},{"paper":null,"slug":"distinguish-any-fake-videos-unleashing-the","title":"Distinguish Any Fake Videos: Unleashing the Power of Large-scale Data and Motion Features","date":"2024-05-24","arxiv_id":"2405.15343","n_code_links":0,"syntology":null},{"paper":"/paper/filtered-corpus-training-fict-shows-that","slug":"filtered-corpus-training-fict-shows-that","title":"Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidence","date":"2024-05-24","arxiv_id":"2405.15750","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-reflect-human-citation","slug":"large-language-models-reflect-human-citation","title":"Large Language Models Reflect Human Citation Patterns with a Heightened Citation Bias","date":"2024-05-24","arxiv_id":"2405.15739","n_code_links":1,"syntology":null},{"paper":"/paper/machine-unlearning-in-large-language-models","slug":"machine-unlearning-in-large-language-models","title":"Machine Unlearning in Large Language Models","date":"2024-05-24","arxiv_id":"2405.15152","n_code_links":1,"syntology":null},{"paper":"/paper/mambavc-learned-visual-compression-with","slug":"mambavc-learned-visual-compression-with","title":"MambaVC: Learned Visual Compression with Selective State Spaces","date":"2024-05-24","arxiv_id":"2405.15413","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"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) · 0 unverified","official":{"repos":["qinsy123/2024-mambavc"],"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":"matchings-predictions-and-counterfactual-harm","title":"Matchings, Predictions and Counterfactual Harm in Refugee Resettlement Processes","date":"2024-05-24","arxiv_id":"2407.13052","n_code_links":0,"syntology":null},{"paper":"/paper/memo-meaningful-modular-controllers-via-noise","slug":"memo-meaningful-modular-controllers-via-noise","title":"MeMo: Meaningful, Modular Controllers via Noise Injection","date":"2024-05-24","arxiv_id":"2407.01567","n_code_links":0,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"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":null}},{"paper":"/paper/mlps-learn-in-context","slug":"mlps-learn-in-context","title":"MLPs Learn In-Context on Regression and Classification Tasks","date":"2024-05-24","arxiv_id":"2405.15618","n_code_links":2,"syntology":{"ran":15,"of":16,"n_ran_checked":13,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["wtong98/mlp-icl"],"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":["listed","official"]}}},{"paper":"/paper/pointramba-a-hybrid-transformer-mamba","slug":"pointramba-a-hybrid-transformer-mamba","title":"PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis","date":"2024-05-24","arxiv_id":"2405.15463","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":7,"n_instrument":1,"unverified":0,"pointer_only":7,"phrase":"8 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xiaoyao3302/pointramba"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/spectraformer-a-unified-random-feature","slug":"spectraformer-a-unified-random-feature","title":"Spectraformer: A Unified Random Feature Framework for Transformer","date":"2024-05-24","arxiv_id":"2405.15310","n_code_links":2,"syntology":null},{"paper":null,"slug":"steerable-transformers","title":"Steerable Transformers","date":"2024-05-24","arxiv_id":"2405.15932","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-guided-3d-human-motion-generation-with","title":"Text-guided 3D Human Motion Generation with Keyframe-based Parallel Skip Transformer","date":"2024-05-24","arxiv_id":"2405.15439","n_code_links":0,"syntology":null},{"paper":null,"slug":"textit-comet-a-underline-com-munication","title":"Comet: A Communication-efficient and Performant Approximation for Private Transformer Inference","date":"2024-05-24","arxiv_id":"2405.17485","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-better-understanding-of-in-context","title":"Towards Better Understanding of In-Context Learning Ability from In-Context Uncertainty Quantification","date":"2024-05-24","arxiv_id":"2405.15115","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-understanding-how-transformer-perform","title":"The Buffer Mechanism for Multi-Step Information Reasoning in Language Models","date":"2024-05-24","arxiv_id":"2405.15302","n_code_links":0,"syntology":null},{"paper":null,"slug":"unitnorm-rethinking-normalization-for","title":"UnitNorm: Rethinking Normalization for Transformers in Time Series","date":"2024-05-24","arxiv_id":"2405.15903","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-spam-email-classification-using-pre","title":"Zero-Shot Spam Email Classification Using Pre-trained Large Language Models","date":"2024-05-24","arxiv_id":"2405.15936","n_code_links":0,"syntology":null},{"paper":null,"slug":"3d-learnable-supertoken-transformer-for-lidar","title":"3D Learnable Supertoken Transformer for LiDAR Point Cloud Scene Segmentation","date":"2024-05-23","arxiv_id":"2405.15826","n_code_links":0,"syntology":null},{"paper":"/paper/a-declarative-system-for-optimizing-ai","slug":"a-declarative-system-for-optimizing-ai","title":"A Declarative System for Optimizing AI Workloads","date":"2024-05-23","arxiv_id":"2405.14696","n_code_links":1,"syntology":null},{"paper":"/paper/agile-a-novel-framework-of-llm-agents","slug":"agile-a-novel-framework-of-llm-agents","title":"AGILE: A Novel Reinforcement Learning Framework of LLM Agents","date":"2024-05-23","arxiv_id":"2405.14751","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["bytarnish/agile"],"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":"attending-to-topological-spaces-the-cellular","title":"Attending to Topological Spaces: The Cellular Transformer","date":"2024-05-23","arxiv_id":"2405.14094","n_code_links":0,"syntology":null},{"paper":"/paper/autocoder-enhancing-code-large-language-model","slug":"autocoder-enhancing-code-large-language-model","title":"AutoCoder: Enhancing Code Large Language Model with \\textsc{AIEV-Instruct}","date":"2024-05-23","arxiv_id":"2405.14906","n_code_links":1,"syntology":null},{"paper":"/paper/combining-denoising-autoencoders-with","slug":"combining-denoising-autoencoders-with","title":"Combining Denoising Autoencoders with Contrastive Learning to fine-tune Transformer Models","date":"2024-05-23","arxiv_id":"2405.14437","n_code_links":1,"syntology":null}],"record_sha256":"8550c0b354f51ab9c580a26dd17531b28dcedbb022edb5088fc97b7437494082","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}