{"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/residual-connection/papers/139","list_of":"/method/residual-connection","method":"Residual Connection","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":139,"pages_in_order":285,"rows_per_page":100,"rows":[13801,13900],"of":28401,"counts":{"archive_papers_tagged":28401,"with_a_code_link":12847,"where_syntology_ran_a_sample":3897,"not_listed_spam_title":0,"listed":28401,"listed_where_code_ran":3897,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3291,"every_run_a_failure_of_syntologys_instrument":606,"listed_with_a_run_with_no_instrument_failure":3291,"listed_every_run_a_failure_of_syntologys_instrument":606,"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/residual-connection","prev":"/method/residual-connection/papers/138","next":"/method/residual-connection/papers/140","papers":[{"paper":"/paper/logical-reasoning-for-natural-language","slug":"logical-reasoning-for-natural-language","title":"Atomic Inference for NLI with Generated Facts as Atoms","date":"2023-05-22","arxiv_id":"2305.13214","n_code_links":1,"syntology":null},{"paper":"/paper/mailex-email-event-and-argument-extraction","slug":"mailex-email-event-and-argument-extraction","title":"MAILEX: Email Event and Argument Extraction","date":"2023-05-22","arxiv_id":"2305.13469","n_code_links":1,"syntology":null},{"paper":null,"slug":"materialistic-selecting-similar-materials-in","title":"Materialistic: Selecting Similar Materials in Images","date":"2023-05-22","arxiv_id":"2305.13291","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-inductive-biases-of-in-context","slug":"measuring-inductive-biases-of-in-context","title":"Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations","date":"2023-05-22","arxiv_id":"2305.13299","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-instruction-tuning-of-llama-for","title":"Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance","date":"2023-05-22","arxiv_id":"2305.13225","n_code_links":0,"syntology":null},{"paper":null,"slug":"parallel-attention-and-feed-forward-net","title":"Investigating the Role of Feed-Forward Networks in Transformers Using Parallel Attention and Feed-Forward Net Design","date":"2023-05-22","arxiv_id":"2305.13297","n_code_links":0,"syntology":null},{"paper":"/paper/recurrentgpt-interactive-generation-of","slug":"recurrentgpt-interactive-generation-of","title":"RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text","date":"2023-05-22","arxiv_id":"2305.13304","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["aiwaves-cn/recurrentgpt"],"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/rwkv-reinventing-rnns-for-the-transformer-era","slug":"rwkv-reinventing-rnns-for-the-transformer-era","title":"RWKV: Reinventing RNNs for the Transformer Era","date":"2023-05-22","arxiv_id":"2305.13048","n_code_links":14,"syntology":{"ran":6,"of":11,"n_ran_checked":4,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"6 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; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["BlinkDL/RWKV-LM","blinkdl/chatrwkv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/scitab-a-challenging-benchmark-for","slug":"scitab-a-challenging-benchmark-for","title":"SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables","date":"2023-05-22","arxiv_id":"2305.13186","n_code_links":1,"syntology":null},{"paper":"/paper/sparsefit-few-shot-prompting-with-sparse-fine","slug":"sparsefit-few-shot-prompting-with-sparse-fine","title":"SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations","date":"2023-05-22","arxiv_id":"2305.13235","n_code_links":1,"syntology":null},{"paper":null,"slug":"spatiotemporal-attention-based-semantic","title":"Spatiotemporal Attention-based Semantic Compression for Real-time Video Recognition","date":"2023-05-22","arxiv_id":"2305.12796","n_code_links":0,"syntology":null},{"paper":null,"slug":"stock-and-market-index-prediction-using","title":"Stock and market index prediction using Informer network","date":"2023-05-22","arxiv_id":"2305.14382","n_code_links":0,"syntology":null},{"paper":null,"slug":"syntactic-knowledge-via-graph-attention-with","title":"Syntactic Knowledge via Graph Attention with BERT in Machine Translation","date":"2023-05-22","arxiv_id":"2305.13413","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-emergence-of-economic-rationality-of-gpt","title":"The Emergence of Economic Rationality of GPT","date":"2023-05-22","arxiv_id":"2305.12763","n_code_links":0,"syntology":null},{"paper":null,"slug":"tokenized-graph-transformer-with-neighborhood","title":"Tokenized Graph Transformer with Neighborhood Augmentation for Node Classification in Large Graphs","date":"2023-05-22","arxiv_id":"2305.12677","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-dialogue-systems-with-agency-in-human","title":"Investigating Agency of LLMs in Human-AI Collaboration Tasks","date":"2023-05-22","arxiv_id":"2305.12815","n_code_links":0,"syntology":null},{"paper":null,"slug":"tsptq-vit-two-scaled-post-training","title":"TSPTQ-ViT: Two-scaled post-training quantization for vision transformer","date":"2023-05-22","arxiv_id":"2305.12901","n_code_links":0,"syntology":null},{"paper":"/paper/vdt-an-empirical-study-on-video-diffusion","slug":"vdt-an-empirical-study-on-video-diffusion","title":"VDT: General-purpose Video Diffusion Transformers via Mask Modeling","date":"2023-05-22","arxiv_id":"2305.13311","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":4,"n_instrument":4,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rerv/vdt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/videollm-modeling-video-sequence-with-large","slug":"videollm-modeling-video-sequence-with-large","title":"VideoLLM: Modeling Video Sequence with Large Language Models","date":"2023-05-22","arxiv_id":"2305.13292","n_code_links":1,"syntology":null},{"paper":null,"slug":"why-current-rain-denoising-models-fail-on","title":"Why current rain denoising models fail on CycleGAN created rain images in autonomous driving","date":"2023-05-22","arxiv_id":"2305.12983","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deeper-autoregressive-approach-to-non","title":"A Deeper (Autoregressive) Approach to Non-Convergent Discourse Parsing","date":"2023-05-21","arxiv_id":"2305.12510","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-symbolic-framework-for-systematic","title":"A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers","date":"2023-05-21","arxiv_id":"2305.12563","n_code_links":0,"syntology":null},{"paper":"/paper/bertrlfuzzer-a-bert-and-reinforcement","slug":"bertrlfuzzer-a-bert-and-reinforcement","title":"BertRLFuzzer: A BERT and Reinforcement Learning Based Fuzzer","date":"2023-05-21","arxiv_id":"2305.12534","n_code_links":1,"syntology":null},{"paper":"/paper/biasasker-measuring-the-bias-in","slug":"biasasker-measuring-the-bias-in","title":"BiasAsker: Measuring the Bias in Conversational AI System","date":"2023-05-21","arxiv_id":"2305.12434","n_code_links":1,"syntology":null},{"paper":"/paper/contrastive-learning-with-logic-driven-data","slug":"contrastive-learning-with-logic-driven-data","title":"Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning","date":"2023-05-21","arxiv_id":"2305.12599","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-performance-of-large-language","slug":"evaluating-the-performance-of-large-language","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","date":"2023-05-21","arxiv_id":"2305.12474","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"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":["openlmlab/gaokao-bench"],"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/explaining-how-transformers-use-context-to","slug":"explaining-how-transformers-use-context-to","title":"Explaining How Transformers Use Context to Build Predictions","date":"2023-05-21","arxiv_id":"2305.12535","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":8,"n_instrument":1,"unverified":3,"pointer_only":1,"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) · 3 unverified","official":{"repos":["mt-upc/logit-explanations"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"f-pabee-flexible-patience-based-early-exiting","title":"F-PABEE: Flexible-patience-based Early Exiting for Single-label and Multi-label text Classification Tasks","date":"2023-05-21","arxiv_id":"2305.11916","n_code_links":0,"syntology":null},{"paper":"/paper/gene-set-summarization-using-large-language","slug":"gene-set-summarization-using-large-language","title":"Gene Set Summarization using Large Language Models","date":"2023-05-21","arxiv_id":"2305.13338","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["monarch-initiative/talisman"],"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":"gpt-3-5-vs-gpt-4-evaluating-chatgpt-s","title":"GPT-3.5, GPT-4, or BARD? Evaluating LLMs Reasoning Ability in Zero-Shot Setting and Performance Boosting Through Prompts","date":"2023-05-21","arxiv_id":"2305.12477","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-paternity-test-gpt-generated-text","title":"DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection","date":"2023-05-21","arxiv_id":"2305.12519","n_code_links":0,"syntology":null},{"paper":null,"slug":"hiint-historical-intra-and-inter-personal","title":"HIINT: Historical, Intra- and Inter- personal Dynamics Modeling with Cross-person Memory Transformer","date":"2023-05-21","arxiv_id":"2305.12369","n_code_links":0,"syntology":null},{"paper":null,"slug":"infor-coef-information-bottleneck-based","title":"Infor-Coef: Information Bottleneck-based Dynamic Token Downsampling for Compact and Efficient language model","date":"2023-05-21","arxiv_id":"2305.12458","n_code_links":0,"syntology":null},{"paper":null,"slug":"ir-models-and-the-covid-19-pandemic-a","title":"IR Models and the COVID-19 Pandemic: A Comparative Study of Performance and Challenges","date":"2023-05-21","arxiv_id":"2305.12528","n_code_links":0,"syntology":null},{"paper":"/paper/learning-joint-2d-3d-diffusion-models-for","slug":"learning-joint-2d-3d-diffusion-models-for","title":"Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generation","date":"2023-05-21","arxiv_id":"2305.12347","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"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) · 1 unverified","official":{"repos":["graph-0/jodo"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":"/paper/model-generated-pretraining-signals-improves","slug":"model-generated-pretraining-signals-improves","title":"Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers","date":"2023-05-21","arxiv_id":"2305.12567","n_code_links":1,"syntology":null},{"paper":null,"slug":"tcn-aa-a-wi-fi-based-temporal-convolution","title":"WiFi-TCN: Temporal Convolution for Human Interaction Recognition based on WiFi signal","date":"2023-05-21","arxiv_id":"2305.18211","n_code_links":0,"syntology":null},{"paper":"/paper/teaching-the-pre-trained-model-to-generate","slug":"teaching-the-pre-trained-model-to-generate","title":"Teaching the Pre-trained Model to Generate Simple Texts for Text Simplification","date":"2023-05-21","arxiv_id":"2305.12463","n_code_links":1,"syntology":null},{"paper":null,"slug":"temporal-fusion-transformers-for-streamflow","title":"Temporal Fusion Transformers for Streamflow Prediction: Value of Combining Attention with Recurrence","date":"2023-05-21","arxiv_id":"2305.12335","n_code_links":0,"syntology":null},{"paper":"/paper/theoremqa-a-theorem-driven-question-answering","slug":"theoremqa-a-theorem-driven-question-answering","title":"TheoremQA: A Theorem-driven Question Answering dataset","date":"2023-05-21","arxiv_id":"2305.12524","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":8,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"10 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wenhuchen/theoremqa"],"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":["found_in_text","official"]}}},{"paper":"/paper/yolov3-with-spatial-pyramid-pooling-for","slug":"yolov3-with-spatial-pyramid-pooling-for","title":"YOLOv3 with Spatial Pyramid Pooling for Object Detection with Unmanned Aerial Vehicles","date":"2023-05-21","arxiv_id":"2305.12344","n_code_links":1,"syntology":null},{"paper":null,"slug":"autoregressive-modeling-with-lookahead","title":"Autoregressive Modeling with Lookahead Attention","date":"2023-05-20","arxiv_id":"2305.12272","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-nlp-models-correctly-reason-over-contexts","title":"Can NLP Models Correctly Reason Over Contexts that Break the Common Assumptions?","date":"2023-05-20","arxiv_id":"2305.12096","n_code_links":0,"syntology":null},{"paper":null,"slug":"cdjur-br-a-golden-collection-of-legal","title":"CDJUR-BR -- A Golden Collection of Legal Document from Brazilian Justice with Fine-Grained Named Entities","date":"2023-05-20","arxiv_id":"2305.18315","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-deep-learning-models","title":"Comparative Analysis of Deep Learning Models for Brand Logo Classification in Real-World Scenarios","date":"2023-05-20","arxiv_id":"2305.12242","n_code_links":0,"syntology":null},{"paper":"/paper/contextualizing-argument-quality-assessment","slug":"contextualizing-argument-quality-assessment","title":"Contextualizing Argument Quality Assessment with Relevant Knowledge","date":"2023-05-20","arxiv_id":"2305.12280","n_code_links":1,"syntology":null},{"paper":null,"slug":"experimental-results-from-applying-gpt-4-to","title":"Experimental results from applying GPT-4 to an unpublished formal language","date":"2023-05-20","arxiv_id":"2305.12196","n_code_links":0,"syntology":null},{"paper":null,"slug":"learn-to-compose-syntactic-and-semantic","title":"Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization","date":"2023-05-20","arxiv_id":"2305.12169","n_code_links":0,"syntology":null},{"paper":"/paper/logicot-logical-chain-of-thought-instruction","slug":"logicot-logical-chain-of-thought-instruction","title":"LogiCoT: Logical Chain-of-Thought Instruction-Tuning","date":"2023-05-20","arxiv_id":"2305.12147","n_code_links":1,"syntology":null},{"paper":"/paper/make-transformer-great-again-for-time-series","slug":"make-transformer-great-again-for-time-series","title":"CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting","date":"2023-05-20","arxiv_id":"2305.12095","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"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":["wxie9/card"],"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":null,"slug":"practical-pcg-through-large-language-models","title":"Practical PCG Through Large Language Models","date":"2023-05-20","arxiv_id":"2305.18243","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-the-architectures-like-pointer","slug":"revisiting-the-architectures-like-pointer","title":"Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond","date":"2023-05-20","arxiv_id":"2305.12289","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentfin-1-0-entity-aware-sentiment-analysis","title":"SEntFiN 1.0: Entity-Aware Sentiment Analysis for Financial News","date":"2023-05-20","arxiv_id":"2305.12257","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sequence-to-sequence-approach-for-arabic","title":"A Sequence-to-Sequence Approach for Arabic Pronoun Resolution","date":"2023-05-19","arxiv_id":"2305.11529","n_code_links":0,"syntology":null},{"paper":null,"slug":"autotrial-prompting-language-models-for","title":"AutoTrial: Prompting Language Models for Clinical Trial Design","date":"2023-05-19","arxiv_id":"2305.11366","n_code_links":0,"syntology":null},{"paper":"/paper/brain-captioning-decoding-human-brain","slug":"brain-captioning-decoding-human-brain","title":"Brain Captioning: Decoding human brain activity into images and text","date":"2023-05-19","arxiv_id":"2305.11560","n_code_links":1,"syntology":null},{"paper":null,"slug":"cct-code-cross-consistency-training-for","title":"CCT-Code: Cross-Consistency Training for Multilingual Clone Detection and Code Search","date":"2023-05-19","arxiv_id":"2305.11626","n_code_links":0,"syntology":null},{"paper":"/paper/clinical-camel-an-open-source-expert-level","slug":"clinical-camel-an-open-source-expert-level","title":"Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding","date":"2023-05-19","arxiv_id":"2305.12031","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bowang-lab/clinical-camel"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/diving-into-the-inter-consistency-of-large","slug":"diving-into-the-inter-consistency-of-large","title":"Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate","date":"2023-05-19","arxiv_id":"2305.11595","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":["waste-wood/ford"],"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":"do-models-really-learn-to-follow-instructions","title":"Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning","date":"2023-05-19","arxiv_id":"2305.11383","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-mixed-transformer-for-single-image","slug":"efficient-mixed-transformer-for-single-image","title":"Efficient Mixed Transformer for Single Image Super-Resolution","date":"2023-05-19","arxiv_id":"2305.11403","n_code_links":2,"syntology":null},{"paper":null,"slug":"enhancing-short-term-wind-speed-forecasting","title":"Enhancing Short-Term Wind Speed Forecasting using Graph Attention and Frequency-Enhanced Mechanisms","date":"2023-05-19","arxiv_id":"2305.11526","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-upper-limits-of-text-based","title":"Exploring the Upper Limits of Text-Based Collaborative Filtering Using Large Language Models: Discoveries and Insights","date":"2023-05-19","arxiv_id":"2305.11700","n_code_links":0,"syntology":null},{"paper":null,"slug":"eye-spatialnet-spatial-information-extraction","title":"Eye-SpatialNet: Spatial Information Extraction from Ophthalmology Notes","date":"2023-05-19","arxiv_id":"2305.11948","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-foundation-models-privacy","title":"Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Models","date":"2023-05-19","arxiv_id":"2305.11414","n_code_links":0,"syntology":null},{"paper":"/paper/graph-propagation-transformer-for-graph","slug":"graph-propagation-transformer-for-graph","title":"Graph Propagation Transformer for Graph Representation Learning","date":"2023-05-19","arxiv_id":"2305.11424","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":4,"n_instrument":0,"unverified":4,"pointer_only":8,"phrase":"4 ran (of which 4 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) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["czczup/gptrans"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-does-generative-retrieval-scale-to","title":"How Does Generative Retrieval Scale to Millions of Passages?","date":"2023-05-19","arxiv_id":"2305.11841","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-universal-phonetic-representation-in","title":"Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition","date":"2023-05-19","arxiv_id":"2305.11569","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-web-navigation-with-instruction","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","date":"2023-05-19","arxiv_id":"2305.11854","n_code_links":0,"syntology":null},{"paper":"/paper/not-all-semantics-are-created-equal","slug":"not-all-semantics-are-created-equal","title":"Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization","date":"2023-05-19","arxiv_id":"2305.11965","n_code_links":1,"syntology":null},{"paper":null,"slug":"ol-transformer-a-fast-and-universal-surrogate","title":"OL-Transformer: A Fast and Universal Surrogate Simulator for Optical Multilayer Thin Film Structures","date":"2023-05-19","arxiv_id":"2305.11984","n_code_links":0,"syntology":null},{"paper":"/paper/pointgpt-auto-regressively-generative-pre-1","slug":"pointgpt-auto-regressively-generative-pre-1","title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","date":"2023-05-19","arxiv_id":"2305.11487","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["CGuangyan-BIT/PointGPT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ramit-reciprocal-attention-mixing-transformer","slug":"ramit-reciprocal-attention-mixing-transformer","title":"Reciprocal Attention Mixing Transformer for Lightweight Image Restoration","date":"2023-05-19","arxiv_id":"2305.11474","n_code_links":1,"syntology":null},{"paper":"/paper/recycle-and-distill-universal-compression","slug":"recycle-and-distill-universal-compression","title":"Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation","date":"2023-05-19","arxiv_id":"2305.11685","n_code_links":1,"syntology":null},{"paper":null,"slug":"reducing-sequence-length-by-predicting-edit","title":"Reducing Sequence Length by Predicting Edit Operations with Large Language Models","date":"2023-05-19","arxiv_id":"2305.11862","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-laws-for-language-encoding-models-in","slug":"scaling-laws-for-language-encoding-models-in","title":"Scaling laws for language encoding models in fMRI","date":"2023-05-19","arxiv_id":"2305.11863","n_code_links":1,"syntology":null},{"paper":"/paper/seegull-a-stereotype-benchmark-with-broad-geo","slug":"seegull-a-stereotype-benchmark-with-broad-geo","title":"SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models","date":"2023-05-19","arxiv_id":"2305.11840","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-agreement-a-framework-for-fine-tuning","title":"Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions","date":"2023-05-19","arxiv_id":"2305.11460","n_code_links":0,"syntology":null},{"paper":"/paper/self-qa-unsupervised-knowledge-guided","slug":"self-qa-unsupervised-knowledge-guided","title":"Self-QA: Unsupervised Knowledge Guided Language Model Alignment","date":"2023-05-19","arxiv_id":"2305.11952","n_code_links":1,"syntology":null},{"paper":null,"slug":"selfzcot-a-self-prompt-zero-shot-cot-from","title":"Hint of Thought prompting: an explainable and zero-shot approach to reasoning tasks with LLMs","date":"2023-05-19","arxiv_id":"2305.11461","n_code_links":0,"syntology":null},{"paper":"/paper/surgical-vqla-transformer-with-gated-vision","slug":"surgical-vqla-transformer-with-gated-vision","title":"Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","date":"2023-05-19","arxiv_id":"2305.11692","n_code_links":2,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"7 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["longbai1006/surgical-vqla"],"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/a-comparative-study-on-e-branchformer-vs","slug":"a-comparative-study-on-e-branchformer-vs","title":"A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks","date":"2023-05-18","arxiv_id":"2305.11073","n_code_links":2,"syntology":null},{"paper":null,"slug":"ahead-of-time-p-tuning","title":"Ahead-of-Time P-Tuning","date":"2023-05-18","arxiv_id":"2305.10835","n_code_links":0,"syntology":null},{"paper":null,"slug":"aiwriting-relations-between-image-generation","title":"AIwriting: Relations Between Image Generation and Digital Writing","date":"2023-05-18","arxiv_id":"2305.10834","n_code_links":0,"syntology":null},{"paper":null,"slug":"annotation-free-audio-visual-segmentation","title":"Annotation-free Audio-Visual Segmentation","date":"2023-05-18","arxiv_id":"2305.11019","n_code_links":0,"syntology":null},{"paper":"/paper/bioaug-conditional-generation-based-data","slug":"bioaug-conditional-generation-based-data","title":"BioAug: Conditional Generation based Data Augmentation for Low-Resource Biomedical NER","date":"2023-05-18","arxiv_id":"2305.10647","n_code_links":1,"syntology":null},{"paper":null,"slug":"boost-vision-transformer-with-gpu-friendly-1","title":"Boost Vision Transformer with GPU-Friendly Sparsity and Quantization","date":"2023-05-18","arxiv_id":"2305.10727","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-machines-and-children-using","title":"Comparing Machines and Children: Using Developmental Psychology Experiments to Assess the Strengths and Weaknesses of LaMDA Responses","date":"2023-05-18","arxiv_id":"2305.11243","n_code_links":0,"syntology":null},{"paper":null,"slug":"coordinated-transformer-with-position-sample","title":"Coordinated Transformer with Position \\& Sample-aware Central Loss for Anatomical Landmark Detection","date":"2023-05-18","arxiv_id":"2305.11338","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-methods-for-extracting","title":"Deep Learning Methods for Extracting Metaphorical Names of Flowers and Plants","date":"2023-05-18","arxiv_id":"2305.10833","n_code_links":0,"syntology":null},{"paper":"/paper/ditto-a-simple-and-efficient-approach-to","slug":"ditto-a-simple-and-efficient-approach-to","title":"Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings","date":"2023-05-18","arxiv_id":"2305.10786","n_code_links":1,"syntology":null},{"paper":"/paper/evidence-of-meaning-in-language-models","slug":"evidence-of-meaning-in-language-models","title":"Emergent Representations of Program Semantics in Language Models Trained on Programs","date":"2023-05-18","arxiv_id":"2305.11169","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":0,"n_instrument":12,"unverified":1,"pointer_only":13,"phrase":"12 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; 12 where Syntology's instrument failed) · 1 unverified","official":{"repos":["charlesjin/emergent-semantics"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/funasr-a-fundamental-end-to-end-speech","slug":"funasr-a-fundamental-end-to-end-speech","title":"FunASR: A Fundamental End-to-End Speech Recognition Toolkit","date":"2023-05-18","arxiv_id":"2305.11013","n_code_links":1,"syntology":null},{"paper":null,"slug":"generalized-multiple-intent-conditioned-slot","title":"Generalized Multiple Intent Conditioned Slot Filling","date":"2023-05-18","arxiv_id":"2305.11023","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-planning-in-pddl-domains-with","slug":"generalized-planning-in-pddl-domains-with","title":"Generalized Planning in PDDL Domains with Pretrained Large Language Models","date":"2023-05-18","arxiv_id":"2305.11014","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":["tomsilver/llm-genplan"],"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/large-language-models-can-be-guided-to-evade","slug":"large-language-models-can-be-guided-to-evade","title":"Large Language Models can be Guided to Evade AI-Generated Text Detection","date":"2023-05-18","arxiv_id":"2305.10847","n_code_links":1,"syntology":null},{"paper":null,"slug":"less-is-more-a-slim-architecture-for-optimal","title":"Less is More! A slim architecture for optimal language translation","date":"2023-05-18","arxiv_id":"2305.10991","n_code_links":0,"syntology":null},{"paper":"/paper/lima-less-is-more-for-alignment","slug":"lima-less-is-more-for-alignment","title":"LIMA: Less Is More for Alignment","date":"2023-05-18","arxiv_id":"2305.11206","n_code_links":5,"syntology":null},{"paper":"/paper/mlongt5-a-multilingual-and-efficient-text-to","slug":"mlongt5-a-multilingual-and-efficient-text-to","title":"mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences","date":"2023-05-18","arxiv_id":"2305.11129","n_code_links":1,"syntology":null},{"paper":"/paper/molxpt-wrapping-molecules-with-text-for","slug":"molxpt-wrapping-molecules-with-text-for","title":"MolXPT: Wrapping Molecules with Text for Generative Pre-training","date":"2023-05-18","arxiv_id":"2305.10688","n_code_links":1,"syntology":null}],"record_sha256":"07ec863f966f7aa0b175a6eb4936abe9a9f8fa634c7e7c4538bf4ed3a7046850","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}