{"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/transformer/papers/83","list_of":"/method/transformer","method":"Transformer","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":83,"pages_in_order":140,"rows_per_page":100,"rows":[8201,8300],"of":13999,"counts":{"archive_papers_tagged":13999,"with_a_code_link":6572,"where_syntology_ran_a_sample":2248,"not_listed_spam_title":0,"listed":13999,"listed_where_code_ran":2248,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1919,"every_run_a_failure_of_syntologys_instrument":329,"listed_with_a_run_with_no_instrument_failure":1919,"listed_every_run_a_failure_of_syntologys_instrument":329,"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/transformer","prev":"/method/transformer/papers/82","next":"/method/transformer/papers/84","papers":[{"paper":"/paper/learning-to-generate-novel-scientific","slug":"learning-to-generate-novel-scientific","title":"SciMON: Scientific Inspiration Machines Optimized for Novelty","date":"2023-05-23","arxiv_id":"2305.14259","n_code_links":1,"syntology":null},{"paper":"/paper/let-s-think-frame-by-frame-evaluating-video","slug":"let-s-think-frame-by-frame-evaluating-video","title":"Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought","date":"2023-05-23","arxiv_id":"2305.13903","n_code_links":1,"syntology":null},{"paper":"/paper/llm-powered-data-augmentation-for-enhanced","slug":"llm-powered-data-augmentation-for-enhanced","title":"LLM-powered Data Augmentation for Enhanced Cross-lingual Performance","date":"2023-05-23","arxiv_id":"2305.14288","n_code_links":1,"syntology":null},{"paper":"/paper/llms-as-factual-reasoners-insights-from","slug":"llms-as-factual-reasoners-insights-from","title":"LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond","date":"2023-05-23","arxiv_id":"2305.14540","n_code_links":1,"syntology":null},{"paper":null,"slug":"nail-lexical-retrieval-indices-with-efficient","title":"NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoders","date":"2023-05-23","arxiv_id":"2305.14499","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-structural-expressive-power-of-graph","title":"On Structural Expressive Power of Graph Transformers","date":"2023-05-23","arxiv_id":"2305.13987","n_code_links":0,"syntology":null},{"paper":"/paper/patch-mix-contrastive-learning-with-audio","slug":"patch-mix-contrastive-learning-with-audio","title":"Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification","date":"2023-05-23","arxiv_id":"2305.14032","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["raymin0223/patch-mix_contrastive_learning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pre-training-multi-task-contrastive-learning","title":"Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding","date":"2023-05-23","arxiv_id":"2305.14232","n_code_links":0,"syntology":null},{"paper":"/paper/qlora-efficient-finetuning-of-quantized-llms","slug":"qlora-efficient-finetuning-of-quantized-llms","title":"QLoRA: Efficient Finetuning of Quantized LLMs","date":"2023-05-23","arxiv_id":"2305.14314","n_code_links":20,"syntology":{"ran":18,"of":26,"n_ran_checked":6,"n_instrument":12,"unverified":8,"pointer_only":17,"phrase":"18 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified","official":{"repos":["artidoro/qlora","timdettmers/bitsandbytes"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["community","listed","official","unlocated"]}}},{"paper":null,"slug":"rethinking-speech-recognition-with-a","title":"Rethinking Speech Recognition with A Multimodal Perspective via Acoustic and Semantic Cooperative Decoding","date":"2023-05-23","arxiv_id":"2305.14049","n_code_links":0,"syntology":null},{"paper":null,"slug":"source-free-domain-adaptation-for-rgb-d","title":"Source-Free Domain Adaptation for RGB-D Semantic Segmentation with Vision Transformers","date":"2023-05-23","arxiv_id":"2305.14269","n_code_links":0,"syntology":null},{"paper":"/paper/text-is-all-you-need-learning-language","slug":"text-is-all-you-need-learning-language","title":"Text Is All You Need: Learning Language Representations for Sequential Recommendation","date":"2023-05-23","arxiv_id":"2305.13731","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":null}},{"paper":null,"slug":"towards-a-unified-view-of-sparse-feed-forward","title":"Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model","date":"2023-05-23","arxiv_id":"2305.13999","n_code_links":0,"syntology":null},{"paper":"/paper/towards-massively-multi-domain-multilingual","slug":"towards-massively-multi-domain-multilingual","title":"ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment","date":"2023-05-23","arxiv_id":"2305.14463","n_code_links":1,"syntology":null},{"paper":"/paper/vdd-varied-drone-dataset-for-semantic","slug":"vdd-varied-drone-dataset-for-semantic","title":"VDD: Varied Drone Dataset for Semantic Segmentation","date":"2023-05-23","arxiv_id":"2305.13608","n_code_links":1,"syntology":null},{"paper":"/paper/wikichat-a-few-shot-llm-based-chatbot","slug":"wikichat-a-few-shot-llm-based-chatbot","title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","date":"2023-05-23","arxiv_id":"2305.14292","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["stanford-oval/wikichat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/zeroscrolls-a-zero-shot-benchmark-for-long","slug":"zeroscrolls-a-zero-shot-benchmark-for-long","title":"ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding","date":"2023-05-23","arxiv_id":"2305.14196","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tau-nlp/zero_scrolls"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/are-large-language-models-good-evaluators-for","slug":"are-large-language-models-good-evaluators-for","title":"Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization","date":"2023-05-22","arxiv_id":"2305.13091","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":["damo-nlp-sg/llm_summeval"],"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/beneath-surface-similarity-large-language","slug":"beneath-surface-similarity-large-language","title":"Beneath Surface Similarity: Large Language Models Make Reasonable Scientific Analogies after Structure Abduction","date":"2023-05-22","arxiv_id":"2305.12660","n_code_links":1,"syntology":null},{"paper":"/paper/bidirectional-transformer-reranker-for","slug":"bidirectional-transformer-reranker-for","title":"Bidirectional Transformer Reranker for Grammatical Error Correction","date":"2023-05-22","arxiv_id":"2305.13000","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-chatgpt-defend-the-truth-automatic","title":"Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate","date":"2023-05-22","arxiv_id":"2305.13160","n_code_links":0,"syntology":null},{"paper":null,"slug":"cognitive-network-science-reveals-bias-in-gpt","title":"Cognitive network science reveals bias in GPT-3, ChatGPT, and GPT-4 mirroring math anxiety in high-school students","date":"2023-05-22","arxiv_id":"2305.18320","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-and-enhancing-structural","slug":"evaluating-and-enhancing-structural","title":"Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study","date":"2023-05-22","arxiv_id":"2305.13062","n_code_links":1,"syntology":null},{"paper":"/paper/explaincpe-a-free-text-explanation-benchmark","slug":"explaincpe-a-free-text-explanation-benchmark","title":"ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination","date":"2023-05-22","arxiv_id":"2305.12945","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-energy-based-language-models-with","slug":"exploring-energy-based-language-models-with","title":"Exploring Energy-based Language Models with Different Architectures and Training Methods for Speech Recognition","date":"2023-05-22","arxiv_id":"2305.12676","n_code_links":2,"syntology":null},{"paper":null,"slug":"g3detector-general-gpt-generated-text","title":"G3Detector: General GPT-Generated Text Detector","date":"2023-05-22","arxiv_id":"2305.12680","n_code_links":0,"syntology":null},{"paper":null,"slug":"gncformer-enhanced-self-attention-for","title":"GNCformer Enhanced Self-attention for Automatic Speech Recognition","date":"2023-05-22","arxiv_id":"2305.12755","n_code_links":0,"syntology":null},{"paper":"/paper/how-language-model-hallucinations-can","slug":"how-language-model-hallucinations-can","title":"How Language Model Hallucinations Can Snowball","date":"2023-05-22","arxiv_id":"2305.13534","n_code_links":1,"syntology":null},{"paper":"/paper/iterative-forward-tuning-boosts-in-context","slug":"iterative-forward-tuning-boosts-in-context","title":"Iterative Forward Tuning Boosts In-Context Learning in Language Models","date":"2023-05-22","arxiv_id":"2305.13016","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-pedestrian-actions-to-ensure-safe","title":"Learning Pedestrian Actions to Ensure Safe Autonomous Driving","date":"2023-05-22","arxiv_id":"2305.13051","n_code_links":0,"syntology":null},{"paper":"/paper/learning-subpocket-prototypes-for","slug":"learning-subpocket-prototypes-for","title":"Learning Subpocket Prototypes for Generalizable Structure-based Drug Design","date":"2023-05-22","arxiv_id":"2305.13997","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["zaixizhang/flag"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"paper":"/paper/llms-for-knowledge-graph-construction-and","slug":"llms-for-knowledge-graph-construction-and","title":"LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities","date":"2023-05-22","arxiv_id":"2305.13168","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":["zjunlp/autokg"],"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":"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":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":"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":"/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":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-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/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":"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":"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":"/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":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":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":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":"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":"/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/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":"/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":"/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":"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/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/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":"/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":"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":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":"/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":"/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":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/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},{"paper":null,"slug":"multi-resolution-spatiotemporal-enhanced","title":"Brain Imaging-to-Graph Generation using Adversarial Hierarchical Diffusion Models for MCI Causality Analysis","date":"2023-05-18","arxiv_id":"2305.10754","n_code_links":0,"syntology":null},{"paper":null,"slug":"selecting-learnable-training-samples-is-all","title":"Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detection","date":"2023-05-18","arxiv_id":"2305.10801","n_code_links":0,"syntology":null},{"paper":null,"slug":"support-for-stock-trend-prediction-using","title":"Support for Stock Trend Prediction Using Transformers and Sentiment Analysis","date":"2023-05-18","arxiv_id":"2305.14368","n_code_links":0,"syntology":null},{"paper":null,"slug":"textdiffuser-diffusion-models-as-text-1","title":"TextDiffuser: Diffusion Models as Text Painters","date":"2023-05-18","arxiv_id":"2305.10855","n_code_links":0,"syntology":null},{"paper":"/paper/vaxformer-antigenicity-controlled-transformer","slug":"vaxformer-antigenicity-controlled-transformer","title":"Vaxformer: Antigenicity-controlled Transformer for Vaccine Design Against SARS-CoV-2","date":"2023-05-18","arxiv_id":"2305.11194","n_code_links":1,"syntology":null},{"paper":"/paper/a-quantitative-study-of-nlp-approaches-to","slug":"a-quantitative-study-of-nlp-approaches-to","title":"A quantitative study of NLP approaches to question difficulty estimation","date":"2023-05-17","arxiv_id":"2305.10236","n_code_links":1,"syntology":null},{"paper":null,"slug":"cagevit-convolutional-activation-guided","title":"CageViT: Convolutional Activation Guided Efficient Vision Transformer","date":"2023-05-17","arxiv_id":"2305.09924","n_code_links":0,"syntology":null},{"paper":null,"slug":"costformer-cost-transformer-for-cost","title":"CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo","date":"2023-05-17","arxiv_id":"2305.10320","n_code_links":0,"syntology":null},{"paper":null,"slug":"eened-end-to-end-neural-epilepsy-detection","title":"EENED: End-to-End Neural Epilepsy Detection based on Convolutional Transformer","date":"2023-05-17","arxiv_id":"2305.10502","n_code_links":0,"syntology":null},{"paper":"/paper/efficientsci-densely-connected-network-with-1","slug":"efficientsci-densely-connected-network-with-1","title":"EfficientSCI: Densely Connected Network with Space-time Factorization for Large-scale Video Snapshot Compressive Imaging","date":"2023-05-17","arxiv_id":"2305.10006","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["ucaswangls/efficientsci"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"g-adapter-towards-structure-aware-parameter","title":"G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networks","date":"2023-05-17","arxiv_id":"2305.10329","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-speaker-verification-with-self","title":"Improving Speaker Verification with Self-Pretrained Transformer Models","date":"2023-05-17","arxiv_id":"2305.10517","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-scale-text-analysis-using-generative","title":"Large-Scale Text Analysis Using Generative Language Models: A Case Study in Discovering Public Value Expressions in AI Patents","date":"2023-05-17","arxiv_id":"2305.10383","n_code_links":0,"syntology":null},{"paper":null,"slug":"qualifying-chinese-medical-licensing","title":"Large Language Models Leverage External Knowledge to Extend Clinical Insight Beyond Language Boundaries","date":"2023-05-17","arxiv_id":"2305.10163","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-data-augmentation-for-tabular-data","slug":"rethinking-data-augmentation-for-tabular-data","title":"Rethinking Data Augmentation for Tabular Data in Deep Learning","date":"2023-05-17","arxiv_id":"2305.10308","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":["somaonishi/mtr"],"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":null,"slug":"short-term-electricity-load-forecasting-using","title":"Short-Term Electricity Load Forecasting Using the Temporal Fusion Transformer: Effect of Grid Hierarchies and Data Sources","date":"2023-05-17","arxiv_id":"2305.10559","n_code_links":0,"syntology":null},{"paper":"/paper/token-wise-decomposition-of-autoregressive","slug":"token-wise-decomposition-of-autoregressive","title":"Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model Predictions","date":"2023-05-17","arxiv_id":"2305.10614","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":7,"n_instrument":0,"unverified":5,"pointer_only":7,"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) · 5 unverified","official":{"repos":["byungdoh/llm_decomposition"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/tree-of-thoughts-deliberate-problem-solving-1","slug":"tree-of-thoughts-deliberate-problem-solving-1","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","date":"2023-05-17","arxiv_id":"2305.10601","n_code_links":6,"syntology":{"ran":19,"of":24,"n_ran_checked":18,"n_instrument":1,"unverified":5,"pointer_only":1,"phrase":"19 ran (of which 6 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["princeton-nlp/tree-of-thought-llm","ysymyth/tree-of-thought-llm"],"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":["community","listed","official"]}}}],"record_sha256":"555c3a46a51ff80b3d90b6e1a1276fa4155205869ce5dd223d5a7dda8f03cd2c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}