{"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/69","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":69,"pages_in_order":140,"rows_per_page":100,"rows":[6801,6900],"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/68","next":"/method/transformer/papers/70","papers":[{"paper":"/paper/sparse-universal-transformer","slug":"sparse-universal-transformer","title":"Sparse Universal Transformer","date":"2023-10-11","arxiv_id":"2310.07096","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"towards-foundation-models-for-learning-on","title":"From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Models","date":"2023-10-11","arxiv_id":"2310.07338","n_code_links":0,"syntology":null},{"paper":null,"slug":"wigenai-the-symphony-of-wireless-and","title":"Diffusion Models for Wireless Communications","date":"2023-10-11","arxiv_id":"2310.07312","n_code_links":0,"syntology":null},{"paper":null,"slug":"advective-diffusion-transformers-for","title":"Supercharging Graph Transformers with Advective Diffusion","date":"2023-10-10","arxiv_id":"2310.06417","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-clinical-coding-using-off-the-shelf","title":"Automated clinical coding using off-the-shelf large language models","date":"2023-10-10","arxiv_id":"2310.06552","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-adaptation-of-large-vision-1","slug":"efficient-adaptation-of-large-vision-1","title":"Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing","date":"2023-10-10","arxiv_id":"2310.06234","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["davidyanande/arc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/evit-an-eagle-vision-transformer-with-bi","slug":"evit-an-eagle-vision-transformer-with-bi","title":"EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention","date":"2023-10-10","arxiv_id":"2310.06629","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-and-evaluating-tests-for-k-12","title":"Generating and Evaluating Tests for K-12 Students with Language Model Simulations: A Case Study on Sentence Reading Efficiency","date":"2023-10-10","arxiv_id":"2310.06837","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-as-an-agronomist-assistant-answering","title":"GPT-4 as an Agronomist Assistant? Answering Agriculture Exams Using Large Language Models","date":"2023-10-10","arxiv_id":"2310.06225","n_code_links":0,"syntology":null},{"paper":"/paper/itransformer-inverted-transformers-are","slug":"itransformer-inverted-transformers-are","title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","date":"2023-10-10","arxiv_id":"2310.06625","n_code_links":11,"syntology":{"ran":8,"of":10,"n_ran_checked":7,"n_instrument":1,"unverified":2,"pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 4 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["thuml/iTransformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/large-language-models-for-propaganda","slug":"large-language-models-for-propaganda","title":"Large Language Models for Propaganda Detection","date":"2023-10-10","arxiv_id":"2310.06422","n_code_links":2,"syntology":null},{"paper":"/paper/learning-stackable-and-skippable-lego-bricks","slug":"learning-stackable-and-skippable-lego-bricks","title":"Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling","date":"2023-10-10","arxiv_id":"2310.06389","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":8,"n_instrument":5,"unverified":4,"pointer_only":8,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","official":{"repos":["JegZheng/LEGODiffusion"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"llms-as-potential-brainstorming-partners-for","title":"LLMs as Potential Brainstorming Partners for Math and Science Problems","date":"2023-10-10","arxiv_id":"2310.10677","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-jailbreak-challenges-in-large","slug":"multilingual-jailbreak-challenges-in-large","title":"Multilingual Jailbreak Challenges in Large Language Models","date":"2023-10-10","arxiv_id":"2310.06474","n_code_links":1,"syntology":null},{"paper":null,"slug":"newton-are-large-language-models-capable-of","title":"NEWTON: Are Large Language Models Capable of Physical Reasoning?","date":"2023-10-10","arxiv_id":"2310.07018","n_code_links":0,"syntology":null},{"paper":"/paper/swe-bench-can-language-models-resolve-real","slug":"swe-bench-can-language-models-resolve-real","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","date":"2023-10-10","arxiv_id":"2310.06770","n_code_links":8,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":null}},{"paper":"/paper/wavenet-wave-aware-image-enhancement","slug":"wavenet-wave-aware-image-enhancement","title":"WaveNet: Wave-Aware Image Enhancement","date":"2023-10-10","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/what-if-the-tv-was-off-examining","slug":"what-if-the-tv-was-off-examining","title":"What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models","date":"2023-10-10","arxiv_id":"2310.06627","n_code_links":1,"syntology":null},{"paper":"/paper/why-bother-with-geometry-on-the-relevance-of","slug":"why-bother-with-geometry-on-the-relevance-of","title":"Why bother with geometry? On the relevance of linear decompositions of Transformer embeddings","date":"2023-10-10","arxiv_id":"2310.06977","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-glance-is-enough-extract-target-sentence-by","title":"A Glance is Enough: Extract Target Sentence By Looking at A keyword","date":"2023-10-09","arxiv_id":"2310.05352","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-meta-learning-perspective-on-transformers","title":"A Meta-Learning Perspective on Transformers for Causal Language Modeling","date":"2023-10-09","arxiv_id":"2310.05884","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-and-robust-framework-for-cross","slug":"a-simple-and-robust-framework-for-cross","title":"A Simple and Robust Framework for Cross-Modality Medical Image Segmentation applied to Vision Transformers","date":"2023-10-09","arxiv_id":"2310.05572","n_code_links":2,"syntology":null},{"paper":null,"slug":"dyst-towards-dynamic-neural-scene","title":"DyST: Towards Dynamic Neural Scene Representations on Real-World Videos","date":"2023-10-09","arxiv_id":"2310.06020","n_code_links":0,"syntology":null},{"paper":"/paper/fireact-toward-language-agent-fine-tuning","slug":"fireact-toward-language-agent-fine-tuning","title":"FireAct: Toward Language Agent Fine-tuning","date":"2023-10-09","arxiv_id":"2310.05915","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-graphs-with-large-language-models","title":"Integrating Graphs with Large Language Models: Methods and Prospects","date":"2023-10-09","arxiv_id":"2310.05499","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-stock-features-and-global","title":"Integrating Stock Features and Global Information via Large Language Models for Enhanced Stock Return Prediction","date":"2023-10-09","arxiv_id":"2310.05627","n_code_links":0,"syntology":null},{"paper":"/paper/learning-language-guided-adaptive-hyper","slug":"learning-language-guided-adaptive-hyper","title":"Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis","date":"2023-10-09","arxiv_id":"2310.05804","n_code_links":1,"syntology":null},{"paper":null,"slug":"memory-consistent-neural-networks-for","title":"Memory-Consistent Neural Networks for Imitation Learning","date":"2023-10-09","arxiv_id":"2310.06171","n_code_links":0,"syntology":null},{"paper":"/paper/put-your-money-where-your-mouth-is-evaluating","slug":"put-your-money-where-your-mouth-is-evaluating","title":"Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena","date":"2023-10-09","arxiv_id":"2310.05746","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["jiangjiechen/auction-arena"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/reinforcement-learning-in-the-era-of-llms","slug":"reinforcement-learning-in-the-era-of-llms","title":"Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond","date":"2023-10-09","arxiv_id":"2310.06147","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"sc-safety-a-multi-round-open-ended-question","title":"SC-Safety: A Multi-round Open-ended Question Adversarial Safety Benchmark for Large Language Models in Chinese","date":"2023-10-09","arxiv_id":"2310.05818","n_code_links":0,"syntology":null},{"paper":null,"slug":"simplr-a-simple-and-plain-transformer-for","title":"SimPLR: A Simple and Plain Transformer for Scaling-Efficient Object Detection and Segmentation","date":"2023-10-09","arxiv_id":"2310.05920","n_code_links":0,"syntology":null},{"paper":null,"slug":"take-a-step-back-evoking-reasoning-via","title":"Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models","date":"2023-10-09","arxiv_id":"2310.06117","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-importance-of-prompt-tuning-for-automated","title":"The Importance of Prompt Tuning for Automated Neuron Explanations","date":"2023-10-09","arxiv_id":"2310.06200","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-fusion-with-optimal-transport","slug":"transformer-fusion-with-optimal-transport","title":"Transformer Fusion with Optimal Transport","date":"2023-10-09","arxiv_id":"2310.05719","n_code_links":1,"syntology":{"ran":3,"of":10,"n_ran_checked":0,"n_instrument":3,"unverified":7,"pointer_only":10,"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) · 7 unverified","official":{"repos":["graldij/transformer-fusion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transformers-and-large-language-models-for","title":"Transformers and Large Language Models for Chemistry and Drug Discovery","date":"2023-10-09","arxiv_id":"2310.06083","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatradio-valuer-a-chat-large-language-model","title":"ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data","date":"2023-10-08","arxiv_id":"2310.05242","n_code_links":0,"syntology":null},{"paper":"/paper/gmmformer-gaussian-mixture-model-based","slug":"gmmformer-gaussian-mixture-model-based","title":"GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval","date":"2023-10-08","arxiv_id":"2310.05195","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"6 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["huangmozhi9527/GMMFormer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/harnessing-the-power-of-large-language-models-1","slug":"harnessing-the-power-of-large-language-models-1","title":"Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements","date":"2023-10-08","arxiv_id":"2310.05140","n_code_links":1,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":5,"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) · 4 unverified","official":{"repos":["27182812/LLM4ED"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/llm4vv-developing-llm-driven-testsuite-for","slug":"llm4vv-developing-llm-driven-testsuite-for","title":"LLM4VV: Developing LLM-Driven Testsuite for Compiler Validation","date":"2023-10-08","arxiv_id":"2310.04963","n_code_links":1,"syntology":null},{"paper":"/paper/tempo-prompt-based-generative-pre-trained","slug":"tempo-prompt-based-generative-pre-trained","title":"TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting","date":"2023-10-08","arxiv_id":"2310.04948","n_code_links":2,"syntology":{"ran":6,"of":14,"n_ran_checked":4,"n_instrument":2,"unverified":8,"pointer_only":0,"phrase":"6 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; 2 where Syntology's instrument failed) · 8 unverified","official":{"repos":["dc-research/tempo"],"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":["listed","official"]}}},{"paper":"/paper/zero-shot-detection-of-machine-generated","slug":"zero-shot-detection-of-machine-generated","title":"Zero-Shot Detection of Machine-Generated Codes","date":"2023-10-08","arxiv_id":"2310.05103","n_code_links":1,"syntology":null},{"paper":null,"slug":"diffnas-bootstrapping-diffusion-models-by","title":"DiffNAS: Bootstrapping Diffusion Models by Prompting for Better Architectures","date":"2023-10-07","arxiv_id":"2310.04750","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-spatial-trajectory","title":"Large Language Models for Spatial Trajectory Patterns Mining","date":"2023-10-07","arxiv_id":"2310.04942","n_code_links":0,"syntology":null},{"paper":"/paper/lauragpt-listen-attend-understand-and","slug":"lauragpt-listen-attend-understand-and","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","date":"2023-10-07","arxiv_id":"2310.04673","n_code_links":2,"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":null}},{"paper":null,"slug":"modeling-non-uniform-uncertainty-in-reaction","title":"Beyond the Typical: Modeling Rare Plausible Patterns in Chemical Reactions by Leveraging Sequential Mixture-of-Experts","date":"2023-10-07","arxiv_id":"2310.04674","n_code_links":0,"syntology":null},{"paper":null,"slug":"transcc-transformer-network-for-coronary","title":"TransCC: Transformer Network for Coronary Artery CCTA Segmentation","date":"2023-10-07","arxiv_id":"2310.04779","n_code_links":0,"syntology":null},{"paper":"/paper/a-language-agent-approach-to-formal-theorem","slug":"a-language-agent-approach-to-formal-theorem","title":"An In-Context Learning Agent for Formal Theorem-Proving","date":"2023-10-06","arxiv_id":"2310.04353","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-pruning-make-large-language-models-more","title":"Can pruning make Large Language Models more efficient?","date":"2023-10-06","arxiv_id":"2310.04573","n_code_links":0,"syntology":null},{"paper":null,"slug":"clusvpr-efficient-visual-place-recognition","title":"ClusVPR: Efficient Visual Place Recognition with Clustering-based Weighted Transformer","date":"2023-10-06","arxiv_id":"2310.04099","n_code_links":0,"syntology":null},{"paper":null,"slug":"coding-by-design-gpt-4-empowers-agile-model","title":"Coding by Design: GPT-4 empowers Agile Model Driven Development","date":"2023-10-06","arxiv_id":"2310.04304","n_code_links":0,"syntology":null},{"paper":"/paper/degradation-aware-self-attention-based","slug":"degradation-aware-self-attention-based","title":"Degradation-Aware Self-Attention Based Transformer for Blind Image Super-Resolution","date":"2023-10-06","arxiv_id":"2310.04180","n_code_links":1,"syntology":null},{"paper":"/paper/exploiting-transformer-activation-sparsity","slug":"exploiting-transformer-activation-sparsity","title":"Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion","date":"2023-10-06","arxiv_id":"2310.04361","n_code_links":2,"syntology":{"ran":15,"of":17,"n_ran_checked":14,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["bartwojcik/d2dmoe","bartwojcik/sadmoe"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/fedconv-enhancing-convolutional-neural","slug":"fedconv-enhancing-convolutional-neural","title":"FedConv: Enhancing Convolutional Neural Networks for Handling Data Heterogeneity in Federated Learning","date":"2023-10-06","arxiv_id":"2310.04412","n_code_links":1,"syntology":{"ran":16,"of":18,"n_ran_checked":10,"n_instrument":6,"unverified":2,"pointer_only":4,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ucsc-vlaa/fedconv"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"functional-interpolation-for-relative","title":"Functional Interpolation for Relative Positions Improves Long Context Transformers","date":"2023-10-06","arxiv_id":"2310.04418","n_code_links":0,"syntology":null},{"paper":"/paper/language-agent-tree-search-unifies-reasoning","slug":"language-agent-tree-search-unifies-reasoning","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","date":"2023-10-06","arxiv_id":"2310.04406","n_code_links":2,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lapisrocks/languageagenttreesearch","andyz245/LanguageAgentTreeSearch"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/privit-vision-transformers-for-fast-private","slug":"privit-vision-transformers-for-fast-private","title":"PriViT: Vision Transformers for Fast Private Inference","date":"2023-10-06","arxiv_id":"2310.04604","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["nyu-dice-lab/privit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/sub-token-vit-embedding-via-stochastic","slug":"sub-token-vit-embedding-via-stochastic","title":"Sub-token ViT Embedding via Stochastic Resonance Transformers","date":"2023-10-06","arxiv_id":"2310.03967","n_code_links":1,"syntology":null},{"paper":"/paper/tic-exploring-vision-transformer-in","slug":"tic-exploring-vision-transformer-in","title":"TiC: Exploring Vision Transformer in Convolution","date":"2023-10-06","arxiv_id":"2310.04134","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-machine-learning-for-social-good","title":"Adversarial Machine Learning for Social Good: Reframing the Adversary as an Ally","date":"2023-10-05","arxiv_id":"2310.03614","n_code_links":0,"syntology":null},{"paper":"/paper/automating-human-tutor-style-programming","slug":"automating-human-tutor-style-programming","title":"Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation","date":"2023-10-05","arxiv_id":"2310.03780","n_code_links":2,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["machine-teaching-group/lak2024_gpt4-hints-gpt3.5val","machine-teaching-group/lak2024_gpt4hints-gpt3.5val"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"benchmarking-a-foundation-llm-on-its-ability","title":"Benchmarking a foundation LLM on its ability to re-label structure names in accordance with the AAPM TG-263 report","date":"2023-10-05","arxiv_id":"2310.03874","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-large-language-models-as-ai","slug":"benchmarking-large-language-models-as-ai","title":"MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation","date":"2023-10-05","arxiv_id":"2310.03302","n_code_links":2,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["snap-stanford/mlagentbench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-large-language-models-be-good-path","slug":"can-large-language-models-be-good-path","title":"Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning","date":"2023-10-05","arxiv_id":"2310.03249","n_code_links":1,"syntology":{"ran":28,"of":28,"n_ran_checked":28,"n_instrument":0,"unverified":0,"pointer_only":28,"phrase":"28 ran (of which 0 constructed an object rather than computing a result; 28 with no instrument failure: 0 honoured, 0 violated, 28 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mohamedaghzal/llms-as-path-planners"],"state":"official (archive's flag): 28 ran","n_ran":28,"n_constructed":0,"n_ran_no_instrument_failure":28,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"drag-view-generalizable-novel-view-synthesis","title":"Pose-Free Generalizable Rendering Transformer","date":"2023-10-05","arxiv_id":"2310.03704","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-hallucinations-in-chinese-large","slug":"evaluating-hallucinations-in-chinese-large","title":"Evaluating Hallucinations in Chinese Large Language Models","date":"2023-10-05","arxiv_id":"2310.03368","n_code_links":3,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xiami2019/halluqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"heap-hierarchical-policies-for-web-actions","title":"SteP: Stacked LLM Policies for Web Actions","date":"2023-10-05","arxiv_id":"2310.03720","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-personalized-story-evaluation","title":"Learning Personalized Alignment for Evaluating Open-ended Text Generation","date":"2023-10-05","arxiv_id":"2310.03304","n_code_links":0,"syntology":null},{"paper":"/paper/mathcoder-seamless-code-integration-in-llms","slug":"mathcoder-seamless-code-integration-in-llms","title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","date":"2023-10-05","arxiv_id":"2310.03731","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mathllm/mathcoder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"molecule-design-by-latent-prompt-transformer","title":"Molecule Design by Latent Prompt Transformer","date":"2023-10-05","arxiv_id":"2310.03253","n_code_links":0,"syntology":null},{"paper":"/paper/procedural-text-mining-with-large-language","slug":"procedural-text-mining-with-large-language","title":"Procedural Text Mining with Large Language Models","date":"2023-10-05","arxiv_id":"2310.03376","n_code_links":1,"syntology":null},{"paper":"/paper/reformulating-domain-adaptation-of-large","slug":"reformulating-domain-adaptation-of-large","title":"Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise: A Case Study on Chinese Legal Domain","date":"2023-10-05","arxiv_id":"2310.03328","n_code_links":1,"syntology":null},{"paper":null,"slug":"rtdk-bo-high-dimensional-bayesian","title":"RTDK-BO: High Dimensional Bayesian Optimization with Reinforced Transformer Deep kernels","date":"2023-10-05","arxiv_id":"2310.03912","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-a-foundation-model-for-time-series","title":"Toward a Foundation Model for Time Series Data","date":"2023-10-05","arxiv_id":"2310.03916","n_code_links":0,"syntology":null},{"paper":null,"slug":"tuning-in-to-neural-encoding-linking-human","title":"Tuning In to Neural Encoding: Linking Human Brain and Artificial Supervised Representations of Language","date":"2023-10-05","arxiv_id":"2310.04460","n_code_links":0,"syntology":null},{"paper":null,"slug":"visual-inspection-for-illicit-items-in-x-ray","title":"Visual inspection for illicit items in X-ray images using Deep Learning","date":"2023-10-05","arxiv_id":"2310.03658","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-of-quantisation-aware-training-on","title":"A Study of Quantisation-aware Training on Time Series Transformer Models for Resource-constrained FPGAs","date":"2023-10-04","arxiv_id":"2310.02654","n_code_links":0,"syntology":null},{"paper":"/paper/can-language-models-employ-the-socratic","slug":"can-language-models-employ-the-socratic","title":"Can Language Models Employ the Socratic Method? Experiments with Code Debugging","date":"2023-10-04","arxiv_id":"2310.03210","n_code_links":1,"syntology":null},{"paper":null,"slug":"citing-large-language-models-create","title":"CITING: Large Language Models Create Curriculum for Instruction Tuning","date":"2023-10-04","arxiv_id":"2310.02527","n_code_links":0,"syntology":null},{"paper":null,"slug":"decision-convformer-local-filtering-in","title":"Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making","date":"2023-10-04","arxiv_id":"2310.03022","n_code_links":0,"syntology":null},{"paper":"/paper/delving-into-clip-latent-space-for-video","slug":"delving-into-clip-latent-space-for-video","title":"Delving into CLIP latent space for Video Anomaly Recognition","date":"2023-10-04","arxiv_id":"2310.02835","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["luca-zanella-dvl/AnomalyCLIP"],"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/dq-lore-dual-queries-with-low-rank","slug":"dq-lore-dual-queries-with-low-rank","title":"DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning","date":"2023-10-04","arxiv_id":"2310.02954","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":3,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ai4fun/dq-lore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"paper":"/paper/get-group-event-transformer-for-event-based-1","slug":"get-group-event-transformer-for-event-based-1","title":"GET: Group Event Transformer for Event-Based Vision","date":"2023-10-04","arxiv_id":"2310.02642","n_code_links":2,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"pointer_only":11,"phrase":"8 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["peterande/get-group-event-transformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gpt-4-as-an-interface-between-researchers-and","title":"GPT-4 as an interface between researchers and computational software: improving usability and reproducibility","date":"2023-10-04","arxiv_id":"2310.11458","n_code_links":0,"syntology":null},{"paper":"/paper/how-far-are-large-language-models-from-agents","slug":"how-far-are-large-language-models-from-agents","title":"How FaR Are Large Language Models From Agents with Theory-of-Mind?","date":"2023-10-04","arxiv_id":"2310.03051","n_code_links":1,"syntology":null},{"paper":"/paper/land-cover-change-detection-using-paired","slug":"land-cover-change-detection-using-paired","title":"ObjFormer: Learning Land-Cover Changes From Paired OSM Data and Optical High-Resolution Imagery via Object-Guided Transformer","date":"2023-10-04","arxiv_id":"2310.02674","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-model-cascades-with-mixture-of","slug":"large-language-model-cascades-with-mixture-of","title":"Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning","date":"2023-10-04","arxiv_id":"2310.03094","n_code_links":1,"syntology":null},{"paper":null,"slug":"medprompt-cross-modal-prompting-for-multi","title":"MedPrompt: Cross-Modal Prompting for Multi-Task Medical Image Translation","date":"2023-10-04","arxiv_id":"2310.02663","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-prompt-transformer-with-hybrid","slug":"multimodal-prompt-transformer-with-hybrid","title":"Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in Conversation","date":"2023-10-04","arxiv_id":"2310.04456","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-question-answering-for-unified","slug":"multimodal-question-answering-for-unified","title":"Multimodal Question Answering for Unified Information Extraction","date":"2023-10-04","arxiv_id":"2310.03017","n_code_links":1,"syntology":null},{"paper":null,"slug":"munch-modelling-unique-n-controllable-heads","title":"MUNCH: Modelling Unique 'N Controllable Heads","date":"2023-10-04","arxiv_id":"2310.02753","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-architecture-impact-on-identifying","title":"Neural architecture impact on identifying temporally extended Reinforcement Learning tasks","date":"2023-10-04","arxiv_id":"2310.03161","n_code_links":0,"syntology":null},{"paper":"/paper/out-of-distribution-detection-by-leveraging","slug":"out-of-distribution-detection-by-leveraging","title":"Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness","date":"2023-10-04","arxiv_id":"2310.02832","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":["fjelenic/between-layer-ood"],"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":"robust-and-interpretable-medical-image","title":"Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models","date":"2023-10-04","arxiv_id":"2310.03182","n_code_links":0,"syntology":null},{"paper":null,"slug":"schyena-foundation-model-for-full-length","title":"scHyena: Foundation Model for Full-Length Single-Cell RNA-Seq Analysis in Brain","date":"2023-10-04","arxiv_id":"2310.02713","n_code_links":0,"syntology":null},{"paper":"/paper/t-3-bench-benchmarking-current-progress-in","slug":"t-3-bench-benchmarking-current-progress-in","title":"T$^3$Bench: Benchmarking Current Progress in Text-to-3D Generation","date":"2023-10-04","arxiv_id":"2310.02977","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":["THU-LYJ-Lab/T3Bench"],"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":"understanding-in-context-learning-in","title":"Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions","date":"2023-10-04","arxiv_id":"2310.03016","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-and-improving-generator","title":"Benchmarking and Improving Generator-Validator Consistency of Language Models","date":"2023-10-03","arxiv_id":"2310.01846","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-gpt-4-replicate-empirical-software","title":"Can GPT-4 Replicate Empirical Software Engineering Research?","date":"2023-10-03","arxiv_id":"2310.01727","n_code_links":0,"syntology":null},{"paper":"/paper/can-large-language-models-provide-useful","slug":"can-large-language-models-provide-useful","title":"Can large language models provide useful feedback on research papers? A large-scale empirical analysis","date":"2023-10-03","arxiv_id":"2310.01783","n_code_links":1,"syntology":null}],"record_sha256":"f4e9460ada11af4aa6878b18f7c343238c7f85136f6ada7ab9932d913a631898","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}