{"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/linear-layer/papers/114","list_of":"/method/linear-layer","method":"Linear Layer","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":114,"pages_in_order":255,"rows_per_page":100,"rows":[11301,11400],"of":25421,"counts":{"archive_papers_tagged":25421,"with_a_code_link":11479,"where_syntology_ran_a_sample":3523,"not_listed_spam_title":0,"listed":25421,"listed_where_code_ran":3523,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2976,"every_run_a_failure_of_syntologys_instrument":547,"listed_with_a_run_with_no_instrument_failure":2976,"listed_every_run_a_failure_of_syntologys_instrument":547,"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/linear-layer","prev":"/method/linear-layer/papers/113","next":"/method/linear-layer/papers/115","papers":[{"paper":"/paper/dementia-assessment-using-mandarin-speech","slug":"dementia-assessment-using-mandarin-speech","title":"Dementia Assessment Using Mandarin Speech with an Attention-based Speech Recognition Encoder","date":"2023-10-06","arxiv_id":"2310.03985","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":null,"slug":"keyword-augmented-retrieval-novel-framework","title":"Keyword Augmented Retrieval: Novel framework for Information Retrieval integrated with speech interface","date":"2023-10-06","arxiv_id":"2310.04205","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":null,"slug":"quantized-transformer-language-model","title":"Quantized Transformer Language Model Implementations on Edge Devices","date":"2023-10-06","arxiv_id":"2310.03971","n_code_links":0,"syntology":null},{"paper":null,"slug":"segmented-harmonic-loss-handling-class","title":"Segmented Harmonic Loss: Handling Class-Imbalanced Multi-Label Clinical Data for Medical Coding with Large Language Models","date":"2023-10-06","arxiv_id":"2310.04595","n_code_links":0,"syntology":null},{"paper":"/paper/slogan-generation-with-noise-perturbation","slug":"slogan-generation-with-noise-perturbation","title":"Effective Slogan Generation with Noise Perturbation","date":"2023-10-06","arxiv_id":"2310.04472","n_code_links":1,"syntology":null},{"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/agent-instructs-large-language-models-to-be","slug":"agent-instructs-large-language-models-to-be","title":"Agent Instructs Large Language Models to be General Zero-Shot Reasoners","date":"2023-10-05","arxiv_id":"2310.03710","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["wang-research-lab/agentinstruct"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/dspy-compiling-declarative-language-model","slug":"dspy-compiling-declarative-language-model","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","date":"2023-10-05","arxiv_id":"2310.03714","n_code_links":3,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["stanfordnlp/dspy"],"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/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":"exploring-dino-emergent-properties-and","title":"Exploring DINO: Emergent Properties and Limitations for Synthetic Aperture Radar Imagery","date":"2023-10-05","arxiv_id":"2310.03513","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-aligned-language-models","slug":"fine-tuning-aligned-language-models","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","date":"2023-10-05","arxiv_id":"2310.03693","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":["llm-tuning-safety/llms-finetuning-safety"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/hard-view-selection-for-contrastive-learning","slug":"hard-view-selection-for-contrastive-learning","title":"Beyond Random Augmentations: Pretraining with Hard Views","date":"2023-10-05","arxiv_id":"2310.03940","n_code_links":2,"syntology":null},{"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":"/paper/smoothllm-defending-large-language-models","slug":"smoothllm-defending-large-language-models","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","date":"2023-10-05","arxiv_id":"2310.03684","n_code_links":1,"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":null,"slug":"a-survey-of-gpt-3-family-large-language","title":"A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4","date":"2023-10-04","arxiv_id":"2310.12321","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":"covid-19-south-african-vaccine-hesitancy","title":"COVID-19 South African Vaccine Hesitancy Models Show Boost in Performance Upon Fine-Tuning on M-pox Tweets","date":"2023-10-04","arxiv_id":"2310.04453","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":null,"slug":"improving-drumming-robot-via-attention","title":"Improving Drumming Robot Via Attention Transformer Network","date":"2023-10-04","arxiv_id":"2310.02565","n_code_links":0,"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/memoria-hebbian-memory-architecture-for-human","slug":"memoria-hebbian-memory-architecture-for-human","title":"Memoria: Resolving Fateful Forgetting Problem through Human-Inspired Memory Architecture","date":"2023-10-04","arxiv_id":"2310.03052","n_code_links":1,"syntology":{"ran":1,"of":10,"n_ran_checked":0,"n_instrument":1,"unverified":9,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","official":{"repos":["cosmoquester/memoria"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":9,"ran_from_kinds":["official"]}}},{"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/nola-networks-as-linear-combination-of-low","slug":"nola-networks-as-linear-combination-of-low","title":"NOLA: Compressing LoRA using Linear Combination of Random Basis","date":"2023-10-04","arxiv_id":"2310.02556","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":2,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["UCDvision/NOLA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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":"reinforcement-learning-based-mixture-of","title":"Reinforcement Learning-based Mixture of Vision Transformers for Video Violence Recognition","date":"2023-10-04","arxiv_id":"2310.03108","n_code_links":0,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-to-improve","slug":"retrieval-augmented-generation-to-improve","title":"Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference","date":"2023-10-04","arxiv_id":"2310.03184","n_code_links":2,"syntology":{"ran":12,"of":20,"n_ran_checked":12,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["digitalharborfoundation/rag-for-math-qa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"retrieval-meets-long-context-large-language","title":"Retrieval meets Long Context Large Language Models","date":"2023-10-04","arxiv_id":"2310.03025","n_code_links":0,"syntology":null},{"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/slowformer-universal-adversarial-patch-for","slug":"slowformer-universal-adversarial-patch-for","title":"SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers","date":"2023-10-04","arxiv_id":"2310.02544","n_code_links":1,"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},{"paper":"/paper/contrastive-post-training-large-language","slug":"contrastive-post-training-large-language","title":"Automatic Pair Construction for Contrastive Post-training","date":"2023-10-03","arxiv_id":"2310.02263","n_code_links":1,"syntology":null},{"paper":null,"slug":"de-novo-drug-design-with-joint-transformers","title":"De Novo Drug Design with Joint Transformers","date":"2023-10-03","arxiv_id":"2310.02066","n_code_links":0,"syntology":null},{"paper":"/paper/ecoassistant-using-llm-assistant-more","slug":"ecoassistant-using-llm-assistant-more","title":"EcoAssistant: Using LLM Assistant More Affordably and Accurately","date":"2023-10-03","arxiv_id":"2310.03046","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":["jieyuz2/ecoassistant"],"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":"/paper/editing-personality-for-llms","slug":"editing-personality-for-llms","title":"Editing Personality for Large Language Models","date":"2023-10-03","arxiv_id":"2310.02168","n_code_links":1,"syntology":null},{"paper":"/paper/halle-switch-rethinking-and-controlling","slug":"halle-switch-rethinking-and-controlling","title":"HallE-Control: Controlling Object Hallucination in Large Multimodal Models","date":"2023-10-03","arxiv_id":"2310.01779","n_code_links":2,"syntology":{"ran":6,"of":9,"n_ran_checked":3,"n_instrument":3,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["bronyayang/HallE_Switch","bronyayang/halle_control"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"harnessing-pre-trained-sentence-transformers","title":"Harnessing Pre-Trained Sentence Transformers for Offensive Language Detection in Indian Languages","date":"2023-10-03","arxiv_id":"2310.02249","n_code_links":0,"syntology":null},{"paper":"/paper/instance-needs-more-care-rewriting-prompts","slug":"instance-needs-more-care-rewriting-prompts","title":"Instances Need More Care: Rewriting Prompts for Instances with LLMs in the Loop Yields Better Zero-Shot Performance","date":"2023-10-03","arxiv_id":"2310.02107","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["salokr/propmted"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"investigating-large-language-models","title":"Investigating Large Language Models' Perception of Emotion Using Appraisal Theory","date":"2023-10-03","arxiv_id":"2310.04450","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-resource-languages-jailbreak-gpt-4","title":"Low-Resource Languages Jailbreak GPT-4","date":"2023-10-03","arxiv_id":"2310.02446","n_code_links":0,"syntology":null},{"paper":"/paper/probabilistically-rewired-message-passing","slug":"probabilistically-rewired-message-passing","title":"Probabilistically Rewired Message-Passing Neural Networks","date":"2023-10-03","arxiv_id":"2310.02156","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["chendiqian/PR-MPNN"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"protoner-few-shot-incremental-learning-for","title":"ProtoNER: Few shot Incremental Learning for Named Entity Recognition using Prototypical Networks","date":"2023-10-03","arxiv_id":"2310.02372","n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforcement-learning-from-automatic","title":"Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation","date":"2023-10-03","arxiv_id":"2310.02368","n_code_links":0,"syntology":null},{"paper":null,"slug":"residualtransformer-residual-low-rank","title":"ResidualTransformer: Residual Low-Rank Learning with Weight-Sharing for Transformer Layers","date":"2023-10-03","arxiv_id":"2310.02489","n_code_links":0,"syntology":null},{"paper":null,"slug":"secure-and-effective-data-appraisal-for","title":"SelectFormer: Private and Practical Data Selection for Transformers","date":"2023-10-03","arxiv_id":"2310.02373","n_code_links":0,"syntology":null},{"paper":null,"slug":"selective-feature-adapter-for-dense-vision","title":"Selective Feature Adapter for Dense Vision Transformers","date":"2023-10-03","arxiv_id":"2310.01843","n_code_links":0,"syntology":null},{"paper":"/paper/self-taught-optimizer-stop-recursively-self","slug":"self-taught-optimizer-stop-recursively-self","title":"Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation","date":"2023-10-03","arxiv_id":"2310.02304","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["microsoft/stop"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-inhibitor-relu-and-addition-based","title":"The Inhibitor: ReLU and Addition-Based Attention for Efficient Transformers","date":"2023-10-03","arxiv_id":"2310.02041","n_code_links":0,"syntology":null},{"paper":null,"slug":"video-transformers-under-occlusion-how","title":"How Physics and Background Attributes Impact Video Transformers in Robotic Manipulation: A Case Study on Planar Pushing","date":"2023-10-03","arxiv_id":"2310.02044","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-s-next-in-affective-modeling-large","title":"What's Next in Affective Modeling? Large Language Models","date":"2023-10-03","arxiv_id":"2310.18322","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-remote-sensing-segmentation-with","title":"Efficient Remote Sensing Segmentation With Generative Adversarial Transformer","date":"2023-10-02","arxiv_id":"2310.01292","n_code_links":0,"syntology":null},{"paper":"/paper/evolutionary-neural-architecture-search-for-1","slug":"evolutionary-neural-architecture-search-for-1","title":"Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing","date":"2023-10-02","arxiv_id":"2310.01180","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":10,"n_instrument":1,"unverified":3,"pointer_only":14,"phrase":"11 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["devilyangs/enas-kt"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/gpt-driver-learning-to-drive-with-gpt","slug":"gpt-driver-learning-to-drive-with-gpt","title":"GPT-Driver: Learning to Drive with GPT","date":"2023-10-02","arxiv_id":"2310.01415","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pointscoder/gpt-driver"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/improving-dialogue-management-quality","slug":"improving-dialogue-management-quality","title":"Improving Dialogue Management: Quality Datasets vs Models","date":"2023-10-02","arxiv_id":"2310.01339","n_code_links":1,"syntology":null},{"paper":"/paper/label-supervised-llama-finetuning","slug":"label-supervised-llama-finetuning","title":"Label Supervised LLaMA Finetuning","date":"2023-10-02","arxiv_id":"2310.01208","n_code_links":2,"syntology":null},{"paper":"/paper/large-language-model-powered-smart-contract","slug":"large-language-model-powered-smart-contract","title":"Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives","date":"2023-10-02","arxiv_id":"2310.01152","n_code_links":1,"syntology":null},{"paper":"/paper/linear-attention-is-maybe-all-you-need-to","slug":"linear-attention-is-maybe-all-you-need-to","title":"Linear attention is (maybe) all you need (to understand transformer optimization)","date":"2023-10-02","arxiv_id":"2310.01082","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":null}},{"paper":"/paper/llm-lies-hallucinations-are-not-bugs-but","slug":"llm-lies-hallucinations-are-not-bugs-but","title":"LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples","date":"2023-10-02","arxiv_id":"2310.01469","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["pku-yuangroup/hallucination-attack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"loft-local-proxy-fine-tuning-for-improving","title":"LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model","date":"2023-10-02","arxiv_id":"2310.04445","n_code_links":0,"syntology":null},{"paper":"/paper/making-llama-see-and-draw-with-seed-tokenizer","slug":"making-llama-see-and-draw-with-seed-tokenizer","title":"Making LLaMA SEE and Draw with SEED Tokenizer","date":"2023-10-02","arxiv_id":"2310.01218","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":6,"n_instrument":2,"unverified":3,"pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ailab-cvc/seed"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"melody-conditioned-lyrics-generation-via-fine","title":"Syllable-level lyrics generation from melody exploiting character-level language model","date":"2023-10-02","arxiv_id":"2310.00863","n_code_links":0,"syntology":null},{"paper":null,"slug":"modality-aware-transformer-for-time-series","title":"Modality-aware Transformer for Financial Time series Forecasting","date":"2023-10-02","arxiv_id":"2310.01232","n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-models-for-data","title":"Natural Language Models for Data Visualization Utilizing nvBench Dataset","date":"2023-10-02","arxiv_id":"2310.00832","n_code_links":0,"syntology":null}],"record_sha256":"1b4d6ac20135b0ca963f64a101e60a7856d385701109fe9cc834977909c2eb1c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}