{"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/softmax/papers/176","list_of":"/method/softmax","method":"Softmax","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":176,"pages_in_order":375,"rows_per_page":100,"rows":[17501,17600],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/175","next":"/method/softmax/papers/177","papers":[{"paper":null,"slug":"mixed-distillation-helps-smaller-language","title":"Mixed Distillation Helps Smaller Language Model Better Reasoning","date":"2023-12-17","arxiv_id":"2312.10730","n_code_links":0,"syntology":null},{"paper":"/paper/multi-label-classification-of-covid-tweets","slug":"multi-label-classification-of-covid-tweets","title":"Multi-Label Classification of COVID-Tweets Using Large Language Models","date":"2023-12-17","arxiv_id":"2312.10748","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-level-reasoning-for-robotic-assembly","title":"Multi-level Reasoning for Robotic Assembly: From Sequence Inference to Contact Selection","date":"2023-12-17","arxiv_id":"2312.10571","n_code_links":0,"syntology":null},{"paper":"/paper/pedestrian-attribute-recognition-via-clip","slug":"pedestrian-attribute-recognition-via-clip","title":"Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion","date":"2023-12-17","arxiv_id":"2312.10692","n_code_links":2,"syntology":null},{"paper":null,"slug":"t2m-hifigpt-generating-high-quality-human","title":"T2M-HiFiGPT: Generating High Quality Human Motion from Textual Descriptions with Residual Discrete Representations","date":"2023-12-17","arxiv_id":"2312.10628","n_code_links":0,"syntology":null},{"paper":"/paper/towards-compact-3d-representations-via-point","slug":"towards-compact-3d-representations-via-point","title":"Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders","date":"2023-12-17","arxiv_id":"2312.10726","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comparative-analysis-of-large-language","title":"A Comparative Analysis of Large Language Models for Code Documentation Generation","date":"2023-12-16","arxiv_id":"2312.10349","n_code_links":0,"syntology":null},{"paper":"/paper/an-attentive-inductive-bias-for-sequential","slug":"an-attentive-inductive-bias-for-sequential","title":"An Attentive Inductive Bias for Sequential Recommendation beyond the Self-Attention","date":"2023-12-16","arxiv_id":"2312.10325","n_code_links":2,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jeongwhanchoi/BSARec"],"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":null,"slug":"cross-linguistic-offensive-language-detection","title":"Cross-Linguistic Offensive Language Detection: BERT-Based Analysis of Bengali, Assamese, & Bodo Conversational Hateful Content from Social Media","date":"2023-12-16","arxiv_id":"2312.10528","n_code_links":0,"syntology":null},{"paper":null,"slug":"deepart-a-benchmark-to-advance-fidelity","title":"DeepArt: A Benchmark to Advance Fidelity Research in AI-Generated Content","date":"2023-12-16","arxiv_id":"2312.10407","n_code_links":0,"syntology":null},{"paper":"/paper/fusing-conditional-submodular-gan-and","slug":"fusing-conditional-submodular-gan-and","title":"Fusing Conditional Submodular GAN and Programmatic Weak Supervision","date":"2023-12-16","arxiv_id":"2312.10366","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kyrs/subpws-gan"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/investigating-shallow-and-deep-learning","slug":"investigating-shallow-and-deep-learning","title":"Investigating Shallow and Deep Learning Techniques for Emotion Classification in Short Persian Texts","date":"2023-12-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/recprompt-a-prompt-tuning-framework-for-news","slug":"recprompt-a-prompt-tuning-framework-for-news","title":"RecPrompt: A Self-tuning Prompting Framework for News Recommendation Using Large Language Models","date":"2023-12-16","arxiv_id":"2312.10463","n_code_links":1,"syntology":null},{"paper":null,"slug":"resonet-robust-and-explainable-enso-forecasts","title":"ResoNet: Robust and Explainable ENSO Forecasts with Hybrid Convolution and Transformer Networks","date":"2023-12-16","arxiv_id":"2312.10429","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-disentangled-representation-2","title":"Self-Supervised Disentangled Representation Learning for Robust Target Speech Extraction","date":"2023-12-16","arxiv_id":"2312.10305","n_code_links":0,"syntology":null},{"paper":"/paper/spt-fine-tuning-transformer-based-language","slug":"spt-fine-tuning-transformer-based-language","title":"SPT: Fine-Tuning Transformer-based Language Models Efficiently with Sparsification","date":"2023-12-16","arxiv_id":"2312.10365","n_code_links":1,"syntology":null},{"paper":null,"slug":"tender-notice-extraction-from-e-papers-using","title":"Tender Notice Extraction from E-papers Using Neural Network","date":"2023-12-16","arxiv_id":"2312.10437","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-case-study-of-image-enhancement-algorithms","title":"A Case Study of Image Enhancement Algorithms' Effectiveness of Improving Neural Networks' Performance on Adverse Images","date":"2023-12-15","arxiv_id":"2312.09509","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-dataset-for-financial-education-text","title":"A Novel Dataset for Financial Education Text Simplification in Spanish","date":"2023-12-15","arxiv_id":"2312.09897","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-neural-network-training-a-brief","slug":"accelerating-neural-network-training-a-brief","title":"Accelerating Neural Network Training: A Brief Review","date":"2023-12-15","arxiv_id":"2312.10024","n_code_links":1,"syntology":null},{"paper":null,"slug":"algorithms-for-automatic-intents-extraction","title":"Algorithms for automatic intents extraction and utterances classification for goal-oriented dialogue systems","date":"2023-12-15","arxiv_id":"2312.09658","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-empirical-windowing-an-attention-based","title":"Beyond Empirical Windowing: An Attention-Based Approach for Trust Prediction in Autonomous Vehicles","date":"2023-12-15","arxiv_id":"2312.10209","n_code_links":0,"syntology":null},{"paper":"/paper/binary-code-summarization-benchmarking","slug":"binary-code-summarization-benchmarking","title":"Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models","date":"2023-12-15","arxiv_id":"2312.09601","n_code_links":1,"syntology":null},{"paper":null,"slug":"distilling-large-language-models-for-matching","title":"Distilling Large Language Models for Matching Patients to Clinical Trials","date":"2023-12-15","arxiv_id":"2312.09958","n_code_links":0,"syntology":null},{"paper":null,"slug":"eating-speed-measurement-using-wrist-worn-imu","title":"Eating Speed Measurement Using Wrist-Worn IMU Sensors Towards Free-Living Environments","date":"2023-12-15","arxiv_id":"2401.05376","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-automatic-text-simplification-of","slug":"exploring-automatic-text-simplification-of","title":"Exploring Automatic Text Simplification of German Narrative Documents","date":"2023-12-15","arxiv_id":"2312.09907","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-multi-level-threats-in-telegram","slug":"exploring-multi-level-threats-in-telegram","title":"Exploring Multi-Level Threats in Telegram Data with AI-Human Annotation: A Preliminary Study","date":"2023-12-15","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fragility-robustness-and-antifragility-in","title":"Fragility, Robustness and Antifragility in Deep Learning","date":"2023-12-15","arxiv_id":"2312.09821","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-uncertainty-aggregation-and","title":"Hierarchical Uncertainty Aggregation and Emphasis Loss for Active Learning in Object Detection","date":"2023-12-15","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/icd-lm-configuring-vision-language-in-context","slug":"icd-lm-configuring-vision-language-in-context","title":"Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models","date":"2023-12-15","arxiv_id":"2312.10104","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["forjadeforest/icd-lm","forjadeforest/lever-lm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"integrating-ai-and-learning-analytics-for","title":"Integrating AI and Learning Analytics for Data-Driven Pedagogical Decisions and Personalized Interventions in Education","date":"2023-12-15","arxiv_id":"2312.09548","n_code_links":0,"syntology":null},{"paper":null,"slug":"no-skim-towards-efficiency-robustness","title":"No-Skim: Towards Efficiency Robustness Evaluation on Skimming-based Language Models","date":"2023-12-15","arxiv_id":"2312.09494","n_code_links":0,"syntology":null},{"paper":"/paper/openmedcalc-augmentation-of-chatgpt-with","slug":"openmedcalc-augmentation-of-chatgpt-with","title":"OpenMedCalc: Augmentation of ChatGPT with Clinician-Informed Tools Improves Performance on Medical Calculation Tasks","date":"2023-12-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/part-representation-learning-with-teacher","slug":"part-representation-learning-with-teacher","title":"Part Representation Learning with Teacher-Student Decoder for Occluded Person Re-identification","date":"2023-12-15","arxiv_id":"2312.09797","n_code_links":1,"syntology":null},{"paper":"/paper/point-transformer-v3-simpler-faster-stronger","slug":"point-transformer-v3-simpler-faster-stronger","title":"Point Transformer V3: Simpler, Faster, Stronger","date":"2023-12-15","arxiv_id":"2312.10035","n_code_links":3,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":3,"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) · 4 unverified","official":{"repos":["Pointcept/Pointcept","pointcept/pointtransformerv3"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"red-ai-inconsistent-responses-from-gpt3-5","title":"Red AI? Inconsistent Responses from GPT3.5 Models on Political Issues in the US and China","date":"2023-12-15","arxiv_id":"2312.09917","n_code_links":0,"syntology":null},{"paper":null,"slug":"system-integration-of-xilinx-dpu-and-hdmi-for","title":"System Integration of Xilinx DPU and HDMI for Real-Time inference in PYNQ Environment with Image Enhancement","date":"2023-12-15","arxiv_id":"2312.09506","n_code_links":0,"syntology":null},{"paper":null,"slug":"acoustic-models-of-brazilian-portuguese","title":"Acoustic models of Brazilian Portuguese Speech based on Neural Transformers","date":"2023-12-14","arxiv_id":"2312.09265","n_code_links":0,"syntology":null},{"paper":"/paper/agent-attention-on-the-integration-of-softmax","slug":"agent-attention-on-the-integration-of-softmax","title":"Agent Attention: On the Integration of Softmax and Linear Attention","date":"2023-12-14","arxiv_id":"2312.08874","n_code_links":2,"syntology":{"ran":13,"of":19,"n_ran_checked":9,"n_instrument":4,"unverified":6,"pointer_only":19,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["leaplabthu/agent-attention"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/auto-prox-training-free-vision-transformer","slug":"auto-prox-training-free-vision-transformer","title":"Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery","date":"2023-12-14","arxiv_id":"2312.09059","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"5 ran (of which 0 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) · 0 unverified","official":{"repos":["lilujunai/auto-prox-aaai24"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/bipft-binary-pre-trained-foundation","slug":"bipft-binary-pre-trained-foundation","title":"BiPFT: Binary Pre-trained Foundation Transformer with Low-rank Estimation of Binarization Residual Polynomials","date":"2023-12-14","arxiv_id":"2312.08937","n_code_links":1,"syntology":null},{"paper":"/paper/boosting-llm-reasoning-push-the-limits-of-few","slug":"boosting-llm-reasoning-push-the-limits-of-few","title":"Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning","date":"2023-12-14","arxiv_id":"2312.08901","n_code_links":0,"syntology":null},{"paper":null,"slug":"brain-diffuser-with-hierarchical-transformer","title":"BDHT: Generative AI Enables Causality Analysis for Mild Cognitive Impairment","date":"2023-12-14","arxiv_id":"2312.09022","n_code_links":0,"syntology":null},{"paper":"/paper/dissecting-vocabulary-biases-datasets-through","slug":"dissecting-vocabulary-biases-datasets-through","title":"Dissecting vocabulary biases datasets through statistical testing and automated data augmentation for artifact mitigation in Natural Language Inference","date":"2023-12-14","arxiv_id":"2312.08747","n_code_links":1,"syntology":null},{"paper":null,"slug":"entity-augmented-code-generation","title":"Dynamic Retrieval-Augmented Generation","date":"2023-12-14","arxiv_id":"2312.08976","n_code_links":0,"syntology":null},{"paper":"/paper/factorization-vision-transformer-modeling","slug":"factorization-vision-transformer-modeling","title":"Factorization Vision Transformer: Modeling Long Range Dependency with Local Window Cost","date":"2023-12-14","arxiv_id":"2312.08614","n_code_links":1,"syntology":null},{"paper":null,"slug":"guided-diffusion-from-self-supervised","title":"Guided Diffusion from Self-Supervised Diffusion Features","date":"2023-12-14","arxiv_id":"2312.08825","n_code_links":0,"syntology":null},{"paper":"/paper/heterogeneous-graph-neural-architecture","slug":"heterogeneous-graph-neural-architecture","title":"Heterogeneous Graph Neural Architecture Search with GPT-4","date":"2023-12-14","arxiv_id":"2312.08680","n_code_links":1,"syntology":null},{"paper":"/paper/holodeck-language-guided-generation-of-3d","slug":"holodeck-language-guided-generation-of-3d","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","date":"2023-12-14","arxiv_id":"2312.09067","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":["allenai/Holodeck"],"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":"inter-layer-scheduling-space-exploration-for","title":"Inter-Layer Scheduling Space Exploration for Multi-model Inference on Heterogeneous Chiplets","date":"2023-12-14","arxiv_id":"2312.09401","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-long-sequences-in-spiking-neural","title":"Learning Long Sequences in Spiking Neural Networks","date":"2023-12-14","arxiv_id":"2401.00955","n_code_links":0,"syntology":null},{"paper":"/paper/modeling-complex-mathematical-reasoning-via","slug":"modeling-complex-mathematical-reasoning-via","title":"Modeling Complex Mathematical Reasoning via Large Language Model based MathAgent","date":"2023-12-14","arxiv_id":"2312.08926","n_code_links":1,"syntology":null},{"paper":null,"slug":"motion-flow-matching-for-human-motion","title":"Motion Flow Matching for Human Motion Synthesis and Editing","date":"2023-12-14","arxiv_id":"2312.08895","n_code_links":0,"syntology":null},{"paper":"/paper/next-tdnn-modernizing-multi-scale-temporal","slug":"next-tdnn-modernizing-multi-scale-temporal","title":"NeXt-TDNN: Modernizing Multi-Scale Temporal Convolution Backbone for Speaker Verification","date":"2023-12-14","arxiv_id":"2312.08603","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-image-based-detection-of-tomato-and","title":"On the Image-Based Detection of Tomato and Corn leaves Diseases : An in-depth comparative experiments","date":"2023-12-14","arxiv_id":"2312.08659","n_code_links":0,"syntology":null},{"paper":"/paper/polyper-boundary-sensitive-polyp-segmentation","slug":"polyper-boundary-sensitive-polyp-segmentation","title":"Polyper: Boundary Sensitive Polyp Segmentation","date":"2023-12-14","arxiv_id":"2312.08735","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-evaluation-improves-selective-generation","title":"Self-Evaluation Improves Selective Generation in Large Language Models","date":"2023-12-14","arxiv_id":"2312.09300","n_code_links":0,"syntology":null},{"paper":null,"slug":"successor-heads-recurring-interpretable","title":"Successor Heads: Recurring, Interpretable Attention Heads In The Wild","date":"2023-12-14","arxiv_id":"2312.09230","n_code_links":0,"syntology":null},{"paper":"/paper/tinygsm-achieving-80-on-gsm8k-with-small","slug":"tinygsm-achieving-80-on-gsm8k-with-small","title":"TinyGSM: achieving >80% on GSM8k with small language models","date":"2023-12-14","arxiv_id":"2312.09241","n_code_links":0,"syntology":null},{"paper":"/paper/vl-gpt-a-generative-pre-trained-transformer","slug":"vl-gpt-a-generative-pre-trained-transformer","title":"VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation","date":"2023-12-14","arxiv_id":"2312.09251","n_code_links":1,"syntology":null},{"paper":"/paper/vsformer-visual-spatial-fusion-transformer","slug":"vsformer-visual-spatial-fusion-transformer","title":"VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning","date":"2023-12-14","arxiv_id":"2312.08774","n_code_links":1,"syntology":null},{"paper":null,"slug":"weak-to-strong-generalization-eliciting","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","date":"2023-12-14","arxiv_id":"2312.09390","n_code_links":0,"syntology":null},{"paper":"/paper/weaving-pathways-for-justice-with-gpt-llm","slug":"weaving-pathways-for-justice-with-gpt-llm","title":"Weaving Pathways for Justice with GPT: LLM-driven automated drafting of interactive legal applications","date":"2023-12-14","arxiv_id":"2312.09198","n_code_links":1,"syntology":null},{"paper":null,"slug":"zebra-extending-context-window-with-layerwise","title":"Zebra: Extending Context Window with Layerwise Grouped Local-Global Attention","date":"2023-12-14","arxiv_id":"2312.08618","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-gpt4-v-on-structured-reasoning","title":"Assessing GPT4-V on Structured Reasoning Tasks","date":"2023-12-13","arxiv_id":"2312.11524","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-english-evaluating-llms-for-arabic","title":"Beyond English: Evaluating LLMs for Arabic Grammatical Error Correction","date":"2023-12-13","arxiv_id":"2312.08400","n_code_links":0,"syntology":null},{"paper":"/paper/causality-analysis-for-evaluating-the","slug":"causality-analysis-for-evaluating-the","title":"Causality Analysis for Evaluating the Security of Large Language Models","date":"2023-12-13","arxiv_id":"2312.07876","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":6,"n_instrument":1,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["casperllm/casper"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/chat-3d-v2-bridging-3d-scene-and-large","slug":"chat-3d-v2-bridging-3d-scene-and-large","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","date":"2023-12-13","arxiv_id":"2312.08168","n_code_links":2,"syntology":{"ran":11,"of":11,"n_ran_checked":6,"n_instrument":5,"unverified":0,"pointer_only":5,"phrase":"11 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["chat-3d/chat-3d-v2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"coie-chain-of-instruct-editing-for-multi","title":"CoIE: Chain-of-Instruct Editing for Multi-Attribute Face Manipulation","date":"2023-12-13","arxiv_id":"2312.07879","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-yolov8-and-mask-rcnn-for-object","title":"Comparing YOLOv8 and Mask RCNN for object segmentation in complex orchard environments","date":"2023-12-13","arxiv_id":"2312.07935","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-multi-object-pose-estimation-using","title":"Efficient Multi-Object Pose Estimation using Multi-Resolution Deformable Attention and Query Aggregation","date":"2023-12-13","arxiv_id":"2312.08268","n_code_links":0,"syntology":null},{"paper":null,"slug":"ehancing-ct-image-synthesis-from-multi-modal","title":"Enhancing CT Image synthesis from multi-modal MRI data based on a multi-task neural network framework","date":"2023-12-13","arxiv_id":"2312.08343","n_code_links":0,"syntology":null},{"paper":null,"slug":"high-throughput-biomedical-relation","title":"High-throughput Biomedical Relation Extraction for Semi-Structured Web Articles Empowered by Large Language Models","date":"2023-12-13","arxiv_id":"2312.08274","n_code_links":0,"syntology":null},{"paper":null,"slug":"invariant-graph-transformer","title":"Fine-grained Graph Rationalization","date":"2023-12-13","arxiv_id":"2312.07859","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-are-complex-table","title":"Large Language Models are Complex Table Parsers","date":"2023-12-13","arxiv_id":"2312.11521","n_code_links":0,"syntology":null},{"paper":"/paper/mono3dvg-3d-visual-grounding-in-monocular","slug":"mono3dvg-3d-visual-grounding-in-monocular","title":"Mono3DVG: 3D Visual Grounding in Monocular Images","date":"2023-12-13","arxiv_id":"2312.08022","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":5,"n_instrument":1,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zhanyang-nwpu/mono3dvg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/n-gram-unsupervised-compoundation-and-feature","slug":"n-gram-unsupervised-compoundation-and-feature","title":"N-Gram Unsupervised Compoundation and Feature Injection for Better Symbolic Music Understanding","date":"2023-12-13","arxiv_id":"2312.08931","n_code_links":2,"syntology":null},{"paper":null,"slug":"native-language-identification-with-large","title":"Native Language Identification with Large Language Models","date":"2023-12-13","arxiv_id":"2312.07819","n_code_links":0,"syntology":null},{"paper":"/paper/prompt-engineering-assisted-malware-dynamic","slug":"prompt-engineering-assisted-malware-dynamic","title":"Prompt Engineering-assisted Malware Dynamic Analysis Using GPT-4","date":"2023-12-13","arxiv_id":"2312.08317","n_code_links":1,"syntology":null},{"paper":null,"slug":"pronerf-learning-efficient-projection-aware","title":"ProNeRF: Learning Efficient Projection-Aware Ray Sampling for Fine-Grained Implicit Neural Radiance Fields","date":"2023-12-13","arxiv_id":"2312.08136","n_code_links":0,"syntology":null},{"paper":"/paper/switchhead-accelerating-transformers-with","slug":"switchhead-accelerating-transformers-with","title":"SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention","date":"2023-12-13","arxiv_id":"2312.07987","n_code_links":2,"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":["robertcsordas/switchhead","robertcsordas/moe_attention"],"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":"/paper/universal-incomplete-view-ct-reconstruction","slug":"universal-incomplete-view-ct-reconstruction","title":"Prompted Contextual Transformer for Incomplete-View CT Reconstruction","date":"2023-12-13","arxiv_id":"2312.07846","n_code_links":1,"syntology":null},{"paper":null,"slug":"vision-transformer-based-deep-learning-for","title":"Vision Transformer-Based Deep Learning for Histologic Classification of Endometrial Cancer","date":"2023-12-13","arxiv_id":"2312.08479","n_code_links":0,"syntology":null},{"paper":"/paper/ai-control-improving-safety-despite","slug":"ai-control-improving-safety-despite","title":"AI Control: Improving Safety Despite Intentional Subversion","date":"2023-12-12","arxiv_id":"2312.06942","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"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":["rgreenblatt/control-evaluations"],"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":null,"slug":"benchmarking-deep-learning-classifiers-for","title":"Benchmarking Deep Learning Classifiers for SAR Automatic Target Recognition","date":"2023-12-12","arxiv_id":"2312.06940","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-a-transformer-represent-a-kalman-filter","title":"Can a Transformer Represent a Kalman Filter?","date":"2023-12-12","arxiv_id":"2312.06937","n_code_links":0,"syntology":null},{"paper":"/paper/context-matter-data-efficient-augmentation-of","slug":"context-matter-data-efficient-augmentation-of","title":"Context Matters: Data-Efficient Augmentation of Large Language Models for Scientific Applications","date":"2023-12-12","arxiv_id":"2312.07069","n_code_links":2,"syntology":null},{"paper":null,"slug":"exploring-large-language-models-to-facilitate","title":"Exploring Large Language Models to Facilitate Variable Autonomy for Human-Robot Teaming","date":"2023-12-12","arxiv_id":"2312.07214","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-plain-vit-reconstruction-for-multi","slug":"exploring-plain-vit-reconstruction-for-multi","title":"Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection","date":"2023-12-12","arxiv_id":"2312.07495","n_code_links":1,"syntology":null},{"paper":"/paper/harnessing-retrieval-augmented-generation-rag","slug":"harnessing-retrieval-augmented-generation-rag","title":"Harnessing Retrieval-Augmented Generation (RAG) for Uncovering Knowledge Gaps","date":"2023-12-12","arxiv_id":"2312.07796","n_code_links":1,"syntology":null},{"paper":null,"slug":"hyper-restormer-a-general-hyperspectral-image","title":"Hyper-Restormer: A General Hyperspectral Image Restoration Transformer for Remote Sensing Imaging","date":"2023-12-12","arxiv_id":"2312.07016","n_code_links":0,"syntology":null},{"paper":"/paper/image-content-generation-with-causal","slug":"image-content-generation-with-causal","title":"Image Content Generation with Causal Reasoning","date":"2023-12-12","arxiv_id":"2312.07132","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":2,"n_instrument":2,"unverified":4,"pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ieit-agi/mix-shannon"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/language-guided-transformer-for-federated","slug":"language-guided-transformer-for-federated","title":"Language-Guided Transformer for Federated Multi-Label Classification","date":"2023-12-12","arxiv_id":"2312.07165","n_code_links":1,"syntology":null},{"paper":"/paper/large-foundation-models-for-power-systems","slug":"large-foundation-models-for-power-systems","title":"Large Foundation Models for Power Systems","date":"2023-12-12","arxiv_id":"2312.07044","n_code_links":1,"syntology":null},{"paper":null,"slug":"llmeval-a-preliminary-study-on-how-to","title":"LLMEval: A Preliminary Study on How to Evaluate Large Language Models","date":"2023-12-12","arxiv_id":"2312.07398","n_code_links":0,"syntology":null},{"paper":"/paper/mixed-pseudo-labels-for-semi-supervised","slug":"mixed-pseudo-labels-for-semi-supervised","title":"Mixed Pseudo Labels for Semi-Supervised Object Detection","date":"2023-12-12","arxiv_id":"2312.07006","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-large-language-models-leak-human","slug":"multilingual-large-language-models-leak-human","title":"Multilingual large language models leak human stereotypes across language boundaries","date":"2023-12-12","arxiv_id":"2312.07141","n_code_links":1,"syntology":null},{"paper":"/paper/neural-machine-translation-of-clinical-text","slug":"neural-machine-translation-of-clinical-text","title":"Neural Machine Translation of Clinical Text: An Empirical Investigation into Multilingual Pre-Trained Language Models and Transfer-Learning","date":"2023-12-12","arxiv_id":"2312.07250","n_code_links":1,"syntology":null},{"paper":"/paper/one-step-diffusion-distillation-via-deep-1","slug":"one-step-diffusion-distillation-via-deep-1","title":"One-Step Diffusion Distillation via Deep Equilibrium Models","date":"2023-12-12","arxiv_id":"2401.08639","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["locuslab/get"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/perseus-removing-energy-bloat-from-large","slug":"perseus-removing-energy-bloat-from-large","title":"Reducing Energy Bloat in Large Model Training","date":"2023-12-12","arxiv_id":"2312.06902","n_code_links":2,"syntology":null}],"record_sha256":"cde744a6137b81477acd30b4ea4abdb9cbc33a52de64e326065207b1605902db","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}