{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/residual-connection/papers/85","list_of":"/method/residual-connection","method":"Residual Connection","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":85,"pages_in_order":285,"rows_per_page":100,"rows":[8401,8500],"of":28401,"counts":{"archive_papers_tagged":28401,"with_a_code_link":12847,"where_syntology_ran_a_sample":3897,"not_listed_spam_title":0,"listed":28401,"listed_where_code_ran":3897,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3291,"every_run_a_failure_of_syntologys_instrument":606,"listed_with_a_run_with_no_instrument_failure":3291,"listed_every_run_a_failure_of_syntologys_instrument":606,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/residual-connection","prev":"/method/residual-connection/papers/84","next":"/method/residual-connection/papers/86","papers":[{"paper":null,"slug":"unraveling-the-mystery-of-scaling-laws-part-i","title":"Unraveling the Mystery of Scaling Laws: Part I","date":"2024-03-11","arxiv_id":"2403.06563","n_code_links":0,"syntology":null},{"paper":null,"slug":"attacking-transformers-with-feature-diversity","title":"Attacking Transformers with Feature Diversity Adversarial Perturbation","date":"2024-03-10","arxiv_id":"2403.07942","n_code_links":0,"syntology":null},{"paper":"/paper/finding-visual-saliency-in-continuous-spike","slug":"finding-visual-saliency-in-continuous-spike","title":"Finding Visual Saliency in Continuous Spike Stream","date":"2024-03-10","arxiv_id":"2403.06233","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":11,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["bit-vision/svs"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/framequant-flexible-low-bit-quantization-for","slug":"framequant-flexible-low-bit-quantization-for","title":"FrameQuant: Flexible Low-Bit Quantization for Transformers","date":"2024-03-10","arxiv_id":"2403.06082","n_code_links":1,"syntology":{"ran":12,"of":18,"n_ran_checked":11,"n_instrument":1,"unverified":6,"pointer_only":18,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["vsingh-group/framequant"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/target-constrained-bidirectional-planning-for","slug":"target-constrained-bidirectional-planning-for","title":"Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialogue","date":"2024-03-10","arxiv_id":"2403.06063","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-in-vehicle-multi-task-facial","title":"Towards In-Vehicle Multi-Task Facial Attribute Recognition: Investigating Synthetic Data and Vision Foundation Models","date":"2024-03-10","arxiv_id":"2403.06088","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-audio-textual-diffusion-model-for","title":"An Audio-textual Diffusion Model For Converting Speech Signals Into Ultrasound Tongue Imaging Data","date":"2024-03-09","arxiv_id":"2403.05820","n_code_links":0,"syntology":null},{"paper":"/paper/autoeval-done-right-using-synthetic-data-for","slug":"autoeval-done-right-using-synthetic-data-for","title":"AutoEval Done Right: Using Synthetic Data for Model Evaluation","date":"2024-03-09","arxiv_id":"2403.07008","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":["pierreboyeau/autoeval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/clinicalmamba-a-generative-clinical-language","slug":"clinicalmamba-a-generative-clinical-language","title":"ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes","date":"2024-03-09","arxiv_id":"2403.05795","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, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["whaleloops/clinicalmamba"],"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":"enhancing-multi-hop-knowledge-graph-reasoning","title":"Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques","date":"2024-03-09","arxiv_id":"2403.05801","n_code_links":0,"syntology":null},{"paper":"/paper/general-surgery-vision-transformer-a-video","slug":"general-surgery-vision-transformer-a-video","title":"General surgery vision transformer: A video pre-trained foundation model for general surgery","date":"2024-03-09","arxiv_id":"2403.05949","n_code_links":1,"syntology":null},{"paper":null,"slug":"hufu-a-modality-agnositc-watermarking-system","title":"TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers","date":"2024-03-09","arxiv_id":"2403.05842","n_code_links":0,"syntology":null},{"paper":"/paper/long-term-frame-event-visual-tracking","slug":"long-term-frame-event-visual-tracking","title":"Long-term Frame-Event Visual Tracking: Benchmark Dataset and Baseline","date":"2024-03-09","arxiv_id":"2403.05839","n_code_links":4,"syntology":null},{"paper":null,"slug":"segmentation-guided-sparse-transformer-for","title":"Segmentation Guided Sparse Transformer for Under-Display Camera Image Restoration","date":"2024-03-09","arxiv_id":"2403.05906","n_code_links":0,"syntology":null},{"paper":"/paper/a-benchmark-of-domain-adapted-large-language","slug":"a-benchmark-of-domain-adapted-large-language","title":"A Dataset and Benchmark for Hospital Course Summarization with Adapted Large Language Models","date":"2024-03-08","arxiv_id":"2403.05720","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-novel-nuanced-conversation-evaluation","title":"A Novel Nuanced Conversation Evaluation Framework for Large Language Models in Mental Health","date":"2024-03-08","arxiv_id":"2403.09705","n_code_links":0,"syntology":null},{"paper":null,"slug":"actformer-scalable-collaborative-perception","title":"ActFormer: Scalable Collaborative Perception via Active Queries","date":"2024-03-08","arxiv_id":"2403.04968","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-in-depth-evaluation-of-gpt-4-in-sentence","title":"An In-depth Evaluation of GPT-4 in Sentence Simplification with Error-based Human Assessment","date":"2024-03-08","arxiv_id":"2403.04963","n_code_links":0,"syntology":null},{"paper":"/paper/are-large-language-models-aligned-with-people","slug":"are-large-language-models-aligned-with-people","title":"Are Large Language Models Aligned with People's Social Intuitions for Human-Robot Interactions?","date":"2024-03-08","arxiv_id":"2403.05701","n_code_links":1,"syntology":null},{"paper":"/paper/bias-augmented-consistency-training-reduces","slug":"bias-augmented-consistency-training-reduces","title":"Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought","date":"2024-03-08","arxiv_id":"2403.05518","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["raybears/cot-transparency"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-t-remember-details-in-long-documents-you","slug":"can-t-remember-details-in-long-documents-you","title":"Can't Remember Details in Long Documents? You Need Some R&R","date":"2024-03-08","arxiv_id":"2403.05004","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":9,"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) · 0 unverified","official":{"repos":["casetext/r-and-r"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/commitbench-a-benchmark-for-commit-message","slug":"commitbench-a-benchmark-for-commit-message","title":"CommitBench: A Benchmark for Commit Message Generation","date":"2024-03-08","arxiv_id":"2403.05188","n_code_links":1,"syntology":null},{"paper":"/paper/considering-nonstationary-within-multivariate","slug":"considering-nonstationary-within-multivariate","title":"Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting","date":"2024-03-08","arxiv_id":"2403.05406","n_code_links":1,"syntology":{"ran":12,"of":17,"n_ran_checked":12,"n_instrument":0,"unverified":5,"pointer_only":17,"phrase":"12 ran (of which 10 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) · 5 unverified","official":{"repos":["flare200020/HTV_Trans"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":10,"n_ran_no_instrument_failure":12,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cost-performance-optimization-for-processing","title":"Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs","date":"2024-03-08","arxiv_id":"2403.05434","n_code_links":0,"syntology":null},{"paper":null,"slug":"decomposing-vision-based-llm-predictions-for","title":"How Well Do Multi-modal LLMs Interpret CT Scans? An Auto-Evaluation Framework for Analyses","date":"2024-03-08","arxiv_id":"2403.05680","n_code_links":0,"syntology":null},{"paper":null,"slug":"denoising-autoregressive-representation","title":"Denoising Autoregressive Representation Learning","date":"2024-03-08","arxiv_id":"2403.05196","n_code_links":0,"syntology":null},{"paper":"/paper/dualbev-cnn-is-all-you-need-in-view","slug":"dualbev-cnn-is-all-you-need-in-view","title":"DualBEV: Unifying Dual View Transformation with Probabilistic Correspondences","date":"2024-03-08","arxiv_id":"2403.05402","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":["peidongli/dualbev"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-automatic-modulation-recognition-1","title":"Enhancing Automatic Modulation Recognition for IoT Applications Using Transformers","date":"2024-03-08","arxiv_id":"2403.15417","n_code_links":0,"syntology":null},{"paper":"/paper/erbench-an-entity-relationship-based","slug":"erbench-an-entity-relationship-based","title":"ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models","date":"2024-03-08","arxiv_id":"2403.05266","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dilab-kaist/erbench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/gemini-1-5-unlocking-multimodal-understanding","slug":"gemini-1-5-unlocking-multimodal-understanding","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","date":"2024-03-08","arxiv_id":"2403.05530","n_code_links":1,"syntology":null},{"paper":null,"slug":"inverse-design-of-photonic-crystal-surface","title":"Inverse Design of Photonic Crystal Surface Emitting Lasers is a Sequence Modeling Problem","date":"2024-03-08","arxiv_id":"2403.05149","n_code_links":0,"syntology":null},{"paper":"/paper/jointmotion-joint-self-supervision-for-joint","slug":"jointmotion-joint-self-supervision-for-joint","title":"JointMotion: Joint Self-Supervision for Joint Motion Prediction","date":"2024-03-08","arxiv_id":"2403.05489","n_code_links":1,"syntology":null},{"paper":"/paper/lightm-unet-mamba-assists-in-lightweight-unet","slug":"lightm-unet-mamba-assists-in-lightweight-unet","title":"LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentation","date":"2024-03-08","arxiv_id":"2403.05246","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["mrblankness/lightm-unet"],"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/llm4decompile-decompiling-binary-code-with","slug":"llm4decompile-decompiling-binary-code-with","title":"LLM4Decompile: Decompiling Binary Code with Large Language Models","date":"2024-03-08","arxiv_id":"2403.05286","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"pointer_only":1,"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) · 4 unverified","official":{"repos":["albertan017/LLM4Decompile"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/mammil-multiple-instance-learning-for-whole","slug":"mammil-multiple-instance-learning-for-whole","title":"MamMIL: Multiple Instance Learning for Whole Slide Images with State Space Models","date":"2024-03-08","arxiv_id":"2403.05160","n_code_links":1,"syntology":null},{"paper":null,"slug":"med3dinsight-enhancing-3d-medical-image","title":"Med3DInsight: Enhancing 3D Medical Image Understanding with 2D Multi-Modal Large Language Models","date":"2024-03-08","arxiv_id":"2403.05141","n_code_links":0,"syntology":null},{"paper":null,"slug":"node-centrality-approximation-for-large","title":"Node Centrality Approximation For Large Networks Based On Inductive Graph Neural Networks","date":"2024-03-08","arxiv_id":"2403.04977","n_code_links":0,"syntology":null},{"paper":null,"slug":"piperag-fast-retrieval-augmented-generation","title":"PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design","date":"2024-03-08","arxiv_id":"2403.05676","n_code_links":0,"syntology":null},{"paper":"/paper/rat-retrieval-augmented-thoughts-elicit","slug":"rat-retrieval-augmented-thoughts-elicit","title":"RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation","date":"2024-03-08","arxiv_id":"2403.05313","n_code_links":1,"syntology":null},{"paper":null,"slug":"rule-driven-news-captioning","title":"Rule-driven News Captioning","date":"2024-03-08","arxiv_id":"2403.05101","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-multiple-instance-learning","title":"Self-Supervised Multiple Instance Learning for Acute Myeloid Leukemia Classification","date":"2024-03-08","arxiv_id":"2403.05379","n_code_links":0,"syntology":null},{"paper":null,"slug":"sf-mmcn-a-low-power-re-configurable-server","title":"SF-MMCN: Low-Power Sever Flow Multi-Mode Diffusion Model Accelerator","date":"2024-03-08","arxiv_id":"2403.10542","n_code_links":0,"syntology":null},{"paper":"/paper/sirst-5k-exploring-massive-negatives","slug":"sirst-5k-exploring-massive-negatives","title":"SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection","date":"2024-03-08","arxiv_id":"2403.05416","n_code_links":1,"syntology":null},{"paper":"/paper/spatial-aware-transformer-gru-framework-for","slug":"spatial-aware-transformer-gru-framework-for","title":"Spatial-aware Transformer-GRU Framework for Enhanced Glaucoma Diagnosis from 3D OCT Imaging","date":"2024-03-08","arxiv_id":"2403.05702","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-impact-of-quantization-on-the-robustness","title":"The Impact of Quantization on the Robustness of Transformer-based Text Classifiers","date":"2024-03-08","arxiv_id":"2403.05365","n_code_links":0,"syntology":null},{"paper":null,"slug":"will-gpt-4-run-doom","title":"Will GPT-4 Run DOOM?","date":"2024-03-08","arxiv_id":"2403.05468","n_code_links":0,"syntology":null},{"paper":null,"slug":"acc-vit-atrous-convolution-s-comeback-in","title":"ACC-ViT : Atrous Convolution's Comeback in Vision Transformers","date":"2024-03-07","arxiv_id":"2403.04200","n_code_links":0,"syntology":null},{"paper":"/paper/aligning-gptrec-with-beyond-accuracy-goals","slug":"aligning-gptrec-with-beyond-accuracy-goals","title":"Aligning GPTRec with Beyond-Accuracy Goals with Reinforcement Learning","date":"2024-03-07","arxiv_id":"2403.04875","n_code_links":1,"syntology":null},{"paper":"/paper/ao-detr-anti-overlapping-detr-for-x-ray","slug":"ao-detr-anti-overlapping-detr-for-x-ray","title":"AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection","date":"2024-03-07","arxiv_id":"2403.04309","n_code_links":1,"syntology":null},{"paper":null,"slug":"attempt-towards-stress-transfer-in-speech-to","title":"Attempt Towards Stress Transfer in Speech-to-Speech Machine Translation","date":"2024-03-07","arxiv_id":"2403.04178","n_code_links":0,"syntology":null},{"paper":"/paper/auformer-vision-transformers-are-parameter","slug":"auformer-vision-transformers-are-parameter","title":"AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors","date":"2024-03-07","arxiv_id":"2403.04697","n_code_links":1,"syntology":null},{"paper":"/paper/automating-the-information-extraction-from","slug":"automating-the-information-extraction-from","title":"Automating the Information Extraction from Semi-Structured Interview Transcripts","date":"2024-03-07","arxiv_id":"2403.04819","n_code_links":1,"syntology":null},{"paper":"/paper/disentangled-diffusion-based-3d-human-pose","slug":"disentangled-diffusion-based-3d-human-pose","title":"Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser","date":"2024-03-07","arxiv_id":"2403.04444","n_code_links":1,"syntology":null},{"paper":"/paper/federated-recommendation-via-hybrid-retrieval","slug":"federated-recommendation-via-hybrid-retrieval","title":"Federated Recommendation via Hybrid Retrieval Augmented Generation","date":"2024-03-07","arxiv_id":"2403.04256","n_code_links":1,"syntology":null},{"paper":null,"slug":"feedback-generation-for-programming-exercises","title":"Feedback-Generation for Programming Exercises With GPT-4","date":"2024-03-07","arxiv_id":"2403.04449","n_code_links":0,"syntology":null},{"paper":"/paper/halueval-wild-evaluating-hallucinations-of","slug":"halueval-wild-evaluating-hallucinations-of","title":"HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild","date":"2024-03-07","arxiv_id":"2403.04307","n_code_links":1,"syntology":null},{"paper":"/paper/llms-in-the-imaginarium-tool-learning-through","slug":"llms-in-the-imaginarium-tool-learning-through","title":"LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error","date":"2024-03-07","arxiv_id":"2403.04746","n_code_links":1,"syntology":{"ran":6,"of":13,"n_ran_checked":6,"n_instrument":0,"unverified":7,"pointer_only":1,"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) · 7 unverified","official":{"repos":["microsoft/simulated-trial-and-error"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/pixart-s-weak-to-strong-training-of-diffusion","slug":"pixart-s-weak-to-strong-training-of-diffusion","title":"PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","date":"2024-03-07","arxiv_id":"2403.04692","n_code_links":2,"syntology":{"ran":6,"of":9,"n_ran_checked":3,"n_instrument":3,"unverified":3,"pointer_only":6,"phrase":"6 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; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["PixArt-alpha/PixArt-sigma"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"ratsf-empowering-customer-service-volume","title":"RATSF: Empowering Customer Service Volume Management through Retrieval-Augmented Time-Series Forecasting","date":"2024-03-07","arxiv_id":"2403.04180","n_code_links":0,"syntology":null},{"paper":"/paper/solving-inverse-problems-with-model-mismatch","slug":"solving-inverse-problems-with-model-mismatch","title":"Solving Inverse Problems with Model Mismatch using Untrained Neural Networks within Model-based Architectures","date":"2024-03-07","arxiv_id":"2403.04847","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 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) · 1 unverified","official":{"repos":["invprobs/a-adaptive-model-based-methods"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/speech-emotion-recognition-via-cnn","slug":"speech-emotion-recognition-via-cnn","title":"Speech Emotion Recognition Via CNN-Transformer and Multidimensional Attention Mechanism","date":"2024-03-07","arxiv_id":"2403.04743","n_code_links":1,"syntology":null},{"paper":null,"slug":"telecom-language-models-must-they-be-large","title":"Telecom Language Models: Must They Be Large?","date":"2024-03-07","arxiv_id":"2403.04666","n_code_links":0,"syntology":null},{"paper":"/paper/yi-open-foundation-models-by-01-ai","slug":"yi-open-foundation-models-by-01-ai","title":"Yi: Open Foundation Models by 01.AI","date":"2024-03-07","arxiv_id":"2403.04652","n_code_links":1,"syntology":{"ran":2,"of":8,"n_ran_checked":0,"n_instrument":2,"unverified":6,"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) · 6 unverified","official":{"repos":["01-ai/yi"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"assessing-the-aesthetic-evaluation","title":"Assessing the Aesthetic Evaluation Capabilities of GPT-4 with Vision: Insights from Group and Individual Assessments","date":"2024-03-06","arxiv_id":"2403.03594","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-hallucination-in-large-language","slug":"benchmarking-hallucination-in-large-language","title":"Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem","date":"2024-03-06","arxiv_id":"2403.03558","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-large-language-models-do-analytical","title":"Can Large Language Models do Analytical Reasoning?","date":"2024-03-06","arxiv_id":"2403.04031","n_code_links":0,"syntology":null},{"paper":null,"slug":"design-of-an-open-source-architecture-for","title":"Design of an Open-Source Architecture for Neural Machine Translation","date":"2024-03-06","arxiv_id":"2403.03582","n_code_links":0,"syntology":null},{"paper":null,"slug":"designing-informative-metrics-for-few-shot","title":"Designing Informative Metrics for Few-Shot Example Selection","date":"2024-03-06","arxiv_id":"2403.03861","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-asd-detection-accuracy-a-combined","slug":"enhancing-asd-detection-accuracy-a-combined","title":"Enhancing ASD detection accuracy: a combined approach of machine learning and deep learning models with natural language processing","date":"2024-03-06","arxiv_id":"2403.03581","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-price-prediction-in-cryptocurrency","title":"Enhancing Price Prediction in Cryptocurrency Using Transformer Neural Network and Technical Indicators","date":"2024-03-06","arxiv_id":"2403.03606","n_code_links":0,"syntology":null},{"paper":"/paper/faaf-facts-as-a-function-for-the-evaluation","slug":"faaf-facts-as-a-function-for-the-evaluation","title":"FaaF: Facts as a Function for the evaluation of generated text","date":"2024-03-06","arxiv_id":"2403.03888","n_code_links":1,"syntology":null},{"paper":"/paper/galore-memory-efficient-llm-training-by","slug":"galore-memory-efficient-llm-training-by","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","date":"2024-03-06","arxiv_id":"2403.03507","n_code_links":3,"syntology":null},{"paper":null,"slug":"general2specialized-llms-translation-for-e","title":"General2Specialized LLMs Translation for E-commerce","date":"2024-03-06","arxiv_id":"2403.03689","n_code_links":0,"syntology":null},{"paper":null,"slug":"guiding-enumerative-program-synthesis-with","title":"Guiding Enumerative Program Synthesis with Large Language Models","date":"2024-03-06","arxiv_id":"2403.03997","n_code_links":0,"syntology":null},{"paper":null,"slug":"inverse-free-fast-natural-gradient-descent","title":"Inverse-Free Fast Natural Gradient Descent Method for Deep Learning","date":"2024-03-06","arxiv_id":"2403.03473","n_code_links":0,"syntology":null},{"paper":null,"slug":"japanese-english-sentence-translation","title":"Japanese-English Sentence Translation Exercises Dataset for Automatic Grading","date":"2024-03-06","arxiv_id":"2403.03396","n_code_links":0,"syntology":null},{"paper":"/paper/joint-multi-task-learning-improves-weakly","slug":"joint-multi-task-learning-improves-weakly","title":"Joint multi-task learning improves weakly-supervised biomarker prediction in computational pathology","date":"2024-03-06","arxiv_id":"2403.03891","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-modal-deep-learning","title":"Multi-modal Deep Learning","date":"2024-03-06","arxiv_id":"2403.03385","n_code_links":0,"syntology":null},{"paper":"/paper/pptc-r-benchmark-towards-evaluating-the","slug":"pptc-r-benchmark-towards-evaluating-the","title":"PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion","date":"2024-03-06","arxiv_id":"2403.03788","n_code_links":1,"syntology":null},{"paper":"/paper/rapidly-developing-high-quality-instruction","slug":"rapidly-developing-high-quality-instruction","title":"Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese","date":"2024-03-06","arxiv_id":"2403.03690","n_code_links":2,"syntology":null},{"paper":null,"slug":"scene-depth-estimation-from-traditional","title":"Scene Depth Estimation from Traditional Oriental Landscape Paintings","date":"2024-03-06","arxiv_id":"2403.03408","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-insights-a-case-study-on-utilizing-chatgpt","title":"AI Insights: A Case Study on Utilizing ChatGPT Intelligence for Research Paper Analysis","date":"2024-03-05","arxiv_id":"2403.03293","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-llm-as-a-judge-for-llm","slug":"an-empirical-study-of-llm-as-a-judge-for-llm","title":"An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4","date":"2024-03-05","arxiv_id":"2403.02839","n_code_links":1,"syntology":{"ran":15,"of":18,"n_ran_checked":15,"n_instrument":0,"unverified":3,"pointer_only":18,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["huihuichyan/unlimitedjudge"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/arnn-attentive-recurrent-neural-network-for","slug":"arnn-attentive-recurrent-neural-network-for","title":"ARNN: Attentive Recurrent Neural Network for Multi-channel EEG Signals to Identify Epileptic Seizures","date":"2024-03-05","arxiv_id":"2403.03276","n_code_links":1,"syntology":null},{"paper":null,"slug":"attentionstitch-how-attention-solves-the","title":"AttentionStitch: How Attention Solves the Speech Editing Problem","date":"2024-03-05","arxiv_id":"2403.04804","n_code_links":0,"syntology":null},{"paper":"/paper/behavior-generation-with-latent-actions","slug":"behavior-generation-with-latent-actions","title":"Behavior Generation with Latent Actions","date":"2024-03-05","arxiv_id":"2403.03181","n_code_links":2,"syntology":{"ran":8,"of":14,"n_ran_checked":7,"n_instrument":1,"unverified":6,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["jayLEE0301/vq_bet_official"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"clevr-poc-reasoning-intensive-visual-question","title":"CLEVR-POC: Reasoning-Intensive Visual Question Answering in Partially Observable Environments","date":"2024-03-05","arxiv_id":"2403.03203","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-domain-image-conversion-by-cycledm","title":"Cross-Domain Image Conversion by CycleDM","date":"2024-03-05","arxiv_id":"2403.02919","n_code_links":0,"syntology":null},{"paper":null,"slug":"drug-resistance-revealed-by-in-silico-deep","title":"Drug Resistance Predictions Based on a Directed Flag Transformer","date":"2024-03-05","arxiv_id":"2403.02603","n_code_links":0,"syntology":null},{"paper":null,"slug":"emerging-synergies-between-large-language","title":"Emerging Synergies Between Large Language Models and Machine Learning in Ecommerce Recommendations","date":"2024-03-05","arxiv_id":"2403.02760","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-weakly-supervised-3d-medical-image","slug":"enhancing-weakly-supervised-3d-medical-image","title":"Enhancing Weakly Supervised 3D Medical Image Segmentation through Probabilistic-aware Learning","date":"2024-03-05","arxiv_id":"2403.02566","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-and-optimizing-educational-content","slug":"evaluating-and-optimizing-educational-content","title":"Evaluating and Optimizing Educational Content with Large Language Model Judgments","date":"2024-03-05","arxiv_id":"2403.02795","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["StanfordAI4HI/ed-expert-simulator"],"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/evolution-transformer-in-context-evolutionary","slug":"evolution-transformer-in-context-evolutionary","title":"Evolution Transformer: In-Context Evolutionary Optimization","date":"2024-03-05","arxiv_id":"2403.02985","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-naive-approaches-to-tell-apart-llms","slug":"exploring-naive-approaches-to-tell-apart-llms","title":"Exploring Naive Approaches to Tell Apart LLMs Productions from Human-written Text","date":"2024-03-05","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"far-flexible-accurate-and-robust-6dof","title":"FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation","date":"2024-03-05","arxiv_id":"2403.03221","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-well-can-transformers-emulate-in-context","title":"How Well Can Transformers Emulate In-context Newton's Method?","date":"2024-03-05","arxiv_id":"2403.03183","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-event-definition-following-for-zero","title":"Improving Event Definition Following For Zero-Shot Event Detection","date":"2024-03-05","arxiv_id":"2403.02586","n_code_links":0,"syntology":null},{"paper":"/paper/injecagent-benchmarking-indirect-prompt","slug":"injecagent-benchmarking-indirect-prompt","title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents","date":"2024-03-05","arxiv_id":"2403.02691","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["uiuc-kang-lab/injecagent"],"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":"injecttst-a-transformer-method-of-injecting","title":"InjectTST: A Transformer Method of Injecting Global Information into Independent Channels for Long Time Series Forecasting","date":"2024-03-05","arxiv_id":"2403.02814","n_code_links":0,"syntology":null},{"paper":"/paper/jmi-at-semeval-2024-task-3-two-step-approach","slug":"jmi-at-semeval-2024-task-3-two-step-approach","title":"JMI at SemEval 2024 Task 3: Two-step approach for multimodal ECAC using in-context learning with GPT and instruction-tuned Llama models","date":"2024-03-05","arxiv_id":"2403.04798","n_code_links":1,"syntology":{"ran":5,"of":12,"n_ran_checked":5,"n_instrument":0,"unverified":7,"pointer_only":12,"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) · 7 unverified","official":{"repos":["cmooncs/semeval-2024_multimodal_ecpe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}}],"record_sha256":"20ac2584ec4f83236b406d64bac5b9def2a9e9deb06fcb01182a1d4d98b7eb9b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}