{"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/79","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":79,"pages_in_order":375,"rows_per_page":100,"rows":[7801,7900],"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/78","next":"/method/softmax/papers/80","papers":[{"paper":null,"slug":"understanding-student-sentiment-on-mental","title":"Understanding Student Sentiment on Mental Health Support in Colleges Using Large Language Models","date":"2024-11-18","arxiv_id":"2412.04326","n_code_links":0,"syntology":null},{"paper":"/paper/unveiling-the-inflexibility-of-adaptive","slug":"unveiling-the-inflexibility-of-adaptive","title":"Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting","date":"2024-11-18","arxiv_id":"2411.11448","n_code_links":1,"syntology":null},{"paper":"/paper/versatune-fine-tuning-multi-ability-llms","slug":"versatune-fine-tuning-multi-ability-llms","title":"VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs","date":"2024-11-18","arxiv_id":"2411.11266","n_code_links":1,"syntology":null},{"paper":null,"slug":"video-to-task-learning-via-motion-guided","title":"Video-to-Task Learning via Motion-Guided Attention for Few-Shot Action Recognition","date":"2024-11-18","arxiv_id":"2411.11335","n_code_links":0,"syntology":null},{"paper":null,"slug":"different-horses-for-different-courses","title":"Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML","date":"2024-11-17","arxiv_id":"2411.11101","n_code_links":0,"syntology":null},{"paper":null,"slug":"direct-and-explicit-3d-generation-from-a","title":"Direct and Explicit 3D Generation from a Single Image","date":"2024-11-17","arxiv_id":"2411.10947","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamics-of-resource-allocation-in-o-rans-an","title":"Dynamics of Resource Allocation in O-RANs: An In-depth Exploration of On-Policy and Off-Policy Deep Reinforcement Learning for Real-Time Applications","date":"2024-11-17","arxiv_id":"2412.01839","n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-vlm-localizability-and-semantics","slug":"exploiting-vlm-localizability-and-semantics","title":"Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection","date":"2024-11-17","arxiv_id":"2411.10922","n_code_links":1,"syntology":null},{"paper":null,"slug":"freqformer-frequency-domain-transformer-for-3","title":"Freqformer: Frequency-Domain Transformer for 3-D Visualization and Quantification of Human Retinal Circulation","date":"2024-11-17","arxiv_id":"2411.11189","n_code_links":0,"syntology":null},{"paper":null,"slug":"ive-enhanced-probabilistic-forecasting-of","title":"IVE: Enhanced Probabilistic Forecasting of Intraday Volume Ratio with Transformers","date":"2024-11-17","arxiv_id":"2411.10956","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-enhanced-transformer-for","title":"Knowledge-enhanced Transformer for Multivariate Long Sequence Time-series Forecasting","date":"2024-11-17","arxiv_id":"2411.11046","n_code_links":0,"syntology":null},{"paper":"/paper/sageattention2-technical-report-accurate-4","slug":"sageattention2-technical-report-accurate-4","title":"SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization","date":"2024-11-17","arxiv_id":"2411.10958","n_code_links":2,"syntology":{"ran":0,"of":6,"n_ran_checked":0,"n_instrument":0,"unverified":6,"pointer_only":3,"phrase":"0 ran · 6 unverified","official":{"repos":["thu-ml/SageAttention"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":[]}}},{"paper":null,"slug":"skeleton-guided-spatial-temporal-feature","title":"Skeleton-Guided Spatial-Temporal Feature Learning for Video-Based Visible-Infrared Person Re-Identification","date":"2024-11-17","arxiv_id":"2411.11069","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-adaptive-hybrid-focal-entropy-loss","title":"A Novel Adaptive Hybrid Focal-Entropy Loss for Enhancing Diabetic Retinopathy Detection Using Convolutional Neural Networks","date":"2024-11-16","arxiv_id":"2411.10843","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-approach-to-eliminating","title":"A Novel Approach to Eliminating Hallucinations in Large Language Model-Assisted Causal Discovery","date":"2024-11-16","arxiv_id":"2411.12759","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-wearable-gait-monitoring-system-for-17-gait","title":"A Wearable Gait Monitoring System for 17 Gait Parameters Based on Computer Vision","date":"2024-11-16","arxiv_id":"2411.10739","n_code_links":0,"syntology":null},{"paper":null,"slug":"allrestorer-all-in-one-transformer-for-image","title":"AllRestorer: All-in-One Transformer for Image Restoration under Composite Degradations","date":"2024-11-16","arxiv_id":"2411.10708","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-based-u-net-method-for-autonomous","title":"Attention-based U-Net Method for Autonomous Lane Detection","date":"2024-11-16","arxiv_id":"2411.10902","n_code_links":0,"syntology":null},{"paper":"/paper/bag-of-design-choices-for-inference-of-high","slug":"bag-of-design-choices-for-inference-of-high","title":"Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer","date":"2024-11-16","arxiv_id":"2411.10781","n_code_links":1,"syntology":null},{"paper":null,"slug":"constructing-accurate-machine-learned","title":"Constructing accurate machine-learned potentials and performing highly efficient atomistic simulations to predict structural and thermal properties","date":"2024-11-16","arxiv_id":"2411.10911","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-bi-rads-network-for-improved-cancer","title":"Deep BI-RADS Network for Improved Cancer Detection from Mammograms","date":"2024-11-16","arxiv_id":"2411.10894","n_code_links":0,"syntology":null},{"paper":"/paper/deep-feature-response-discriminative","slug":"deep-feature-response-discriminative","title":"Deep Feature Response Discriminative Calibration","date":"2024-11-16","arxiv_id":"2411.13582","n_code_links":1,"syntology":null},{"paper":"/paper/explainable-dnn-based-beamformer-with","slug":"explainable-dnn-based-beamformer-with","title":"Explainable DNN-based Beamformer with Postfilter","date":"2024-11-16","arxiv_id":"2411.10854","n_code_links":1,"syntology":null},{"paper":null,"slug":"fias-feature-imbalance-aware-medical-image","title":"FIAS: Feature Imbalance-Aware Medical Image Segmentation with Dynamic Fusion and Mixing Attention","date":"2024-11-16","arxiv_id":"2411.10881","n_code_links":0,"syntology":null},{"paper":null,"slug":"infrared-assisted-single-stage-framework-for","title":"Infrared-Assisted Single-Stage Framework for Joint Restoration and Fusion of Visible and Infrared Images under Hazy Conditions","date":"2024-11-16","arxiv_id":"2411.12586","n_code_links":0,"syntology":null},{"paper":null,"slug":"intentgpt-few-shot-intent-discovery-with","title":"IntentGPT: Few-shot Intent Discovery with Large Language Models","date":"2024-11-16","arxiv_id":"2411.10670","n_code_links":0,"syntology":null},{"paper":"/paper/metala-unified-optimal-linear-approximation","slug":"metala-unified-optimal-linear-approximation","title":"MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map","date":"2024-11-16","arxiv_id":"2411.10741","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":{"repos":["BICLab/MetaLA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/mpoxvlm-a-vision-language-model-for","slug":"mpoxvlm-a-vision-language-model-for","title":"MpoxVLM: A Vision-Language Model for Diagnosing Skin Lesions from Mpox Virus Infection","date":"2024-11-16","arxiv_id":"2411.10888","n_code_links":1,"syntology":null},{"paper":null,"slug":"one-layer-transformer-provably-learns-one","title":"One-Layer Transformer Provably Learns One-Nearest Neighbor In Context","date":"2024-11-16","arxiv_id":"2411.10830","n_code_links":0,"syntology":null},{"paper":null,"slug":"spdfusion-an-infrared-and-visible-image","title":"SPDFusion: An Infrared and Visible Image Fusion Network Based on a Non-Euclidean Representation of Riemannian Manifolds","date":"2024-11-16","arxiv_id":"2411.10679","n_code_links":0,"syntology":null},{"paper":"/paper/a-hard-label-cryptanalytic-extraction-of-non","slug":"a-hard-label-cryptanalytic-extraction-of-non","title":"A Hard-Label Cryptanalytic Extraction of Non-Fully Connected Deep Neural Networks using Side-Channel Attacks","date":"2024-11-15","arxiv_id":"2411.10174","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-low-resolution-image-is-worth-1x1-words","title":"A Low-Resolution Image is Worth 1x1 Words: Enabling Fine Image Super-Resolution with Transformers and TaylorShift","date":"2024-11-15","arxiv_id":"2411.10231","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-scale-spatial-temporal-network-for","title":"A Multi-Scale Spatial-Temporal Network for Wireless Video Transmission","date":"2024-11-15","arxiv_id":"2411.09936","n_code_links":0,"syntology":null},{"paper":null,"slug":"boundary-attention-constrained-zero-shot","title":"Boundary Attention Constrained Zero-Shot Layout-To-Image Generation","date":"2024-11-15","arxiv_id":"2411.10495","n_code_links":0,"syntology":null},{"paper":null,"slug":"building-6g-radio-foundation-models-with","title":"Building 6G Radio Foundation Models with Transformer Architectures","date":"2024-11-15","arxiv_id":"2411.09996","n_code_links":0,"syntology":null},{"paper":null,"slug":"cmath-cross-modality-augmented-transformer","title":"CMATH: Cross-Modality Augmented Transformer with Hierarchical Variational Distillation for Multimodal Emotion Recognition in Conversation","date":"2024-11-15","arxiv_id":"2411.10060","n_code_links":0,"syntology":null},{"paper":null,"slug":"coloredit-training-free-image-guided-color","title":"ColorEdit: Training-free Image-Guided Color editing with diffusion model","date":"2024-11-15","arxiv_id":"2411.10232","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-machine-learning-7","title":"Comparative Analysis of Machine Learning Approaches for Bone Age Assessment: A Comprehensive Study on Three Distinct Models","date":"2024-11-15","arxiv_id":"2411.10345","n_code_links":0,"syntology":null},{"paper":null,"slug":"cosam-self-correcting-sam-for-domain","title":"CoSAM: Self-Correcting SAM for Domain Generalization in 2D Medical Image Segmentation","date":"2024-11-15","arxiv_id":"2411.10136","n_code_links":0,"syntology":null},{"paper":null,"slug":"dayu-data-driven-model-for-geostationary","title":"DaYu: Data-Driven Model for Geostationary Satellite Observed Cloud Images Forecasting","date":"2024-11-15","arxiv_id":"2411.10144","n_code_links":0,"syntology":null},{"paper":null,"slug":"debias-clr-a-contrastive-learning-based","title":"Debias-CLR: A Contrastive Learning Based Debiasing Method for Algorithmic Fairness in Healthcare Applications","date":"2024-11-15","arxiv_id":"2411.10544","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-the-adversarially-learned-injection","title":"Detecting the Adversarially-Learned Injection Attacks via Knowledge Graphs","date":"2024-11-15","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dimodif-discourse-modality-information","title":"DiMoDif: Discourse Modality-information Differentiation for Audio-visual Deepfake Detection and Localization","date":"2024-11-15","arxiv_id":"2411.10193","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-prompt-formatting-have-any-impact-on-llm","title":"Does Prompt Formatting Have Any Impact on LLM Performance?","date":"2024-11-15","arxiv_id":"2411.10541","n_code_links":0,"syntology":null},{"paper":"/paper/echomimicv2-towards-striking-simplified-and","slug":"echomimicv2-towards-striking-simplified-and","title":"EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation","date":"2024-11-15","arxiv_id":"2411.10061","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["antgroup/echomimic_v2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evidential-federated-learning-for-skin-lesion","title":"Evidential Federated Learning for Skin Lesion Image Classification","date":"2024-11-15","arxiv_id":"2411.10071","n_code_links":0,"syntology":null},{"paper":"/paper/fitdit-advancing-the-authentic-garment","slug":"fitdit-advancing-the-authentic-garment","title":"FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on","date":"2024-11-15","arxiv_id":"2411.10499","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":0,"n_instrument":5,"unverified":1,"pointer_only":6,"phrase":"5 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; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["BoyuanJiang/FitDiT"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/hysteresis-activation-function-for-efficient","slug":"hysteresis-activation-function-for-efficient","title":"Hysteresis Activation Function for Efficient Inference","date":"2024-11-15","arxiv_id":"2411.10573","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":["idankdev/helu"],"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/information-extraction-from-clinical-notes","slug":"information-extraction-from-clinical-notes","title":"Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models?","date":"2024-11-15","arxiv_id":"2411.10020","n_code_links":1,"syntology":null},{"paper":null,"slug":"kat-to-kans-a-review-of-kolmogorov-arnold","title":"KAT to KANs: A Review of Kolmogorov-Arnold Networks and the Neural Leap Forward","date":"2024-11-15","arxiv_id":"2411.10622","n_code_links":0,"syntology":null},{"paper":null,"slug":"lateral-movement-detection-via-time-aware","title":"Lateral Movement Detection via Time-aware Subgraph Classification on Authentication Logs","date":"2024-11-15","arxiv_id":"2411.10279","n_code_links":0,"syntology":null},{"paper":null,"slug":"lora-litee-a-computationally-efficient","title":"LoRA-LiteE: A Computationally Efficient Framework for Chatbot Preference-Tuning","date":"2024-11-15","arxiv_id":"2411.09947","n_code_links":0,"syntology":null},{"paper":"/paper/mars-unleashing-the-power-of-variance","slug":"mars-unleashing-the-power-of-variance","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","date":"2024-11-15","arxiv_id":"2411.10438","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["AGI-Arena/MARS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/memorization-in-attention-only-transformers","slug":"memorization-in-attention-only-transformers","title":"Memorization in Attention-only Transformers","date":"2024-11-15","arxiv_id":"2411.10115","n_code_links":1,"syntology":null},{"paper":null,"slug":"mitigating-parameter-degeneracy-using-joint","title":"Mitigating Parameter Degeneracy using Joint Conditional Diffusion Model for WECC Composite Load Model in Power Systems","date":"2024-11-15","arxiv_id":"2411.10431","n_code_links":0,"syntology":null},{"paper":null,"slug":"morpho-aware-global-attention-for-image","title":"Morpho-Aware Global Attention for Image Matting","date":"2024-11-15","arxiv_id":"2411.10251","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-goals-of-linguistic-theory-revisiting","title":"\"On the goals of linguistic theory\": Revisiting Chomskyan theories in the era of AI","date":"2024-11-15","arxiv_id":"2411.10533","n_code_links":0,"syntology":null},{"paper":null,"slug":"probabilistic-prior-driven-attention","title":"Probabilistic Prior Driven Attention Mechanism Based on Diffusion Model for Imaging Through Atmospheric Turbulence","date":"2024-11-15","arxiv_id":"2411.10321","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompting-and-fine-tuning-large-language","title":"Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation","date":"2024-11-15","arxiv_id":"2411.10129","n_code_links":0,"syntology":null},{"paper":null,"slug":"repurposing-stable-diffusion-attention-for","title":"Repurposing Stable Diffusion Attention for Training-Free Unsupervised Interactive Segmentation","date":"2024-11-15","arxiv_id":"2411.10411","n_code_links":0,"syntology":null},{"paper":"/paper/retr-multi-view-radar-detection-transformer","slug":"retr-multi-view-radar-detection-transformer","title":"RETR: Multi-View Radar Detection Transformer for Indoor Perception","date":"2024-11-15","arxiv_id":"2411.10293","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["merlresearch/radar-detection-transformer"],"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":null,"slug":"scaling-law-for-post-training-after-model","title":"P$^2$ Law: Scaling Law for Post-Training After Model Pruning","date":"2024-11-15","arxiv_id":"2411.10272","n_code_links":0,"syntology":null},{"paper":null,"slug":"seeing-clearly-by-layer-two-enhancing","title":"Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs","date":"2024-11-15","arxiv_id":"2411.09968","n_code_links":0,"syntology":null},{"paper":"/paper/smoothcache-a-universal-inference","slug":"smoothcache-a-universal-inference","title":"SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers","date":"2024-11-15","arxiv_id":"2411.10510","n_code_links":1,"syntology":null},{"paper":null,"slug":"softlms-efficient-adaptive-low-rank","title":"SoftLMs: Efficient Adaptive Low-Rank Approximation of Language Models using Soft-Thresholding Mechanism","date":"2024-11-15","arxiv_id":"2411.10543","n_code_links":0,"syntology":null},{"paper":null,"slug":"take-package-as-language-anomaly-detection","title":"Take Package as Language: Anomaly Detection Using Transformer","date":"2024-11-15","arxiv_id":"2412.04473","n_code_links":0,"syntology":null},{"paper":null,"slug":"ultra-unveiling-latent-token-interpretability","title":"ULTra: Unveiling Latent Token Interpretability in Transformer Based Understanding","date":"2024-11-15","arxiv_id":"2411.12589","n_code_links":0,"syntology":null},{"paper":"/paper/vision-eagle-attention-a-new-lens-for","slug":"vision-eagle-attention-a-new-lens-for","title":"Vision Eagle Attention: a new lens for advancing image classification","date":"2024-11-15","arxiv_id":"2411.10564","n_code_links":1,"syntology":null},{"paper":null,"slug":"visual-question-answering-based-evaluation","title":"Visual question answering based evaluation metrics for text-to-image generation","date":"2024-11-15","arxiv_id":"2411.10183","n_code_links":0,"syntology":null},{"paper":"/paper/wavchat-a-survey-of-spoken-dialogue-models","slug":"wavchat-a-survey-of-spoken-dialogue-models","title":"WavChat: A Survey of Spoken Dialogue Models","date":"2024-11-15","arxiv_id":"2411.13577","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-centralized-distributed-transfer-model-for","title":"A Centralized-Distributed Transfer Model for Cross-Domain Recommendation Based on Multi-Source Heterogeneous Transfer Learning","date":"2024-11-14","arxiv_id":"2411.09286","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-strategic-topology-on-information","title":"A Strategic Topology on Information Structures","date":"2024-11-14","arxiv_id":"2411.09149","n_code_links":0,"syntology":null},{"paper":null,"slug":"adopting-rag-for-llm-aided-future-vehicle","title":"Adopting RAG for LLM-Aided Future Vehicle Design","date":"2024-11-14","arxiv_id":"2411.09590","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-driven-inverse-design-of-materials-past","title":"AI-driven inverse design of materials: Past, present and future","date":"2024-11-14","arxiv_id":"2411.09429","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-explainable-attention-model-for-cervical","title":"An Explainable Attention Model for Cervical Precancer Risk Classification using Colposcopic Images","date":"2024-11-14","arxiv_id":"2411.09469","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-performance-of-the-dinov2-self","title":"Assessing the Performance of the DINOv2 Self-supervised Learning Vision Transformer Model for the Segmentation of the Left Atrium from MRI Images","date":"2024-11-14","arxiv_id":"2411.09598","n_code_links":0,"syntology":null},{"paper":null,"slug":"automating-autograding-large-language-models","title":"Automating Autograding: Large Language Models as Test Suite Generators for Introductory Programming","date":"2024-11-14","arxiv_id":"2411.09261","n_code_links":0,"syntology":null},{"paper":null,"slug":"babylm-challenge-exploring-the-effect-of","title":"BabyLM Challenge: Exploring the Effect of Variation Sets on Language Model Training Efficiency","date":"2024-11-14","arxiv_id":"2411.09587","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-static-tools-evaluating-large-language","title":"Beyond Static Tools: Evaluating Large Language Models for Cryptographic Misuse Detection","date":"2024-11-14","arxiv_id":"2411.09772","n_code_links":0,"syntology":null},{"paper":null,"slug":"comprehensive-and-practical-evaluation-of","title":"Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering","date":"2024-11-14","arxiv_id":"2411.09213","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-for-fetal-inflammatory-response","title":"Deep Learning for Fetal Inflammatory Response Diagnosis in the Umbilical Cord","date":"2024-11-14","arxiv_id":"2411.09767","n_code_links":0,"syntology":null},{"paper":null,"slug":"dscformer-a-dual-branch-network-integrating","title":"DSCformer: A Dual-Branch Network Integrating Enhanced Dynamic Snake Convolution and SegFormer for Crack Segmentation","date":"2024-11-14","arxiv_id":"2411.09371","n_code_links":0,"syntology":null},{"paper":null,"slug":"dt-jrd-deep-transformer-based-just","title":"DT-JRD: Deep Transformer based Just Recognizable Difference Prediction Model for Video Coding for Machines","date":"2024-11-14","arxiv_id":"2411.09308","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-gender-bias-in-large-language-1","title":"Evaluating Gender Bias in Large Language Models","date":"2024-11-14","arxiv_id":"2411.09826","n_code_links":0,"syntology":null},{"paper":null,"slug":"grainrec-graph-and-attention-integrated","title":"GRAINRec: Graph and Attention Integrated Approach for Real-Time Session-Based Item Recommendations","date":"2024-11-14","arxiv_id":"2411.09152","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-vision-foundation-models-for-high","slug":"harnessing-vision-foundation-models-for-high","title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation","date":"2024-11-14","arxiv_id":"2411.09219","n_code_links":1,"syntology":null},{"paper":null,"slug":"hategpt-unleashing-gpt-3-5-turbo-to-combat","title":"HateGPT: Unleashing GPT-3.5 Turbo to Combat Hate Speech on X","date":"2024-11-14","arxiv_id":"2411.09214","n_code_links":0,"syntology":null},{"paper":"/paper/heuristical-comparison-of-vision-transformers","slug":"heuristical-comparison-of-vision-transformers","title":"Heuristical Comparison of Vision Transformers Against Convolutional Neural Networks for Semantic Segmentation on Remote Sensing Imagery","date":"2024-11-14","arxiv_id":"2411.09101","n_code_links":1,"syntology":null},{"paper":"/paper/initial-nugget-evaluation-results-for-the","slug":"initial-nugget-evaluation-results-for-the","title":"Initial Nugget Evaluation Results for the TREC 2024 RAG Track with the AutoNuggetizer Framework","date":"2024-11-14","arxiv_id":"2411.09607","n_code_links":2,"syntology":null},{"paper":"/paper/learning-parameter-sharing-with-tensor","slug":"learning-parameter-sharing-with-tensor","title":"Learning Parameter Sharing with Tensor Decompositions and Sparsity","date":"2024-11-14","arxiv_id":"2411.09816","n_code_links":1,"syntology":null},{"paper":null,"slug":"les-talker-fine-grained-emotion-editing-for","title":"LES-Talker: Fine-Grained Emotion Editing for Talking Head Generation in Linear Emotion Space","date":"2024-11-14","arxiv_id":"2411.09268","n_code_links":0,"syntology":null},{"paper":null,"slug":"local-deployment-of-large-scale-music-ai","title":"Local deployment of large-scale music AI models on commodity hardware","date":"2024-11-14","arxiv_id":"2411.09625","n_code_links":0,"syntology":null},{"paper":"/paper/local-global-attention-an-adaptive-mechanism","slug":"local-global-attention-an-adaptive-mechanism","title":"Local-Global Attention: An Adaptive Mechanism for Multi-Scale Feature Integration","date":"2024-11-14","arxiv_id":"2411.09604","n_code_links":1,"syntology":null},{"paper":"/paper/mm-eval-a-hierarchical-benchmark-for-modern","slug":"mm-eval-a-hierarchical-benchmark-for-modern","title":"MM-Eval: A Hierarchical Benchmark for Modern Mongolian Evaluation in LLMs","date":"2024-11-14","arxiv_id":"2411.09492","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-surprising-effectiveness-of-attention","slug":"on-the-surprising-effectiveness-of-attention","title":"On the Surprising Effectiveness of Attention Transfer for Vision Transformers","date":"2024-11-14","arxiv_id":"2411.09702","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"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":["alexlioralexli/attention-transfer"],"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":"/paper/opengemm-a-high-utilization-gemm-accelerator","slug":"opengemm-a-high-utilization-gemm-accelerator","title":"OpenGeMM: A High-Utilization GeMM Accelerator Generator with Lightweight RISC-V Control and Tight Memory Coupling","date":"2024-11-14","arxiv_id":"2411.09543","n_code_links":1,"syntology":null},{"paper":null,"slug":"partial-multi-view-clustering-via-meta","title":"Partial Multi-View Clustering via Meta-Learning and Contrastive Feature Alignment","date":"2024-11-14","arxiv_id":"2411.09758","n_code_links":0,"syntology":null},{"paper":null,"slug":"re-parameterization-of-lightweight","title":"Re-Parameterization of Lightweight Transformer for On-Device Speech Emotion Recognition","date":"2024-11-14","arxiv_id":"2411.09339","n_code_links":0,"syntology":null},{"paper":"/paper/reducing-reasoning-costs-the-path-of","slug":"reducing-reasoning-costs-the-path-of","title":"Reducing Reasoning Costs: The Path of Optimization for Chain of Thought via Sparse Attention Mechanism","date":"2024-11-14","arxiv_id":"2411.09111","n_code_links":1,"syntology":null},{"paper":"/paper/sag-vit-a-scale-aware-high-fidelity-patching","slug":"sag-vit-a-scale-aware-high-fidelity-patching","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","date":"2024-11-14","arxiv_id":"2411.09420","n_code_links":1,"syntology":null}],"record_sha256":"686d03211cc2962541d418045f538ae43b215ebc147914e2a7c0071e1b75c5d7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}