{"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":"/task/decoder/papers/52","list_of":"/task/decoder","task":"Decoder","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":52,"pages_in_order":104,"rows_per_page":100,"rows":[5101,5200],"of":10368,"counts":{"archive_papers_tagged":10368,"with_a_code_link":4358,"where_syntology_ran_a_sample":1061,"not_listed_spam_title":0,"listed":10368,"listed_where_code_ran":1061,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":909,"every_run_a_failure_of_syntologys_instrument":152,"listed_with_a_run_with_no_instrument_failure":909,"listed_every_run_a_failure_of_syntologys_instrument":152,"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":"/task/decoder","prev":"/task/decoder/papers/51","next":"/task/decoder/papers/53","papers":[{"url":null,"slug":"scaling-laws-of-decoder-only-models-on-the","title":"Scaling Laws of Decoder-Only Models on the Multilingual Machine Translation Task","date":"2024-09-23","arxiv_id":"2409.15051","repositories_listed":0,"syntology":null},{"url":null,"slug":"transukan-computing-efficient-hybrid-kan","title":"TransUKAN:Computing-Efficient Hybrid KAN-Transformer for Enhanced Medical Image Segmentation","date":"2024-09-23","arxiv_id":"2409.14676","repositories_listed":0,"syntology":null},{"url":null,"slug":"dsparse-dynamic-sparse-embedding-for","title":"DSparsE: Dynamic Sparse Embedding for Knowledge Graph Completion","date":"2024-09-22","arxiv_id":"2410.07140","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-13972","title":"Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch","date":"2024-09-21","arxiv_id":"2409.13972","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-14107","title":"Routing in Sparsely-gated Language Models responds to Context","date":"2024-09-21","arxiv_id":"2409.14107","repositories_listed":0,"syntology":null},{"url":null,"slug":"splatloc-3d-gaussian-splatting-based-visual","title":"SplatLoc: 3D Gaussian Splatting-based Visual Localization for Augmented Reality","date":"2024-09-21","arxiv_id":"2409.14067","repositories_listed":0,"syntology":null},{"url":null,"slug":"emmett-efficient-multimodal-machine","title":"EMMeTT: Efficient Multimodal Machine Translation Training","date":"2024-09-20","arxiv_id":"2409.13523","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-open-vocabulary-video-visual","title":"End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting","date":"2024-09-19","arxiv_id":"2409.12499","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-tokenization-needed-for-masked-particle","title":"Is Tokenization Needed for Masked Particle Modelling?","date":"2024-09-19","arxiv_id":"2409.12589","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmt-net-lane-model-transformer-network-for","title":"LMT-Net: Lane Model Transformer Network for Automated HD Mapping from Sparse Vehicle Observations","date":"2024-09-19","arxiv_id":"2409.12409","repositories_listed":0,"syntology":null},{"url":null,"slug":"ndvq-robust-neural-audio-codec-with-normal","title":"NDVQ: Robust Neural Audio Codec with Normal Distribution-Based Vector Quantization","date":"2024-09-19","arxiv_id":"2409.12717","repositories_listed":0,"syntology":null},{"url":null,"slug":"pmr-net-parallel-multi-resolution-encoder","title":"PMR-Net: Parallel Multi-Resolution Encoder-Decoder Network Framework for Medical Image Segmentation","date":"2024-09-19","arxiv_id":"2409.12678","repositories_listed":0,"syntology":null},{"url":null,"slug":"extract-and-abstract-unifying-extractive-and","title":"Extract-and-Abstract: Unifying Extractive and Abstractive Summarization within Single Encoder-Decoder Framework","date":"2024-09-18","arxiv_id":"2409.11827","repositories_listed":0,"syntology":null},{"url":"/paper/gca-sun-a-gated-context-aware-swin-unet-for","slug":"gca-sun-a-gated-context-aware-swin-unet-for","title":"GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting","date":"2024-09-18","arxiv_id":"2409.12249","repositories_listed":0,"syntology":null},{"url":null,"slug":"pieclam-a-universal-graph-autoencoder-based","title":"PieClam: A Universal Graph Autoencoder Based on Overlapping Inclusive and Exclusive Communities","date":"2024-09-18","arxiv_id":"2409.11618","repositories_listed":0,"syntology":null},{"url":null,"slug":"vl-reader-vision-and-language-reconstructor","title":"VL-Reader: Vision and Language Reconstructor is an Effective Scene Text Recognizer","date":"2024-09-18","arxiv_id":"2409.11656","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-thought-prompting-for-speech","title":"Chain-of-Thought Prompting for Speech Translation","date":"2024-09-17","arxiv_id":"2409.11538","repositories_listed":0,"syntology":null},{"url":null,"slug":"discrete-unit-based-masking-for-improving","title":"Discrete Unit based Masking for Improving Disentanglement in Voice Conversion","date":"2024-09-17","arxiv_id":"2409.11560","repositories_listed":0,"syntology":null},{"url":null,"slug":"robot-manipulation-in-salient-vision-through","title":"Robot Manipulation in Salient Vision through Referring Image Segmentation and Geometric Constraints","date":"2024-09-17","arxiv_id":"2409.11518","repositories_listed":0,"syntology":null},{"url":null,"slug":"dae-fuse-an-adaptive-discriminative","title":"DAE-Fuse: An Adaptive Discriminative Autoencoder for Multi-Modality Image Fusion","date":"2024-09-16","arxiv_id":"2409.10080","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-and-transfer-dynamic-class-aware","title":"Prompt-and-Transfer: Dynamic Class-aware Enhancement for Few-shot Segmentation","date":"2024-09-16","arxiv_id":"2409.10389","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-attention-limits-working-memory-capacity","title":"Self-Attention Limits Working Memory Capacity of Transformer-Based Models","date":"2024-09-16","arxiv_id":"2409.10715","repositories_listed":0,"syntology":null},{"url":null,"slug":"vae-qwgan-improving-quantum-gans-for-high","title":"VAE-QWGAN: Addressing Mode Collapse in Quantum GANs via Autoencoding Priors","date":"2024-09-16","arxiv_id":"2409.10339","repositories_listed":0,"syntology":null},{"url":null,"slug":"dm-dual-path-magnitude-network-for-general","title":"DM: Dual-path Magnitude Network for General Speech Restoration","date":"2024-09-13","arxiv_id":"2409.08702","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-disentanglement-in-a-phoneme","title":"Investigating Disentanglement in a Phoneme-level Speech Codec for Prosody Modeling","date":"2024-09-13","arxiv_id":"2409.08664","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmac-td-producing-time-domain-explanations","title":"LMAC-TD: Producing Time Domain Explanations for Audio Classifiers","date":"2024-09-13","arxiv_id":"2409.08655","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-speech-transformer-decoders-when","title":"Multi-modal Speech Transformer Decoders: When Do Multiple Modalities Improve Accuracy?","date":"2024-09-13","arxiv_id":"2409.09221","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectral-u-net-enhancing-medical-image","title":"Spectral U-Net: Enhancing Medical Image Segmentation via Spectral Decomposition","date":"2024-09-13","arxiv_id":"2409.09216","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-attention-based-influence-model-for","title":"Cross-Attention Based Influence Model for Manual and Nonmanual Sign Language Analysis","date":"2024-09-12","arxiv_id":"2409.08162","repositories_listed":0,"syntology":null},{"url":"/paper/depth-matters-exploring-deep-interactions-of","slug":"depth-matters-exploring-deep-interactions-of","title":"Depth Matters: Exploring Deep Interactions of RGB-D for Semantic Segmentation in Traffic Scenes","date":"2024-09-12","arxiv_id":"2409.07995","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-speech-llama-inference-with-multi","title":"Faster Speech-LLaMA Inference with Multi-token Prediction","date":"2024-09-12","arxiv_id":"2409.08148","repositories_listed":0,"syntology":null},{"url":null,"slug":"interact-inter-dependency-aware-action","title":"InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulation","date":"2024-09-12","arxiv_id":"2409.07914","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-translation-with-large-language-1","title":"Machine Translation with Large Language Models: Decoder Only vs. Encoder-Decoder","date":"2024-09-12","arxiv_id":"2409.13747","repositories_listed":0,"syntology":null},{"url":null,"slug":"pavesam-segment-anything-for-pavement","title":"PaveSAM Segment Anything for Pavement Distress","date":"2024-09-11","arxiv_id":"2409.07295","repositories_listed":0,"syntology":null},{"url":null,"slug":"bottleneck-based-encoder-decoder-architecture","title":"Bottleneck-based Encoder-decoder ARchitecture (BEAR) for Learning Unbiased Consumer-to-Consumer Image Representations","date":"2024-09-10","arxiv_id":"2409.06187","repositories_listed":0,"syntology":null},{"url":null,"slug":"e2llm-encoder-elongated-large-language-models","title":"E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning","date":"2024-09-10","arxiv_id":"2409.06679","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-law-hypothesis-for-multimodal-model","title":"Scaling Law Hypothesis for Multimodal Model","date":"2024-09-10","arxiv_id":"2409.06754","repositories_listed":0,"syntology":null},{"url":null,"slug":"ad-net-attention-based-dilated-convolutional","title":"AD-Net: Attention-based dilated convolutional residual network with guided decoder for robust skin lesion segmentation","date":"2024-09-09","arxiv_id":"2409.05420","repositories_listed":0,"syntology":null},{"url":null,"slug":"elsevier-arena-human-evaluation-of-chemistry","title":"Elsevier Arena: Human Evaluation of Chemistry/Biology/Health Foundational Large Language Models","date":"2024-09-09","arxiv_id":"2409.05486","repositories_listed":0,"syntology":null},{"url":null,"slug":"fif-unet-an-efficient-unet-using-feature","title":"FIF-UNet: An Efficient UNet Using Feature Interaction and Fusion for Medical Image Segmentation","date":"2024-09-09","arxiv_id":"2409.05324","repositories_listed":0,"syntology":null},{"url":null,"slug":"cycle-pixel-difference-network-for-crisp-edge","title":"Cycle Pixel Difference Network for Crisp Edge Detection","date":"2024-09-06","arxiv_id":"2409.04272","repositories_listed":0,"syntology":null},{"url":null,"slug":"opal-outlier-preserved-microscaling","title":"OPAL: Outlier-Preserved Microscaling Quantization Accelerator for Generative Large Language Models","date":"2024-09-06","arxiv_id":"2409.05902","repositories_listed":0,"syntology":null},{"url":null,"slug":"ui-jepa-towards-active-perception-of-user","title":"UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity","date":"2024-09-06","arxiv_id":"2409.04081","repositories_listed":0,"syntology":null},{"url":null,"slug":"unit-unifying-image-and-text-recognition-in","title":"UNIT: Unifying Image and Text Recognition in One Vision Encoder","date":"2024-09-06","arxiv_id":"2409.04095","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-multi-source-visual-prompt-tuning","title":"End-to-end Multi-source Visual Prompt Tuning for Survival Analysis in Whole Slide Images","date":"2024-09-05","arxiv_id":"2409.03804","repositories_listed":0,"syntology":null},{"url":null,"slug":"frozenseg-harmonizing-frozen-foundation","title":"FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation","date":"2024-09-05","arxiv_id":"2409.03525","repositories_listed":0,"syntology":null},{"url":null,"slug":"screenmark-watermarking-arbitrary-visual","title":"ScreenMark: Watermarking Arbitrary Visual Content on Screen","date":"2024-09-05","arxiv_id":"2409.03487","repositories_listed":0,"syntology":null},{"url":null,"slug":"tbconvl-net-a-hybrid-deep-learning","title":"TBConvL-Net: A Hybrid Deep Learning Architecture for Robust Medical Image Segmentation","date":"2024-09-05","arxiv_id":"2409.03367","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-extraction-of-noise-robust-discrete","title":"Efficient Extraction of Noise-Robust Discrete Units from Self-Supervised Speech Models","date":"2024-09-04","arxiv_id":"2409.02565","repositories_listed":0,"syntology":null},{"url":null,"slug":"historical-german-text-normalization-using","title":"Historical German Text Normalization Using Type- and Token-Based Language Modeling","date":"2024-09-04","arxiv_id":"2409.02841","repositories_listed":0,"syntology":null},{"url":null,"slug":"iconformer-dynamic-parameter-efficient-tuning","title":"iConFormer: Dynamic Parameter-Efficient Tuning with Input-Conditioned Adaptation","date":"2024-09-04","arxiv_id":"2409.02838","repositories_listed":0,"syntology":null},{"url":null,"slug":"rate-adaptive-generative-semantic","title":"Rate-Adaptive Generative Semantic Communication Using Conditional Diffusion Models","date":"2024-09-04","arxiv_id":"2409.02597","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-what-you-cant-compress","title":"Sample what you cant compress","date":"2024-09-04","arxiv_id":"2409.02529","repositories_listed":0,"syntology":null},{"url":null,"slug":"waveletgpt-wavelets-meet-large-language","title":"Wavelet GPT: Wavelet Inspired Large Language Models","date":"2024-09-04","arxiv_id":"2409.12924","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-multivariate-autoencoder-for-capturing","title":"Deep multivariate autoencoder for capturing complexity in Brain Structure and Behaviour Relationships","date":"2024-09-03","arxiv_id":"2409.01638","repositories_listed":0,"syntology":null},{"url":null,"slug":"f2former-when-fractional-fourier-meets-deep","title":"F2former: When Fractional Fourier Meets Deep Wiener Deconvolution and Selective Frequency Transformer for Image Deblurring","date":"2024-09-03","arxiv_id":"2409.02056","repositories_listed":0,"syntology":null},{"url":null,"slug":"pureformer-vc-non-parallel-one-shot-voice","title":"Pureformer-VC: Non-parallel One-Shot Voice Conversion with Pure Transformer Blocks and Triplet Discriminative Training","date":"2024-09-03","arxiv_id":"2409.01668","repositories_listed":0,"syntology":null},{"url":null,"slug":"vired-prediction-of-visual-relations-in","title":"ViRED: Prediction of Visual Relations in Engineering Drawings","date":"2024-09-02","arxiv_id":"2409.00909","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-guided-multi-scale-interaction","title":"Attention-Guided Multi-scale Interaction Network for Face Super-Resolution","date":"2024-09-01","arxiv_id":"2409.00591","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-senet-and-resnet-synergy-within-an","title":"Leveraging SeNet and ResNet Synergy within an Encoder-Decoder Architecture for Glioma Detection","date":"2024-09-01","arxiv_id":"2409.00804","repositories_listed":0,"syntology":null},{"url":null,"slug":"modifying-the-u-net-s-encoder-decoder","title":"Modifying the U-Net's Encoder-Decoder Architecture for Segmentation of Tumors in Breast Ultrasound Images","date":"2024-09-01","arxiv_id":"2409.00647","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-paragraph-level-handwriting","title":"Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models","date":"2024-09-01","arxiv_id":"2409.00786","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-the-target-word-of-game-playing","title":"Predicting the Target Word of Game-playing Conversations using a Low-Rank Dialect Adapter for Decoder Models","date":"2024-08-31","arxiv_id":"2409.00358","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-multi-talker-asr-performance-with","title":"Advancing Multi-talker ASR Performance with Large Language Models","date":"2024-08-30","arxiv_id":"2408.17431","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-natural-language","title":"Retrieval-Augmented Natural Language Reasoning for Explainable Visual Question Answering","date":"2024-08-30","arxiv_id":"2408.17006","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-terrain-physical-parameters-from","title":"Identifying Terrain Physical Parameters from Vision -- Towards Physical-Parameter-Aware Locomotion and Navigation","date":"2024-08-29","arxiv_id":"2408.16567","repositories_listed":0,"syntology":null},{"url":null,"slug":"making-the-most-of-your-model-methods-for","title":"Making the Most of your Model: Methods for Finetuning and Applying Pretrained Transformers","date":"2024-08-29","arxiv_id":"2408.16241","repositories_listed":0,"syntology":null},{"url":null,"slug":"revising-multimodal-vaes-with-diffusion","title":"Multimodal ELBO with Diffusion Decoders","date":"2024-08-29","arxiv_id":"2408.16883","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-baseline-with-single-encoder-for","title":"A Simple Baseline with Single-encoder for Referring Image Segmentation","date":"2024-08-28","arxiv_id":"2408.15521","repositories_listed":0,"syntology":null},{"url":null,"slug":"dolphin-long-context-as-a-new-modality-for","title":"Squid: Long Context as a New Modality for Energy-Efficient On-Device Language Models","date":"2024-08-28","arxiv_id":"2408.15518","repositories_listed":0,"syntology":null},{"url":null,"slug":"dqformer-towards-unified-lidar-panoptic","title":"DQFormer: Towards Unified LiDAR Panoptic Segmentation with Decoupled Queries","date":"2024-08-28","arxiv_id":"2408.15813","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-adversarial-training-for-zero","title":"Multi-modal Adversarial Training for Zero-Shot Voice Cloning","date":"2024-08-28","arxiv_id":"2408.15916","repositories_listed":0,"syntology":null},{"url":null,"slug":"targetin-the-partition-function-of-chemically","title":"Targeting the partition function of chemically disordered materials with a generative approach based on inverse variational autoencoders","date":"2024-08-27","arxiv_id":"2408.14928","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaknet-discontinuity-resilient-multi-scale","title":"BreakNet: Discontinuity-Resilient Multi-Scale Transformer Segmentation of Retinal Layers","date":"2024-08-26","arxiv_id":"2408.14606","repositories_listed":0,"syntology":null},{"url":null,"slug":"driving-in-the-occupancy-world-vision-centric","title":"Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving","date":"2024-08-26","arxiv_id":"2408.14197","repositories_listed":0,"syntology":null},{"url":null,"slug":"papr-reduction-based-on-deep-learning","title":"Deep Learning Autoencoders for Reducing PAPR in Coherent Optical Systems","date":"2024-08-26","arxiv_id":"2408.14248","repositories_listed":0,"syntology":null},{"url":null,"slug":"pixel-aligned-multi-view-generation-with","title":"Pixel-Aligned Multi-View Generation with Depth Guided Decoder","date":"2024-08-26","arxiv_id":"2408.14016","repositories_listed":0,"syntology":null},{"url":null,"slug":"anople-few-shot-anomaly-detection-via-bi","title":"AnoPLe: Few-Shot Anomaly Detection via Bi-directional Prompt Learning with Only Normal Samples","date":"2024-08-24","arxiv_id":"2408.13516","repositories_listed":0,"syntology":null},{"url":null,"slug":"focused-discriminative-training-for-streaming","title":"Focused Discriminative Training For Streaming CTC-Trained Automatic Speech Recognition Models","date":"2024-08-23","arxiv_id":"2408.13008","repositories_listed":0,"syntology":null},{"url":null,"slug":"specgaussian-with-latent-features-a-high","title":"SpecGaussian with Latent Features: A High-quality Modeling of the View-dependent Appearance for 3D Gaussian Splatting","date":"2024-08-23","arxiv_id":"2409.05868","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-parking-perception-by-multi-task","title":"Enhanced Parking Perception by Multi-Task Fisheye Cross-view Transformers","date":"2024-08-22","arxiv_id":"2408.12575","repositories_listed":0,"syntology":null},{"url":null,"slug":"euis-net-a-convolutional-neural-network-for","title":"EUIS-Net: A Convolutional Neural Network for Efficient Ultrasound Image Segmentation","date":"2024-08-22","arxiv_id":"2408.12323","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-robust-features-for-scatter-removal","title":"Learning Robust Features for Scatter Removal and Reconstruction in Dynamic ICF X-Ray Tomography","date":"2024-08-22","arxiv_id":"2408.12766","repositories_listed":0,"syntology":null},{"url":null,"slug":"unco-towards-unifying-neural-combinatorial","title":"Bridging Large Language Models and Optimization: A Unified Framework for Text-attributed Combinatorial Optimization","date":"2024-08-22","arxiv_id":"2408.12214","repositories_listed":0,"syntology":null},{"url":null,"slug":"clinical-context-aware-radiology-report","title":"Clinical Context-aware Radiology Report Generation from Medical Images using Transformers","date":"2024-08-21","arxiv_id":"2408.11344","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-estimation-of-last-mile-electric","title":"Energy Estimation of Last Mile Electric Vehicle Routes","date":"2024-08-21","arxiv_id":"2408.12006","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypergraph-learning-based-recommender-system","title":"Hypergraph Learning based Recommender System for Anomaly Detection, Control and Optimization","date":"2024-08-21","arxiv_id":"2408.11359","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-for-page-stream","title":"Large Language Models for Page Stream Segmentation","date":"2024-08-21","arxiv_id":"2408.11981","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-interchangeability-of-positional","title":"Towards Inducing Document-Level Abilities in Standard Multilingual Neural Machine Translation Models","date":"2024-08-21","arxiv_id":"2408.11382","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-reinforcement-learning-based","title":"An End-to-End Reinforcement Learning Based Approach for Micro-View Order-Dispatching in Ride-Hailing","date":"2024-08-20","arxiv_id":"2408.10479","repositories_listed":0,"syntology":null},{"url":null,"slug":"sdi-net-toward-sufficient-dual-view","title":"SDI-Net: Toward Sufficient Dual-View Interaction for Low-light Stereo Image Enhancement","date":"2024-08-20","arxiv_id":"2408.10934","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-is-a-smoothed-cubic-spline","title":"Attention is a smoothed cubic spline","date":"2024-08-19","arxiv_id":"2408.09624","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-optimal-radius-and-subcarrier-mapping","title":"On the Optimal Radius and Subcarrier Mapping for Binary Modulation on Conjugate-Reciprocal Zeros","date":"2024-08-19","arxiv_id":"2408.10029","repositories_listed":0,"syntology":null},{"url":null,"slug":"summarizing-long-regulatory-documents-with-a","title":"Summarizing long regulatory documents with a multi-step pipeline","date":"2024-08-19","arxiv_id":"2408.09777","repositories_listed":0,"syntology":null},{"url":null,"slug":"maskbev-towards-a-unified-framework-for-bev","title":"MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation","date":"2024-08-17","arxiv_id":"2408.09122","repositories_listed":0,"syntology":null},{"url":null,"slug":"realistic-extreme-image-rescaling-via","title":"Timestep-Aware Diffusion Model for Extreme Image Rescaling","date":"2024-08-17","arxiv_id":"2408.09151","repositories_listed":0,"syntology":null},{"url":null,"slug":"ris-based-over-the-air-diffractional-channel","title":"RIS-based Over-the-air Diffractional Channel Coding","date":"2024-08-17","arxiv_id":"2408.09132","repositories_listed":0,"syntology":null},{"url":null,"slug":"priormapnet-enhancing-online-vectorized-hd","title":"PriorMapNet: Enhancing Online Vectorized HD Map Construction with Priors","date":"2024-08-16","arxiv_id":"2408.08802","repositories_listed":0,"syntology":null},{"url":null,"slug":"tuning-a-sam-based-model-with-multi-cognitive","title":"Tuning a SAM-Based Model with Multi-Cognitive Visual Adapter to Remote Sensing Instance Segmentation","date":"2024-08-16","arxiv_id":"2408.08576","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-large-language-model-based-speech","title":"Enhancing Large Language Model-based Speech Recognition by Contextualization for Rare and Ambiguous Words","date":"2024-08-15","arxiv_id":"2408.08027","repositories_listed":0,"syntology":null}],"record_sha256":"bf3a7c222b0cd7630a92dd7b88c1babad80706a450a3a21948482c7575ab4132","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}