{"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/59","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":59,"pages_in_order":104,"rows_per_page":100,"rows":[5801,5900],"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/58","next":"/task/decoder/papers/60","papers":[{"url":null,"slug":"univie-a-unified-label-space-approach-to","title":"UniVIE: A Unified Label Space Approach to Visual Information Extraction from Form-like Documents","date":"2024-01-17","arxiv_id":"2401.09220","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-2d-temporal-map-diffusion-models","title":"Multi-scale 2D Temporal Map Diffusion Models for Natural Language Video Localization","date":"2024-01-16","arxiv_id":"2401.08232","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-hiding-cameras-optical","title":"Information hiding cameras: optical concealment of object information into ordinary images","date":"2024-01-15","arxiv_id":"2401.07856","repositories_listed":0,"syntology":null},{"url":null,"slug":"jewelry-recognition-via-encoder-decoder","title":"Jewelry Recognition via Encoder-Decoder Models","date":"2024-01-15","arxiv_id":"2401.08003","repositories_listed":0,"syntology":null},{"url":null,"slug":"mask-adaptive-gated-convolution-and-bi","title":"Mask-adaptive Gated Convolution and Bi-directional Progressive Fusion Network for Depth Completion","date":"2024-01-15","arxiv_id":"2401.07439","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-video-saliency-prediction","title":"Transformer-based Video Saliency Prediction with High Temporal Dimension Decoding","date":"2024-01-15","arxiv_id":"2401.07942","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-landmark-detection-on-human-point-clouds-a","title":"3D Landmark Detection on Human Point Clouds: A Benchmark and A Dual Cascade Point Transformer Framework","date":"2024-01-14","arxiv_id":"2401.07251","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-reconstruction-of-interacting-multi-person","title":"3D Reconstruction of Interacting Multi-Person in Clothing from a Single Image","date":"2024-01-12","arxiv_id":"2401.06415","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-behaviour-of-connectionist-speech","title":"Dynamic Behaviour of Connectionist Speech Recognition with Strong Latency Constraints","date":"2024-01-12","arxiv_id":"2401.06588","repositories_listed":0,"syntology":null},{"url":null,"slug":"cosseggaussians-compact-and-swift-scene","title":"Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation","date":"2024-01-11","arxiv_id":"2401.05925","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-information-theoretic-approach-to-12","title":"An Information Theoretic Approach to Interaction-Grounded Learning","date":"2024-01-10","arxiv_id":"2401.05015","repositories_listed":0,"syntology":null},{"url":null,"slug":"attendre-wait-to-attend-by-retrieval-with","title":"Attendre: Wait To Attend By Retrieval With Evicted Queries in Memory-Based Transformers for Long Context Processing","date":"2024-01-10","arxiv_id":"2401.04881","repositories_listed":0,"syntology":null},{"url":"/paper/himtm-hierarchical-multi-scale-masked-time","slug":"himtm-hierarchical-multi-scale-masked-time","title":"HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling for Long-Term Forecasting","date":"2024-01-10","arxiv_id":"2401.05012","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-distortion-aware-change-detection-in","title":"Toward distortion-aware change detection in realistic scenarios","date":"2024-01-10","arxiv_id":"2401.05157","repositories_listed":0,"syntology":null},{"url":null,"slug":"cuff-less-arterial-blood-pressure-waveform","title":"Cuff-less Arterial Blood Pressure Waveform Synthesis from Single-site PPG using Transformer & Frequency-domain Learning","date":"2024-01-09","arxiv_id":"2401.05452","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-learning-based-fleet-scheduling-for","title":"Graph Learning-based Fleet Scheduling for Urban Air Mobility under Operational Constraints, Varying Demand & Uncertainties","date":"2024-01-09","arxiv_id":"2401.04851","repositories_listed":0,"syntology":null},{"url":null,"slug":"masked-autoencoder-for-graph-clustering","title":"Masked AutoEncoder for Graph Clustering without Pre-defined Cluster Number k","date":"2024-01-09","arxiv_id":"2401.04741","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-multi-truck","title":"Deep Reinforcement Learning for Multi-Truck Vehicle Routing Problems with Multi-Leg Demand Routes","date":"2024-01-08","arxiv_id":"2401.08669","repositories_listed":0,"syntology":null},{"url":null,"slug":"sibyl-forecasting-time-evolving-query","title":"Sibyl: Forecasting Time-Evolving Query Workloads","date":"2024-01-08","arxiv_id":"2401.03723","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-microphone-speaker-separation-and","title":"Single-Microphone Speaker Separation and Voice Activity Detection in Noisy and Reverberant Environments","date":"2024-01-07","arxiv_id":"2401.03448","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-classification-based-on-knowledge-graphs","title":"Text Classification Based on Knowledge Graphs and Improved Attention Mechanism","date":"2024-01-07","arxiv_id":"2401.03591","repositories_listed":0,"syntology":null},{"url":null,"slug":"pixar-auto-regressive-language-modeling-in","title":"PIXAR: Auto-Regressive Language Modeling in Pixel Space","date":"2024-01-06","arxiv_id":"2401.03321","repositories_listed":0,"syntology":null},{"url":null,"slug":"mami-multi-attentional-mutual-information-for","title":"MAMI: Multi-Attentional Mutual-Information for Long Sequence Neuron Captioning","date":"2024-01-05","arxiv_id":"2401.02744","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-based-diffusion-generator-for","title":"Energy based diffusion generator for efficient sampling of Boltzmann distributions","date":"2024-01-04","arxiv_id":"2401.02080","repositories_listed":0,"syntology":null},{"url":"/paper/improving-diffusion-based-image-synthesis-1","slug":"improving-diffusion-based-image-synthesis-1","title":"Improving Diffusion-Based Image Synthesis with Context Prediction","date":"2024-01-04","arxiv_id":"2401.02015","repositories_listed":0,"syntology":null},{"url":null,"slug":"kernel-u-net-hierarchical-and-symmetrical","title":"Kernel-U-Net: Multivariate Time Series Forecasting using Custom Kernels","date":"2024-01-03","arxiv_id":"2401.01479","repositories_listed":0,"syntology":null},{"url":null,"slug":"nu-class-net-a-novel-deep-learning-based","title":"NU-Class Net: A Novel Approach for Video Quality Enhancement","date":"2024-01-02","arxiv_id":"2401.01163","repositories_listed":0,"syntology":null},{"url":null,"slug":"capturing-closely-interacted-two-person","title":"Capturing Closely Interacted Two-Person Motions with Reaction Priors","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"choose-what-you-need-disentangled-1","title":"Choose What You Need: Disentangled Representation Learning for Scene Text Recognition Removal and Editing","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"diffforensics-leveraging-diffusion-prior-to","title":"DiffForensics: Leveraging Diffusion Prior to Image Forgery Detection and Localization","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-syntactic-interaction-clues-for","title":"Discovering Syntactic Interaction Clues for Human-Object Interaction Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ease-detr-easing-the-competition-among-object","title":"EASE-DETR: Easing the Competition among Object Queries","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"estimating-extreme-3d-image-rotations-using","title":"Estimating Extreme 3D Image Rotations using Cascaded Attention","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-region-word-alignment-in-built-in","title":"Exploring Region-Word Alignment in Built-in Detector for Open-Vocabulary Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fsrt-facial-scene-representation-transformer-1","title":"FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance Head-pose and Facial Expression Features","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-depth-completion-via-depth-feature","title":"Improving Depth Completion via Depth Feature Upsampling","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-training-efficiency-of-diffusion","title":"Improving Training Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecture","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-prompt-perceiver-empower-1","title":"Multimodal Prompt Perceiver: Empower Adaptiveness Generalizability and Fidelity for All-in-One Image Restoration","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ote-exploring-accurate-scene-text-recognition","title":"OTE: Exploring Accurate Scene Text Recognition Using One Token","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parenerf-toward-fast-large-scale-dynamic-nerf","title":"PaReNeRF: Toward Fast Large-scale Dynamic NeRF with Patch-based Reference","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"posturehmr-posture-transformation-for-3d","title":"PostureHMR: Posture Transformation for 3D Human Mesh Recovery","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"practical-measurements-of-translucent","title":"Practical Measurements of Translucent Materials with Inter-Pixel Translucency Prior","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-acquisition-and-reconstruction-of","title":"Real-time Acquisition and Reconstruction of Dynamic Volumes with Neural Structured Illumination","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-representation-learning-from-7","title":"Self-Supervised Representation Learning from Arbitrary Scenarios","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bidirectional-trained-tree-structured-decoder","title":"Bidirectional Trained Tree-Structured Decoder for Handwritten Mathematical Expression Recognition","date":"2023-12-31","arxiv_id":"2401.00435","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learned-models-for-magnetic-materials","title":"Machine-learned models for magnetic materials","date":"2023-12-29","arxiv_id":"2401.00072","repositories_listed":0,"syntology":null},{"url":null,"slug":"ffca-net-stereo-image-compression-via-fast","title":"FFCA-Net: Stereo Image Compression via Fast Cascade Alignment of Side Information","date":"2023-12-28","arxiv_id":"2312.16963","repositories_listed":0,"syntology":null},{"url":"/paper/geometry-biased-transformer-for-robust-multi","slug":"geometry-biased-transformer-for-robust-multi","title":"Geometry-Biased Transformer for Robust Multi-View 3D Human Pose Reconstruction","date":"2023-12-28","arxiv_id":"2312.17106","repositories_listed":0,"syntology":null},{"url":null,"slug":"ann-vs-snn-a-case-study-for-neural-decoding","title":"Combining SNNs with Filtering for Efficient Neural Decoding in Implantable Brain-Machine Interfaces","date":"2023-12-26","arxiv_id":"2312.15889","repositories_listed":0,"syntology":null},{"url":null,"slug":"discrete-messages-improve-communication","title":"Discrete Messages Improve Communication Efficiency among Isolated Intelligent Agents","date":"2023-12-26","arxiv_id":"2312.15985","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-3d-reconstruction-from-single","title":"Scalable 3D Reconstruction From Single Particle X-Ray Diffraction Images Based on Online Machine Learning","date":"2023-12-22","arxiv_id":"2312.14432","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-sensing-and-task-oriented","title":"Joint Sensing and Task-Oriented Communications with Image and Wireless Data Modalities for Dynamic Spectrum Access","date":"2023-12-21","arxiv_id":"2312.13931","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-of-feature-interaction-for-multi","title":"BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-task Dense Predictions","date":"2023-12-21","arxiv_id":"2312.13514","repositories_listed":0,"syntology":null},{"url":"/paper/videopoet-a-large-language-model-for-zero","slug":"videopoet-a-large-language-model-for-zero","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","date":"2023-12-21","arxiv_id":"2312.14125","repositories_listed":0,"syntology":null},{"url":null,"slug":"bevseg2tp-surround-view-camera-bird-s-eye","title":"BEVSeg2TP: Surround View Camera Bird's-Eye-View Based Joint Vehicle Segmentation and Ego Vehicle Trajectory Prediction","date":"2023-12-20","arxiv_id":"2312.13081","repositories_listed":0,"syntology":null},{"url":null,"slug":"computational-spectral-imaging-with-unified","title":"Computational Spectral Imaging with Unified Encoding Model: A Comparative Study and Beyond","date":"2023-12-20","arxiv_id":"2312.13310","repositories_listed":0,"syntology":null},{"url":null,"slug":"llamavae-guiding-large-language-model","title":"LlaMaVAE: Guiding Large Language Model Generation via Continuous Latent Sentence Spaces","date":"2023-12-20","arxiv_id":"2312.13208","repositories_listed":0,"syntology":null},{"url":null,"slug":"ppea-depth-progressive-parameter-efficient","title":"PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimation","date":"2023-12-20","arxiv_id":"2312.13066","repositories_listed":0,"syntology":null},{"url":null,"slug":"slp-net-an-efficient-lightweight-network-for","title":"SLP-Net:An efficient lightweight network for segmentation of skin lesions","date":"2023-12-20","arxiv_id":"2312.12789","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-distribution-masked-autoencoders-for","title":"Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation","date":"2023-12-19","arxiv_id":"2312.12480","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-llm-inference-solution-on-intel-gpu","title":"Efficient LLM inference solution on Intel GPU","date":"2023-12-19","arxiv_id":"2401.05391","repositories_listed":0,"syntology":null},{"url":null,"slug":"external-knowledge-augmented-polyphone","title":"External Knowledge Augmented Polyphone Disambiguation Using Large Language Model","date":"2023-12-19","arxiv_id":"2312.11920","repositories_listed":0,"syntology":null},{"url":null,"slug":"stylespeech-self-supervised-style-enhancing","title":"StyleSpeech: Self-supervised Style Enhancing with VQ-VAE-based Pre-training for Expressive Audiobook Speech Synthesis","date":"2023-12-19","arxiv_id":"2312.12181","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-network-for-multi-person-tracking","title":"Transformer Network for Multi-Person Tracking and Re-Identification in Unconstrained Environment","date":"2023-12-19","arxiv_id":"2312.11929","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-contamination-issues-in-brain-to-text","title":"Cross-Subject Data Splitting for Brain-to-Text Decoding","date":"2023-12-18","arxiv_id":"2312.10987","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-linguistic-representation-for","title":"Generative linguistic representation for spoken language identification","date":"2023-12-18","arxiv_id":"2312.10964","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantized-decoder-in-learned-image","title":"Quantized Decoder in Learned Image Compression for Deterministic Reconstruction","date":"2023-12-18","arxiv_id":"2312.11209","repositories_listed":0,"syntology":null},{"url":null,"slug":"esdmr-net-a-lightweight-network-with-expand","title":"ESDMR-Net: A Lightweight Network With Expand-Squeeze and Dual Multiscale Residual Connections for Medical Image Segmentation","date":"2023-12-17","arxiv_id":"2312.10585","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-fidelity-face-swapping-with-style","title":"High-Fidelity Face Swapping with Style Blending","date":"2023-12-17","arxiv_id":"2312.10843","repositories_listed":0,"syntology":null},{"url":null,"slug":"all-attention-u-net-for-semantic-segmentation","title":"All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images","date":"2023-12-16","arxiv_id":"2312.10483","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-segment-segmenting-images-in-sensor-for","title":"Q-Segment: Segmenting Images In-Sensor for Vessel-Based Medical Diagnosis","date":"2023-12-15","arxiv_id":"2312.09854","repositories_listed":0,"syntology":null},{"url":null,"slug":"sketch-and-shift-a-robust-decoder-for","title":"Sketch and shift: a robust decoder for compressive clustering","date":"2023-12-15","arxiv_id":"2312.09940","repositories_listed":0,"syntology":null},{"url":null,"slug":"u2-kws-unified-two-pass-open-vocabulary","title":"U2-KWS: Unified Two-pass Open-vocabulary Keyword Spotting with Keyword Bias","date":"2023-12-15","arxiv_id":"2312.09760","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-sparse-cross-attention-based-graph","title":"A Sparse Cross Attention-based Graph Convolution Network with Auxiliary Information Awareness for Traffic Flow Prediction","date":"2023-12-14","arxiv_id":"2312.09050","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-cross-modal-alignment-with","title":"Improving Cross-modal Alignment with Synthetic Pairs for Text-only Image Captioning","date":"2023-12-14","arxiv_id":"2312.08865","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmap-multi-modal-alignment-prompt-for-cross","title":"MmAP : Multi-modal Alignment Prompt for Cross-domain Multi-task Learning","date":"2023-12-14","arxiv_id":"2312.08636","repositories_listed":0,"syntology":null},{"url":null,"slug":"encoder-minimal-and-decoder-minimal-framework","title":"Encoder-minimal and Decoder-minimal Framework for Remote Sensing Image Dehazing","date":"2023-12-13","arxiv_id":"2312.07849","repositories_listed":0,"syntology":null},{"url":null,"slug":"svinvnet-a-densely-connected-encoder-decoder","title":"SVInvNet: A Densely Connected Encoder-Decoder Architecture for Seismic Velocity Inversion","date":"2023-12-13","arxiv_id":"2312.08194","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-encoder-decoder-model-for","title":"Attention Based Encoder Decoder Model for Video Captioning in Nepali (2023)","date":"2023-12-12","arxiv_id":"2312.07418","repositories_listed":0,"syntology":null},{"url":null,"slug":"bed-bi-encoder-decoder-model-for-canonical","title":"BED: Bi-Encoder-Decoder Model for Canonical Relation Extraction","date":"2023-12-12","arxiv_id":"2312.07088","repositories_listed":0,"syntology":null},{"url":null,"slug":"mind-3d-reconstruct-high-quality-3d-objects","title":"MinD-3D: Reconstruct High-quality 3D objects in Human Brain","date":"2023-12-12","arxiv_id":"2312.07485","repositories_listed":0,"syntology":null},{"url":null,"slug":"polynomial-based-self-attention-for-table","title":"Polynomial-based Self-Attention for Table Representation learning","date":"2023-12-12","arxiv_id":"2312.07753","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-gua-speech-system-description-for-cnvsrc","title":"The GUA-Speech System Description for CNVSRC Challenge 2023","date":"2023-12-12","arxiv_id":"2312.07254","repositories_listed":0,"syntology":null},{"url":null,"slug":"dig-csi-a-distributed-and-generative-model","title":"Dig-CSI: A Distributed and Generative Model Assisted CSI Feedback Training Framework","date":"2023-12-10","arxiv_id":"2312.05921","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangled-representation-learning-for-3","title":"Disentangled Representation Learning for Controllable Person Image Generation","date":"2023-12-10","arxiv_id":"2312.05798","repositories_listed":0,"syntology":null},{"url":"/paper/opensd-unified-open-vocabulary-segmentation","slug":"opensd-unified-open-vocabulary-segmentation","title":"OpenSD: Unified Open-Vocabulary Segmentation and Detection","date":"2023-12-10","arxiv_id":"2312.06703","repositories_listed":0,"syntology":null},{"url":null,"slug":"transglow-attention-augmented-transduction","title":"TransGlow: Attention-augmented Transduction model based on Graph Neural Networks for Water Flow Forecasting","date":"2023-12-10","arxiv_id":"2312.05961","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-neural-machine-translation-by-multi","title":"Improving Neural Machine Translation by Multi-Knowledge Integration with Prompting","date":"2023-12-08","arxiv_id":"2312.04807","repositories_listed":0,"syntology":null},{"url":null,"slug":"eclipse-a-resource-efficient-text-to-image","title":"ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations","date":"2023-12-07","arxiv_id":"2312.04655","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-training-or-not-an-exploration-of-pre","title":"Joint Training or Not: An Exploration of Pre-trained Speech Models in Audio-Visual Speaker Diarization","date":"2023-12-07","arxiv_id":"2312.04131","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-spatial-temporal-representation","title":"Jointly spatial-temporal representation learning for individual trajectories","date":"2023-12-07","arxiv_id":"2312.04055","repositories_listed":0,"syntology":null},{"url":null,"slug":"lsegdiff-a-latent-diffusion-model-for-medical","title":"LSegDiff: A Latent Diffusion Model for Medical Image Segmentation","date":"2023-12-07","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-text-to-text-model-for-multilingual","title":"A Text-to-Text Model for Multilingual Offensive Language Identification","date":"2023-12-06","arxiv_id":"2312.03379","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-answer-information-methods-for","title":"Exploring Answer Information Methods for Question Generation with Transformers","date":"2023-12-06","arxiv_id":"2312.03483","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-data-and-resource-efficient-device","title":"Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models","date":"2023-12-06","arxiv_id":"2312.03632","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-learnt-video-codecs-with","title":"Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillation","date":"2023-12-05","arxiv_id":"2312.02605","repositories_listed":0,"syntology":null},{"url":null,"slug":"harmonizing-global-voices-culturally-aware","title":"Enhancing Content Moderation with Culturally-Aware Models","date":"2023-12-05","arxiv_id":"2312.02401","repositories_listed":0,"syntology":null},{"url":null,"slug":"mgtr-multi-granular-transformer-for-motion","title":"MGTR: Multi-Granular Transformer for Motion Prediction with LiDAR","date":"2023-12-05","arxiv_id":"2312.02409","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-prompt-perceiver-empower","title":"Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration","date":"2023-12-05","arxiv_id":"2312.02918","repositories_listed":0,"syntology":null},{"url":null,"slug":"pmmtalk-speech-driven-3d-facial-animation","title":"PMMTalk: Speech-Driven 3D Facial Animation from Complementary Pseudo Multi-modal Features","date":"2023-12-05","arxiv_id":"2312.02781","repositories_listed":0,"syntology":null}],"record_sha256":"488a2f79a6b28903b88b7302c2bc5300857f892ac3b36cdbfe82f31f470dd086","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}