{"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/55","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":55,"pages_in_order":104,"rows_per_page":100,"rows":[5401,5500],"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/54","next":"/task/decoder/papers/56","papers":[{"url":null,"slug":"ssnvc-single-stream-neural-video-compression","title":"SSNVC: Single Stream Neural Video Compression with Implicit Temporal Information","date":"2024-06-11","arxiv_id":"2406.07645","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-object-detection-with","title":"Unsupervised Object Detection with Theoretical Guarantees","date":"2024-06-11","arxiv_id":"2406.07284","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-representation-learning-with-1","title":"Visual Representation Learning with Stochastic Frame Prediction","date":"2024-06-11","arxiv_id":"2406.07398","repositories_listed":0,"syntology":null},{"url":null,"slug":"brainchat-decoding-semantic-information-from","title":"BrainChat: Decoding Semantic Information from fMRI using Vision-language Pretrained Models","date":"2024-06-10","arxiv_id":"2406.07584","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-neural-compression-with-inference","title":"Efficient Neural Compression with Inference-time Decoding","date":"2024-06-10","arxiv_id":"2406.06237","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-physical-simulation-with-message","title":"Learning Physical Simulation with Message Passing Transformer","date":"2024-06-10","arxiv_id":"2406.06060","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-prompting-decoder-helps-better-language","title":"Multi-Prompting Decoder Helps Better Language Understanding","date":"2024-06-10","arxiv_id":"2406.06279","repositories_listed":0,"syntology":null},{"url":null,"slug":"zak-otfs-and-turbo-signal-processing-for","title":"Zak-OTFS and Turbo Signal Processing for Joint Sensing and Communication","date":"2024-06-10","arxiv_id":"2406.06024","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoregressive-diffusion-transformer-for-text","title":"Autoregressive Diffusion Transformer for Text-to-Speech Synthesis","date":"2024-06-08","arxiv_id":"2406.05551","repositories_listed":0,"syntology":null},{"url":null,"slug":"nacala-roof-material-drone-imagery-for-roof","title":"Nacala-Roof-Material: Drone Imagery for Roof Detection, Classification, and Segmentation to Support Mosquito-borne Disease Risk Assessment","date":"2024-06-07","arxiv_id":"2406.04949","repositories_listed":0,"syntology":null},{"url":null,"slug":"sc2-towards-enhancing-content-preservation","title":"SC2: Towards Enhancing Content Preservation and Style Consistency in Long Text Style Transfer","date":"2024-06-07","arxiv_id":"2406.04578","repositories_listed":0,"syntology":null},{"url":null,"slug":"food-facial-authentication-and-out-of","title":"FOOD: Facial Authentication and Out-of-Distribution Detection with Short-Range FMCW Radar","date":"2024-06-06","arxiv_id":"2406.04546","repositories_listed":0,"syntology":null},{"url":null,"slug":"mambadepth-enhancing-long-range-dependency","title":"MambaDepth: Enhancing Long-range Dependency for Self-Supervised Fine-Structured Monocular Depth Estimation","date":"2024-06-06","arxiv_id":"2406.04532","repositories_listed":0,"syntology":null},{"url":null,"slug":"polyp-and-surgical-instrument-segmentation","title":"Polyp and Surgical Instrument Segmentation with Double Encoder-Decoder Networks","date":"2024-06-06","arxiv_id":"2406.03901","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformers-need-glasses-information-over","title":"Transformers need glasses! Information over-squashing in language tasks","date":"2024-06-06","arxiv_id":"2406.04267","repositories_listed":0,"syntology":null},{"url":null,"slug":"4d-asr-joint-beam-search-integrating-ctc","title":"Joint Beam Search Integrating CTC, Attention, and Transducer Decoders","date":"2024-06-05","arxiv_id":"2406.02950","repositories_listed":0,"syntology":null},{"url":null,"slug":"fils-self-supervised-video-feature-prediction","title":"FILS: Self-Supervised Video Feature Prediction In Semantic Language Space","date":"2024-06-05","arxiv_id":"2406.03447","repositories_listed":0,"syntology":null},{"url":null,"slug":"maginet-mask-aware-graph-imputation-network","title":"MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data","date":"2024-06-05","arxiv_id":"2406.03511","repositories_listed":0,"syntology":null},{"url":null,"slug":"modabs-multi-objective-learning-for-dynamic","title":"MODABS: Multi-Objective Learning for Dynamic Aspect-Based Summarization","date":"2024-06-05","arxiv_id":"2406.03479","repositories_listed":0,"syntology":null},{"url":null,"slug":"discrete-multimodal-transformers-with-a","title":"Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing","date":"2024-06-04","arxiv_id":"2406.06582","repositories_listed":0,"syntology":null},{"url":null,"slug":"keyword-guided-adaptation-of-automatic-speech","title":"Keyword-Guided Adaptation of Automatic Speech Recognition","date":"2024-06-04","arxiv_id":"2406.02649","repositories_listed":0,"syntology":null},{"url":null,"slug":"nutrition-estimation-for-dietary-management-a","title":"Nutrition Estimation for Dietary Management: A Transformer Approach with Depth Sensing","date":"2024-06-04","arxiv_id":"2406.01938","repositories_listed":0,"syntology":null},{"url":null,"slug":"short-term-inland-vessel-trajectory","title":"Short-term Inland Vessel Trajectory Prediction with Encoder-Decoder Models","date":"2024-06-04","arxiv_id":"2406.02770","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-out-of-distribution-detection-in","title":"Towards Out-of-Distribution Detection in Vocoder Recognition via Latent Feature Reconstruction","date":"2024-06-04","arxiv_id":"2406.02233","repositories_listed":0,"syntology":null},{"url":null,"slug":"ua-track-uncertainty-aware-end-to-end-3d","title":"S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking","date":"2024-06-04","arxiv_id":"2406.02147","repositories_listed":0,"syntology":null},{"url":"/paper/3d-wholebody-pose-estimation-based-on-1","slug":"3d-wholebody-pose-estimation-based-on-1","title":"3D WholeBody Pose Estimation based on Semantic Graph Attention Network and Distance Information","date":"2024-06-03","arxiv_id":"2406.01196","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-play-atari-in-a-world-of-tokens","title":"Learning to Play Atari in a World of Tokens","date":"2024-06-03","arxiv_id":"2406.01361","repositories_listed":0,"syntology":null},{"url":null,"slug":"patch-based-encoder-decoder-architecture-for","title":"Patch-Based Encoder-Decoder Architecture for Automatic Transmitted Light to Fluorescence Imaging Transition: Contribution to the LightMyCells Challenge","date":"2024-06-03","arxiv_id":"2406.01187","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-inference-explaining-decoder-only","title":"Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions","date":"2024-06-03","arxiv_id":"2406.02625","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-to-sequence-multi-modal-speech-in","title":"Sequence-to-Sequence Multi-Modal Speech In-Painting","date":"2024-06-03","arxiv_id":"2406.01321","repositories_listed":0,"syntology":null},{"url":null,"slug":"ccf-cross-correcting-framework-for-pedestrian","title":"CCF: Cross Correcting Framework for Pedestrian Trajectory Prediction","date":"2024-06-02","arxiv_id":"2406.00749","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-fast-cognitive-signal-decoding-with","title":"D-FaST: Cognitive Signal Decoding with Disentangled Frequency-Spatial-Temporal Attention","date":"2024-06-02","arxiv_id":"2406.02602","repositories_listed":0,"syntology":null},{"url":null,"slug":"t2lm-long-term-3d-human-motion-generation","title":"T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences","date":"2024-06-02","arxiv_id":"2406.00636","repositories_listed":0,"syntology":null},{"url":null,"slug":"coded-computing-a-learning-theoretic","title":"Coded Computing for Resilient Distributed Computing: A Learning-Theoretic Framework","date":"2024-06-01","arxiv_id":"2406.00300","repositories_listed":0,"syntology":null},{"url":null,"slug":"henasy-learning-to-assemble-scene-entities","title":"HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model","date":"2024-06-01","arxiv_id":"2406.00307","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-attention-based-multi-context","title":"An Attention-Based Multi-Context Convolutional Encoder-Decoder Neural Network for Work Zone Traffic Impact Prediction","date":"2024-05-31","arxiv_id":"2405.21045","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-iterated-learning-model-of-language-change","title":"An iterated learning model of language change that mixes supervised and unsupervised learning","date":"2024-05-31","arxiv_id":"2405.20818","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-estimate-system-specifications-in","title":"Learning to Estimate System Specifications in Linear Temporal Logic using Transformers and Mamba","date":"2024-05-31","arxiv_id":"2405.20917","repositories_listed":0,"syntology":null},{"url":null,"slug":"malt-multi-scale-action-learning-transformer","title":"MALT: Multi-scale Action Learning Transformer for Online Action Detection","date":"2024-05-31","arxiv_id":"2405.20892","repositories_listed":0,"syntology":null},{"url":null,"slug":"textual-inversion-and-self-supervised","title":"Textual Inversion and Self-supervised Refinement for Radiology Report Generation","date":"2024-05-31","arxiv_id":"2405.20607","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hardware-efficient-emg-decoder-with-an","title":"Hardware-Efficient EMG Decoding for Next-Generation Hand Prostheses","date":"2024-05-30","arxiv_id":"2405.20052","repositories_listed":0,"syntology":null},{"url":null,"slug":"soft-partitioning-of-latent-space-for","title":"Soft Partitioning of Latent Space for Semantic Channel Equalization","date":"2024-05-30","arxiv_id":"2405.20085","repositories_listed":0,"syntology":null},{"url":null,"slug":"stratified-avatar-generation-from-sparse","title":"Stratified Avatar Generation from Sparse Observations","date":"2024-05-30","arxiv_id":"2405.20786","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-encoder-decoder-structures-in","title":"Understanding Encoder-Decoder Structures in Machine Learning Using Information Measures","date":"2024-05-30","arxiv_id":"2405.20452","repositories_listed":0,"syntology":null},{"url":null,"slug":"llama-reg-using-llama-2-for-unsupervised","title":"LLaMA-Reg: Using LLaMA 2 for Unsupervised Medical Image Registration","date":"2024-05-29","arxiv_id":"2405.18774","repositories_listed":0,"syntology":null},{"url":null,"slug":"monde-mixture-of-near-data-experts-for-large","title":"MoNDE: Mixture of Near-Data Experts for Large-Scale Sparse Models","date":"2024-05-29","arxiv_id":"2405.18832","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-channel-multi-step-spectrum-prediction","title":"Multi-Channel Multi-Step Spectrum Prediction Using Transformer and Stacked Bi-LSTM","date":"2024-05-29","arxiv_id":"2405.19138","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-generative-embedding-model","title":"Multi-Modal Generative Embedding Model","date":"2024-05-29","arxiv_id":"2405.19333","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-regularised-reinforcement-learning","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","date":"2024-05-29","arxiv_id":"2405.19107","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-foundation-model-inference-on-a","title":"Optimizing Foundation Model Inference on a Many-tiny-core Open-source RISC-V Platform","date":"2024-05-29","arxiv_id":"2405.19284","repositories_listed":0,"syntology":null},{"url":null,"slug":"stat-shrinking-transformers-after-training","title":"STAT: Shrinking Transformers After Training","date":"2024-05-29","arxiv_id":"2406.00061","repositories_listed":0,"syntology":null},{"url":null,"slug":"zipper-a-multi-tower-decoder-architecture-for","title":"Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities","date":"2024-05-29","arxiv_id":"2405.18669","repositories_listed":0,"syntology":null},{"url":null,"slug":"finercut-finer-grained-interpretable-layer","title":"FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models","date":"2024-05-28","arxiv_id":"2405.18218","repositories_listed":0,"syntology":null},{"url":null,"slug":"implicitly-guided-design-with-propen-match","title":"Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient","date":"2024-05-28","arxiv_id":"2405.18075","repositories_listed":0,"syntology":null},{"url":null,"slug":"tooncrafter-generative-cartoon-interpolation","title":"ToonCrafter: Generative Cartoon Interpolation","date":"2024-05-28","arxiv_id":"2405.17933","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-one-layer-decoder-only-transformer-is-a-two","title":"A One-Layer Decoder-Only Transformer is a Two-Layer RNN: With an Application to Certified Robustness","date":"2024-05-27","arxiv_id":"2405.17361","repositories_listed":0,"syntology":null},{"url":null,"slug":"beamvq-aligning-space-time-forecasting-model","title":"BeamVQ: Aligning Space-Time Forecasting Model via Self-training on Physics-aware Metrics","date":"2024-05-27","arxiv_id":"2405.17051","repositories_listed":0,"syntology":null},{"url":null,"slug":"behaviorgpt-smart-agent-simulation-for","title":"BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction","date":"2024-05-27","arxiv_id":"2405.17372","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-the-layered-intrinsic","title":"Exploiting the Layered Intrinsic Dimensionality of Deep Models for Practical Adversarial Training","date":"2024-05-27","arxiv_id":"2405.17130","repositories_listed":0,"syntology":null},{"url":null,"slug":"listenable-maps-for-zero-shot-audio","title":"Listenable Maps for Zero-Shot Audio Classifiers","date":"2024-05-27","arxiv_id":"2405.17615","repositories_listed":0,"syntology":null},{"url":null,"slug":"selfcp-compressing-long-prompt-to-1-12-using","title":"SelfCP: Compressing Over-Limit Prompt via the Frozen Large Language Model Itself","date":"2024-05-27","arxiv_id":"2405.17052","repositories_listed":0,"syntology":null},{"url":null,"slug":"uit-darkcow-team-at-imageclefmedical-caption","title":"UIT-DarkCow team at ImageCLEFmedical Caption 2024: Diagnostic Captioning for Radiology Images Efficiency with Transformer Models","date":"2024-05-27","arxiv_id":"2405.17002","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-and-language-navigation-generative","title":"Vision-and-Language Navigation Generative Pretrained Transformer","date":"2024-05-27","arxiv_id":"2405.16994","repositories_listed":0,"syntology":null},{"url":null,"slug":"acceleration-of-grokking-in-learning","title":"Acceleration of Grokking in Learning Arithmetic Operations via Kolmogorov-Arnold Representation","date":"2024-05-26","arxiv_id":"2405.16658","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-enhanced-encoder-decoder-network","title":"An Enhanced Encoder-Decoder Network Architecture for Reducing Information Loss in Image Semantic Segmentation","date":"2024-05-26","arxiv_id":"2406.01605","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-pre-trained-large-language","title":"Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks","date":"2024-05-24","arxiv_id":"2405.15453","repositories_listed":0,"syntology":null},{"url":null,"slug":"blaze3dm-marry-triplane-representation-with","title":"Blaze3DM: Marry Triplane Representation with Diffusion for 3D Medical Inverse Problem Solving","date":"2024-05-24","arxiv_id":"2405.15241","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-light-video-enhancement-via-spatial","title":"Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition","date":"2024-05-24","arxiv_id":"2405.15660","repositories_listed":0,"syntology":null},{"url":null,"slug":"bitune-bidirectional-instruction-tuning","title":"Bitune: Bidirectional Instruction-Tuning","date":"2024-05-23","arxiv_id":"2405.14862","repositories_listed":0,"syntology":null},{"url":null,"slug":"hc-gae-the-hierarchical-cluster-based-graph","title":"HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning","date":"2024-05-23","arxiv_id":"2405.14742","repositories_listed":0,"syntology":null},{"url":null,"slug":"litevae-lightweight-and-efficient-variational","title":"LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models","date":"2024-05-23","arxiv_id":"2405.14477","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-example-selection-for-retrieval","title":"Optimizing example selection for retrieval-augmented machine translation with translation memories","date":"2024-05-23","arxiv_id":"2405.15070","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-and-accurate-zero-shot-high","title":"Real-Time and Accurate: Zero-shot High-Fidelity Singing Voice Conversion with Multi-Condition Flow Synthesis","date":"2024-05-23","arxiv_id":"2405.15093","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-posterior-stability-for-time","title":"A Study of Posterior Stability for Time-Series Latent Diffusion","date":"2024-05-22","arxiv_id":"2405.14021","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-transformer-variant-for-multi-step","title":"A Transformer variant for multi-step forecasting of water level and hydrometeorological sensitivity analysis based on explainable artificial intelligence technology","date":"2024-05-22","arxiv_id":"2405.13646","repositories_listed":0,"syntology":null},{"url":null,"slug":"cg-fedllm-how-to-compress-gradients-in","title":"CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models","date":"2024-05-22","arxiv_id":"2405.13746","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-many-bytes-can-you-take-out-of-brain-to","title":"How Many Bytes Can You Take Out Of Brain-To-Text Decoding?","date":"2024-05-22","arxiv_id":"2405.14055","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-optimization-of-streaming-and-non","title":"Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation","date":"2024-05-22","arxiv_id":"2405.13514","repositories_listed":0,"syntology":null},{"url":null,"slug":"magic-map-guided-few-shot-audio-visual","title":"MAGIC: Map-Guided Few-Shot Audio-Visual Acoustics Modeling","date":"2024-05-22","arxiv_id":"2405.13860","repositories_listed":0,"syntology":null},{"url":null,"slug":"rank-reduction-autoencoders-enhancing","title":"Rank Reduction Autoencoders","date":"2024-05-22","arxiv_id":"2405.13980","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-laws-for-large-time-series-models","title":"Scaling-laws for Large Time-series Models","date":"2024-05-22","arxiv_id":"2405.13867","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-agnostic-decision-transformer-for-multi","title":"Task-agnostic Decision Transformer for Multi-type Agent Control with Federated Split Training","date":"2024-05-22","arxiv_id":"2405.13445","repositories_listed":0,"syntology":null},{"url":null,"slug":"customtext-customized-textual-image","title":"CustomText: Customized Textual Image Generation using Diffusion Models","date":"2024-05-21","arxiv_id":"2405.12531","repositories_listed":0,"syntology":null},{"url":null,"slug":"face-adapter-for-pre-trained-diffusion-models","title":"Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control","date":"2024-05-21","arxiv_id":"2405.12970","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-local-detail-guided-transformer-for","title":"Global-Local Detail Guided Transformer for Sea Ice Recognition in Optical Remote Sensing Images","date":"2024-05-21","arxiv_id":"2405.13197","repositories_listed":0,"syntology":null},{"url":null,"slug":"reallm-a-general-framework-for-llm","title":"ReALLM: A general framework for LLM compression and fine-tuning","date":"2024-05-21","arxiv_id":"2405.13155","repositories_listed":0,"syntology":null},{"url":null,"slug":"typeii-csinet-csi-feedback-with-typeii","title":"TypeII-CsiNet: CSI Feedback with TypeII Codebook","date":"2024-05-21","arxiv_id":"2405.12569","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-constraint-enforcing-reward-for-adversarial","title":"A Constraint-Enforcing Reward for Adversarial Attacks on Text Classifiers","date":"2024-05-20","arxiv_id":"2405.11904","repositories_listed":0,"syntology":null},{"url":null,"slug":"embsum-leveraging-the-summarization","title":"EmbSum: Leveraging the Summarization Capabilities of Large Language Models for Content-Based Recommendations","date":"2024-05-19","arxiv_id":"2405.11441","repositories_listed":0,"syntology":null},{"url":null,"slug":"micap-a-unified-model-for-identity-aware","title":"MICap: A Unified Model for Identity-aware Movie Descriptions","date":"2024-05-19","arxiv_id":"2405.11483","repositories_listed":0,"syntology":null},{"url":"/paper/unifying-3d-vision-language-understanding-via","slug":"unifying-3d-vision-language-understanding-via","title":"Unifying 3D Vision-Language Understanding via Promptable Queries","date":"2024-05-19","arxiv_id":"2405.11442","repositories_listed":0,"syntology":null},{"url":null,"slug":"fuse-calibrate-a-bi-directional-vision","title":"Fuse & Calibrate: A bi-directional Vision-Language Guided Framework for Referring Image Segmentation","date":"2024-05-18","arxiv_id":"2405.11205","repositories_listed":0,"syntology":null},{"url":null,"slug":"planttracing-tracing-arabidopsis-thaliana","title":"PlantTracing: Tracing Arabidopsis Thaliana Apex with CenterTrack","date":"2024-05-18","arxiv_id":"2405.11351","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-and-explaining-hearing-aid-usage","title":"Predicting and Explaining Hearing Aid Usage Using Encoder-Decoder with Attention Mechanism and SHAP","date":"2024-05-18","arxiv_id":"2405.11275","repositories_listed":0,"syntology":null},{"url":null,"slug":"coregan-contrastive-regularized-generative","title":"CoReGAN: Contrastive Regularized Generative Adversarial Network for Guided Depth Map Super Resolution","date":"2024-05-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"duospacenet-leveraging-both-bird-s-eye-view","title":"DuoSpaceNet: Leveraging Both Bird's-Eye-View and Perspective View Representations for 3D Object Detection","date":"2024-05-17","arxiv_id":"2405.10577","repositories_listed":0,"syntology":null},{"url":null,"slug":"geocc-geometrically-enhanced-3d-occupancy","title":"GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision","date":"2024-05-17","arxiv_id":"2405.10591","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-semantic-prior-features-guided","title":"Multi-scale Semantic Prior Features Guided Deep Neural Network for Urban Street-view Image","date":"2024-05-17","arxiv_id":"2405.10504","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-deep-learning-of-myocardium","title":"Simultaneous Deep Learning of Myocardium Segmentation and T2 Quantification for Acute Myocardial Infarction MRI","date":"2024-05-17","arxiv_id":"2405.10570","repositories_listed":0,"syntology":null},{"url":null,"slug":"specialising-and-analysing-instruction-tuned","title":"Specialising and Analysing Instruction-Tuned and Byte-Level Language Models for Organic Reaction Prediction","date":"2024-05-17","arxiv_id":"2405.10625","repositories_listed":0,"syntology":null}],"record_sha256":"92b26c5ad974293c86c996bd4ef16d7297a15884ed1203334350e0e281376e2b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}