{"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/51","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":51,"pages_in_order":104,"rows_per_page":100,"rows":[5001,5100],"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/50","next":"/task/decoder/papers/52","papers":[{"url":null,"slug":"analyzing-context-contributions-in-llm-based","title":"Analyzing Context Contributions in LLM-based Machine Translation","date":"2024-10-21","arxiv_id":"2410.16246","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-pretraining-via-active-forgetting","title":"Exploring Pretraining via Active Forgetting for Improving Cross Lingual Transfer for Decoder Language Models","date":"2024-10-21","arxiv_id":"2410.16168","repositories_listed":0,"syntology":null},{"url":null,"slug":"haheae-learning-generalisable-joint","title":"HaHeAE: Learning Generalisable Joint Representations of Human Hand and Head Movements in Extended Reality","date":"2024-10-21","arxiv_id":"2410.16430","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-search-space-in-gboard-decoder","title":"Neural Search Space in Gboard Decoder","date":"2024-10-21","arxiv_id":"2410.15575","repositories_listed":0,"syntology":null},{"url":null,"slug":"seadag-semi-autoregressive-diffusion-for","title":"SeaDAG: Semi-autoregressive Diffusion for Conditional Directed Acyclic Graph Generation","date":"2024-10-21","arxiv_id":"2410.16119","repositories_listed":0,"syntology":null},{"url":null,"slug":"slic-secure-learned-image-codec-through","title":"SLIC: Secure Learned Image Codec through Compressed Domain Watermarking to Defend Image Manipulation","date":"2024-10-19","arxiv_id":"2410.15075","repositories_listed":0,"syntology":null},{"url":null,"slug":"extreme-precipitation-nowcasting-using-multi","title":"Extreme Precipitation Nowcasting using Multi-Task Latent Diffusion Models","date":"2024-10-18","arxiv_id":"2410.14103","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymkv-enabling-1-bit-quantization-of-kv","title":"AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations","date":"2024-10-17","arxiv_id":"2410.13212","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-augmented-predictive-deep-neural-network","title":"Data-Augmented Predictive Deep Neural Network: Enhancing the extrapolation capabilities of non-intrusive surrogate models","date":"2024-10-17","arxiv_id":"2410.13376","repositories_listed":0,"syntology":null},{"url":"/paper/improving-multi-modal-large-language-model","slug":"improving-multi-modal-large-language-model","title":"Improving Multi-modal Large Language Model through Boosting Vision Capabilities","date":"2024-10-17","arxiv_id":"2410.13733","repositories_listed":0,"syntology":null},{"url":null,"slug":"aero-softmax-only-llms-for-efficient-private","title":"AERO: Softmax-Only LLMs for Efficient Private Inference","date":"2024-10-16","arxiv_id":"2410.13060","repositories_listed":0,"syntology":null},{"url":null,"slug":"cascade-learning-in-multi-task-encoder","title":"Cascade learning in multi-task encoder-decoder networks for concurrent bone segmentation and glenohumeral joint assessment in shoulder CT scans","date":"2024-10-16","arxiv_id":"2410.12641","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-efficient-and-tensorized","title":"Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models","date":"2024-10-16","arxiv_id":"2410.13097","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-much-do-contextualized-representations","title":"How much do contextualized representations encode long-range context?","date":"2024-10-16","arxiv_id":"2410.12292","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-role-of-activation-functions-in-eeg-to","title":"On the Role of Activation Functions in EEG-To-Text Decoder","date":"2024-10-16","arxiv_id":"2410.12572","repositories_listed":0,"syntology":null},{"url":null,"slug":"sifisinger-a-high-fidelity-end-to-end-singing","title":"SiFiSinger: A High-Fidelity End-to-End Singing Voice Synthesizer based on Source-filter Model","date":"2024-10-16","arxiv_id":"2410.12536","repositories_listed":0,"syntology":null},{"url":null,"slug":"test-time-adaptation-for-image-compression","title":"Test-time adaptation for image compression with distribution regularization","date":"2024-10-16","arxiv_id":"2410.12191","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-arbitrary-qubo-optimization-analysis","title":"Towards Arbitrary QUBO Optimization: Analysis of Classical and Quantum-Activated Feedforward Neural Networks","date":"2024-10-16","arxiv_id":"2410.12636","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-on-multi-dimensional-data-a","title":"Transfer Learning on Multi-Dimensional Data: A Novel Approach to Neural Network-Based Surrogate Modeling","date":"2024-10-16","arxiv_id":"2410.12241","repositories_listed":0,"syntology":null},{"url":null,"slug":"spiking-neural-belief-propagation-decoder-for","title":"Spiking Neural Belief Propagation Decoder for Short Block Length LDPC Codes","date":"2024-10-15","arxiv_id":"2410.11543","repositories_listed":0,"syntology":null},{"url":null,"slug":"trajectory-prediction-for-autonomous-driving-2","title":"Trajectory Prediction for Autonomous Driving using Agent-Interaction Graph Embedding","date":"2024-10-15","arxiv_id":"2410.23298","repositories_listed":0,"syntology":null},{"url":null,"slug":"umambatsf-a-u-shaped-multi-scale-long-term","title":"UmambaTSF: A U-shaped Multi-Scale Long-Term Time Series Forecasting Method Using Mamba","date":"2024-10-15","arxiv_id":"2410.11278","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-ground-vlms-without-forgetting","title":"Learning to Ground VLMs without Forgetting","date":"2024-10-14","arxiv_id":"2410.10491","repositories_listed":0,"syntology":null},{"url":null,"slug":"lisac-learned-coded-waveform-design-for-isac","title":"LISAC: Learned Coded Waveform Design for ISAC with OFDM","date":"2024-10-14","arxiv_id":"2410.10711","repositories_listed":0,"syntology":null},{"url":null,"slug":"lkaseg-remote-sensing-image-semantic","title":"LKASeg:Remote-Sensing Image Semantic Segmentation with Large Kernel Attention and Full-Scale Skip Connections","date":"2024-10-14","arxiv_id":"2410.10433","repositories_listed":0,"syntology":null},{"url":null,"slug":"pubic-symphysis-fetal-head-segmentation","title":"Pubic Symphysis-Fetal Head Segmentation Network Using BiFormer Attention Mechanism and Multipath Dilated Convolution","date":"2024-10-14","arxiv_id":"2410.10352","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-transformer-based-generative-chemical","title":"A Transformer Based Generative Chemical Language AI Model for Structural Elucidation of Organic Compounds","date":"2024-10-13","arxiv_id":"2410.14719","repositories_listed":0,"syntology":null},{"url":null,"slug":"am-sam-automated-prompting-and-mask","title":"AM-SAM: Automated Prompting and Mask Calibration for Segment Anything Model","date":"2024-10-13","arxiv_id":"2410.09714","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-kan-effective-for-identifying-and","title":"WormKAN: Are KAN Effective for Identifying and Tracking Concept Drift in Time Series?","date":"2024-10-13","arxiv_id":"2410.10041","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-scene-dynamics-a-generative","title":"Compressing Scene Dynamics: A Generative Approach","date":"2024-10-13","arxiv_id":"2410.09768","repositories_listed":0,"syntology":null},{"url":"/paper/leveraging-customer-feedback-for-multi-modal","slug":"leveraging-customer-feedback-for-multi-modal","title":"Leveraging Customer Feedback for Multi-modal Insight Extraction","date":"2024-10-13","arxiv_id":"2410.09999","repositories_listed":0,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/leveraging-customer-feedback-for-multi-modal#ran","syntology_url":"https://syntology.ai/paper/2410.09999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09999"}},"official":null}},{"url":null,"slug":"controlrm-fast-and-controllable-3d-generation","title":"ControLRM: Fast and Controllable 3D Generation via Large Reconstruction Model","date":"2024-10-12","arxiv_id":"2410.09592","repositories_listed":0,"syntology":null},{"url":null,"slug":"gem-vpc-a-dual-graph-enhanced-multimodal","title":"GEM-VPC: A dual Graph-Enhanced Multimodal integration for Video Paragraph Captioning","date":"2024-10-12","arxiv_id":"2410.09377","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-sam-based-tool-for-semi-automatic-food","title":"A SAM based Tool for Semi-Automatic Food Annotation","date":"2024-10-11","arxiv_id":"2410.19756","repositories_listed":0,"syntology":null},{"url":null,"slug":"extra-global-attention-designation-using","title":"Extra Global Attention Designation Using Keyword Detection in Sparse Transformer Architectures","date":"2024-10-11","arxiv_id":"2410.08971","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-chip-learning-via-transformer-in-context","title":"On-Chip Learning via Transformer In-Context Learning","date":"2024-10-11","arxiv_id":"2410.08711","repositories_listed":0,"syntology":null},{"url":null,"slug":"path-minimizing-latent-odes-for-improved","title":"Path-minimizing Latent ODEs for improved extrapolation and inference","date":"2024-10-11","arxiv_id":"2410.08923","repositories_listed":0,"syntology":null},{"url":null,"slug":"spikebottlenet-energy-efficient-spike-neural","title":"SpikeBottleNet: Spike-Driven Feature Compression Architecture for Edge-Cloud Co-Inference","date":"2024-10-11","arxiv_id":"2410.08673","repositories_listed":0,"syntology":null},{"url":null,"slug":"videosam-open-world-video-segmentation","title":"VideoSAM: Open-World Video Segmentation","date":"2024-10-11","arxiv_id":"2410.08781","repositories_listed":0,"syntology":null},{"url":null,"slug":"mechanistic-permutability-match-features","title":"Mechanistic Permutability: Match Features Across Layers","date":"2024-10-10","arxiv_id":"2410.07656","repositories_listed":0,"syntology":null},{"url":null,"slug":"morcode-face-morphing-attack-generation-using","title":"MorCode: Face Morphing Attack Generation using Generative Codebooks","date":"2024-10-10","arxiv_id":"2410.07625","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-representation-learning-for","title":"Scalable Representation Learning for Multimodal Tabular Transactions","date":"2024-10-10","arxiv_id":"2410.07851","repositories_listed":0,"syntology":null},{"url":null,"slug":"test-time-intensity-consistency-adaptation","title":"Test-Time Intensity Consistency Adaptation for Shadow Detection","date":"2024-10-10","arxiv_id":"2410.07695","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-transformers-reason-logically-a-study-in","title":"Can Transformers Reason Logically? A Study in SAT Solving","date":"2024-10-09","arxiv_id":"2410.07432","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-better-language-models-have-crisper-vision","title":"Do better language models have crisper vision?","date":"2024-10-09","arxiv_id":"2410.07173","repositories_listed":0,"syntology":null},{"url":null,"slug":"inattention-linear-context-scaling-for","title":"InAttention: Linear Context Scaling for Transformers","date":"2024-10-09","arxiv_id":"2410.07063","repositories_listed":0,"syntology":null},{"url":null,"slug":"root-defence-strategies-ensuring-safety-of","title":"Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level","date":"2024-10-09","arxiv_id":"2410.06809","repositories_listed":0,"syntology":null},{"url":null,"slug":"broadway-boost-your-text-to-video-generation","title":"BroadWay: Boost Your Text-to-Video Generation Model in a Training-free Way","date":"2024-10-08","arxiv_id":"2410.06241","repositories_listed":0,"syntology":null},{"url":null,"slug":"gesture2text-a-generalizable-decoder-for-word","title":"Gesture2Text: A Generalizable Decoder for Word-Gesture Keyboards in XR Through Trajectory Coarse Discretization and Pre-training","date":"2024-10-08","arxiv_id":"2410.18099","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-embedding-accuracy-for-document","title":"Improving Embedding Accuracy for Document Retrieval Using Entity Relationship Maps and Model-Aware Contrastive Sampling","date":"2024-10-08","arxiv_id":"2410.18105","repositories_listed":0,"syntology":null},{"url":"/paper/label-confidence-weighted-learning-for-target","slug":"label-confidence-weighted-learning-for-target","title":"Label Confidence Weighted Learning for Target-level Sentence Simplification","date":"2024-10-08","arxiv_id":"2410.05748","repositories_listed":0,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/label-confidence-weighted-learning-for-target#ran","syntology_url":"https://syntology.ai/paper/2410.05748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05748"}},"official":null}},{"url":null,"slug":"rradistill-distilling-llms-passage-ranking","title":"RRADistill: Distilling LLMs' Passage Ranking Ability for Long-Tail Queries Document Re-Ranking on a Search Engine","date":"2024-10-08","arxiv_id":"2410.18097","repositories_listed":0,"syntology":null},{"url":null,"slug":"control-oriented-clustering-of-visual-latent","title":"Control-oriented Clustering of Visual Latent Representation","date":"2024-10-07","arxiv_id":"2410.05063","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-transformer-with-reinforced","title":"Efficient transformer with reinforced position embedding for language models","date":"2024-10-07","arxiv_id":"2410.04731","repositories_listed":0,"syntology":null},{"url":null,"slug":"masked-autoencoder-with-swin-transformer","title":"Masked Autoencoder with Swin Transformer Network for Mitigating Electrode Shift in HD-EMG-based Gesture Recognition","date":"2024-10-07","arxiv_id":"2410.17261","repositories_listed":0,"syntology":null},{"url":null,"slug":"damro-dive-into-the-attention-mechanism-of","title":"DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination","date":"2024-10-06","arxiv_id":"2410.04514","repositories_listed":0,"syntology":null},{"url":null,"slug":"mecformer-multi-task-whole-slide-image","title":"MECFormer: Multi-task Whole Slide Image Classification with Expert Consultation Network","date":"2024-10-06","arxiv_id":"2410.04507","repositories_listed":0,"syntology":null},{"url":null,"slug":"od-stega-llm-based-near-imperceptible","title":"OD-Stega: LLM-Based Near-Imperceptible Steganography via Optimized Distributions","date":"2024-10-06","arxiv_id":"2410.04328","repositories_listed":0,"syntology":null},{"url":null,"slug":"e-vae-denoising-as-visual-decoding","title":"Epsilon-VAE: Denoising as Visual Decoding","date":"2024-10-05","arxiv_id":"2410.04081","repositories_listed":0,"syntology":null},{"url":null,"slug":"error-correction-code-transformer-from-non","title":"Error Correction Code Transformer: From Non-Unified to Unified","date":"2024-10-04","arxiv_id":"2410.03364","repositories_listed":0,"syntology":null},{"url":null,"slug":"hatformer-historic-handwritten-arabic-text","title":"HATFormer: Historic Handwritten Arabic Text Recognition with Transformers","date":"2024-10-03","arxiv_id":"2410.02179","repositories_listed":0,"syntology":null},{"url":null,"slug":"key-grid-unsupervised-3d-keypoints-detection","title":"Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features","date":"2024-10-03","arxiv_id":"2410.02237","repositories_listed":0,"syntology":null},{"url":null,"slug":"comuni-decomposing-common-and-unique-video","title":"COMUNI: Decomposing Common and Unique Video Signals for Diffusion-based Video Generation","date":"2024-10-02","arxiv_id":"2410.01718","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-streaming-llm-for-speech","title":"Efficient Streaming LLM for Speech Recognition","date":"2024-10-02","arxiv_id":"2410.03752","repositories_listed":0,"syntology":null},{"url":null,"slug":"entp-encoder-only-next-token-prediction","title":"ENTP: Encoder-only Next Token Prediction","date":"2024-10-02","arxiv_id":"2410.01600","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-adaptation-of-unlimiformer-for-decoder","title":"On The Adaptation of Unlimiformer for Decoder-Only Transformers","date":"2024-10-02","arxiv_id":"2410.01637","repositories_listed":0,"syntology":null},{"url":null,"slug":"pertok-expressive-encoding-and-modeling-of","title":"PerTok: Expressive Encoding and Modeling of Symbolic Musical Ideas and Variations","date":"2024-10-02","arxiv_id":"2410.02060","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-transformer-based-deep-reinforcement","title":"A transformer-based deep reinforcement learning approach to spatial navigation in a partially observable Morris Water Maze","date":"2024-10-01","arxiv_id":"2410.12820","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-medical-radiograph-representation","title":"Advancing Medical Radiograph Representation Learning: A Hybrid Pre-training Paradigm with Multilevel Semantic Granularity","date":"2024-10-01","arxiv_id":"2410.00448","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-the-synergistic-effects-of","title":"Investigating the Synergistic Effects of Dropout and Residual Connections on Language Model Training","date":"2024-10-01","arxiv_id":"2410.01019","repositories_listed":0,"syntology":null},{"url":null,"slug":"restoring-super-high-resolution-gps-mobility","title":"Restoring Super-High Resolution GPS Mobility Data","date":"2024-10-01","arxiv_id":"2410.12818","repositories_listed":0,"syntology":null},{"url":null,"slug":"spherical-analysis-of-learning-nonlinear","title":"Spherical Analysis of Learning Nonlinear Functionals","date":"2024-10-01","arxiv_id":"2410.01047","repositories_listed":0,"syntology":null},{"url":null,"slug":"stanh-parametric-quantization-for-variable","title":"STanH : Parametric Quantization for Variable Rate Learned Image Compression","date":"2024-10-01","arxiv_id":"2410.00557","repositories_listed":0,"syntology":null},{"url":null,"slug":"timesync-temporal-intent-modelling-with","title":"TIMeSynC: Temporal Intent Modelling with Synchronized Context Encodings for Financial Service Applications","date":"2024-10-01","arxiv_id":"2410.12825","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-speech-recognition-and-end-of","title":"Predictive Speech Recognition and End-of-Utterance Detection Towards Spoken Dialog Systems","date":"2024-09-30","arxiv_id":"2409.19990","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-medical-image-representation","title":"Universal Medical Image Representation Learning with Compositional Decoders","date":"2024-09-30","arxiv_id":"2409.19890","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-attention-frequency-fusion-at-multi","title":"Dual-Attention Frequency Fusion at Multi-Scale for Joint Segmentation and Deformable Medical Image Registration","date":"2024-09-29","arxiv_id":"2409.19658","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-long-form-speech-recognition-for","title":"Efficient Long-Form Speech Recognition for General Speech In-Context Learning","date":"2024-09-29","arxiv_id":"2409.19757","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-aligned-network-for-referring-image","title":"Fully Aligned Network for Referring Image Segmentation","date":"2024-09-29","arxiv_id":"2409.19569","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuromax-enhancing-neural-topic-modeling-via","title":"NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization","date":"2024-09-29","arxiv_id":"2409.19749","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-encoding-and-decoding-for-implicit-video","title":"Fast Encoding and Decoding for Implicit Video Representation","date":"2024-09-28","arxiv_id":"2409.19429","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-textgcn-based-decoding-approach-for","title":"A TextGCN-Based Decoding Approach for Improving Remote Sensing Image Captioning","date":"2024-09-27","arxiv_id":"2409.18467","repositories_listed":0,"syntology":null},{"url":null,"slug":"am-mteeg-multi-task-eeg-classification-based","title":"AM-MTEEG: Multi-task EEG classification based on impulsive associative memory","date":"2024-09-27","arxiv_id":"2409.18375","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-retrieval-meets-multi-graded","title":"Generative Retrieval Meets Multi-Graded Relevance","date":"2024-09-27","arxiv_id":"2409.18409","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-free-decoder-inversion-in-latent","title":"Gradient-free Decoder Inversion in Latent Diffusion Models","date":"2024-09-27","arxiv_id":"2409.18442","repositories_listed":0,"syntology":null},{"url":null,"slug":"looking-through-the-mind-s-eye-via-multimodal","title":"Looking through the mind's eye via multimodal encoder-decoder networks","date":"2024-09-27","arxiv_id":"2410.00047","repositories_listed":0,"syntology":null},{"url":null,"slug":"flowmac-conditional-flow-matching-for-audio","title":"FlowMAC: Conditional Flow Matching for Audio Coding at Low Bit Rates","date":"2024-09-26","arxiv_id":"2409.17635","repositories_listed":0,"syntology":null},{"url":null,"slug":"loopsr-looping-sim-and-real-for-lifelong","title":"LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots","date":"2024-09-26","arxiv_id":"2409.17992","repositories_listed":0,"syntology":null},{"url":null,"slug":"paraformer-v2-an-improved-non-autoregressive","title":"Paraformer-v2: An improved non-autoregressive transformer for noise-robust speech recognition","date":"2024-09-26","arxiv_id":"2409.17746","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-monocular-depth-estimation-6","title":"Self-supervised Monocular Depth Estimation with Large Kernel Attention","date":"2024-09-26","arxiv_id":"2409.17895","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-the-role-of-pretraining-in-direct","title":"Unveiling the Role of Pretraining in Direct Speech Translation","date":"2024-09-26","arxiv_id":"2409.18044","repositories_listed":0,"syntology":null},{"url":"/paper/3d-jepa-a-joint-embedding-predictive","slug":"3d-jepa-a-joint-embedding-predictive","title":"3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning","date":"2024-09-24","arxiv_id":"2409.15803","repositories_listed":0,"syntology":null},{"url":null,"slug":"dnagrinder-a-lightweight-and-high-capacity","title":"dnaGrinder: a lightweight and high-capacity genomic foundation model","date":"2024-09-24","arxiv_id":"2409.15697","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-vq-vae-with-prosody-parameters-for","title":"Exploring VQ-VAE with Prosody Parameters for Speaker Anonymization","date":"2024-09-24","arxiv_id":"2409.15882","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypothesis-clustering-and-merging-novel","title":"Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition with Speaker Tokens","date":"2024-09-24","arxiv_id":"2409.15732","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-segment-anything-model-for-unseen","title":"Adapting Segment Anything Model for Unseen Object Instance Segmentation","date":"2024-09-23","arxiv_id":"2409.15481","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-branch-feature-fusion-decoder-for","title":"Cross Branch Feature Fusion Decoder for Consistency Regularization-based Semi-Supervised Change Detection","date":"2024-09-23","arxiv_id":"2409.15021","repositories_listed":0,"syntology":null},{"url":null,"slug":"ldpc-codes-in-cooperative-communication","title":"LDPC Codes in Cooperative Communication","date":"2024-09-23","arxiv_id":"2409.15559","repositories_listed":0,"syntology":null},{"url":null,"slug":"revolutionizing-biomarker-discovery","title":"Revolutionizing Biomarker Discovery: Leveraging Generative AI for Bio-Knowledge-Embedded Continuous Space Exploration","date":"2024-09-23","arxiv_id":"2409.15612","repositories_listed":0,"syntology":null},{"url":null,"slug":"rowsformer-a-robust-watermarking-framework","title":"RoWSFormer: A Robust Watermarking Framework with Swin Transformer for Enhanced Geometric Attack Resilience","date":"2024-09-23","arxiv_id":"2409.14829","repositories_listed":0,"syntology":null}],"record_sha256":"4187f5d7e80d29137910b0534c84fc18e3ed43de22f443b66e83a130c28357d1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}