{"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/48","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":48,"pages_in_order":104,"rows_per_page":100,"rows":[4701,4800],"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/47","next":"/task/decoder/papers/49","papers":[{"url":null,"slug":"decoder-only-llms-are-better-controllers-for","title":"Decoder-Only LLMs are Better Controllers for Diffusion Models","date":"2025-02-06","arxiv_id":"2502.04412","repositories_listed":0,"syntology":null},{"url":null,"slug":"onetrack-m-a-multitask-approach-to","title":"OneTrack-M: A multitask approach to transformer-based MOT models","date":"2025-02-06","arxiv_id":"2502.04478","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-similarity-metrics-for-data","title":"Analyzing Similarity Metrics for Data Selection for Language Model Pretraining","date":"2025-02-04","arxiv_id":"2502.02494","repositories_listed":0,"syntology":null},{"url":null,"slug":"flatten-graphs-as-sequences-transformers-are","title":"Flatten Graphs as Sequences: Transformers are Scalable Graph Generators","date":"2025-02-04","arxiv_id":"2502.02216","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-human-hands-to-robotic-limbs-a-study-in","title":"From Human Hands to Robotic Limbs: A Study in Motor Skill Embodiment for Telemanipulation","date":"2025-02-04","arxiv_id":"2502.02036","repositories_listed":0,"syntology":null},{"url":null,"slug":"mosaic3d-foundation-dataset-and-model-for","title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","date":"2025-02-04","arxiv_id":"2502.02548","repositories_listed":0,"syntology":null},{"url":null,"slug":"neurons-speak-in-ranges-breaking-free-from","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","date":"2025-02-04","arxiv_id":"2502.06809","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-poisson-process-autodecoder-for-x-ray","title":"A Poisson Process AutoDecoder for X-ray Sources","date":"2025-02-03","arxiv_id":"2502.01627","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-language-models-with-posterior","title":"Scalable Language Models with Posterior Inference of Latent Thought Vectors","date":"2025-02-03","arxiv_id":"2502.01567","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-efficient-large-multimodal-model","title":"ModServe: Scalable and Resource-Efficient Large Multimodal Model Serving","date":"2025-02-02","arxiv_id":"2502.00937","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimalistic-video-saliency-prediction-via","title":"Minimalistic Video Saliency Prediction via Efficient Decoder & Spatio Temporal Action Cues","date":"2025-02-01","arxiv_id":"2502.00397","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-token-compression-a-training-free","title":"Beyond Token Compression: A Training-Free Reduction Framework for Efficient Visual Processing in MLLMs","date":"2025-01-31","arxiv_id":"2501.19036","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-for-keypoint-detection-in","title":"Transfer Learning for Keypoint Detection in Low-Resolution Thermal TUG Test Images","date":"2025-01-30","arxiv_id":"2501.18453","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-embedding-clustering-for","title":"Cross-lingual Embedding Clustering for Hierarchical Softmax in Low-Resource Multilingual Speech Recognition","date":"2025-01-29","arxiv_id":"2501.17615","repositories_listed":0,"syntology":null},{"url":null,"slug":"voiceprompter-robust-zero-shot-voice","title":"VoicePrompter: Robust Zero-Shot Voice Conversion with Voice Prompt and Conditional Flow Matching","date":"2025-01-29","arxiv_id":"2501.17612","repositories_listed":0,"syntology":null},{"url":null,"slug":"watch-your-stepp-semantic-traversability","title":"Watch Your STEPP: Semantic Traversability Estimation using Pose Projected Features","date":"2025-01-29","arxiv_id":"2501.17594","repositories_listed":0,"syntology":null},{"url":null,"slug":"cardicat-a-variational-autoencoder-for-high","title":"CardiCat: a Variational Autoencoder for High-Cardinality Tabular Data","date":"2025-01-28","arxiv_id":"2501.17324","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-knowledge-distillation-of-sam-for","title":"Efficient Knowledge Distillation of SAM for Medical Image Segmentation","date":"2025-01-28","arxiv_id":"2501.16740","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-role-of-explicit-temporal","title":"Exploring the Role of Explicit Temporal Modeling in Multimodal Large Language Models for Video Understanding","date":"2025-01-28","arxiv_id":"2501.16786","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexmotion-lightweight-physics-aware-and","title":"FlexMotion: Lightweight, Physics-Aware, and Controllable Human Motion Generation","date":"2025-01-28","arxiv_id":"2501.16778","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-quantum-combinatorial-optimization","title":"Generative quantum combinatorial optimization by means of a novel conditional generative quantum eigensolver","date":"2025-01-28","arxiv_id":"2501.16986","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucinated-translations-in-large","title":"Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization","date":"2025-01-28","arxiv_id":"2501.17295","repositories_listed":0,"syntology":null},{"url":null,"slug":"360brew-a-decoder-only-foundation-model-for","title":"360Brew: A Decoder-only Foundation Model for Personalized Ranking and Recommendation","date":"2025-01-27","arxiv_id":"2501.16450","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-framework-for-uncertainty-prediction","title":"Modular Framework for Uncertainty Prediction in Autonomous Vehicle Motion Forecasting within Complex Traffic Scenarios","date":"2025-01-27","arxiv_id":"2501.16480","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-target-speaker-speech-recognition","title":"End-to-End Target Speaker Speech Recognition Using Context-Aware Attention Mechanisms for Challenging Enrollment Scenario","date":"2025-01-26","arxiv_id":"2501.15466","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-class-incremental-learning-a-hybrid","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","date":"2025-01-26","arxiv_id":"2501.15356","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-machine-translation-ensembling-with","title":"Faster Machine Translation Ensembling with Reinforcement Learning and Competitive Correction","date":"2025-01-25","arxiv_id":"2501.15219","repositories_listed":0,"syntology":null},{"url":null,"slug":"cheapnvs-real-time-on-device-narrow-baseline","title":"CheapNVS: Real-Time On-Device Narrow-Baseline Novel View Synthesis","date":"2025-01-24","arxiv_id":"2501.14533","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-cracknet-a-context-aware-framework","title":"Context-CrackNet: A Context-Aware Framework for Precise Segmentation of Tiny Cracks in Pavement images","date":"2025-01-24","arxiv_id":"2501.14413","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-token-reduction-during-generation-for","title":"Dynamic Token Reduction during Generation for Vision Language Models","date":"2025-01-24","arxiv_id":"2501.14204","repositories_listed":0,"syntology":null},{"url":null,"slug":"glissando-net-deep-single-view-category-level","title":"Glissando-Net: Deep sinGLe vIew category level poSe eStimation ANd 3D recOnstruction","date":"2025-01-24","arxiv_id":"2501.14896","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-position-estimation-for-remote","title":"Predictive Position Estimation for Remote Surgery under Packet Loss Using the Informer Framework","date":"2025-01-24","arxiv_id":"2501.14664","repositories_listed":0,"syntology":null},{"url":"/paper/referdino-referring-video-object-segmentation","slug":"referdino-referring-video-object-segmentation","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","date":"2025-01-24","arxiv_id":"2501.14607","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-encoder-decoder-flow-through","title":"Rethinking Encoder-Decoder Flow Through Shared Structures","date":"2025-01-24","arxiv_id":"2501.14535","repositories_listed":0,"syntology":null},{"url":null,"slug":"crpo-confidence-reward-driven-preference","title":"CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation","date":"2025-01-23","arxiv_id":"2501.13927","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-and-explainable-verification-of","title":"Scalable and Interpretable Verification of Image-based Neural Network Controllers for Autonomous Vehicles","date":"2025-01-23","arxiv_id":"2501.14009","repositories_listed":0,"syntology":null},{"url":null,"slug":"crossdiff-diffusion-probabilistic-model-with","title":"CrossDiff: Diffusion Probabilistic Model With Cross-conditional Encoder-Decoder for Crack Segmentation","date":"2025-01-22","arxiv_id":"2501.12860","repositories_listed":0,"syntology":null},{"url":null,"slug":"ehrenfeucht-haussler-rank-and-chain-of","title":"Ehrenfeucht-Haussler Rank and Chain of Thought","date":"2025-01-22","arxiv_id":"2501.12997","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-based-semantic","title":"Large Language Model-Based Semantic Communication System for Image Transmission","date":"2025-01-22","arxiv_id":"2501.12988","repositories_listed":0,"syntology":null},{"url":null,"slug":"fabsam-a-farmland-boundary-delineation-method","title":"fabSAM: A Farmland Boundary Delineation Method Based on the Segment Anything Model","date":"2025-01-21","arxiv_id":"2501.12487","repositories_listed":0,"syntology":null},{"url":null,"slug":"orcast-operational-high-resolution-current","title":"ORCAst: Operational High-Resolution Current Forecasts","date":"2025-01-21","arxiv_id":"2501.12054","repositories_listed":0,"syntology":null},{"url":null,"slug":"rate-aware-learned-speech-compression","title":"Rate-Aware Learned Speech Compression","date":"2025-01-21","arxiv_id":"2501.11999","repositories_listed":0,"syntology":null},{"url":null,"slug":"teacher-encoder-student-decoder-denoising","title":"Teacher Encoder-Student Decoder Denoising Guided Segmentation Network for Anomaly Detection","date":"2025-01-21","arxiv_id":"2501.12104","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-bearing-sensor-data-compression-via","title":"Efficient Bearing Sensor Data Compression via an Asymmetrical Autoencoder with a Lifting Wavelet Transform Layer","date":"2025-01-20","arxiv_id":"2501.11737","repositories_listed":0,"syntology":null},{"url":"/paper/towards-loss-resilient-image-coding-for","slug":"towards-loss-resilient-image-coding-for","title":"Towards Loss-Resilient Image Coding for Unstable Satellite Networks","date":"2025-01-20","arxiv_id":"2501.11263","repositories_listed":0,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-loss-resilient-image-coding-for#ran","syntology_url":"https://syntology.ai/paper/2501.11263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.11263"}},"official":null}},{"url":null,"slug":"dc-pcn-point-cloud-completion-network-with","title":"DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization","date":"2025-01-19","arxiv_id":"2501.10966","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-early-fusion-strategies-for-1","title":"Rethinking Early-Fusion Strategies for Improved Multimodal Image Segmentation","date":"2025-01-19","arxiv_id":"2501.10958","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffvsr-enhancing-real-world-video-super","title":"DiffVSR: Enhancing Real-World Video Super-Resolution with Diffusion Models for Advanced Visual Quality and Temporal Consistency","date":"2025-01-17","arxiv_id":"2501.10110","repositories_listed":0,"syntology":null},{"url":null,"slug":"himix-reducing-computational-complexity-in","title":"HiMix: Reducing Computational Complexity in Large Vision-Language Models","date":"2025-01-17","arxiv_id":"2501.10318","repositories_listed":0,"syntology":null},{"url":null,"slug":"random-key-algorithms-for-optimizing","title":"Random-Key Algorithms for Optimizing Integrated Operating Room Scheduling","date":"2025-01-17","arxiv_id":"2501.10243","repositories_listed":0,"syntology":null},{"url":null,"slug":"steering-large-language-models-with-feature","title":"Steering Large Language Models with Feature Guided Activation Additions","date":"2025-01-17","arxiv_id":"2501.09929","repositories_listed":0,"syntology":null},{"url":null,"slug":"augrefer-advancing-3d-visual-grounding-via","title":"AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring","date":"2025-01-16","arxiv_id":"2501.09428","repositories_listed":0,"syntology":null},{"url":null,"slug":"complex-valued-neural-networks-for-ultra","title":"Complex-Valued Neural Networks for Ultra-Reliable Massive MIMO","date":"2025-01-16","arxiv_id":"2501.09837","repositories_listed":0,"syntology":null},{"url":null,"slug":"geometry-preserving-encoder-decoder-in-latent","title":"Geometry-Preserving Encoder/Decoder in Latent Generative Models","date":"2025-01-16","arxiv_id":"2501.09876","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-image-restoration","title":"Knowledge Distillation for Image Restoration : Simultaneous Learning from Degraded and Clean Images","date":"2025-01-16","arxiv_id":"2501.09268","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnings-from-scaling-visual-tokenizers-for","title":"Learnings from Scaling Visual Tokenizers for Reconstruction and Generation","date":"2025-01-16","arxiv_id":"2501.09755","repositories_listed":0,"syntology":null},{"url":null,"slug":"soft-knowledge-distillation-with-multi","title":"Soft Knowledge Distillation with Multi-Dimensional Cross-Net Attention for Image Restoration Models Compression","date":"2025-01-16","arxiv_id":"2501.09321","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-spatio-temporal-event-prediction","title":"Fine-grained Spatio-temporal Event Prediction with Self-adaptive Anchor Graph","date":"2025-01-15","arxiv_id":"2501.08653","repositories_listed":0,"syntology":null},{"url":null,"slug":"magnet-augmenting-generative-decoders-with","title":"MAGNET: Augmenting Generative Decoders with Representation Learning and Infilling Capabilities","date":"2025-01-15","arxiv_id":"2501.08648","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-fake-news-video-explanation","title":"Multimodal Fake News Video Explanation: Dataset, Analysis and Evaluation","date":"2025-01-15","arxiv_id":"2501.08514","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-encoder-frozen-decoder-approach-for","title":"A Multi-Encoder Frozen-Decoder Approach for Fine-Tuning Large Language Models","date":"2025-01-14","arxiv_id":"2501.07818","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-learning-with-embedding-layer","title":"Continual Learning with Embedding Layer Surgery and Task-wise Beam Search using Whisper","date":"2025-01-14","arxiv_id":"2501.07875","repositories_listed":0,"syntology":null},{"url":null,"slug":"v-trans4style-visual-transition","title":"V-Trans4Style: Visual Transition Recommendation for Video Production Style Adaptation","date":"2025-01-14","arxiv_id":"2501.07983","repositories_listed":0,"syntology":null},{"url":null,"slug":"dataset-distillation-as-pushforward-optimal","title":"Dataset Distillation as Pushforward Optimal Quantization","date":"2025-01-13","arxiv_id":"2501.07681","repositories_listed":0,"syntology":null},{"url":null,"slug":"msv-mamba-a-multiscale-vision-mamba-network","title":"MSV-Mamba: A Multiscale Vision Mamba Network for Echocardiography Segmentation","date":"2025-01-13","arxiv_id":"2501.07120","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-key-value-cache-fusion-for-position","title":"Parallel Key-Value Cache Fusion for Position Invariant RAG","date":"2025-01-13","arxiv_id":"2501.07523","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-learning-of-point-cloud","title":"Representation Learning of Point Cloud Upsampling in Global and Local Inputs","date":"2025-01-13","arxiv_id":"2501.07076","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-prompt-compression-without-multi-layer","title":"Better Prompt Compression Without Multi-Layer Perceptrons","date":"2025-01-12","arxiv_id":"2501.06730","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-autoencoders-for-tokenization","title":"Comparison of Autoencoders for tokenization of ASL datasets","date":"2025-01-12","arxiv_id":"2501.06942","repositories_listed":0,"syntology":null},{"url":null,"slug":"sam-da-decoder-adapter-for-efficient-medical","title":"SAM-DA: Decoder Adapter for Efficient Medical Domain Adaptation","date":"2025-01-12","arxiv_id":"2501.06836","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-cd-remote-sensing-image-semantic","title":"Semantic-CD: Remote Sensing Image Semantic Change Detection towards Open-vocabulary Setting","date":"2025-01-12","arxiv_id":"2501.06808","repositories_listed":0,"syntology":null},{"url":"/paper/cpdr-towards-highly-efficient-salient-object","slug":"cpdr-towards-highly-efficient-salient-object","title":"CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement","date":"2025-01-11","arxiv_id":"2501.06441","repositories_listed":0,"syntology":null},{"url":null,"slug":"mars6-a-small-and-robust-hierarchical-codec","title":"MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model","date":"2025-01-10","arxiv_id":"2501.05787","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-creating-a-brain-to-text-decoder","title":"On Creating A Brain-To-Text Decoder","date":"2025-01-10","arxiv_id":"2501.06326","repositories_listed":0,"syntology":null},{"url":null,"slug":"swin-x2s-reconstructing-3d-shape-from-2d","title":"Swin-X2S: Reconstructing 3D Shape from 2D Biplanar X-ray with Swin Transformers","date":"2025-01-10","arxiv_id":"2501.05961","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniq-unified-decoder-with-task-specific","title":"UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation","date":"2025-01-10","arxiv_id":"2501.05687","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-pre-trained-llms-for-multivariate-time","title":"Using Pre-trained LLMs for Multivariate Time Series Forecasting","date":"2025-01-10","arxiv_id":"2501.06386","repositories_listed":0,"syntology":null},{"url":null,"slug":"radiotransformer-accurate-radio-map","title":"RMTransformer: Accurate Radio Map Construction and Coverage Prediction","date":"2025-01-09","arxiv_id":"2501.05190","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-salient-object-detection-with-1","title":"Boosting Salient Object Detection with Knowledge Distillated from Large Foundation Models","date":"2025-01-08","arxiv_id":"2501.04582","repositories_listed":0,"syntology":null},{"url":null,"slug":"endodino-a-foundation-model-for-gi-endoscopy","title":"EndoDINO: A Foundation Model for GI Endoscopy","date":"2025-01-08","arxiv_id":"2501.05488","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-graph-constrastive-learning-and","title":"Multimodal Graph Constrastive Learning and Prompt for ChartQA","date":"2025-01-08","arxiv_id":"2501.04303","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-time-and-parameters-for-nonlinear","title":"Leveraging time and parameters for nonlinear model reduction methods","date":"2025-01-07","arxiv_id":"2501.03853","repositories_listed":0,"syntology":null},{"url":null,"slug":"lilmaps-learnable-implicit-language-maps","title":"LiLMaps: Learnable Implicit Language Maps","date":"2025-01-06","arxiv_id":"2501.03304","repositories_listed":0,"syntology":null},{"url":null,"slug":"piano-transcription-by-hierarchical-language","title":"Piano Transcription by Hierarchical Language Modeling with Pretrained Roll-based Encoders","date":"2025-01-06","arxiv_id":"2501.03038","repositories_listed":0,"syntology":null},{"url":null,"slug":"digital-deep-joint-source-channel-coding-with","title":"Blind Training for Channel-Adaptive Digital Semantic Communications","date":"2025-01-04","arxiv_id":"2501.02273","repositories_listed":0,"syntology":null},{"url":null,"slug":"guiding-medical-vision-language-models-with","title":"Guiding Medical Vision-Language Models with Explicit Visual Prompts: Framework Design and Comprehensive Exploration of Prompt Variations","date":"2025-01-04","arxiv_id":"2501.02385","repositories_listed":0,"syntology":null},{"url":null,"slug":"prepending-or-cross-attention-for-speech-to","title":"Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison","date":"2025-01-04","arxiv_id":"2501.02370","repositories_listed":0,"syntology":null},{"url":null,"slug":"revelio-a-real-world-screen-camera","title":"Revelio: A Real-World Screen-Camera Communication System with Visually Imperceptible Data Embedding","date":"2025-01-04","arxiv_id":"2501.02349","repositories_listed":0,"syntology":null},{"url":"/paper/end-to-end-long-document-summarization-using","slug":"end-to-end-long-document-summarization-using","title":"End-to-End Long Document Summarization using Gradient Caching","date":"2025-01-03","arxiv_id":"2501.01805","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptvc-high-quality-voice-conversion-with","title":"AdaptVC: High Quality Voice Conversion with Adaptive Learning","date":"2025-01-02","arxiv_id":"2501.01347","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-latent-properties-to-optimize","title":"Exploiting Latent Properties to Optimize Neural Codecs","date":"2025-01-02","arxiv_id":"2501.01231","repositories_listed":0,"syntology":null},{"url":null,"slug":"nny-net-swin-next-with-cross-attention-for-3d","title":"nnY-Net: Swin-NeXt with Cross-Attention for 3D Medical Images Segmentation","date":"2025-01-02","arxiv_id":"2501.01406","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-mvp-3d-multiview-pretraining-for","title":"3D-MVP: 3D Multiview Pretraining for Manipulation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semantic-knowledge-complementarity-based","title":"A Semantic Knowledge Complementarity based Decoupling Framework for Semi-supervised Class-imbalanced Medical Image Segmentation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"annotation-ambiguity-aware-semi-supervised","title":"Annotation Ambiguity Aware Semi-Supervised Medical Image Segmentation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decouple-distortion-from-perception-region","title":"Decouple Distortion from Perception: Region Adaptive Diffusion for Extreme-low Bitrate Perception Image Compression","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"entitysam-segment-everything-in-video","title":"EntitySAM: Segment Everything in Video","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-historical-information-for-rgbe","title":"Exploring Historical Information for RGBE Visual Tracking with Mamba","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fulltransnet-full-transformer-with-local","title":"FullTransNet: Full Transformer with Local-Global Attention for Video Summarization","date":"2025-01-01","arxiv_id":"2501.00882","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-gaussian-splatting-for-unbounded","title":"Generative Gaussian Splatting for Unbounded 3D City Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"94c37550421351e7f0b9a87e485bddfcb3cedf15c11a72402e89cac096b7a036","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}