{"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/knowledge-distillation/papers/29","list_of":"/task/knowledge-distillation","task":"Knowledge Distillation","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":29,"pages_in_order":43,"rows_per_page":100,"rows":[2801,2900],"of":4240,"counts":{"archive_papers_tagged":4240,"with_a_code_link":1740,"where_syntology_ran_a_sample":451,"not_listed_spam_title":0,"listed":4240,"listed_where_code_ran":451,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":380,"every_run_a_failure_of_syntologys_instrument":71,"listed_with_a_run_with_no_instrument_failure":380,"listed_every_run_a_failure_of_syntologys_instrument":71,"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/knowledge-distillation","prev":"/task/knowledge-distillation/papers/28","next":"/task/knowledge-distillation/papers/30","papers":[{"url":null,"slug":"exploring-multi-modal-contextual-knowledge","title":"Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection","date":"2023-08-30","arxiv_id":"2308.15846","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-knowledge-distillation-for-bert","title":"Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning","date":"2023-08-26","arxiv_id":"2308.13958","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-face-alignment-through-fusion-of-head-pose","title":"3D Face Alignment Through Fusion of Head Pose Information and Features","date":"2023-08-25","arxiv_id":"2308.13327","repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-efficient-federated-learning-for","title":"REFT: Resource-Efficient Federated Training Framework for Heterogeneous and Resource-Constrained Environments","date":"2023-08-25","arxiv_id":"2308.13662","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-representation-learning-with-3","title":"Self-Supervised Representation Learning with Cross-Context Learning between Global and Hypercolumn Features","date":"2023-08-25","arxiv_id":"2308.13392","repositories_listed":0,"syntology":null},{"url":null,"slug":"dlip-distilling-language-image-pre-training","title":"DLIP: Distilling Language-Image Pre-training","date":"2023-08-24","arxiv_id":"2308.12956","repositories_listed":0,"syntology":null},{"url":null,"slug":"fall-detection-using-knowledge-distillation","title":"Fall Detection using Knowledge Distillation Based Long short-term memory for Offline Embedded and Low Power Devices","date":"2023-08-24","arxiv_id":"2308.12481","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-controllable-multi-task","title":"Efficient Controllable Multi-Task Architectures","date":"2023-08-22","arxiv_id":"2308.11744","repositories_listed":0,"syntology":null},{"url":"/paper/multimodal-locally-enhanced-transformer-for","slug":"multimodal-locally-enhanced-transformer-for","title":"Multimodal Locally Enhanced Transformer for Continuous Sign Language Recognition","date":"2023-08-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-disparity-aware-distillation","title":"Representation Disparity-aware Distillation for 3D Object Detection","date":"2023-08-20","arxiv_id":"2308.10308","repositories_listed":0,"syntology":null},{"url":null,"slug":"ccface-classification-consistency-for-low","title":"CCFace: Classification Consistency for Low-Resolution Face Recognition","date":"2023-08-18","arxiv_id":"2308.09230","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlimited-knowledge-distillation-for-action","title":"Unlimited Knowledge Distillation for Action Recognition in the Dark","date":"2023-08-18","arxiv_id":"2308.09327","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-lightweight-object-detectors-via","title":"Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation","date":"2023-08-17","arxiv_id":"2308.09105","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-through-guidance-knowledge","title":"Learning Through Guidance: Knowledge Distillation for Endoscopic Image Classification","date":"2023-08-17","arxiv_id":"2308.08731","repositories_listed":0,"syntology":null},{"url":null,"slug":"radio2text-streaming-speech-recognition-using","title":"Radio2Text: Streaming Speech Recognition Using mmWave Radio Signals","date":"2023-08-16","arxiv_id":"2308.08125","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-model-compression-for-large","title":"A Survey on Model Compression for Large Language Models","date":"2023-08-15","arxiv_id":"2308.07633","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-knowledge-from-resource-management","title":"Distilling Knowledge from Resource Management Algorithms to Neural Networks: A Unified Training Assistance Approach","date":"2023-08-15","arxiv_id":"2308.07511","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-face-forgery-detection-via","title":"Continual Face Forgery Detection via Historical Distribution Preserving","date":"2023-08-11","arxiv_id":"2308.06217","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-general-and-fast-video-derain-via","title":"Towards General and Fast Video Derain via Knowledge Distillation","date":"2023-08-10","arxiv_id":"2308.05346","repositories_listed":0,"syntology":null},{"url":null,"slug":"fpga-resource-aware-structured-pruning-for","title":"FPGA Resource-aware Structured Pruning for Real-Time Neural Networks","date":"2023-08-09","arxiv_id":"2308.05170","repositories_listed":0,"syntology":null},{"url":null,"slug":"sci-cot-leveraging-large-language-models-for","title":"Sci-CoT: Leveraging Large Language Models for Enhanced Knowledge Distillation in Small Models for Scientific QA","date":"2023-08-09","arxiv_id":"2308.04679","repositories_listed":0,"syntology":null},{"url":null,"slug":"teacher-student-architecture-for-knowledge-1","title":"Teacher-Student Architecture for Knowledge Distillation: A Survey","date":"2023-08-08","arxiv_id":"2308.04268","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapter-based-selective-knowledge","title":"Adapter-based Selective Knowledge Distillation for Federated Multi-domain Meeting Summarization","date":"2023-08-07","arxiv_id":"2308.03275","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-incremental-learning-with-self","title":"Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning","date":"2023-08-04","arxiv_id":"2308.02346","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-aware-human-pose-generation-using","title":"Scene-aware Human Pose Generation using Transformer","date":"2023-08-04","arxiv_id":"2308.02177","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-vision-transformer-based-framework-for","title":"A vision transformer-based framework for knowledge transfer from multi-modal to mono-modal lymphoma subtyping models","date":"2023-08-02","arxiv_id":"2308.01328","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-expert-models-for-training-deep","title":"Leveraging Expert Models for Training Deep Neural Networks in Scarce Data Domains: Application to Offline Handwritten Signature Verification","date":"2023-08-02","arxiv_id":"2308.01136","repositories_listed":0,"syntology":null},{"url":null,"slug":"three-factors-to-improve-out-of-distribution","title":"Three Factors to Improve Out-of-Distribution Detection","date":"2023-08-02","arxiv_id":"2308.01030","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-better-query-classification-with","title":"Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search","date":"2023-08-02","arxiv_id":"2308.01098","repositories_listed":0,"syntology":null},{"url":null,"slug":"ada-dqa-adaptive-diverse-quality-aware","title":"Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment","date":"2023-08-01","arxiv_id":"2308.00729","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-learning-for-data-and-model","title":"Federated Learning for Data and Model Heterogeneity in Medical Imaging","date":"2023-07-31","arxiv_id":"2308.00155","repositories_listed":0,"syntology":null},{"url":null,"slug":"sampling-to-distill-knowledge-transfer-from","title":"Sampling to Distill: Knowledge Transfer from Open-World Data","date":"2023-07-31","arxiv_id":"2307.16601","repositories_listed":0,"syntology":null},{"url":null,"slug":"upfl-unsupervised-personalized-federated","title":"UPFL: Unsupervised Personalized Federated Learning towards New Clients","date":"2023-07-29","arxiv_id":"2307.15994","repositories_listed":0,"syntology":null},{"url":null,"slug":"incrementally-computable-neural-networks","title":"Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs","date":"2023-07-27","arxiv_id":"2307.14988","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-cross-client-gans-based-attack-in","title":"Mitigating Cross-client GANs-based Attack in Federated Learning","date":"2023-07-25","arxiv_id":"2307.13314","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-good-student-is-cooperative-and-reliable","title":"A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation","date":"2023-07-24","arxiv_id":"2307.12574","repositories_listed":0,"syntology":null},{"url":null,"slug":"hetefedrec-federated-recommender-systems-with","title":"HeteFedRec: Federated Recommender Systems with Model Heterogeneity","date":"2023-07-24","arxiv_id":"2307.12810","repositories_listed":0,"syntology":null},{"url":null,"slug":"distribution-shift-matters-for-knowledge","title":"Distribution Shift Matters for Knowledge Distillation with Webly Collected Images","date":"2023-07-21","arxiv_id":"2307.11469","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-methods-for-yolov5-a-review","title":"Model Compression Methods for YOLOv5: A Review","date":"2023-07-21","arxiv_id":"2307.11904","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantized-feature-distillation-for-network","title":"Quantized Feature Distillation for Network Quantization","date":"2023-07-20","arxiv_id":"2307.10638","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-object-detection-1","title":"Knowledge Distillation for Object Detection: from generic to remote sensing datasets","date":"2023-07-18","arxiv_id":"2307.09264","repositories_listed":0,"syntology":null},{"url":null,"slug":"teach-model-to-answer-questions-after","title":"Teach model to answer questions after comprehending the document","date":"2023-07-18","arxiv_id":"2307.08931","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-knowledge-distillation-from-large","title":"Domain Knowledge Distillation from Large Language Model: An Empirical Study in the Autonomous Driving Domain","date":"2023-07-17","arxiv_id":"2307.11769","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-techniques-for-optimizing","title":"A Survey of Techniques for Optimizing Transformer Inference","date":"2023-07-16","arxiv_id":"2307.07982","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-ner-for-financial-transaction","title":"Cross-Lingual NER for Financial Transaction Data in Low-Resource Languages","date":"2023-07-16","arxiv_id":"2307.08714","repositories_listed":0,"syntology":null},{"url":null,"slug":"mint-boosting-generalization-in-mathematical","title":"MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning","date":"2023-07-16","arxiv_id":"2307.07951","repositories_listed":0,"syntology":null},{"url":null,"slug":"intuitive-access-to-smartphone-settings-using","title":"Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning","date":"2023-07-15","arxiv_id":"2307.09177","repositories_listed":0,"syntology":null},{"url":null,"slug":"soccerkdnet-a-knowledge-distillation","title":"SoccerKDNet: A Knowledge Distillation Framework for Action Recognition in Soccer Videos","date":"2023-07-15","arxiv_id":"2307.07768","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreamteacher-pretraining-image-backbones-with","title":"DreamTeacher: Pretraining Image Backbones with Deep Generative Models","date":"2023-07-14","arxiv_id":"2307.07487","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-metric-learning-approach-for-endoscopic","title":"A metric learning approach for endoscopic kidney stone identification","date":"2023-07-13","arxiv_id":"2307.07046","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-staged-knowledge-distillation-in-video","title":"The Staged Knowledge Distillation in Video Classification: Harmonizing Student Progress by a Complementary Weakly Supervised Framework","date":"2023-07-11","arxiv_id":"2307.05201","repositories_listed":0,"syntology":null},{"url":"/paper/contextual-affinity-distillation-for-image","slug":"contextual-affinity-distillation-for-image","title":"Contextual Affinity Distillation for Image Anomaly Detection","date":"2023-07-06","arxiv_id":"2307.03101","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-device-constrained-self-supervised-speech","title":"On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation","date":"2023-07-06","arxiv_id":"2307.02720","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-missing-modality-knowledge-from","title":"Distilling Missing Modality Knowledge from Ultrasound for Endometriosis Diagnosis with Magnetic Resonance Images","date":"2023-07-05","arxiv_id":"2307.02000","repositories_listed":0,"syntology":null},{"url":"/paper/kdstm-neural-semi-supervised-topic-modeling","slug":"kdstm-neural-semi-supervised-topic-modeling","title":"KDSTM: Neural Semi-supervised Topic Modeling with Knowledge Distillation","date":"2023-07-04","arxiv_id":"2307.01878","repositories_listed":0,"syntology":{"n":8,"n_ran":6,"n_constructed":1,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/kdstm-neural-semi-supervised-topic-modeling#ran","syntology_url":"https://syntology.ai/paper/2307.01878","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01878"}},"official":null}},{"url":null,"slug":"review-helps-learn-better-temporal-supervised","title":"Review helps learn better: Temporal Supervised Knowledge Distillation","date":"2023-07-03","arxiv_id":"2307.00811","repositories_listed":0,"syntology":null},{"url":null,"slug":"shared-growth-of-graph-neural-networks-via","title":"Shared Growth of Graph Neural Networks via Prompted Free-direction Knowledge Distillation","date":"2023-07-02","arxiv_id":"2307.00534","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-tailed-continual-learning-for-visual","title":"Long-Tailed Continual Learning For Visual Food Recognition","date":"2023-07-01","arxiv_id":"2307.00183","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-egocentric-action-anticipation-an","title":"Streaming egocentric action anticipation: An evaluation scheme and approach","date":"2023-06-29","arxiv_id":"2306.16682","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-overfitting-of-the-episodic","title":"Understanding the Overfitting of the Episodic Meta-training","date":"2023-06-29","arxiv_id":"2306.16873","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dimensional-structure-based-knowledge","title":"A Dimensional Structure based Knowledge Distillation Method for Cross-Modal Learning","date":"2023-06-28","arxiv_id":"2306.15977","repositories_listed":0,"syntology":null},{"url":"/paper/exploring-dual-model-knowledge-distillation","slug":"exploring-dual-model-knowledge-distillation","title":"Exploring Dual Model Knowledge Distillation for Anomaly Detection","date":"2023-06-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-the-gap-between-streaming-and-non","title":"Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillation","date":"2023-06-27","arxiv_id":"2306.15171","repositories_listed":0,"syntology":null},{"url":null,"slug":"shoggoth-towards-efficient-edge-cloud","title":"Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning","date":"2023-06-27","arxiv_id":"2306.15333","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-molecular-graph-neural-networks","title":"Accelerating Molecular Graph Neural Networks via Knowledge Distillation","date":"2023-06-26","arxiv_id":"2306.14818","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-architecture-distillation-for-face","title":"Cross Architecture Distillation for Face Recognition","date":"2023-06-26","arxiv_id":"2306.14662","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-learning-on-non-iid-data-via-local","title":"Federated Learning on Non-iid Data via Local and Global Distillation","date":"2023-06-26","arxiv_id":"2306.14443","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-mapless-trajectory-prediction","title":"Enhancing Mapless Trajectory Prediction through Knowledge Distillation","date":"2023-06-25","arxiv_id":"2306.14177","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-adversarial-distillation-for-point","title":"Feature Adversarial Distillation for Point Cloud Classification","date":"2023-06-25","arxiv_id":"2306.14221","repositories_listed":0,"syntology":null},{"url":null,"slug":"gkd-generalized-knowledge-distillation-for","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","date":"2023-06-23","arxiv_id":"2306.13649","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-via-token-level","title":"Knowledge Distillation via Token-level Relationship Graph","date":"2023-06-20","arxiv_id":"2306.12442","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-advances-in-direct-speech-to-text","title":"Recent Advances in Direct Speech-to-text Translation","date":"2023-06-20","arxiv_id":"2306.11646","repositories_listed":0,"syntology":null},{"url":null,"slug":"categories-of-response-based-feature-based","title":"Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation","date":"2023-06-19","arxiv_id":"2306.10687","repositories_listed":0,"syntology":null},{"url":null,"slug":"fsar-federated-skeleton-based-action","title":"FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation","date":"2023-06-19","arxiv_id":"2306.11046","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-learning-for-multi-label","title":"Semi-Supervised Learning for Multi-Label Cardiovascular Diseases Prediction:A Multi-Dataset Study","date":"2023-06-18","arxiv_id":"2306.10494","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-efficient-audio","title":"Knowledge Distillation for Efficient Audio-Visual Video Captioning","date":"2023-06-16","arxiv_id":"2306.09947","repositories_listed":0,"syntology":null},{"url":null,"slug":"squeezing-nnu-nets-with-knowledge","title":"Squeezing nnU-Nets with Knowledge Distillation for On-Board Cloud Detection","date":"2023-06-16","arxiv_id":"2306.09886","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-knowledge-distillation-for-surgical","title":"Self-Knowledge Distillation for Surgical Phase Recognition","date":"2023-06-15","arxiv_id":"2306.08961","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterogeneous-continual-learning-1","title":"Heterogeneous Continual Learning","date":"2023-06-14","arxiv_id":"2306.08593","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-multimodal-representation-learning-1","title":"Enhanced Multimodal Representation Learning with Cross-modal KD","date":"2023-06-13","arxiv_id":"2306.07646","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-frame-level-classifier-for-word","title":"Improving Frame-level Classifier for Word Timings with Non-peaky CTC in End-to-End Automatic Speech Recognition","date":"2023-06-09","arxiv_id":"2306.07949","repositories_listed":0,"syntology":null},{"url":null,"slug":"boot-data-free-distillation-of-denoising","title":"BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping","date":"2023-06-08","arxiv_id":"2306.05544","repositories_listed":0,"syntology":null},{"url":null,"slug":"population-based-evolutionary-gaming-for","title":"Population-Based Evolutionary Gaming for Unsupervised Person Re-identification","date":"2023-06-08","arxiv_id":"2306.05236","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-economic-trade-offs-of-large-language","title":"The economic trade-offs of large language models: A case study","date":"2023-06-08","arxiv_id":"2306.07402","repositories_listed":0,"syntology":null},{"url":null,"slug":"faithful-knowledge-distillation","title":"Faithful Knowledge Distillation","date":"2023-06-07","arxiv_id":"2306.04431","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-framework-for-satellite-image","title":"Zero shot framework for satellite image restoration","date":"2023-06-05","arxiv_id":"2306.02921","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-transformers-compressing-transformers","title":"Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference","date":"2023-06-04","arxiv_id":"2306.02379","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-distillation-reducing-re","title":"Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models","date":"2023-06-02","arxiv_id":"2306.01322","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-translation-with-foundation-models-and","title":"Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23","date":"2023-06-02","arxiv_id":"2306.01327","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-cross-lingual-transfer-learning-for","title":"Improved Cross-Lingual Transfer Learning For Automatic Speech Translation","date":"2023-06-01","arxiv_id":"2306.00789","repositories_listed":0,"syntology":null},{"url":null,"slug":"accurate-and-structured-pruning-for-efficient","title":"Accurate and Structured Pruning for Efficient Automatic Speech Recognition","date":"2023-05-31","arxiv_id":"2305.19549","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-recipe-for-efficient-sbir-models-combining","title":"A Recipe for Efficient SBIR Models: Combining Relative Triplet Loss with Batch Normalization and Knowledge Distillation","date":"2023-05-30","arxiv_id":"2305.18988","repositories_listed":0,"syntology":null},{"url":null,"slug":"keyword-based-sampling-keys-for-large","title":"KEYword based Sampling (KEYS) for Large Language Models","date":"2023-05-30","arxiv_id":"2305.18679","repositories_listed":0,"syntology":null},{"url":null,"slug":"research-on-multilingual-news-clustering","title":"Research on Multilingual News Clustering Based on Cross-Language Word Embeddings","date":"2023-05-30","arxiv_id":"2305.18880","repositories_listed":0,"syntology":null},{"url":null,"slug":"griprank-bridging-the-gap-between-retrieval","title":"GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking","date":"2023-05-29","arxiv_id":"2305.18144","repositories_listed":0,"syntology":null},{"url":null,"slug":"conaclip-exploring-distillation-of-fully","title":"ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval","date":"2023-05-28","arxiv_id":"2305.17652","repositories_listed":0,"syntology":null},{"url":null,"slug":"abc-kd-attention-based-compression-knowledge","title":"ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression","date":"2023-05-26","arxiv_id":"2305.16665","repositories_listed":0,"syntology":null},{"url":null,"slug":"collective-knowledge-graph-completion-with","title":"Collective Knowledge Graph Completion with Mutual Knowledge Distillation","date":"2023-05-25","arxiv_id":"2305.15895","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-knowledge-distillation-for","title":"Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource Languages","date":"2023-05-25","arxiv_id":"2305.16302","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairness-continual-learning-approach-to","title":"Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments","date":"2023-05-25","arxiv_id":"2305.15700","repositories_listed":0,"syntology":null}],"record_sha256":"ae0af1931eee2c616b9c9aa19fe5cdb4db3bf25c420cb8ff6deefd28ff08d12e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}