{"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/quantization/papers/19","list_of":"/task/quantization","task":"Quantization","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":19,"pages_in_order":50,"rows_per_page":100,"rows":[1801,1900],"of":4925,"counts":{"archive_papers_tagged":4925,"with_a_code_link":1596,"where_syntology_ran_a_sample":515,"not_listed_spam_title":0,"listed":4925,"listed_where_code_ran":515,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":452,"every_run_a_failure_of_syntologys_instrument":63,"listed_with_a_run_with_no_instrument_failure":452,"listed_every_run_a_failure_of_syntologys_instrument":63,"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/quantization","prev":"/task/quantization/papers/18","next":"/task/quantization/papers/20","papers":[{"url":null,"slug":"bridging-the-gap-between-gaussian-diffusion","title":"Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression","date":"2025-04-03","arxiv_id":"2504.02579","repositories_listed":0,"syntology":null},{"url":null,"slug":"hpgn-hybrid-priors-guided-network-for","title":"HPGN: Hybrid Priors-Guided Network for Compressed Low-Light Image Enhancement","date":"2025-04-03","arxiv_id":"2504.02373","repositories_listed":0,"syntology":null},{"url":null,"slug":"moment-quantization-for-video-temporal","title":"Moment Quantization for Video Temporal Grounding","date":"2025-04-03","arxiv_id":"2504.02286","repositories_listed":0,"syntology":null},{"url":null,"slug":"llmpi-optimizing-llms-for-high-throughput-on","title":"LLMPi: Optimizing LLMs for High-Throughput on Raspberry Pi","date":"2025-04-02","arxiv_id":"2504.02118","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-reasoning-meets-compression-benchmarking","title":"When Reasoning Meets Compression: Benchmarking Compressed Large Reasoning Models on Complex Reasoning Tasks","date":"2025-04-02","arxiv_id":"2504.02010","repositories_listed":0,"syntology":null},{"url":null,"slug":"qsvit-a-methodology-for-quantizing-spiking","title":"QSViT: A Methodology for Quantizing Spiking Vision Transformers","date":"2025-04-01","arxiv_id":"2504.00948","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-hemorrhage-and-the-robustness-limits-of","title":"Model Hemorrhage and the Robustness Limits of Large Language Models","date":"2025-03-31","arxiv_id":"2503.23924","repositories_listed":0,"syntology":null},{"url":null,"slug":"squat-subspace-orthogonal-kv-cache","title":"SQuat: Subspace-orthogonal KV Cache Quantization","date":"2025-03-31","arxiv_id":"2503.24358","repositories_listed":0,"syntology":null},{"url":null,"slug":"style-quantization-for-data-efficient-gan","title":"Style Quantization for Data-Efficient GAN Training","date":"2025-03-31","arxiv_id":"2503.24282","repositories_listed":0,"syntology":null},{"url":null,"slug":"cocktail-chunk-adaptive-mixed-precision","title":"Cocktail: Chunk-Adaptive Mixed-Precision Quantization for Long-Context LLM Inference","date":"2025-03-30","arxiv_id":"2503.23294","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuralgs-bridging-neural-fields-and-3d","title":"NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations","date":"2025-03-29","arxiv_id":"2503.23162","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-tail-crisis-in-nearest-neighbor-language","title":"Long-Tail Crisis in Nearest Neighbor Language Models","date":"2025-03-28","arxiv_id":"2503.22426","repositories_listed":0,"syntology":null},{"url":null,"slug":"make-some-noise-towards-llm-audio-reasoning","title":"Make Some Noise: Towards LLM audio reasoning and generation using sound tokens","date":"2025-03-28","arxiv_id":"2503.22275","repositories_listed":0,"syntology":null},{"url":null,"slug":"mcrb-for-parameter-estimation-from-one-bit","title":"MCRB for Parameter Estimation from One-Bit Quantized and Oversampled Measurements","date":"2025-03-28","arxiv_id":"2503.22860","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-71-2-m-w-speech-recognition-accelerator","title":"A 71.2-$μ$W Speech Recognition Accelerator with Recurrent Spiking Neural Network","date":"2025-03-27","arxiv_id":"2503.21337","repositories_listed":0,"syntology":null},{"url":null,"slug":"moqa-rethinking-moe-quantization-with-multi","title":"MoQa: Rethinking MoE Quantization with Multi-stage Data-model Distribution Awareness","date":"2025-03-27","arxiv_id":"2503.21135","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-mambair-accurate-quantized-mamba-for","title":"Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration","date":"2025-03-27","arxiv_id":"2503.21970","repositories_listed":0,"syntology":null},{"url":null,"slug":"mar-3d-progressive-masked-auto-regressor-for","title":"MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation","date":"2025-03-26","arxiv_id":"2503.20519","repositories_listed":0,"syntology":null},{"url":null,"slug":"sinr-sparsity-driven-compressed-implicit","title":"SINR: Sparsity Driven Compressed Implicit Neural Representations","date":"2025-03-25","arxiv_id":"2503.19576","repositories_listed":0,"syntology":null},{"url":null,"slug":"4dgc-rate-aware-4d-gaussian-compression-for","title":"4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video","date":"2025-03-24","arxiv_id":"2503.18421","repositories_listed":0,"syntology":null},{"url":null,"slug":"ffn-fusion-rethinking-sequential-computation","title":"FFN Fusion: Rethinking Sequential Computation in Large Language Models","date":"2025-03-24","arxiv_id":"2503.18908","repositories_listed":0,"syntology":null},{"url":null,"slug":"granq-granular-zero-shot-quantization-with","title":"GranQ: Granular Zero-Shot Quantization with Channel-Wise Activation Scaling in QAT","date":"2025-03-24","arxiv_id":"2503.18339","repositories_listed":0,"syntology":null},{"url":null,"slug":"oaken-fast-and-efficient-llm-serving-with","title":"Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization","date":"2025-03-24","arxiv_id":"2503.18599","repositories_listed":0,"syntology":null},{"url":null,"slug":"qsid-mpc-model-predictive-control-with-system","title":"QSID-MPC: Model Predictive Control with System Identification from Quantized Data","date":"2025-03-24","arxiv_id":"2503.19102","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-aware-llms-a-step-towards-sustainable","title":"Energy-Aware LLMs: A step towards sustainable AI for downstream applications","date":"2025-03-22","arxiv_id":"2503.17783","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-quantization-with-post-training","title":"Improving Quantization with Post-Training Model Expansion","date":"2025-03-21","arxiv_id":"2503.17513","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-continuous-and-discrete-tokens-for","title":"Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation","date":"2025-03-20","arxiv_id":"2503.16430","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-autoregressive-image-generation","title":"Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction","date":"2025-03-20","arxiv_id":"2503.16194","repositories_listed":0,"syntology":null},{"url":null,"slug":"leantta-a-backpropagation-free-and-stateless","title":"LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices","date":"2025-03-20","arxiv_id":"2503.15889","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-linear-block-codes-with-gradient","title":"Learning Linear Block Codes with Gradient Quantization","date":"2025-03-20","arxiv_id":"2503.16169","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-networks-according-to-the-principles","title":"Neural Networks: According to the Principles of Grassmann Algebra","date":"2025-03-20","arxiv_id":"2503.16364","repositories_listed":0,"syntology":null},{"url":null,"slug":"plug-and-play-1-x-bit-kv-cache-quantization","title":"Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models","date":"2025-03-20","arxiv_id":"2503.16257","repositories_listed":0,"syntology":null},{"url":null,"slug":"specache-speculative-key-value-caching-for","title":"SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs","date":"2025-03-20","arxiv_id":"2503.16163","repositories_listed":0,"syntology":null},{"url":null,"slug":"parq-piecewise-affine-regularized","title":"PARQ: Piecewise-Affine Regularized Quantization","date":"2025-03-19","arxiv_id":"2503.15748","repositories_listed":0,"syntology":null},{"url":null,"slug":"rag-based-user-profiling-for-precision","title":"RAG-based User Profiling for Precision Planning in Mixed-precision Over-the-Air Federated Learning","date":"2025-03-19","arxiv_id":"2503.15569","repositories_listed":0,"syntology":null},{"url":null,"slug":"mag-multi-modal-aligned-autoregressive-co","title":"MAG: Multi-Modal Aligned Autoregressive Co-Speech Gesture Generation without Vector Quantization","date":"2025-03-18","arxiv_id":"2503.14040","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-machine-unlearning-for-quantized","title":"Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels","date":"2025-03-18","arxiv_id":"2503.13917","repositories_listed":0,"syntology":null},{"url":null,"slug":"act360-an-efficient-360-degree-action","title":"ACT360: An Efficient 360-Degree Action Detection and Summarization Framework for Mission-Critical Training and Debriefing","date":"2025-03-17","arxiv_id":"2503.12852","repositories_listed":0,"syntology":null},{"url":null,"slug":"cluscomp-a-simple-paradigm-for-model","title":"ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning","date":"2025-03-17","arxiv_id":"2503.13089","repositories_listed":0,"syntology":null},{"url":null,"slug":"compmarkgs-robust-watermarking-for","title":"CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting","date":"2025-03-17","arxiv_id":"2503.12836","repositories_listed":0,"syntology":null},{"url":null,"slug":"ml-specqd-multi-level-speculative-decoding","title":"ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts","date":"2025-03-17","arxiv_id":"2503.13565","repositories_listed":0,"syntology":null},{"url":null,"slug":"versatile-physics-based-character-control","title":"Versatile Physics-based Character Control with Hybrid Latent Representation","date":"2025-03-17","arxiv_id":"2503.12814","repositories_listed":0,"syntology":null},{"url":null,"slug":"pathology-image-compression-with-pre-trained","title":"Pathology Image Compression with Pre-trained Autoencoders","date":"2025-03-14","arxiv_id":"2503.11591","repositories_listed":0,"syntology":null},{"url":null,"slug":"stabilizing-quantization-aware-training-by","title":"Stabilizing Quantization-Aware Training by Implicit-Regularization on Hessian Matrix","date":"2025-03-14","arxiv_id":"2503.11159","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-flatness-in-generative-models","title":"Understanding Flatness in Generative Models: Its Role and Benefits","date":"2025-03-14","arxiv_id":"2503.11078","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-tomato-maturity-estimation-using-an","title":"Automated Tomato Maturity Estimation Using an Optimized Residual Model with Pruning and Quantization Techniques","date":"2025-03-13","arxiv_id":"2503.10940","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-codebook-vq-enhanced-image","title":"Dual Codebook VQ: Enhanced Image Reconstruction with Reduced Codebook Size","date":"2025-03-13","arxiv_id":"2503.10832","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-synchronization-of-multi-agent-systems","title":"Global synchronization of multi-agent systems with nonlinear interactions","date":"2025-03-13","arxiv_id":"2503.10205","repositories_listed":0,"syntology":null},{"url":null,"slug":"ouromamba-a-data-free-quantization-framework","title":"OuroMamba: A Data-Free Quantization Framework for Vision Mamba Models","date":"2025-03-13","arxiv_id":"2503.10959","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantitative-analysis-of-deeply-quantized","title":"Quantitative Analysis of Deeply Quantized Tiny Neural Networks Robust to Adversarial Attacks","date":"2025-03-12","arxiv_id":"2503.08973","repositories_listed":0,"syntology":null},{"url":null,"slug":"sometimes-painful-but-certainly-promising","title":"Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge","date":"2025-03-12","arxiv_id":"2503.09114","repositories_listed":0,"syntology":null},{"url":null,"slug":"vim-vq-efficient-post-training-vector","title":"ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba","date":"2025-03-12","arxiv_id":"2503.09509","repositories_listed":0,"syntology":null},{"url":null,"slug":"accurate-int8-training-through-dynamic-block","title":"Accurate INT8 Training Through Dynamic Block-Level Fallback","date":"2025-03-11","arxiv_id":"2503.08040","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantization-design-for-deep-learning-based","title":"Quantization Design for Deep Learning-Based CSI Feedback","date":"2025-03-11","arxiv_id":"2503.08125","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-the-limits-of-quantization-aware","title":"Breaking the Limits of Quantization-Aware Defenses: QADT-R for Robustness Against Patch-Based Adversarial Attacks in QNNs","date":"2025-03-10","arxiv_id":"2503.07058","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-multimodal-artificial","title":"Lightweight Multimodal Artificial Intelligence Framework for Maritime Multi-Scene Recognition","date":"2025-03-10","arxiv_id":"2503.06978","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-vacuous-generalization-bounds-for-deep","title":"Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models","date":"2025-03-10","arxiv_id":"2503.07325","repositories_listed":0,"syntology":null},{"url":null,"slug":"post-training-quantization-for-diffusion","title":"Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping","date":"2025-03-10","arxiv_id":"2503.06930","repositories_listed":0,"syntology":null},{"url":null,"slug":"synchronized-video-to-audio-generation-via","title":"Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition","date":"2025-03-10","arxiv_id":"2503.06984","repositories_listed":0,"syntology":null},{"url":null,"slug":"vocaleyes-enhancing-environmental-perception","title":"VocalEyes: Enhancing Environmental Perception for the Visually Impaired through Vision-Language Models and Distance-Aware Object Detection","date":"2025-03-10","arxiv_id":"2503.16488","repositories_listed":0,"syntology":null},{"url":null,"slug":"pathvq-reforming-computational-pathology","title":"PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization","date":"2025-03-09","arxiv_id":"2503.06482","repositories_listed":0,"syntology":null},{"url":null,"slug":"saq-sam-semantically-aligned-quantization-for","title":"SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model","date":"2025-03-09","arxiv_id":"2503.06515","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-delta-parameters-as-jpeg-images-data","title":"Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform","date":"2025-03-09","arxiv_id":"2503.06676","repositories_listed":0,"syntology":null},{"url":null,"slug":"silent-hazards-of-token-reduction-in-vision","title":"Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study","date":"2025-03-09","arxiv_id":"2503.06794","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-superior-quantization-accuracy-a","title":"Towards Superior Quantization Accuracy: A Layer-sensitive Approach","date":"2025-03-09","arxiv_id":"2503.06518","repositories_listed":0,"syntology":null},{"url":null,"slug":"tr-dq-time-rotation-diffusion-quantization","title":"TR-DQ: Time-Rotation Diffusion Quantization","date":"2025-03-09","arxiv_id":"2503.06564","repositories_listed":0,"syntology":null},{"url":null,"slug":"discrete-contrastive-learning-for-diffusion","title":"Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving","date":"2025-03-07","arxiv_id":"2503.05229","repositories_listed":0,"syntology":null},{"url":null,"slug":"frequency-autoregressive-image-generation","title":"Frequency Autoregressive Image Generation with Continuous Tokens","date":"2025-03-07","arxiv_id":"2503.05305","repositories_listed":0,"syntology":null},{"url":null,"slug":"lvlm-compress-bench-benchmarking-the-broader","title":"LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression","date":"2025-03-06","arxiv_id":"2503.04982","repositories_listed":0,"syntology":null},{"url":null,"slug":"universality-of-layer-level-entropy-weighted","title":"Universality of Layer-Level Entropy-Weighted Quantization Beyond Model Architecture and Size","date":"2025-03-06","arxiv_id":"2503.04704","repositories_listed":0,"syntology":null},{"url":null,"slug":"vqel-enabling-self-developed-symbolic","title":"VQEL: Enabling Self-Developed Symbolic Language in Agents through Vector Quantization in Emergent Language Games","date":"2025-03-06","arxiv_id":"2503.04940","repositories_listed":0,"syntology":null},{"url":null,"slug":"ahcptq-accurate-and-hardware-compatible-post","title":"AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model","date":"2025-03-05","arxiv_id":"2503.03088","repositories_listed":0,"syntology":null},{"url":null,"slug":"english-k-quantization-of-llms-does-not","title":"English K_Quantization of LLMs Does Not Disproportionately Diminish Multilingual Performance","date":"2025-03-05","arxiv_id":"2503.03592","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-jet-tagging-with-mlp-mixers-on-fpgas","title":"Fast Jet Tagging with MLP-Mixers on FPGAs","date":"2025-03-05","arxiv_id":"2503.03103","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-relation-between-speech-quality-and","title":"On the Relation Between Speech Quality and Quantized Latent Representations of Neural Codecs","date":"2025-03-05","arxiv_id":"2503.03304","repositories_listed":0,"syntology":null},{"url":null,"slug":"rd-efficient-fpga-deployment-of-learned-image","title":"Lightweight Embedded FPGA Deployment of Learned Image Compression with Knowledge Distillation and Hybrid Quantization","date":"2025-03-05","arxiv_id":"2503.04832","repositories_listed":0,"syntology":null},{"url":null,"slug":"bdslw401-transformer-based-word-level-bangla","title":"BdSLW401: Transformer-Based Word-Level Bangla Sign Language Recognition Using Relative Quantization Encoding (RQE)","date":"2025-03-04","arxiv_id":"2503.02360","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-c-when-quantization-meets-cache-in","title":"Q&C: When Quantization Meets Cache in Efficient Image Generation","date":"2025-03-04","arxiv_id":"2503.02508","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-meets-dense-unified-generative","title":"Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations","date":"2025-03-04","arxiv_id":"2503.02453","repositories_listed":0,"syntology":null},{"url":null,"slug":"ders-towards-extremely-efficient-upcycled","title":"DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models","date":"2025-03-03","arxiv_id":"2503.01359","repositories_listed":0,"syntology":null},{"url":null,"slug":"dilemma-joint-llm-quantization-and","title":"DILEMMA: Joint LLM Quantization and Distributed LLM Inference Over Edge Computing Systems","date":"2025-03-03","arxiv_id":"2503.01704","repositories_listed":0,"syntology":null},{"url":null,"slug":"kurtail-kurtosis-based-llm-quantization","title":"KurTail : Kurtosis-based LLM Quantization","date":"2025-03-03","arxiv_id":"2503.01483","repositories_listed":0,"syntology":null},{"url":null,"slug":"regularization-based-framework-for","title":"Regularization-based Framework for Quantization-, Fault- and Variability-Aware Training","date":"2025-03-03","arxiv_id":"2503.01297","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-improved-text-aligned-codebook","title":"Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text","date":"2025-03-03","arxiv_id":"2503.01261","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01019","title":"MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations","date":"2025-03-02","arxiv_id":"2503.01019","repositories_listed":0,"syntology":null},{"url":null,"slug":"strong-solutions-and-quantization-based","title":"Strong Solutions and Quantization-Based Numerical Schemes for a Class of Non-Markovian Volatility Models","date":"2025-02-28","arxiv_id":"2503.00243","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-the-tip-of-efficiency-uncovering-the","title":"Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models","date":"2025-02-27","arxiv_id":"2502.19883","repositories_listed":0,"syntology":null},{"url":null,"slug":"halo-hardware-aware-quantization-with-low","title":"HALO: Hardware-aware quantization with low critical-path-delay weights for LLM acceleration","date":"2025-02-27","arxiv_id":"2502.19662","repositories_listed":0,"syntology":null},{"url":null,"slug":"speculative-decoding-and-beyond-an-in-depth","title":"Speculative Decoding and Beyond: An In-Depth Review of Techniques","date":"2025-02-27","arxiv_id":"2502.19732","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-nonlinear-transform-coding","title":"Transformer-Based Nonlinear Transform Coding for Multi-Rate CSI Compression in MIMO-OFDM Systems","date":"2025-02-27","arxiv_id":"2502.19847","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-language-models-for-specialized","title":"Compressing Language Models for Specialized Domains","date":"2025-02-25","arxiv_id":"2502.18424","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-free-and-parallel-computation-for","title":"Memory-Free and Parallel Computation for Quantized Spiking Neural Networks","date":"2025-02-25","arxiv_id":"2503.00040","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-privacy-preserving-properties-of","title":"On the Privacy-Preserving Properties of Spiking Neural Networks with Unique Surrogate Gradients and Quantization Levels","date":"2025-02-25","arxiv_id":"2502.18623","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-driven-semantic-quantization-and","title":"Task-Driven Semantic Quantization and Imitation Learning for Goal-Oriented Communications","date":"2025-02-25","arxiv_id":"2502.17842","repositories_listed":0,"syntology":null},{"url":null,"slug":"unbiased-and-sign-compression-in-distributed","title":"Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs","date":"2025-02-24","arxiv_id":"2502.17009","repositories_listed":0,"syntology":null},{"url":null,"slug":"compression-scaling-laws-unifying-sparsity","title":"Compression Scaling Laws:Unifying Sparsity and Quantization","date":"2025-02-23","arxiv_id":"2502.16440","repositories_listed":0,"syntology":null},{"url":null,"slug":"dr-splat-directly-referring-3d-gaussian","title":"Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration","date":"2025-02-23","arxiv_id":"2502.16652","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-efficient-transformer-inference","title":"Energy-Efficient Transformer Inference: Optimization Strategies for Time Series Classification","date":"2025-02-23","arxiv_id":"2502.16627","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-2-bit-wideband-5g-mm-wave-ris-with-low-side","title":"A 2-bit Wideband 5G mm-Wave RIS with Low Side Lobe Levels and no Quantization Lobe","date":"2025-02-22","arxiv_id":"2502.16267","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-using-continuous","title":"Speech Enhancement Using Continuous Embeddings of Neural Audio Codec","date":"2025-02-22","arxiv_id":"2502.16240","repositories_listed":0,"syntology":null}],"record_sha256":"3af4e602658bdf16a18bddb57c6139270b226c0145eb849edd6343f06872b2f0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}