Robuta

https://www.semanticscholar.org/topic/Adaptive-compression/171506 Adaptive compression | Semantic Scholar Adaptive compression is a type of data compression which changes compression algorithms based on the type of data being compressed. adaptive compressionsemanticscholar https://openreview.net/forum?id=G9xhvGPtte&referrer=%5Bthe%20profile%20of%20Jun%20Chen%5D(%2Fprofile%3Fid%3D~Jun_Chen11) LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding | OpenReview Multimodal Large Language Models (MLLMs) have shown promising progress in understanding and analyzing video content. However, processing long videos remains a... adaptive compressionlong videolanguage understandingspatiotemporalopenreview https://openreview.net/forum?id=lD9Kc22Wls&referrer=%5Bthe%20profile%20of%20Ilia%20Markov%5D(%2Fprofile%3Fid%3D~Ilia_Markov1) Quantized Optimistic Dual Averaging with Adaptive Layer-wise Compression | OpenReview We develop a general layer-wise and adaptive compression framework with applications to solving variational inequality problems (VI) in a large-scale and... quantizedoptimisticdualaveragingadaptive https://deepai.org/publication/real-time-adaptive-image-compression Real-Time Adaptive Image Compression | DeepAI May 16, 2017 - 05/16/17 - We present a machine learning-based approach to lossy image compression which outperforms all existing codecs, while running in re... real timeimage compressionadaptivedeepai https://en.wikipedia.org/wiki/Adaptive_scalable_texture_compression Adaptive scalable texture compression - Wikipedia texture compressionadaptivescalablewikipedia https://arxiv.org/abs/2605.02888 [2605.02888] SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection Abstract page for arXiv paper 2605.02888: SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection speculative decoding260502888adaptive https://openreview.net/forum?id=pFyXqxChZc IntSGD: Adaptive Floatless Compression of Stochastic Gradients | OpenReview We propose a family of adaptive integer compression operators for distributed Stochastic Gradient Descent (SGD) that do not communicate a single float. This is... adaptivefloatlesscompressionstochasticgradients https://www.inderscience.com/info/inarticle.php?artid=39184 Article: Image compression using adaptive lifting scheme based on minimum mean square error... Inderscience is a global company, a dynamic leading independent journal publisher disseminates the latest research across the broad fields of science,... https://openreview.net/forum?id=uNrFpDPMyo&referrer=%5Bthe%20profile%20of%20Suyu%20Ge%5D(%2Fprofile%3Fid%3D~Suyu_Ge1) Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs | OpenReview In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language... https://www.amazon.science/publications/byteflow-language-modeling-through-adaptive-byte-compression-without-a-tokenizer ByteFlow: Language modeling through adaptive byte compression without a tokenizer - Amazon Science Modern language models (LMs) still rely on fixed, pre-defined subword tokenizations. Once a tokenizer is trained, the LM can only operate at this fixed level... language modeling https://arxiv.org/abs/2603.04411 [2603.04411] One Size Does Not Fit All: Token-Wise Adaptive Compression for KV Cache Abstract page for arXiv paper 2603.04411: One Size Does Not Fit All: Token-Wise Adaptive Compression for KV Cache one size does not fit all https://www.preprints.org/manuscript/202505.0171 An Enhanced Fractal Image Compression Algorithm Based on Adaptive Non-Uniform Rectangular... The Basic Fractal Image Compression (BFIC) method is widely known for its high computational complexity and long encoding time under a fixed block... fractal image compression https://huggingface.co/papers/2310.01801 Paper page - Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs Join the discussion on this paper page https://deepai.org/publication/adaptive-encoding-strategies-for-erasing-based-lossless-floating-point-compression Adaptive Encoding Strategies for Erasing-Based Lossless Floating-Point Compression | DeepAI Aug 23, 2023 - 08/23/23 - Lossless floating-point time series compression is crucial for a wide range of critical scenarios. Nevertheless, it is a big chall... floating pointadaptiveencodingstrategieserasing