This work introduces PULSE, a practical codec that enables low-latency decoding on diverse hardware platforms with an ultra-low-complexity 5.2 kMAC/pixel neural receiver, and efficient bit-exact entropy coding with an integer linear CDF predictor and a meta prior.
Abstract
Despite recent progress in learned image compression, existing methods remain computationally expensive on resource-constrained hardware, particularly CPUs. We introduce PULSE, a practical codec that enables (1) low-latency decoding on diverse hardware platforms with an ultra-low-complexity 5.2 kMAC/pixel neural receiver, and (2) efficient bit-exact entropy coding with an integer linear CDF predictor and a meta prior. To recover compression performance under this tight budget, we introduce an agentic evolution process guided by heuristic probes that iteratively improves the architecture through human-LLM collaboration. PULSE decodes a 1080p image in 126 ms on a single CPU thread while achieving compression performance comparable to HM. After perceptual optimization, PULSE competes with larger perceptual codecs like MS-ILLM. Codes are at https://github.com/microsoft/GenCodec/tree/main/PULSE
A memory-efficient hardware accelerator for depthwise separable convolution that minimizes off-chip memory traffic and parameter storage and performs the depthwise separable convolution with a small number of logic resources and on-chip memory, confirming its feasibility for resource-constrained edge devices.
Jaeseong Kim, Taehong Min, Chaebin Lee et al.· Electronics· 0 citations
Learned image compression (LIC) is hard to deploy on severely resource-constrained FPGAs, since how fast it actually runs depends not just on arithmetic count, but also on memory traffic, imbalance between different operations, and how the hardware batches its work. We present VQ-LIC, an asymmetric edge-cloud codec in...
Muhammad Fahd Ibrahim Bhatti, Abdullah Bin Faisal, Ahsan Usman et al.· 0 citations
Blackwell's 4-bit floating-point (FP4) tensor cores do not automatically make attention faster because softmax conversion and on-chip dependencies dominate once its matrix products shrink. We address this with \emph{Direct-P} for noncausal inference and a causal path that passes the forward quantization directly into b...
Design rules and a reproducible evaluation protocol are contributed that jointly report quality, memory, and end-to-end speed, and a foundation for automated pipeline search under realistic single-GPU constraints is provided.
This study addresses challenges with Vortex, an architecture compatible with systolic-array-based accelerators with minimal hardware overhead, bridging the gap between extreme compression and efficient inference, and proposes codebook-wise contextual sparsity to align with VQ execution.
Haoxuan Shan, Cong Guo, Bo-Wen Duan et al.· 0 citations
Faster Flash Decoding (FFD) is presented, a novel hardware-algorithm co-design framework designed to break the memory wall in long-context decoding and introduces the top-delta strategy, which dynamically filters blocks to achieve distribution-adaptive sparsity without global synchronization.
Zhigeng Liu, Zhiyuan Ning, Rui-Xiao Li et al.· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
