Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
Recovering high dynamic range (HDR) radiance from a single standard dynamic range (SDR) image is highly ill-posed. Extreme luminance variation and severe quantization in dark regions make accurate reconstruction challenging, often leading to visual artifacts and color distortions.
Although mixture-of-experts, MoE, models have been increasingly adopted to scale large language models with moderate computation cost, it remains challenging to deploy MoE inference over resource-constrained and bandwidth-limited edge infrastructures. Existing distributed MoE serving methods mainly rely on exact expert placement, caching, replication, or communication scheduling, while overlooking the functional similarity among experts, which provides an opportunity to reduce cross-server token transmission.
Hyperspectral image (HSI) classification systems are increasingly deployed on platforms with strict computational budgets, such as UAVs and small spaceborne sensors. In these settings, accuracy alone is not enough; the model must also run within tight latency and memory constraints.
arXiv:2604. 02429v2 Announce Type: replace-cross Abstract: Convolutional neural networks (CNNs) have transformed image processing, but the energy consumption and inference latency of electronic based implementations remain fundamental bottlenecks.
arXiv:2607. 14557v1 Announce Type: new Abstract: Diffusion Multimodal Large Language Models (DMLLMs) are highly effective for multimodal reasoning, yet their inference efficiency is significantly hindered by fixed-length generation constraints.
arXiv:2607. 14640v1 Announce Type: new Abstract: Battery health estimation is fundamental for battery management in battery-powered systems, where inaccurate health states may affect control, maintenance, and service life.
arXiv:2607. 15257v1 Announce Type: new Abstract: Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents.
arXiv:2607. 14293v1 Announce Type: cross Abstract: Ionizing radiation from cosmic rays and gammas can induce discontinuous jumps in the environmental charge of superconducting qubits (charge jumps), causing correlated errors that challenge fault-tolerant quantum computing while simultaneously providing a detection signature for quantum sensing applications.
arXiv:2607. 14181v1 Announce Type: cross Abstract: The growing adoption of local inference frameworks such as Ollama has made it increasingly common for developers to run large code models on laptops and other resource-constrained hardware.
arXiv:2605. 25170v2 Announce Type: replace-cross Abstract: Training data for olfaction is scattered through disparate, non-standardized datasets that limit the ability to build representative world models.
arXiv:2607. 14176v1 Announce Type: new Abstract: Reliable, low-latency uplink connectivity is a key requirement for C-V2X networks in dense urban environments, where fast channel variations and blockages often degrade direct vehicle-to-infrastructure links.
arXiv:2601. 07944v2 Announce Type: replace-cross Abstract: Since the turn of the century, approximate Bayesian inference has steadily evolved as new computational techniques have been incorporated to handle increasingly complex, large-scale predictive problems.
arXiv:2607. 14249v1 Announce Type: new Abstract: Mobile usage traces are critical for tasks such as user behavior prediction and app recommendation, yet their use is constrained by privacy restrictions and costly large-scale data collection.
arXiv:2606. 19729v2 Announce Type: replace-cross Abstract: Planning under uncertainty is an essential capability for autonomous robots.
arXiv:2604. 26979v2 Announce Type: replace-cross Abstract: In-memory computing (IMC) is a paradigm that enables neural network inference by computing analog matrix-vector multiplications (MVM) directly in memory crossbar arrays, with the potential for energy efficiency gains over conventional von Neumann architectures.
arXiv:2602. 13061v2 Announce Type: replace-cross Abstract: The ability of Flow Matching (FM) to model complex conditional distributions has established it as the state-of-the-art for prediction tasks (e.
arXiv:2607. 14622v1 Announce Type: cross Abstract: Low-bit GEMM is increasingly central to efficient ML inference, yet very-low-bit execution remains a poor fit for conventional CPUs.
arXiv:2607. 14661v1 Announce Type: new Abstract: Deploying large language models (LLMs) as personal assistants on mobile devices demands privacy, low latency, and offline availability, yet the computational cost of giant models clashes with strict edge-hardware budgets.
arXiv:2607. 14545v1 Announce Type: new Abstract: Machine-learned predictions can speed up offline NP-hard optimization, but asking a predictor what to do amounts to asking it to solve the problem, and committing an unchecked prediction forfeits every worst-case guarantee.
arXiv:2607. 14618v1 Announce Type: new Abstract: CPUs are the most universal target for on-device LLM inference, but existing low-bit quantization methods offer either coarse operating points or fine-grained mixed precision that is difficult to execute efficiently on CPUs.