Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 10109v1 Announce Type: cross Abstract: Deploying large-scale transformer models on resource-constrained edge devices remains a challenge due to the high energy and memory overhead inherent in static inference, which processes simple and complex tokens with uniform intensity.
arXiv:2604. 04690v2 Announce Type: replace-cross Abstract: Bin picking in real industrial environments remains challenging due to severe clutter, occlusions, and the high cost of traditional 3D sensing setups.
arXiv:2607. 11473v1 Announce Type: cross Abstract: In this paper, we propose TECO, a multi-dimensional pruning framework to collaboratively prune the three dimensions (depth, width, and resolution) of convolutional neural networks (CNNs) for better execution efficiency on embedded hardware.
arXiv:2607. 10805v1 Announce Type: cross Abstract: On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs).
arXiv:2604. 16514v5 Announce Type: replace-cross Abstract: Autoregressive vision-language models (VLMs) deliver strong multimodal capability, but their token-by-token decoding imposes a fundamental inference bottleneck.
arXiv:2603. 16883v2 Announce Type: replace-cross Abstract: Inertial measurement unit-based online handwriting recognition enables the recognition of input signals collected across different writing surfaces but remains challenged by uneven character distributions and inter-writer variability.
arXiv:2510. 08233v3 Announce Type: replace Abstract: Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput.
arXiv:2607. 10044v1 Announce Type: new Abstract: Constrained decoding is essential in generative retrieval, where document identifiers generated directly from a query must exactly match a predefined library of valid IDs.
arXiv:2311. 00314v2 Announce Type: replace Abstract: Topic modeling has emerged as a valuable tool for discovering patterns and topics within large collections of documents.
arXiv:2607. 10942v1 Announce Type: cross Abstract: Physical AI systems, such as autonomous vehicles and intelligent machines, require transformer-based perception models that satisfy stringent edge latency and energy constraints.
arXiv:2607. 10611v1 Announce Type: new Abstract: Training with quantized weights can reduce costs but often results in degraded accuracy, especially when optimization is carried out in low precision, without storing high-precision copies.
arXiv:2607. 10582v1 Announce Type: cross Abstract: Large language model (LLM) agents accumulate heterogeneous context, including system instructions, plans, user turns, retrieved documents, tool outputs, and intermediate reasoning, whose key-value (KV) cache can become a major memory bottleneck.
arXiv:2607. 11211v1 Announce Type: new Abstract: The popularity of large language models (LLMs) escalates an ongoing demand for effective inference.
arXiv:2607. 10406v1 Announce Type: cross Abstract: Self-supervised learning (SSL) has emerged as an effective paradigm for learning transferable representations from large-scale unlabeled whole slide images (WSIs).
arXiv:2607. 10461v1 Announce Type: cross Abstract: Layout-based 3D scene synthesizers place each object using two human-annotated channels: a categorical class label and a canonical-pose convention.
arXiv:2605. 31191v2 Announce Type: replace Abstract: We investigate how teacher-student capacity relationships modulate knowledge distillation (KD) effectiveness in ResNet-based image classification on CIFAR-10.
arXiv:2607. 09709v1 Announce Type: new Abstract: Post-training a code generator against a learned judge can optimize proxy features that raise the score without improving the artifact.
arXiv:2607. 11565v1 Announce Type: cross Abstract: Active flow control involves nonlinear dynamics, partial observations, and computationally expensive simulations, making controller design particularly challenging.
arXiv:2607. 10295v1 Announce Type: cross Abstract: We demonstrate that AI-driven program synthesis can autonomously discover fundamental strategies for decomposing unitary matrices in photonic networks.
arXiv:2607. 09686v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) language models separate total parameter count from per-token active computation, but local inference systems often still require the full model, key-value cache, runtime buffers, and operatingsystem headroom to fit in fast memory.