Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
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:2605. 11165v3 Announce Type: replace Abstract: Federated learning (FL) in heterogeneous environments remains challenging because client models often differ in both architecture and data distribution.
arXiv:2605. 18331v2 Announce Type: replace Abstract: Large Language Models (LLMs) have experienced significant growth and development in recent years.
arXiv:2607. 11796v1 Announce Type: new Abstract: Selective state-space models such as Mamba route information through a bank of first-order modes whose input coupling is set by a learned selection mechanism.
arXiv:2607. 09957v1 Announce Type: cross Abstract: This report studies on-device English-to-Traditional-Chinese subtitle translation for Taiwan under short inputs, short outputs, batch-size-one inference, low latency, and privacy constraints.
arXiv:2607. 10836v1 Announce Type: new Abstract: Multi-agent ensembling multiplies active parameters and inference cost without answering three basic questions: which agents to consult, how deeply a query should traverse a hierarchy of agents, and when inter-agent communication is worth its cost.
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:2607. 09713v1 Announce Type: new Abstract: A key step toward autonomous industrial operation is the ability to create and reconfigure control policies from natural-language requirement specifications, with minimal or no manual redesign.
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:2606. 12936v2 Announce Type: replace-cross Abstract: Wet-lab robots can improve the reproducibility, throughput, and safety of biomedical experiments, but scaling their learning requires customizable simulators for safe and reproducible task generation, open editable laboratory assets, and efficient pipelines that turn limited demonstrations into usable training data.
arXiv:2602. 17686v5 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) reasoning has significantly improved LLMs' mathematical problem-solving capabilities, but distilling such capabilities into smaller models remains challenging due to the capacity mismatch between verbose teachers and compact students.
arXiv:2601. 07155v3 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from large language models to smaller student models; however, conventional supervised KD often suffers from a distribution mismatch between training and inference.
arXiv:2601. 07372v2 Announce Type: replace-cross Abstract: While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup, forcing them to inefficiently simulate retrieval through computation.
arXiv:2607. 09696v1 Announce Type: cross Abstract: Deep neural models for click-through rate prediction often exhibit a sharp decline in validation performance immediately after the first training epoch despite continued improvement in training loss.
arXiv:2607. 10183v1 Announce Type: cross Abstract: Running large language models on consumer devices such as laptops and desktops is challenging because model weights often exceed GPU memory capacity, making offloading inference necessary to extend effective model capacity with CPU memory.
arXiv:2112. 06362v5 Announce Type: replace Abstract: We consider the problem of scheduling in multi-class, parallel-server queuing systems with uncertain rewards from job-server assignments.
arXiv:2607. 10784v1 Announce Type: cross Abstract: Deploying deep learning models for automated electrocardiogram classification on resource-constrained wearable devices remains challenging due to high computational costs.
arXiv:2607. 10855v1 Announce Type: new Abstract: Quantization is a powerful strategy to build capable and resource-efficient large language models (LLMs) by reducing the bitwidth of the parameters.
arXiv:2607. 10618v1 Announce Type: cross Abstract: We consider the recovery of a pair of sparse vectors from a limited number of nonlinear observations of their superposition: $y_i=g(\inner{\ba_i}{\bPhi\bw^\ast+\bPsi\bz^\ast})+e_i$, $i=1,\dots,m$, with $m\ll n$, incoherent orthonormal bases $\bPhi,\bPsi$, a scalar link $g$, and noise $e_i$ that may be heavy-tailed or contaminated.
arXiv:2607. 10137v1 Announce Type: new Abstract: Post-training quantization (PTQ) of large language models degrades sharply below 4-bit precision.