Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2608. 14929v1 Announce Type: cross Abstract: Open-weight language models are fine-tuned, quantized, pruned, and merged, yet their provenance is often undocumented.
arXiv:2608. 14694v1 Announce Type: new Abstract: Foundation models are emerging as a transformative paradigm for AI-native sixth-generation (6G) wireless networks by enabling scalable, transferable, and data-efficient intelligence across diverse communication tasks.
arXiv:2608. 16354v1 Announce Type: new Abstract: Driving video generation models support autonomous-driving development by predicting controllable future scenes for simulation, planning evaluation, and offline data generation.
arXiv:2608. 14563v1 Announce Type: cross Abstract: Forward-Pass-Only MLP training (FPO) adapts large language models without a backward pass through the model body, achieving 2.
arXiv:2608. 14586v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are becoming a promising paradigm for autonomous driving, but their deployment on existing vehicle platforms remains difficult because they introduce both high inference latency and strong GPU-side resource pressure.
arXiv:2608. 14922v1 Announce Type: cross Abstract: Mechanistic interpretability has recently expanded to Vision Transformers (ViTs), with Sparse Autoencoders (SAEs) increasingly used as post-hoc tools to decompose internal representations into sparse and more interpretable features.
arXiv:2608. 15636v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in the field of embodied AI, but their high computational cost and limited predicted action length hinder real-time deployment.
arXiv:2608. 16353v1 Announce Type: cross Abstract: Even well-aligned large language models confidently generate factually incorrect text, making hallucination a persistent reliability risk in high-stakes deployments.
arXiv:2608. 16760v1 Announce Type: new Abstract: Reliable optimization is central to neural network (NN) training, yet Adam, the default optimizer for modern LLMs, rests on a fragile foundation.
arXiv:2608. 15533v1 Announce Type: cross Abstract: Linear attention models eliminate the quadratic prefix computation and context-growing KV cache of softmax attention by replacing pairwise token interactions with recurrent state updates.
arXiv:2608. 15306v1 Announce Type: cross Abstract: High-throughput single-cell and spatial transcriptomic technologies provide high-resolution snapshots of heterogeneous cellular states, but their destructive nature prevents repeated measurements of the same cells over time.
arXiv:2608. 15215v1 Announce Type: cross Abstract: Token-level knowledge distillation (KD) matches two conditional distributions per position, yet the standard objectives compare them pointwise: a Kullback-Leibler gradient is blind to which wrong token receives probability mass.
arXiv:2608. 14658v1 Announce Type: cross Abstract: We introduce pico-type, a byte-level multi-head content classifier with approximately 1.
arXiv:2608. 16010v1 Announce Type: new Abstract: Model compression is critical for deploying networks on resource-constrained edge devices.
arXiv:2509. 10691v3 Announce Type: replace-cross Abstract: Decentralized federated learning enables collaborative model training without a central server, but shared model updates can still leak sensitive information through inversion, reconstruction, and membership inference attacks.
arXiv:2608. 14614v1 Announce Type: cross Abstract: As AI datacenters retire functional GPUs, vast quantities of still capable accelerators enter secondary markets.
arXiv:2608. 16797v1 Announce Type: cross Abstract: Industrial recommenders rely on two model families that have evolved largely independently: feature-interaction models over multi-field user/item features, and sequential models over user-behavior histories.
arXiv:2608. 16316v1 Announce Type: cross Abstract: Large Multimodal Models (LMMs) for video reasoning have long been hindered by the high computational cost of processing vast amounts of visual information.
arXiv:2608. 15475v1 Announce Type: cross Abstract: Quantized Vision-Language-Action (VLA) models expose a weight-fault surface: Rowhammer-style faults can corrupt deployed INT8 bits.
arXiv:2608. 15454v1 Announce Type: new Abstract: Byte-level hierarchical language models (LMs) have recently emerged as a robust alternative to their popular counterparts that use subword tokenization.