Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2608. 16477v1 Announce Type: new Abstract: AI-RAN brings large language model (LLM) serving close to mobile users, but cellular handover can separate an active request from its inference state: the user attaches to a target base station (gNB) while the large and growing key-value (KV) cache remains at the source.
arXiv:2608. 15438v1 Announce Type: cross Abstract: Building approximate nearest neighbor (ANN) indexes at billion scale is often dominated by expensive global clustering or graph construction, making time-to-index a first-order systems concern.
arXiv:2608. 15062v1 Announce Type: cross Abstract: Scaling transformer language models creates an inherent tension between expressivity and memory efficiency.
arXiv:2608. 14684v1 Announce Type: cross Abstract: LLM judges increasingly evaluate responses against fine-grained rubric checklists.
arXiv:2608. 14728v1 Announce Type: cross Abstract: On-policy distillation (OPD) has emerged as an effective paradigm for transferring knowledge between language models, where a student is trained to align its next-token distribution with the teacher's along its own trajectories.
arXiv:2608. 16739v1 Announce Type: new Abstract: Reinforcement learning algorithms for Large Language Models (LLMs) are largely distinguished by their variance reduction strategy.
arXiv:2608. 15516v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated strong performance in multimodal understanding and generation.
arXiv:2608. 16873v1 Announce Type: new Abstract: High-fidelity finite-element simulations can provide accurate numerical predictions for side-branch resonators, but large simulation datasets are expensive to generate and purely data-driven surrogates may become unreliable when simulation-labelled data are scarce.
OceanDepths is the first open, global, AI‑ready dataset that pairs satellite‑derived sea surface temperature, salinity, and height with co‑located EN4 subsurface temperature and salinity profiles, complemented by GLORYS12 reanalysis data. It covers 2000–2024 at 0.1°×0.1° spatial resolution and weekly temporal resolution, providing over 9.5 million paired profiles interpolated to 50 depth levels. The dataset’s 4‑D multivariate structure, high resolution, long temporal extent, and extreme sparsity of subsurface observations make it a challenging testbed for novel AI methods, with demonstrated use in subsurface state reconstruction and potential for observation‑based forecasting.
arXiv:2608. 14774v1 Announce Type: new Abstract: Modern sequence models heavily rely on massive memory footprints and large-batch stochastic optimization, barriers that restrict sample efficiency and continual learning.
arXiv:2608. 14644v1 Announce Type: new Abstract: Real-world LLM deployments increasingly rely on runtime-injected prohibitions--enterprise policies, PII redlines, tool boundaries--that vary per request and per tenant.
arXiv:2608. 16073v1 Announce Type: cross Abstract: Sequential recommenders often struggle with sparse and noisy histories, limiting generalization to unseen interactions.
arXiv:2608. 14624v1 Announce Type: new Abstract: Multi-agent LLM systems have emerged as an important deployment paradigm for AI services, where each user request is decomposed into a sequence of specialized agents.
arXiv:2608. 15117v1 Announce Type: new Abstract: Analytical models of peak VRAM consumption for LLM inference decompose memory into weight-storage, KV-cache, and activation terms parameterized by step count, tool invocations, and context expansion.
arXiv:2608. 14614v1 Announce Type: cross Abstract: As AI datacenters retire functional GPUs, vast quantities of still capable accelerators enter secondary markets.
arXiv:2608. 16010v1 Announce Type: new Abstract: Model compression is critical for deploying networks on resource-constrained edge devices.
arXiv:2608. 15592v1 Announce Type: new Abstract: Efficient LLM serving is often bottlenecked by the need to pad sequences to a fixed maximum length, and this wastes compute and degrades throughput.
arXiv:2603. 02830v2 Announce Type: replace-cross Abstract: Predicting future student responses to questions is particularly valuable for educational learning platforms where it enables effective interventions.
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. 14583v1 Announce Type: cross Abstract: Vehicular Ad Hoc Networks (VANETs) are a key component of intelligent transportation systems, enabling real-time communication between vehicles.