Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 16184v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) is a popular class of large language models (LLMs), offering high efficiency and accuracy.
arXiv:2607. 15810v1 Announce Type: new Abstract: Rollout generation is a major bottleneck in Reinforcement Learning (RL) for Mixture-of-Experts (MoE) Large Language Models, motivating low-precision rollout acceleration such as FP8.
arXiv:2607. 15467v1 Announce Type: new Abstract: Knowledge distillation enables an adversary to replicate a proprietary classifier by querying its prediction interface and training a surrogate on the returned probability vectors.
arXiv:2602. 04643v2 Announce Type: replace Abstract: Time-series anomaly prediction aims to forecast future system failures before they fully emerge, making latent predictive models such as JEPA a promising framework for capturing precursor dynamics.
arXiv:2607. 15919v1 Announce Type: cross Abstract: Data-free knowledge distillation transfers the knowledge encoded in a teacher model to a student model without access to the original training data.
arXiv:2607. 16027v1 Announce Type: new Abstract: Introduction: Biological systems face anatomical and metabolic constraints, including costly synaptic maintenance and limited connectivity.
arXiv:2603. 26556v2 Announce Type: replace-cross Abstract: Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising approach to reducing inference costs.
arXiv:2607. 15328v1 Announce Type: cross Abstract: Complex algorithms such as deep neural networks are increasingly being deployed on embedded, resource constrained platforms.
arXiv:2605. 15422v3 Announce Type: replace Abstract: Modern RL post-training methods such as GRPO and DAPO train on N response sequences of R tokens sampled from a shared prompt of P tokens, but standard FlashAttention replicates all P prompt tokens N times across both forward and backward passes -- duplicating compute and memory on identical hidden states.
arXiv:2607. 15456v1 Announce Type: new Abstract: Looped, weight-tied Transformers reduce parameters by reusing a block, but decoding still stores a separate K/V cache for every recurrence step.
arXiv:2607. 15421v1 Announce Type: new Abstract: Compact medical-image classifiers need efficiency and interpretable evidence, yet these goals are often addressed separately.
arXiv:2607. 16012v1 Announce Type: cross Abstract: Multi-Task Learning (MTL) in robotics perception systems supports comprehensive 3D spatial scene understanding by integrating semantic segmentation and depth estimation.
arXiv:2603. 03751v2 Announce Type: replace-cross Abstract: Cooperative object transport in unstructured environments remains challenging for assistive humanoids because strong, time-varying interaction forces can make tracking-centric whole-body control unreliable, especially in close-contact support tasks.
arXiv:2607. 15621v1 Announce Type: cross Abstract: Large language models bring instruction following and scene reasoning to end-to-end driving, but their inference latency collides with the control rate a vehicle requires.
arXiv:2607. 15509v1 Announce Type: cross Abstract: We present a fully automated closed-loop AutoML framework that uses GPT-5, GPT-4o, and Claude Sonnet 4 as autonomous neural architecture designers for cross-lingual handwritten optical character recognition.
arXiv:2607. 15587v1 Announce Type: new Abstract: Continual learning studies how deployed language models can continually acquire new tasks without expensive retraining from scratch.
arXiv:2607. 15593v1 Announce Type: cross Abstract: LLM agents increasingly rely on tool calling to act on external systems, and the Model Context Protocol (MCP) has quickly become its de facto interface.
arXiv:2603. 02142v2 Announce Type: replace-cross Abstract: Scaling laws assume larger models trained on more data consistently outperform smaller ones -- an assumption that drives model selection in computer vision but remains untested in resource-constrained Earth observation (EO).
arXiv:2607. 15280v1 Announce Type: new Abstract: Sequential diagnosis requires balancing diagnostic accuracy against resource costs through iterative information gathering.
arXiv:2607. 15525v1 Announce Type: cross Abstract: Kolmogorov--Arnold Networks (KANs) replace fixed node activations with learned one-dimensional edge functions, offering an explicit interface for interpretation and a possible alternative to transformer feed-forward networks.