Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2604. 26256v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a critical paradigm for LLM post-training, yet the rollout phase -- accounting for 50--80% of total step time -- is bottlenecked by skewed generation: long-tailed trajectories indispensable for model performance block the entire training pipeline.
arXiv:2509. 14230v2 Announce Type: replace Abstract: While structured pruning presents a highly effective pathway for accelerating Large Language Model (LLM) inference, existing methods frequently suffer from significant performance degradation and demand computationally retraining to recover capabilities.
arXiv:2605. 14672v2 Announce Type: replace Abstract: Estimating an $N \times N$ quantum kernel from circuit fidelities requires $\Theta(N^2 S)$ measurement shots, the dominant bottleneck for deployment on near-term hardware.
arXiv:2607. 16877v1 Announce Type: cross Abstract: The increasing complexity of next-generation wireless networks has driven the integration of artificial intelligence (AI) into wireless communications.
arXiv:2607. 17154v1 Announce Type: cross Abstract: Although mixture-of-experts, MoE, models have been increasingly adopted to scale large language models with moderate computation cost, it remains challenging to deploy MoE inference over resource-constrained and bandwidth-limited edge infrastructures.
arXiv:2607. 16213v1 Announce Type: new Abstract: Large Language Models (LLMs) generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length, creating a major bottleneck.
arXiv:2607. 16209v1 Announce Type: new Abstract: Context reranking and pruning have become essential for improving the efficiency of modern Retrieval-Augmented Generation (RAG) systems, yet an interpretable and unified framework remains underexplored.
arXiv:2607. 18236v1 Announce Type: cross Abstract: Pretrained dense visual features from Vision Transformers (ViTs) are powerful yet have been underutilized in robot learning.
arXiv:2604. 27967v2 Announce Type: replace Abstract: Background: We introduce StructGP, a continuous-time multi-task Gaussian process that couples process convolutions with differentiable structure learning to uncover a sparse, ordered directed acyclic graph (DAG) of inter-variable dependencies while preserving principled uncertainty.
arXiv:2607. 17317v1 Announce Type: cross Abstract: Autonomous systems rely on a perception module to navigate through dynamic environments.
arXiv:2607. 16927v1 Announce Type: cross Abstract: We introduce Deep Adaptive Bayesian Screening (DABS), a method for performing adaptive factorial screening in high-dimensional discrete design spaces.
arXiv:2607. 18110v1 Announce Type: new Abstract: Reinforcement learning (RL) on open-ended tasks compresses an LLM's rubric-based evaluation into a scalar reward, discarding rich textual feedback and conflating responses with distinct quality profiles.
arXiv:2607. 18101v1 Announce Type: new Abstract: On-device model adaptation is essential to enable lifelong personalization on resource-constrained hardware, but compute, power, and memory limitations of such devices make end-to-end backpropagation impractical for modern deep neural networks.
arXiv:2607. 17913v1 Announce Type: cross Abstract: Distributed Fine-Tuning (DFT) of large-scale Foundation Models (FMs) on resource-constrained edge devices is limited by local compute constraints and communication overhead.
arXiv:2607. 16204v1 Announce Type: new Abstract: Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments.
arXiv:2605. 29547v2 Announce Type: replace-cross Abstract: Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components such as ReLU activations and quantization operators.
arXiv:2607. 16276v1 Announce Type: cross Abstract: Quantum-repeater networks require adaptive control policies that balance entanglement generation rate, end-to-end fidelity, purification overhead, and memory-induced latency.
arXiv:2607. 17390v1 Announce Type: cross Abstract: Kernel regression with tensor trains and Hadamard overparameterization (KReTTaH) is introduced as a training-data-free, interpretable, and nonparametric framework for multi-way data imputation.
arXiv:2602. 02138v3 Announce Type: replace-cross Abstract: Despite the remarkable success that Multi-Agent Code Generation Systems (MACGS) have achieved, the inherent complexity of multi-agent architectures produces substantial volumes of intermediate outputs.
arXiv:2607. 16296v1 Announce Type: cross Abstract: Continuous EEG monitoring for epilepsy is constrained by the limited power and memory budgets of wearable and implantable devices.