Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 24083v1 Announce Type: new Abstract: Reinforcement learning can produce robust humanoid controllers, but each new task is typically trained as a separate policy with its own reward design and training process.
arXiv:2607. 23159v1 Announce Type: new Abstract: Test-time search lets small video diffusion models rival larger ones, but costs 2-10x more.
arXiv:2607. 23731v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own trajectories while a teacher supplies dense token-level likelihoods at student-visited prefixes.
arXiv:2607. 24280v1 Announce Type: new Abstract: Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this with outcome-based reinforcement learning (RL) provides only sparse supervision.
arXiv:2607. 24148v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have demonstrated strong potential for embodied AI, yet their high inference latency on GPUs limits real-time deployment.
arXiv:2607. 23503v1 Announce Type: cross Abstract: Internet of Things (IoT) applications generate vast amounts of Correlated Time Series (CTS) data that often contain missing values and require imputation.
arXiv:2607. 24522v1 Announce Type: new Abstract: While on-policy distillation (OPD) effectively addresses sparse rewards and exposure bias in large language model post-training, its extension to flow models remains underexplored.
arXiv:2607. 23293v1 Announce Type: cross Abstract: Image-source-method (ISM)-based room impulse response (RIR) simulation is a useful and physically interpretable tool for acoustic scene modeling, but full-order ISM becomes computationally expensive as the reflection order and room complexity increase.
arXiv:2607. 23044v1 Announce Type: cross Abstract: Quantum devices are open systems whose dynamics interleave coherent evolution with dissipation, and benchmarking, error mitigation, and error correction all rest on a faithful model of both.
arXiv:2506. 01503v2 Announce Type: replace Abstract: With the rise of large pre-trained foundation models for automatic speech recognition new challenges appear.
arXiv:2607. 24213v1 Announce Type: new Abstract: Integrating heterogeneous industrial knowledge, including factual relations and decision constraints, remains a core challenge in industrial information systems.
arXiv:2607. 24562v1 Announce Type: new Abstract: Large language models serve heterogeneous populations structured by domain, topic difficulty, and linguistic style.
arXiv:2607. 23115v1 Announce Type: cross Abstract: This paper aims to enable computation- and communication-efficient GPU sharing across devices within local area networks (LANs), facilitating ubiquitous AI inference on heterogeneous personal devices.
arXiv:2607. 22629v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time.
arXiv:2607. 24672v1 Announce Type: new Abstract: In safety-critical sectors such as robotics and automotive engineering, the deployment of Deep Reinforcement Learning (DRL) is often hindered by the black-box nature of deep neural networks.
arXiv:2607. 22785v1 Announce Type: cross Abstract: Apple-Silicon SoCs share CPU, GPU, and Neural Engine over one unified memory system, raising the question of whether transformer inference can be accelerated by splitting single operators across units.
arXiv:2604. 16648v2 Announce Type: replace Abstract: Tandem mass spectrometry is prominent in scientific discovery workflows for identifying unknown small molecules, yet high-throughput structural elucidation remains challenging.
arXiv:2607. 23794v1 Announce Type: cross Abstract: Pathological diagnosis is inherently multi-scale, requiring the integration of global tissue architecture at low magnification with cellular morphology at higher magnification.
arXiv:2607. 22662v1 Announce Type: new Abstract: Open-web corpora curated via highly selective filters, such as FineWeb-Edu and DCLM, constitute the core of LLM pretraining data and have significantly advanced LLM performance.
arXiv:2512. 12713v2 Announce Type: replace-cross Abstract: Control policies are often implemented with fixed-capacity multilayer perceptrons trained by backpropagation, which require architecture selection in advance and cannot adapt their capacity during learning.