Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2608. 06135v1 Announce Type: new Abstract: Large Language Models (LLMs) such as ChatGPT and Claude are widely used for information retrieval and problem-solving.
arXiv:2608. 06227v1 Announce Type: cross Abstract: Despite advances in artificial intelligence (AI) across multiple sectors, today's AI tools, including deep learning and generative AI, still fail when embedded into physical systems, such as robots and vehicles operating under real-world physical laws.
arXiv:2608. 06146v1 Announce Type: new Abstract: End-to-end document parsers provide a unified interface, but serialize page layouts and regional contents into one autoregressive sequence.
arXiv:2510. 05589v3 Announce Type: replace-cross Abstract: Effective time series forecasting enables various real-world applications, benefiting from the proliferation of mobile devices.
arXiv:2608. 06025v1 Announce Type: new Abstract: In simulation-in-the-loop decision-making systems, reinforcement learning (RL) inference is often constrained by simulator-side execution overhead, where workloads are highly dynamic and sensitive to runtime thread configurations.
arXiv:2608. 05499v1 Announce Type: cross Abstract: Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices.
arXiv:2608. 05587v1 Announce Type: new Abstract: Autonomous mobile GUI agents require accurate action reflection for reliable long-horizon execution.
arXiv:2608. 05326v1 Announce Type: new Abstract: Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache.
arXiv:2608. 05660v1 Announce Type: new Abstract: As language models are increasingly used for tasks that require verifiable reasoning, reliably distinguishing sound reasoning from flawed reasoning has become an important practical problem.
arXiv:2608. 06150v1 Announce Type: new Abstract: Earth-surface monitoring requires change detection models capable of recognizing arbitrary semantic categories.
arXiv:2608. 05813v1 Announce Type: new Abstract: Personalizing language models (LMs) to individual user preferences is essential for aligning responses with diverse goals and backgrounds.
arXiv:2608. 06243v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outcome signals, but these signals are typically sparse and at the sequence-level.
arXiv:2608. 05863v1 Announce Type: new Abstract: Modern models no longer keep a plain KV cache: latent caches, learned sparse selectors and recurrent states each carry the model's memory in a different form, and each fails differently under compression.
arXiv:2608. 05245v1 Announce Type: new Abstract: Reusable skills, which encapsulate the procedural knowledge required to solve real-world professional tasks, offer LLM-based agents a path toward self-evolution in expert domains.
arXiv:2608. 06023v1 Announce Type: new Abstract: To address the limitations of video-based emotion recognition under ambiguous or socially masked behavioral cues, as well as the poor deployability of physiological signals, this paper proposes a reliability-aware physiology-to-video knowledge distillation framework, termed BioKD.
arXiv:2608. 05928v1 Announce Type: new Abstract: Single-cell transcriptomes are sparse observations of coordinated biological programmes, yet most self-supervised models learn by reconstructing individual genes.
arXiv:2608. 05464v1 Announce Type: cross Abstract: The pruning of network connections is key to brain function but, despite its importance, there exist few biologically-plausible pruning rules with demonstrated good performance.
arXiv:2608. 03228v2 Announce Type: replace Abstract: Existing low rank KV cache methods preserve either model weights or key variance, neither of which directly reflects the attention scores used during inference.
arXiv:2608. 05416v1 Announce Type: new Abstract: Can nonlinear dynamical systems be learned through a compact linear state-space representation, without directly solving a non-convex system-identification problem?
arXiv:2608. 06252v1 Announce Type: cross Abstract: Deaf and hard-of-hearing people in Bangladesh communicate mainly through Bangla Sign Language (BdSL).