arXiv:2605. 26660v2 Announce Type: replace Abstract: Quantization is an effective approach to reduce the memory footprint and inference cost of large language models (LLMs), yet maintaining performance in the ultra-low-bit regime remains challenging.
By Phong Nam Huu Nguyen, Khoi M. Le, Cong-Duy T Nguyen, Anh Tuan Luu, Thong Thanh Nguyen, Tho Quan
arXiv:2608. 07335v1 Announce Type: cross Abstract: Recent advancements in deep reinforcement learning have increasingly favored simplified, highly parallelized paradigms.
By Taha Shieenavaz, Shabnam Zareshahraki, Loris Nanni
arXiv:2607. 06601v1 Announce Type: cross Abstract: Conditional computation can decouple language model quality from per-token inference cost, yet leading techniques act on a single axis in isolation: Mixture-of-Experts (MoE) sparsifies the FFN, Mixture-of-Depths (MoD) skips whole transformer blocks, and KV-cache quantization compresses attention memory.
By Andrii Balashov, Olena Ponomarova
Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices. Pruning and quantization address this, but rely on manual, expert choices and on algorithms that are hard to apply across architectures.
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.
By Sadegh Jafari, Mohiuddin Bilwal, Fan Zhou, Brian Gelder, Ali Jannesari
arXiv:2602. 18109v3 Announce Type: replace Abstract: Real-time schedulers must reason about tight deadlines under strict compute budgets.
By Rong Fu, Yibo Meng, Zeyu Zhang, Ziming Guo, Jia Yee Tan, Xiaojing Du, Simon James Fong