Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2609.23989v1 Announce Type: new Abstract: Building general-purpose agents for industrial deployment requires integrating multiple capabilities, each typically acquired at a distinct stage of tr...
arXiv:2609.22981v1 Announce Type: cross Abstract: We present a dual-locking method for securing trained neural networks that combines key-driven index permutation with PIN-based watermarking based on...
arXiv:2609.23444v1 Announce Type: cross Abstract: Engineering change order (ECO) is an important step in repairing timing and electrical violations during the late stages of chip design. Existing Age...
arXiv:2609.24084v1 Announce Type: cross Abstract: Open-weight large language models (LLMs) can be copied, modified, and redeployed behind black-box APIs, making post-release ownership verification di...
arXiv:2609.24757v1 Announce Type: cross Abstract: This paper presents the design, optimization, implementation, and on-board validation of a neural processing unit (NPU) accelerator for real-time veh...
arXiv:2609.12551v2 Announce Type: replace-cross Abstract: AI is beginning to make substantive contributions to LLM inference optimization. Existing AI optimizations are predominantly profiling-based....
arXiv:2609.25623v1 Announce Type: new Abstract: More privileged information does not always make a better teacher. We study this tension in on-policy self-distillation (OPSD), where a frozen copy of...
arXiv:2609.25809v1 Announce Type: new Abstract: Fine-grained mixture-of-experts (MoE) architectures have become a mainstream design for open-weight LLMs, with hundreds of experts and increasingly man...
arXiv:2609.25963v1 Announce Type: new Abstract: Transformer architectures exhibit cross-layer redundancies, yet post-training compression pipelines typically optimize layers in isolation or rely on h...
arXiv:2609.26067v1 Announce Type: new Abstract: Kolmogorov--Arnold Networks (KANs) replace scalar edge weights with learnable univariate functions, increasing flexibility but also parameter memory be...
arXiv:2609.26333v1 Announce Type: new Abstract: Prefill and decode reward different approaches to quantization: low-precision arithmetic accelerates prompt processing, while compact weights reduce me...
arXiv:2609.26355v1 Announce Type: new Abstract: Reinforcement learning has become a central component of large language model (LLM) post-training, yet token-level credit lacks a generally accepted ma...
arXiv:2609.26708v1 Announce Type: new Abstract: Quantization-aware distillation (QAD) restores much of the short-form question-answering performance lost to sub-3-bit quantization, yet leaves mathema...
arXiv:2609.25537v1 Announce Type: new Abstract: Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing laten...
arXiv:2609.26368v1 Announce Type: new Abstract: Long-horizon and multi-turn agents typically generate short actions and process long observations from tools and environments. This growing context dem...
arXiv:2609.25176v1 Announce Type: cross Abstract: Real-time voice assistants must reason over evolving requests, execute actions, and follow conversational rules. Qwen-Audio-3.1-Realtime brings these...
arXiv:2609.25498v1 Announce Type: cross Abstract: Deploying Large Language Models for runtime operational triage incurs prohibitive latency (>100-500 ms), high VRAM requirements (>4-8 GB), and excess...
arXiv:2609.26073v1 Announce Type: new Abstract: Pathology foundation models (PFMs) provide strong tile-level representations but remain difficult to interpret at the cellular and microenvironmental s...
arXiv:2609.26425v1 Announce Type: new Abstract: KV cache memory has become a major deployment bottleneck for video generation and world models, which motivates low-bit quantization study for efficien...
arXiv:2609.24526v2 Announce Type: replace Abstract: Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints...