Structured pruning is a promising approach for compressing large language models (LLMs), yet existing methods rely heavily on greedy heuristics that produce myopic decisions, and often fail to precisely meet target compression budgets. We present SNIPER, a two-stage structured pruning framework that solves a knapsack optimization over coarse-granularity components to yield conditionally optimal parameter allocations with respect to fixed importance estimates, followed by a fine-grained pruning stage to meet strict budget constraints.
Vision-Language-Action (VLA) models promise to bring end-to-end reasoning to autonomous driving, but their computational cost remains far too high for real-time control. The core challenge is structural: VLA inference is not a single bottleneck but a cascade of four.
Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typically emphasize only one side of this requirement: Vision-Language-Action (VLA) models exploit VLM priors for semantic reasoning, while World Action Models (WAMs) provide future-aware prediction through generative world modeling.
arXiv:2608. 11240v1 Announce Type: new Abstract: Vector quantization is an old problem but has recently become central to AI infrastructure.
By Ashwin Padaki, Amir Ingber, Edo Liberty
arXiv:2607. 12501v3 Announce Type: replace Abstract: The Forward-Forward algorithm trains each layer locally, so that a scalar goodness - the sum of squared activations - is high on real inputs and low on contrastive ones.
By Paolo Giannitrapani
arXiv:2608. 12140v1 Announce Type: cross Abstract: Boosted decision trees (BDTs) are widely used in latency-critical applications, but efficient hardware deployment remains challenging.
By Zhiqiang Que, Chang Sun, Haiyang Wang, Dinesh Pamunuwa, Roshan Weerasekera, Qijia Tang, Bakhtiar Zadeh, Wayne Luk, Maria Spiropulu
arXiv:2507. 14267v2 Announce Type: replace Abstract: Large language model (LLM) agents can execute long-horizon scientific workflows, but their numerical outputs are difficult to trust: agents lose context, game verification checks, and can produce large volumes of plausible yet invalid results.
By Ziqi Wang, Hongshuo Huang, Hancheng Zhao, Changwen Xu, Shang Zhu, Jan Janssen, Venkatasubramanian Viswanathan
arXiv:2608. 11829v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a promising post-training technique for enhancing LLM reasoning.
By Xinmu Ge, Zizhuo Zhang, Yu Huang, Jianing Zhu, Lin Yuan, Wanli Gu, Weichang Wu, Weiran Huang, Xiaolu Zhang, Bo Han, Jun Zhou, Jiangchao Yao
arXiv:2608. 11283v1 Announce Type: cross Abstract: Computation-ready metal-organic framework (MOF) databases are essential for high-throughput screening, yet many reported crystal structures remain chemically unreasonable or disordered, compromising simulation fidelity.
By Guobin Zhao, Xiao-Yan Li
arXiv:2602. 17554v3 Announce Type: replace Abstract: Training large-scale generative models is resource-intensive and relies heavily on heuristic dataset weighting.
By Corinna Cortes, Mehryar Mohri, Yutao Zhong
arXiv:2608. 11271v1 Announce Type: cross Abstract: Next-generation Synthetic Aperture Radar (SAR) missions will generate data far faster than they can downlink, making onboard data reduction essential for near-real-time Earth observation.
By C\'edric L\'eonard, Francescopaolo Sica, Martin Schulz
arXiv:2608. 12239v1 Announce Type: cross Abstract: Use this plain-text version for the arXiv abstract field: Learned image compression (LIC) models achieve strong rate-distortion performance but are hindered by high computational complexity and encoding-decoding mismatches across heterogeneous hardware platforms.
By Yuefeng Zhang
arXiv:2608. 11285v1 Announce Type: cross Abstract: Despite the practical relevance of sparse decision-based black-box threats, they have received limited attention in semantic segmentation.
By Dongsu Song, DaeYun GO, Boseung Seo, Jay Hoon Jung
arXiv:2511. 18191v2 Announce Type: replace Abstract: Time series forecasting drives operational decisions under tight latency budgets, and autoregressive time series foundation models (TSFMs) increasingly deliver the most accurate forecasts.
By Pranav Subbaraman, Fang Sun, Jinxi Yu, Yue Yao, Huacong Tang, Xiao Luo, Yizhou Sun
arXiv:2510. 26690v3 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) has become a popular technique for parameter-efficient fine-tuning of large language models (LLMs).
By Amir Reza Mirzaei, Yuqiao Wen, Yanshuai Cao, Lili Mou
arXiv:2608. 11967v1 Announce Type: cross Abstract: Large language model agents increasingly rely on long-horizon reasoning to solve complex tasks involving planning, tool use, and memory.
By Zhixin Zhang, Xinke Jiang, Zhibang Yang, Weixuan Xu, Guohong Qiu, Xu Chu, Junfeng Zhao, Yasha Wang
arXiv:2608. 11532v1 Announce Type: cross Abstract: In recent research on the Digital Twin-based Vehicular Ad hoc Network(DT-VANET), Federated Learning (FL) has shown its ability to provide data privacy.
By Qasim Zia, Saide Zhu, Haoxin Wang, Zafar Iqbal, Yingshu Li
arXiv:2608. 11705v1 Announce Type: new Abstract: Aligned large language models (LLMs) are expected to exhibit safety behavior based on the content of the user request: they should refuse unsafe requests and comply with safe ones.
By Lang Cao
arXiv:2608. 11226v1 Announce Type: new Abstract: Reinforcement-learning post-training dominates modern language-model development, yet its power behavior on GPU hardware has not been characterized, and datacenters manage GPU power with workload-blind mechanisms, static caps and reactive throttling, that slow hardware indiscriminately.
By Eliseo Curcio
arXiv:2608. 11698v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own trajectories under dense token-level supervision from a teacher.
By Yang Sun, Lichao Ma, Houyuan Qin, Yuxin Liu, Hanyang Lu, Yao Zhu, Pinlong Cai, Guohang Yan