arXiv Machine Learning August 28, 2026 By Ahmed E. Helal, Fabio Checconi, Jan Laukemann, Yongseok Soh, Jesmin Jahan Tithi, Fabrizio Petrini, Jee Choi

ReLATE: Accelerating Tensor Decomposition via Safe and Efficient Learning of Sparse Encodings

Read the original on arXiv Machine Learning →

ReLATE is a reinforcement‑learned framework that automatically discovers safe and efficient sparse encodings for tensor decomposition, eliminating the need for expert‑designed formats. It combines model‑free and model‑based learning, elastic training, rule‑driven action masking, and dynamics‑informed filtering to guarantee correct encoding with bounded execution time, even early in training. After offline training, ReLATE deploys the optimal encoding with negligible overhead and achieves up to 2× speedups over the best expert‑designed format, with a geometric‑mean speedup of 1.38–1.41× on diverse real‑world sparse tensors.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 24

Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs

arXiv:2607. 21291v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong generation and reasoning performance, but the Transformer architecture incurs high inference cost.

By Yidu Wu, Xiang Wang, Kejie Zhao, Zhangchi Wang, Qinghai Guo, Xiaoying Tang

llms fine-tuning efficiency safety

arXiv AI

3d ago

Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse Imagination

arXiv:2609.38984v1 Announce Type: cross Abstract: World-action models (WAMs) leverage pretrained video models to improve generalization in robot control by jointly predicting future visual states and...

By Xinling Xie, Haodong Wang, Jiazhi Mi, Zhiming Liu, Zicong Hong, Xiaoyi Pang, Qianli Liu, Yangjia Hu, Ying Chen, Zhengyang Yan, Song Guo

diffusion robotics efficiency

arXiv Machine Learning

Jun 25

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning

arXiv:2501. 14622v5 Announce Type: replace Abstract: Learning efficient representations for decision-making policies is a challenge in imitation learning (IL).

By Aleksandar Vujinovic, Aleksandar Kovacevic

rag diffusion

arXiv Machine Learning

Aug 27

ExFold: Unified Expert Folding for Training-Free MoE Prefill-Decode Acceleration

ExFold is a training‑free expert‑folding framework that jointly accelerates the prefill and decode phases of Mixture‑of‑Experts (MoE) models by projecting the contributions of excluded experts onto a retained expert set using calibrated scalar projectors. It treats both phases as a budgeted output‑approximation problem, achieving token‑level Top‑K folding for prefill and batch‑level expert‑pool folding for decode. Implemented as a plug‑and‑play plugin in vLLM with a lightweight CUDA kernel, ExFold delivers up to 1.41× TTFT and 2.45× TPOT speedups while preserving about 99% of the original model quality.

By Juntong Wu, Yifei Liu, Junyi Chen, Siqi Fan, Chaoran Feng, Minghao Li, Liujie Zhang, Weihang Chen, Li Yuan

arXiv AI

Jun 19

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

arXiv:2606. 20246v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose prohibitive computational burdens during downstream fine-tuning and real-time inference.

By Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha, Khoa Vo, Philip Lund M{\o}ller, Quang T. Nguyen, Long Dinh, Tuan Dam, Vu Duong, Tung M. Luu, Trung Le, Tran Nguyen Le, Minh Vu, An Thai Le, Ngan Le, Daniel Sonntag, James Zou, Jan Peters, Duy M. H. Nguyen, Ngo Anh Vien

robotics fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Aug 26

MoTE: Mixture of Task Experts for Multi-Task Video Understanding

arXiv:2608.24763v1 Announce Type: cross Abstract: Procedural video-language models must solve heterogeneous tasks from the same visual evidence, including action recognition, forecasting, and procedu...

By Muhammad Asad Ali, Umar Khan, Nadia Robertini, Didier Stricker

llms multimodal benchmarks

One email a morning, machine-written

Related stories

Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs

Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse Imagination

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning

ExFold: Unified Expert Folding for Training-Free MoE Prefill-Decode Acceleration

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

MoTE: Mixture of Task Experts for Multi-Task Video Understanding