LeVJEPA is a video encoder that eliminates the need for architectural asymmetries, exponential-moving-average target encoders, stop-gradients, and capacity-limited predictors used in prior self‑supervised methods. It trains a single encoder with an invariance loss over global and local views, regularized by SIGReg to prevent collapse, and achieves strong performance with far less pretraining compute. The approach also allows block‑causal attention, making temporal ordering a property of the encoder itself, and matches or surpasses state‑of‑the‑art baselines on both appearance‑centric and motion‑centric benchmarks.
By Lukas Kuhn, Lucas Maes, Giuseppe Serra, Quentin Le Lidec, Yann LeCun, Randall Balestriero, Florian Buettner
arXiv:2608. 08961v1 Announce Type: new Abstract: AI training's rising resource intensity is straining electricity supplies and carbon budgets, motivating systematic study of memory-efficient training on constrained hardware.
By Sarthak Mahapatra, Zihan Zhou, Khatoon Khedri, Mehdi Hosseinzadeh, Reza Rawassizadeh
The paper introduces Gated Token Recurrence (GTR), a softmax‑free recurrent vision backbone that replaces global softmax attention with gated linear attention, alternating scan directions, and enhanced SwiGLU blocks. GTR is distilled from a DINOv3 teacher using only final‑layer patch‑token alignment, and achieves strong performance on COCO object detection (58.9 box AP) with very low latency (1.908 ms on an RTX 4090). The backbone also transfers to multiple dense prediction tasks and runs efficiently on edge hardware via a specialized CUDA operator and TensorRT deployment.
By Zhe Feng, Longfei Liu, Wei Liu, Kai Chen, Jiangjiang Kong, Wei Zhou, Yifeng Qian, Dexiong Chen, Xuanlong Yu, Xi Shen
AI training's rising resource intensity is straining electricity supplies and carbon budgets, motivating systematic study of memory-efficient training on constrained hardware. We benchmark five gradient optimizers (SGD, Adam, Adagrad, Adadelta, and Conjugate Gradient Descent) under three memory strategies (standard training, gradient checkpointing, and gradient accumulation) across four transformer architectures (ViT, ModernBERT, Llama 3.
arXiv:2609.38090v1 Announce Type: new
Abstract: Mixture-of-Experts (MoE) models are a compelling architecture for scaling model capacity, making them especially attractive for deployment on resource-...
By Sanjali Yadav, Bahar Asgari
arXiv:2606. 01503v1 Announce Type: cross Abstract: Unified vision-language models (VLMs) integrate visual understanding and visual generation within a single autoregressive backbone, but their joint training is computationally expensive and largely overlooked from an efficiency perspective.
By Siyi Chen, Weiming Zhuang, Jingtao Li, Lingjuan Lv
STAPLE is a method that integrates static sparse memory into pretrained language models by adding token‑indexed embeddings as a residual pathway while preserving the original feed‑forward network. On the OLMo‑2 1B and 7B models, STAPLE outperforms dense training and other static sparse baselines, improving benchmark scores by up to 4.27 points and achieving faster decoding with less GPU memory and energy usage. The approach demonstrates that large pretrained models can be expanded efficiently without costly sparse pretraining from scratch.
By Ranajoy Sadhukhan, Euijin Hong, Sheng Cao, Zechun Liu, Shuowei Jin, Sha Li, Changlong Yu, Xin Liu, Qin Lu, Zhenyu Shi, Priyanka Nigam, Beidi Chen
arXiv:2607. 28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs.
By Haozhe Hu, Hao Wu, Peiran Yin, Chao Han, Yunpu Ma, Xiaoyu Shen
Meta’s paper details how the company optimizes AI training on AMD GPUs by co‑designing hardware and models, using an analytical performance model for kernel selection, and extending agentic workflows for microarchitecture‑aware optimizations. The authors compare AMD Instinct MI350X to NVIDIA B200 on a recommendation model, achieving up to 1.5× higher training throughput. Their methods, the first hyperscaler report on productionizing AMD GPUs for large‑scale training, have been incorporated into open‑source PyTorch, Triton, and ROCm.
By Haoyu Zhang, Arshad Rahman, Adnan Aziz, Ajith Prabhudev, Amin Farmahini, Ben Rhoads, Benson Ma, Brian Shi, Cen Zhao, CK Luk, Dingming Wu, Emad El-Haraty, Eric Chen, Frank Li, Gary Huang, Gefei Zuo, Haoran Zhang, Hiwot Kassa, Hongyi Zeng, Jack Taylor, Jeremy Hadidjojo, John Donati, Jonathan Sheffield, Julio Machado Silva, Karthik Ganesan, Kent Russell, KR Kishore, Lei Tian, Liu Ke, Muhammad Osama, Peng Chen, Rakesh Hemnani, Ryan Swann, Saleel Kudchadker, Shankar Yanamandram, Shobhit Kanaujia, Shucai Xiao, Srinath Bayareddy, Srinivas Vaidyanathan, Sudharssun Subramanian, Supadchaya Puangpontip, Taylor Robie, Tianhao Huang, Tyler Hart, Viswesh Sankaran, Weijun Jiang, Wenkai Du, Xiaodong Wang, Xiaohu Guo, Yao Rong, Yinbin Ma, Yue Dong, Yuzhen Huang, Yvonne Liu, Zhan Shu, Dan Rabinovitsj, Ajit Mathews, Chunqiang Tang
arXiv:2607. 02097v1 Announce Type: cross Abstract: Large kernel depthwise convolutions achieve strong performance but suffer from significant degradation as kernel size grows due to irregular memory access from gather-based computation; while Large Kernel Acceleration (LKA) helps on small feature maps, it becomes counterproductive on large feature maps, even slower than non-accelerated implementations.
By Wan Song, Wei Zhou, Rui Wang, Jun Yu, Toru Kurihara, Jiajia Xu, Shu Zhan
arXiv:2603. 12478v2 Announce Type: replace-cross Abstract: Multimodal instruction tuning is often compute-inefficient because training budgets are spread across large mixed image-video pools whose utility is highly uneven.
By Rujie Wu, Haozhe Zhao, Hai Ci, Yizhou Wang
arXiv:2510. 09608v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage.
By Ruyi Xu, Guangxuan Xiao, Yukang Chen, Liuning He, Yao Lu, Song Han