Tootfinder

AI Accelerators for Large Language Model In-ference: Architecture Analysis and Scaling Strategies
Amit Sharma
https://arxiv.org/abs/2506.00008 https://

AI Accelerators for Large Language Model In-ference: Architecture Analysis and Scaling Strategies
The rapid growth of large-language models (LLMs) is driving a new wave of specialized hardware for inference. This paper presents the first workload-centric, cross-architectural performance study of commercial AI accelerators, spanning GPU-based chips, hybrid packages, and wafer-scale engines. We compare memory hierarchies, compute fabrics, and on-chip interconnects, and observe up to 3.7x performance variation across architectures as batch size and sequence length change. Four scaling techniqu…

A "Wenlu" Brain System for Multimodal Cognition and Embodied Decision-Making: A Secure New Architecture for Deep Integration of Foundation Models and Domain Knowledge
Liang Geng
https://arxiv.org/abs/2506.00570

A "Wenlu" Brain System for Multimodal Cognition and Embodied Decision-Making: A Secure New Architecture for Deep Integration of Foundation Models and Domain Knowledge
With the rapid penetration of artificial intelligence across industries and scenarios, a key challenge in building the next-generation intelligent core lies in effectively integrating the language understanding capabilities of foundation models with domain-specific knowledge bases in complex real-world applications. This paper proposes a multimodal cognition and embodied decision-making brain system, ``Wenlu", designed to enable secure fusion of private knowledge and public models, unified proc…

Microscale architected materials for elastic wave guiding: Fabrication and dynamic characterization across length and time scales
Vignesh Kannan, Charles Dorn, Ute Drechsler, Dennis M. Kochmann
https://arxiv.org/abs/2507.01757

Microscale architected materials for elastic wave guiding: Fabrication and dynamic characterization across length and time scales
We present an experimental protocol for the fabrication and characterization of scalable microarchitected elastic waveguides. Using silicon microfabrication techniques, we develop free-standing 2D truss-based architected waveguides with a maximum diameter of 80 mm, unit cells size of 100 micrometer, and minimum beam width of 5 micrometer, thus achieving scale separation. To characterize elastic wave propagation, we introduce a custom-built scanning optical pump-probe experiment that enables con…

High-Layer Attention Pruning with Rescaling
Songtao Liu, Peng Liu
https://arxiv.org/abs/2507.01900 https://arxiv.org/pdf/2507.01900…

High-Layer Attention Pruning with Rescaling
Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional training-free structured pruning methods often employ a heuristic metric that indiscriminately removes some attention heads across all pruning layers, without considering their positions within the network architecture. In this work, we propose a novel pruning algorithm that strategically prunes attention heads in the model's higher layers. Since t…

Alignment between Brains and AI: Evidence for Convergent Evolution across Modalities, Scales and Training Trajectories
Guobin Shen, Dongcheng Zhao, Yiting Dong, Qian Zhang, Yi Zeng
https://arxiv.org/abs/2507.01966

Alignment between Brains and AI: Evidence for Convergent Evolution across Modalities, Scales and Training Trajectories
Artificial and biological systems may evolve similar computational solutions despite fundamental differences in architecture and learning mechanisms -- a form of convergent evolution. We demonstrate this phenomenon through large-scale analysis of alignment between human brain activity and internal representations of over 600 AI models spanning language and vision domains, from 1.33M to 72B parameters. Analyzing 60 million alignment measurements reveals that higher-performing models spontaneousl…

State Similarity in Modular Superconducting Quantum Processors with Classical Communications
Bujiao Wu, Changrong Xie, Peng Mi, Zhiyi Wu, Zechen Guo, Peisheng Huang, Wenhui Huang, Xuandong Sun, Jiawei Zhang, Libo Zhang, Jiawei Qiu, Xiayu Linpeng, Ziyu Tao, Ji Chu, Ji Jiang, Song Liu, Jingjing Niu, Yuxuan Zhou, Yuxuan Du, Wenhui Ren, Youpeng Zhong, Tongliang Liu, Dapeng Yu

State Similarity in Modular Superconducting Quantum Processors with Classical Communications
As quantum devices continue to scale, distributed quantum computing emerges as a promising strategy for executing large-scale tasks across modular quantum processors. A central challenge in this paradigm is verifying the correctness of computational outcomes when subcircuits are executed independently following circuit cutting. Here we propose a cross-platform fidelity estimation algorithm tailored for modular architectures. Our method achieves substantial reductions in sample complexity compar…

A Late Collaborative Perception Framework for 3D Multi-Object and Multi-Source Association and Fusion
Maryem Fadili (VeDeCom, IRSEEM), Mohamed Anis Ghaoui (VeDeCom), Louis Lecrosnier (IRSEEM, ESIGELEC), Steve Pechberti (VeDeCom), Redouane Khemmar (IRSEEM, ESIGELEC, IRSEEM)
https://arxiv.org/abs/2507.02430

A Late Collaborative Perception Framework for 3D Multi-Object and Multi-Source Association and Fusion
In autonomous driving, recent research has increasingly focused on collaborative perception based on deep learning to overcome the limitations of individual perception systems. Although these methods achieve high accuracy, they rely on high communication bandwidth and require unrestricted access to each agent's object detection model architecture and parameters. These constraints pose challenges real-world autonomous driving scenarios, where communication limitations and the need to safeguard p…

Hybrid SLC-MLC RRAM Mixed-Signal Processing-in-Memory Architecture for Transformer Acceleration via Gradient Redistribution
Chang Eun Song, Priyansh Bhatnagar, Zihan Xia, Nam Sung Kim, Tajana Rosing, Mingu Kang
https://arxiv.org/abs/2506.00020

Hybrid SLC-MLC RRAM Mixed-Signal Processing-in-Memory Architecture for Transformer Acceleration via Gradient Redistribution
Transformers, while revolutionary, face challenges due to their demanding computational cost and large data movement. To address this, we propose HyFlexPIM, a novel mixed-signal processing-in-memory (PIM) accelerator for inference that flexibly utilizes both single-level cell (SLC) and multi-level cell (MLC) RRAM technologies to trade-off accuracy and efficiency. HyFlexPIM achieves efficient dual-mode operation by utilizing digital PIM for high-precision and write-intensive operations while ana…

RoboBrain 2.0 Technical Report
BAAI RoboBrain Team, Mingyu Cao, Huajie Tan, Yuheng Ji, Minglan Lin, Zhiyu Li, Zhou Cao, Pengwei Wang, Enshen Zhou, Yi Han, Yingbo Tang, Xiangqi Xu, Wei Guo, Yaoxu Lyu, Yijie Xu, Jiayu Shi, Cheng Chi, Mengdi Zhao, Xiaoshuai Hao, Shanyu Rong, Zhengliang Cai, Bolun Zhang, Shuyi Zhang, Huaihai Lyu, Mengfei Du, Lingfeng Zhang, Xi Feng, Xiaodan Liu, Yance Jiao, Chenrui He, Mengsi Lyu, Zhuo Chen, Yulong Ao, Xue Sun, Zheqi He, Jingshu Zheng, Xi Yang, Donghai Shi…

RoboBrain 2.0 Technical Report
We introduce RoboBrain 2.0, our latest generation of embodied vision-language foundation models, designed to unify perception, reasoning, and planning for complex embodied tasks in physical environments. It comes in two variants: a lightweight 7B model and a full-scale 32B model, featuring a heterogeneous architecture with a vision encoder and a language model. Despite its compact size, RoboBrain 2.0 achieves strong performance across a wide spectrum of embodied reasoning tasks. On both spatial…

CoInfra: A Large-Scale Cooperative Infrastructure Perception System and Dataset in Adverse Weather
Minghao Ning, Yufeng Yang, Keqi Shu, Shucheng Huang, Jiaming Zhong, Maryam Salehi, Mahdi Rahmani, Yukun Lu, Chen Sun, Aladdin Saleh, Ehsan Hashemi, Amir Khajepour
https://arxiv.org/abs/2507.02245

CoInfra: A Large-Scale Cooperative Infrastructure Perception System and Dataset in Adverse Weather
We present CoInfra, a large-scale cooperative infrastructure perception system and dataset designed to advance robust multi-agent perception under real-world and adverse weather conditions. The CoInfra system includes 14 fully synchronized sensor nodes, each equipped with dual RGB cameras and a LiDAR, deployed across a shared region and operating continuously to capture all traffic participants in real-time. A robust, delay-aware synchronization protocol and a scalable system architecture that …