Tootfinder

This https://arxiv.org/abs/2501.05460 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

Efficiently Serving Large Multimodal Models Using EPD Disaggregation
Large Multimodal Models (LMMs) extend Large Language Models (LLMs) by handling diverse inputs such as images, audio, and video, but at the cost of adding a multimodal encoding stage that increases both computational and memory overhead. This step negatively affects key Service Level Objectives (SLOs), such as time to first token (TTFT) and time per output token (TPOT). We introduce Encode-Prefill-Decode (EPD) Disaggregation, a novel framework that separates the encoding, prefill, and decode sta…

ChatGPT-4o, Claude 3.7 Sonnet, Gemini 2.0 Flash, Llama 4, and Copilot comparison: Claude was the best overall with the highest consistency and no hallucinations (Geoffrey A. Fowler/Washington Post)
https://www.washingtonpost.com/technology/

Review | 5 AI bots took our tough reading test. One was smartest — and it wasn’t ChatGPT.
We challenged AI helpers to decode legal contracts, simplify medical research, speed-read a novel and make sense of Trump speeches. Some of the AI analysis was impressive — and some was downright dumb.

UltrasonicSpheres: Localized, Multi-Channel Sound Spheres Using Off-the-Shelf Speakers and Earables
Michael K\"uttner, Valeria Sitz, Kathrin Gerling, Michael Beigl, Tobias R\"oddiger
https://arxiv.org/abs/2506.02715

UltrasonicSpheres: Localized, Multi-Channel Sound Spheres Using Off-the-Shelf Speakers and Earables
We present a demo ofUltrasonicSpheres, a novel system for location-specific audio delivery using wearable earphones that decode ultrasonic signals into audible sound. Unlike conventional beamforming setups, UltrasonicSpheres relies on single ultrasonic speakers to broadcast localized audio with multiple channels, each encoded on a distinct ultrasonic carrier frequency. Users wearing our acoustically transparent earphones can demodulate their selected stream, such as exhibit narrations in a chos…

Hardware-Centric Analysis of DeepSeek's Multi-Head Latent Attention
Robin Geens, Marian Verhelst
https://arxiv.org/abs/2506.02523 https://

Hardware-Centric Analysis of DeepSeek's Multi-Head Latent Attention
Multi-Head Latent Attention (MLA), introduced in DeepSeek-V2, improves the efficiency of large language models by projecting query, key, and value tensors into a compact latent space. This architectural change reduces the KV-cache size and significantly lowers memory bandwidth demands, particularly in the autoregressive decode phase. This letter presents the first hardware-centric analysis of MLA, comparing it to conventional Multi-Head Attention (MHA) and evaluating its implications for accele…

Parallel CPU-GPU Execution for LLM Inference on Constrained GPUs
Jiakun Fan, Yanglin Zhang, Xiangchen Li, Dimitrios S. Nikolopoulos
https://arxiv.org/abs/2506.03296

Parallel CPU-GPU Execution for LLM Inference on Constrained GPUs
Deploying large language models (LLMs) for online inference is often constrained by limited GPU memory, particularly due to the growing KV cache during auto-regressive decoding. Hybrid GPU-CPU execution has emerged as a promising solution by offloading KV cache management and parts of attention computation to the CPU. However, a key bottleneck remains: existing schedulers fail to effectively overlap CPU-offloaded tasks with GPU execution during the latency-critical, bandwidth-bound decode phase…

Over-the-Air Fronthaul Signaling for Uplink Cell-Free Massive MIMO Systems
Zakir Hussain Shaik, Sai Subramanyam Thoota, Emil Bj\"ornson, Erik G. Larsson
https://arxiv.org/abs/2506.00655

Over-the-Air Fronthaul Signaling for Uplink Cell-Free Massive MIMO Systems
We propose a novel resource-efficient over-the-air(OTA) computation framework to address the huge fronthaul computational and control overhead requirements in cell-free massive multiple-input multiple-output (MIMO) networks. We show that the global sufficient statistics to decode the data symbols can be computed OTA using the locally available information at the access points (APs). We provide the essential signal processing aspects at the APs and the central processing unit (CPU) to facilitate…

Will we ever decode the writing system used by the Inca?
Gift article, no paywall.
https://www.theatlantic.com/culture/archiv

Unraveling the Secrets of the Inca Empire
For hundreds of years, Andean people recorded information by tying knots into long cords. Will we ever be able to read them?

Will we ever decode the writing system used by the Inca?
Gift article, no paywall.
https://www.theatlantic.com/culture/archiv

Unraveling the Secrets of the Inca Empire
For hundreds of years, Andean people recorded information by tying knots into long cords. Will we ever be able to read them?