Tootfinder

Suspect in Minnesota Shooting Linked to Security Company, Evangelical Ministry (Wired)
https://www.wired.com/story/shooting-minnesota-melissa-hortman-vance-boelter/
http://www.memeorandum.com/250614/p76#a250614p76

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
Arushi Goel, Sreyan Ghosh, Jaehyeon Kim, Sonal Kumar, Zhifeng Kong, Sang-gil Lee, Chao-Han Huck Yang, Ramani Duraiswami, Dinesh Manocha, Rafael Valle, Bryan Catanzaro
https://arxiv.org/abs/2507.08128…

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
We present Audio Flamingo 3 (AF3), a fully open state-of-the-art (SOTA) large audio-language model that advances reasoning and understanding across speech, sound, and music. AF3 introduces: (i) AF-Whisper, a unified audio encoder trained using a novel strategy for joint representation learning across all 3 modalities of speech, sound, and music; (ii) flexible, on-demand thinking, allowing the model to do chain-of-thought-type reasoning before answering; (iii) multi-turn, multi-audio chat; (iv) …

Lehti: Sota saastuttaa maaperää Ukrainassa – seuraukset näkyvät jo viljelykasveissa #Ukraina

Lehti: Sota saastuttaa maaperää Ukrainassa – seuraukset näkyvät jo viljelykasveissa
Ukrainassa sota saastuttaa maaperää, mikä näkyy viljelykasveissa jo nyt. Suurempi ongelma odottaa kuitenkin sodan päättymisen jälkeen, kun rintamille jääneitä maa-alueita pystytään jälleen viljelemään.

TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices
Sizhen Bian, Mengxi Liu, Vitor Fortes Rey, Daniel Geissler, Paul Lukowicz
https://arxiv.org/abs/2507.07949

TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices
Human Activity Recognition (HAR) on resource-constrained wearable devices demands inference models that harmonize accuracy with computational efficiency. This paper introduces TinierHAR, an ultra-lightweight deep learning architecture that synergizes residual depthwise separable convolutions, gated recurrent units (GRUs), and temporal aggregation to achieve SOTA efficiency without compromising performance. Evaluated across 14 public HAR datasets, TinierHAR reduces Parameters by 2.7x (vs. TinyHA…

RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale
Zhilong Chen, Chengzong Zhao, Boyuan Chen, Dayi Lin, Yihao Chen, Arthur Leung, Gopi Krishnan Rajbahadur, Gustavo A. Oliva, Ahmed E. Hassan
https://arxiv.org/abs/2508.01550

RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale
Training software engineering (SWE) LLMs is bottlenecked by expensive infrastructure, inefficient evaluation pipelines, scarce training data, and costly quality control. We present RepoForge, an autonomous, end-to-end pipeline that generates, evaluates, and trains SWE agents at scale. Our key contributions include: (1) RepoForge-8B-Agent, achieving 17.4\% on SWE-Bench-Verified~\citep{swebench_verified2024}, establishing new state-of-the-art for $\leq$8B non-thinking LLMs; (2) 7,304 executable e…

Real Time FPGA Based Transformers & VLMs for Vision Tasks: SOTA Designs and Optimizations
Safa Mohammed Sali, Mahmoud Meribout, Ashiyana Abdul Majeed
https://arxiv.org/abs/2509.04162

Real Time FPGA Based Transformers & VLMs for Vision Tasks: SOTA Designs and Optimizations
Transformers and vision-language models (VLMs) have emerged as dominant architectures in computer vision and multimodal AI, offering state-of-the-art performance in tasks such as image classification, object detection, visual question answering, and caption generation. However, their high computational complexity, large memory footprints, and irregular data access patterns present significant challenges for deployment in latency- and power-constrained environments. Field-programmable gate array…

Integrated Communication and Computing in Time-Varying mmWave Channels
Joan \c{C}ollaku, Kuranage Roche Rayan Ranasinghe, Giuseppe Thadeu Freitas de Abreu, Takumi Takahashi
https://arxiv.org/abs/2509.07482

Integrated Communication and Computing in Time-Varying mmWave Channels
We propose a novel framework for integrated communication and computing (ICC) transceiver design in time-varying millimeter-wave (mmWave) channels. In particular, in order to cope with the dynamics of time-varying mmWave channels, the detection of communication symbols and the execution of an over-the-air computing (AirComp) operation are performed in parallel with channel tracking, as opposed to existing state-of-the-art (SotA) on ICC where perfect knowledge of the channel at all time instance…

FASL-Seg: Anatomy and Tool Segmentation of Surgical Scenes
Muraam Abdel-Ghani, Mahmoud Ali, Mohamed Ali, Fatmaelzahraa Ahmed, Mohamed Arsalan, Abdulaziz Al-Ali, Shidin Balakrishnan
https://arxiv.org/abs/2509.06159

FASL-Seg: Anatomy and Tool Segmentation of Surgical Scenes
The growing popularity of robotic minimally invasive surgeries has made deep learning-based surgical training a key area of research. A thorough understanding of the surgical scene components is crucial, which semantic segmentation models can help achieve. However, most existing work focuses on surgical tools and overlooks anatomical objects. Additionally, current state-of-the-art (SOTA) models struggle to balance capturing high-level contextual features and low-level edge features. We propose …

Magneto-optical Kerr-effect measurements under pulsed magnetic fields over 40 T using a compact sample fixture
Atsutoshi Ikeda, Sota Nakamura, Soichiro Yamane, Kosuke Noda, Akihiko Ikeda, Shingo Yonezawa
https://arxiv.org/abs/2509.07383

Magneto-optical Kerr-effect measurements under pulsed magnetic fields over 40 T using a compact sample fixture
Magnetic field is one of the most fundamental control parameters in materials science. Pulsed magnetic-field apparatus can generate high magnetic fields that are inaccessible by conventional DC-field magnets. One important issue is that measurement techniques compatible with pulsed fields are rather limited due to short pulse duration and large electromagnetic or mechanical noises originating from field pulses. Magneto-optical Kerr effect (MOKE), change in states of light polarization upon refl…

Two SOTA peaks in one day, with about 25 miles of sublime dirt roads on a beautiful day...does it get any better? Okay, the bands were abysmal. Don't care.
#SOTA #hamradio

Sota eläintarhoista #eläimet #eläinoikeudet

Sota eläintarhoista
Kysymys eläinten oikeudesta hyvään elämään hiertää niin eläintarhoja kuin tutkijoitakin. Englantilainen kahden eläintarhan omistaja haluaa sulkea Euroopan eläintarhat ja vapauttaa eläimet luontoon. Ruotsalaisten eläintarhojen edustajat sanovat, että eläintarhoja tarvitaan nyt enemmän kuin koskaan. Samaan aikaan eläinkarkulaiset ja eläintenhoitajien kuolemat aiheuttavat toistuvia skandaaleja. Voiko eläintarhassa vierailla hyvällä omallatunnolla? Tuotanto: SVT, 2024.

An RGB-D Camera-Based Multi-Small Flying Anchors Control for Wire-Driven Robots Connecting to the Environment
Shintaro Inoue, Kento Kawaharazuka, Keita Yoneda, Sota Yuzaki, Yuta Sahara, Temma Suzuki, Kei Okada
https://arxiv.org/abs/2508.02544

An RGB-D Camera-Based Multi-Small Flying Anchors Control for Wire-Driven Robots Connecting to the Environment
In order to expand the operational range and payload capacity of robots, wire-driven robots that leverage the external environment have been proposed. It can exert forces and operate in spaces far beyond those dictated by its own structural limits. However, for practical use, robots must autonomously attach multiple wires to the environment based on environmental recognition-an operation so difficult that many wire-driven robots remain restricted to specialized, pre-designed environments. Here,…

Adversarial Attacks on Audio Deepfake Detection: A Benchmark and Comparative Study
Kutub Uddin, Muhammad Umar Farooq, Awais Khan, Khalid Mahmood Malik
https://arxiv.org/abs/2509.07132

Adversarial Attacks on Audio Deepfake Detection: A Benchmark and Comparative Study
The widespread use of generative AI has shown remarkable success in producing highly realistic deepfakes, posing a serious threat to various voice biometric applications, including speaker verification, voice biometrics, audio conferencing, and criminal investigations. To counteract this, several state-of-the-art (SoTA) audio deepfake detection (ADD) methods have been proposed to identify generative AI signatures to distinguish between real and deepfake audio. However, the effectiveness of thes…

The Confidence Paradox: Can LLM Know When It's Wrong
Sahil Tripathi, Md Tabrez Nafis, Imran Hussain, Jiechao Gao
https://arxiv.org/abs/2506.23464 https…

The Confidence Paradox: Can LLM Know When It's Wrong
Document Visual Question Answering (DocVQA) systems are increasingly deployed in real world applications, yet they remain ethically opaque-often producing overconfident answers to ambiguous questions or failing to communicate uncertainty in a trustworthy manner. This misalignment between model confidence and actual knowledge poses significant risks, particularly in domains requiring ethical accountability. Existing approaches such as LayoutLMv3, UDOP, and DONUT have advanced SOTA performance by…

ArgCMV: An Argument Summarization Benchmark for the LLM-era
Omkar Gurjar, Agam Goyal, Eshwar Chandrasekharan
https://arxiv.org/abs/2508.19580 https://arxiv…

ArgCMV: An Argument Summarization Benchmark for the LLM-era
Key point extraction is an important task in argument summarization which involves extracting high-level short summaries from arguments. Existing approaches for KP extraction have been mostly evaluated on the popular ArgKP21 dataset. In this paper, we highlight some of the major limitations of the ArgKP21 dataset and demonstrate the need for new benchmarks that are more representative of actual human conversations. Using SoTA large language models (LLMs), we curate a new argument key point extr…

#Qwen3Coder: Most Agentic Code Model Released 🤖
🎯 480B-parameter #MixtureOfExperts #LLM with 35B active parameters achieving

FCPO: Federated Continual Policy Optimization for Real-Time High-Throughput Edge Video Analytics
Lucas Liebe, Thanh-Tung Nguyen, Dongman Lee
https://arxiv.org/abs/2507.18047 htt…

FCPO: Federated Continual Policy Optimization for Real-Time High-Throughput Edge Video Analytics
The growing complexity of Edge Video Analytics (EVA) facilitates new kind of intelligent applications, but creates challenges in real-time inference serving systems. State-of-the-art (SOTA) scheduling systems optimize global workload distributions for heterogeneous devices but often suffer from extended scheduling cycles, leading to sub-optimal processing in rapidly changing Edge environments. Local Reinforcement Learning (RL) enables quick adjustments between cycles but faces scalability, know…

Spectrum Sensing with Deep Clustering: Label-Free Radio Access Technology Recognition
Ljupcho Milosheski, Mihael Mohor\v{c}i\v{c}, Carolina Fortuna
https://arxiv.org/abs/2508.01709

Spectrum Sensing with Deep Clustering: Label-Free Radio Access Technology Recognition
The growth of the number of connected devices and network densification is driving an increasing demand for radio network resources, particularly Radio Frequency (RF) spectrum. Given the dynamic and complex nature of contemporary wireless environments, characterized by a wide variety of devices and multiple RATs, spectrum sensing is envisioned to become a building component of future 6G, including as a component within O-RAN or digital twins. However, the current SotA research for RAT classific…

Minnesota lawmaker shot 9 times at his home in 'targeted' attack is in a critical condition (Patrick Smith/NBC News)
https://www.nbcnews.com/news/us-news/minnesota-lawmaker-shot-9-home-targeted-attack-critical-condition-rcna214048
http://www.memeorandum.com/250620/p57#a250620p57

Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
Zhiting Mei, Christina Zhang, Tenny Yin, Justin Lidard, Ola Shorinwa, Anirudha Majumdar
https://arxiv.org/abs/2506.18183

Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
Reasoning language models have set state-of-the-art (SOTA) records on many challenging benchmarks, enabled by multi-step reasoning induced using reinforcement learning. However, like previous language models, reasoning models are prone to generating confident, plausible responses that are incorrect (hallucinations). Knowing when and how much to trust these models is critical to the safe deployment of reasoning models in real-world applications. To this end, we explore uncertainty quantification…

Brick-splitting Torsion Pairs and Trim Lattices
Sota Asai, Osamu Iyama, Kaveh Mousavand, Charles Paquette
https://arxiv.org/abs/2506.13602 https://

Brick-splitting Torsion Pairs and Trim Lattices
We introduce the notion of brick-splitting torsion pairs as a modern analogue and generalization of the classical notion of splitting torsion pairs. A torsion pair is called brick-splitting if any given brick is either torsion or torsion-free with respect to that torsion pair. After giving some properties of these pairs, we fully characterize them in terms of some lattice-theoretical properties, including left modularity. This leads to the notion of brick-directed algebras, which are those for …

Is attention truly all we need? An empirical study of asset pricing in pretrained RNN sparse and global attention models
Shanyan Lai
https://arxiv.org/abs/2508.19006 https://

Is attention truly all we need? An empirical study of asset pricing in pretrained RNN sparse and global attention models
This study investigates the pretrained RNN attention models with the mainstream attention mechanisms such as additive attention, Luong's three attentions, global self-attention (Self-att) and sliding window sparse attention (Sparse-att) for the empirical asset pricing research on top 420 large-cap US stocks. This is the first paper on the large-scale state-of-the-art (SOTA) attention mechanisms applied in the asset pricing context. They overcome the limitations of the traditional machine learni…

Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation
Donghwa Kang, Doohyun Kim, Sang-Ki Ko, Jinkyu Lee, Hyeongboo Baek, Brent ByungHoon Kang
https://arxiv.org/abs/2508.13812

Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation
State-of-the-art (SOTA) gradient-based adversarial attacks on spiking neural networks (SNNs), which largely rely on extending FGSM and PGD frameworks, face a critical limitation: substantial attack latency from multi-timestep processing, rendering them infeasible for practical real-time applications. This inefficiency stems from their design as direct extensions of ANN paradigms, which fail to exploit key SNN properties. In this paper, we propose the timestep-compressed attack (TCA), a novel fr…

Phase transitions of eutectic high entropy alloy AlCoCrFeNi2.1 under shock compression
Sophie Parsons, Kento Katagiri, Hangman Chen, Anirudh Hari, Tharun Reddy, Sara J. Irvine, Laura Madril, Dorian Luccioni, Jie Ren, Wuxian Yang, Norimasa Ozaki, Alexis Amouretti, Ryosuke Kodama, Hirotaka Nakamura, Yusuke Nakanishi, Masato Ota, Yusuke Seto, Sota Takagi, Takuo Okuchi, Yuhei Umeda, Yuichi Inubushi, Kohei Miyanishi, Keiichi Sueda, Tadashi Togashi, Makina Yabashi, Toshinori Yabuuchi, Wanghu…

Phase transitions of eutectic high entropy alloy AlCoCrFeNi2.1 under shock compression
High entropy alloys (HEAs) are a new class of metals that exhibit unique mechanical performance. Among HEAs, additively manufactured eutectic high entropy alloys (AM-EHEAs) have recently emerged as candidate materials for use in extreme conditions due to their simultaneous high strength and ductility. However, the deformation and structural evolution of AM-EHEAs under conditions of high pressure have not been well characterized, limiting their use in extreme applications. We present dynamic com…

Leveraging OS-Level Primitives for Robotic Action Management
Wenxin Zheng, Boyang Li, Bin Xu, Erhu Feng, Jinyu Gu, Haibo Chen
https://arxiv.org/abs/2508.10259 https://

Leveraging OS-Level Primitives for Robotic Action Management
End-to-end imitation learning frameworks (e.g., VLA) are increasingly prominent in robotics, as they enable rapid task transfer by learning directly from perception to control, eliminating the need for complex hand-crafted features. However, even when employing SOTA VLA-based models, they still exhibit limited generalization capabilities and suboptimal action efficiency, due to the constraints imposed by insufficient robotic training datasets. In addition to addressing this problem using model-…

while the world is working with SOTA #opensource #LLM at over 200 tokens per second, #jetbrains is still trying to fix its

Temporal Neural Cellular Automata: Application to modeling of contrast enhancement in breast MRI
Daniel M. Lang, Richard Osuala, Veronika Spieker, Karim Lekadir, Rickmer Braren, Julia A. Schnabel
https://arxiv.org/abs/2506.18720

Temporal Neural Cellular Automata: Application to modeling of contrast enhancement in breast MRI
Synthetic contrast enhancement offers fast image acquisition and eliminates the need for intravenous injection of contrast agent. This is particularly beneficial for breast imaging, where long acquisition times and high cost are significantly limiting the applicability of magnetic resonance imaging (MRI) as a widespread screening modality. Recent studies have demonstrated the feasibility of synthetic contrast generation. However, current state-of-the-art (SOTA) methods lack sufficient measures …

Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs
Ring Team, Bin Hu, Cai Chen, Deng Zhao, Ding Liu, Dingnan Jin, Feng Zhu, Hao Dai, Hongzhi Luan, Jia Guo, Jiaming Liu, Jiewei Wu, Jun Mei, Jun Zhou, Junbo Zhao, Junwu Xiong, Kaihong Zhang, Kuan Xu, Lei Liang, Liang Jiang, Liangcheng Fu, Longfei Zheng, Qiang Gao, Qing Cui, Quan Wan, Shaomian Zheng, Shuaicheng Li, Tongkai Yang, Wang Ren, Xiaodong Yan, Xiaopei Wan, Xiaoyun Feng, Xin Zhao, Xinxing Yang, Xinyu …

Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs
We present Ring-lite, a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL) to achieve efficient and robust reasoning capabilities. Built upon the publicly available Ling-lite model, a 16.8 billion parameter model with 2.75 billion activated parameters, our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks (e.g., AIME, LiveCodeBench, GPQA-Diamond) while activating only one-third of the par…

Suspected Minnesota lawmaker assassin Vance Boelter captured (Fox News)
https://www.foxnews.com/us/suspected-minnesota-lawmaker-assassin-vance-boelter-captured
http://www.memeorandum.com/250616/p5#a250616p5

CoNav Chair: Development and Evaluation of a Shared Control based Wheelchair for the Built Environment
Yifan Xu, Qianwei Wang, Jordan Lillie, Vineet Kamat, Carol Menassa, Clive D'Souza
https://arxiv.org/abs/2507.11716

CoNav Chair: Development and Evaluation of a Shared Control based Wheelchair for the Built Environment
As the global population of people with disabilities (PWD) continues to grow, so will the need for mobility solutions that promote independent living and social integration. Wheelchairs are vital for the mobility of PWD in both indoor and outdoor environments. The current SOTA in powered wheelchairs is based on either manually controlled or fully autonomous modes of operation, offering limited flexibility and often proving difficult to navigate in spatially constrained environments. Moreover, r…

Enhancing In-Domain and Out-Domain EmoFake Detection via Cooperative Multilingual Speech Foundation Models
Orchid Chetia Phukan, Mohd Mujtaba Akhtar, Girish, Arun Balaji Buduru
https://arxiv.org/abs/2507.12595

Enhancing In-Domain and Out-Domain EmoFake Detection via Cooperative Multilingual Speech Foundation Models
In this work, we address EmoFake Detection (EFD). We hypothesize that multilingual speech foundation models (SFMs) will be particularly effective for EFD due to their pre-training across diverse languages, enabling a nuanced understanding of variations in pitch, tone, and intensity. To validate this, we conduct a comprehensive comparative analysis of state-of-the-art (SOTA) SFMs. Our results shows the superiority of multilingual SFMs for same language (in-domain) as well as cross-lingual (out-d…

3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting
Yuke Xing, Jiarui Wang, Peizhi Niu, Wenjie Huang, Guangtao Zhai, Yiling Xu
https://arxiv.org/abs/2506.14642

3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting
3D Gaussian Splatting (3DGS) has emerged as a promising approach for novel view synthesis, offering real-time rendering with high visual fidelity. However, its substantial storage requirements present significant challenges for practical applications. While recent state-of-the-art (SOTA) 3DGS methods increasingly incorporate dedicated compression modules, there is a lack of a comprehensive framework to evaluate their perceptual impact. Therefore we present 3DGS-IEval-15K, the first large-scale …

Seq vs Seq: An Open Suite of Paired Encoders and Decoders
Orion Weller, Kathryn Ricci, Marc Marone, Antoine Chaffin, Dawn Lawrie, Benjamin Van Durme
https://arxiv.org/abs/2507.11412

Seq vs Seq: An Open Suite of Paired Encoders and Decoders
The large language model (LLM) community focuses almost exclusively on decoder-only language models, since they are easier to use for text generation. However, a large subset of the community still uses encoder-only models for tasks such as classification or retrieval. Previous work has attempted to compare these architectures, but is forced to make comparisons with models that have different numbers of parameters, training techniques, and datasets. We introduce the SOTA open-data Ettin suite o…

FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution
Zhaoyang Wang, Jie Li, Wen Lu, Lihuo He, Maoguo Gong, Xinbo Gao
https://arxiv.org/abs/2506.11545

FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution
State-of-the-art (SOTA) compressed video super-resolution (CVSR) models face persistent challenges, including prolonged inference time, complex training pipelines, and reliance on auxiliary information. As video frame rates continue to increase, the diminishing inter-frame differences further expose the limitations of traditional frame-to-frame information exploitation methods, which are inadequate for addressing current video super-resolution (VSR) demands. To overcome these challenges, we pro…

UI-Venus Technical Report: Building High-performance UI Agents with RFT
Zhangxuan Gu, Zhengwen Zeng, Zhenyu Xu, Xingran Zhou, Shuheng Shen, Yunfei Liu, Beitong Zhou, Changhua Meng, Tianyu Xia, Weizhi Chen, Yue Wen, Jingya Dou, Fei Tang, Jinzhen Lin, Yulin Liu, Zhenlin Guo, Yichen Gong, Heng Jia, Changlong Gao, Yuan Guo, Yong Deng, Zhenyu Guo, Liang Chen, Weiqiang Wang

UI-Venus Technical Report: Building High-performance UI Agents with RFT
We present UI-Venus, a native UI agent that takes only screenshots as input based on a multimodal large language model. UI-Venus achieves SOTA performance on both UI grounding and navigation tasks using only several hundred thousand high-quality training samples through reinforcement finetune (RFT) based on Qwen2.5-VL. Specifically, the 7B and 72B variants of UI-Venus obtain 94.1% / 50.8% and 95.3% / 61.9% on the standard grounding benchmarks, i.e., Screenspot-V2 / Pro, surpassing the previous …

LiLAC: A Lightweight Latent ControlNet for Musical Audio Generation
Tom Baker, Javier Nistal
https://arxiv.org/abs/2506.11476 https://

LiLAC: A Lightweight Latent ControlNet for Musical Audio Generation
Text-to-audio diffusion models produce high-quality and diverse music but many, if not most, of the SOTA models lack the fine-grained, time-varying controls essential for music production. ControlNet enables attaching external controls to a pre-trained generative model by cloning and fine-tuning its encoder on new conditionings. However, this approach incurs a large memory footprint and restricts users to a fixed set of controls. We propose a lightweight, modular architecture that considerably …