Tootfinder

Amkor breaks ground on advanced chip packaging campus in Arizona, with production expected by early 2028; state officials say Amkor's investment could reach $7B (Luke James/Tom's Hardware)
https://www.tomshardware.com/tech-industry

Amkor breaks ground on Arizona advanced packaging campus, plugging critical gap in US semiconductor supply chain — production expected in 2028, investment could extend to $7 billion with 3,000 jobs in tow
Amkor moves in next door to TSMC as CHIPS Act funding continues to turn the Phoenix metro area into a chips hub.

LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA
Jing Huang, Zhiya Tan, Shutao Gong, Fanwei Zeng, Jianshu Li
https://arxiv.org/abs/2509.10026

LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA
As large vision language models (VLMs) advance, their capabilities in multilingual visual question answering (mVQA) have significantly improved. Chain-of-thought (CoT) reasoning has been proven to enhance interpretability and complex reasoning. However, most existing approaches rely primarily on textual CoT and provide limited support for multilingual multimodal reasoning, constraining their deployment in real-world applications. To address this gap, we introduce \textbf{LaV-CoT}, the first Lan…

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
Tianyu Hu, Zhen Tan, Song Wang, Huaizhi Qu, Tianlong Chen
https://arxiv.org/abs/2510.12697 https://

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
With advancements in reasoning capabilities, Large Language Models (LLMs) are increasingly employed for automated judgment tasks. While LLMs-as-Judges offer promise in automating evaluations, current approaches often rely on simplistic aggregation methods (e.g., majority voting), which can fail even when individual agents provide correct answers. To address this, we propose a multi-agent debate judge framework where agents collaboratively reason and iteratively refine their responses. We formal…

GeoGPT.RAG Technical Report
Fei Huang, Fan Wu, Zeqing Zhang, Qihao Wang, Long Zhang, Grant Michael Boquet, Hongyang Chen
https://arxiv.org/abs/2509.09686 https://

GeoGPT.RAG Technical Report
GeoGPT is an open large language model system built to advance research in the geosciences. To enhance its domain-specific capabilities, we integrated Retrieval Augmented Generation(RAG), which augments model outputs with relevant information retrieved from an external knowledge source. GeoGPT uses RAG to draw from the GeoGPT Library, a specialized corpus curated for geoscientific content, enabling it to generate accurate, context-specific answers. Users can also create personalized knowledge b…

Quantum thermodynamics of Gross-Pitaevskii qubits
Sebastian Deffner
https://arxiv.org/abs/2510.12599 https://arxiv.org/pdf/2510.12599

Quantum thermodynamics of Gross-Pitaevskii qubits
What are the resources that can be leveraged for a thermodynamic device to exhibit genuine quantum advantage? Typically, the answer to this question is sought in quantum correlations. In the present work, we show that quantum Otto engines that operate with nonlinear qubits significantly outperform linear engines. To this end, we develop a comprehensive thermodynamic description of nonlinear qubits starting with identifying the proper thermodynamic equilibrium state. We then show that for ideal …

Guess your neighbor's input: Quantum advantage in Feige's game
Simon Schmidt, Sigurd A. L. Storgaard, Michael Walter, Yuming Zhao
https://arxiv.org/abs/2510.08484 https:…

Guess your neighbor's input: Quantum advantage in Feige's game
In this article, we study a nonlocal game with two questions and three answers per player, which was first considered by Feige in 1991, and show that there is quantum advantage in this game. We prove that the game is a robust self-test for the $3$-dimensional maximally entangled state. Furthermore, we show that the game can be seen as the "or" of two games that each do not have quantum advantage. Lastly, we investigate the behavior of the game with respect to parallel repetition in the classica…

After writing some questionable `rust` code for #adventofcode Day 8, I've managed to get the right answers in a reasonable amount of time which has taken far, far longer than I'd care to admit. I'll jump on the Python and Nim solves later because my brain is absolutely fried at the moment.
Solution:

Knowledge Extraction on Semi-Structured Content: Does It Remain Relevant for Question Answering in the Era of LLMs?
Kai Sun, Yin Huang, Srishti Mehra, Mohammad Kachuee, Xilun Chen, Renjie Tao, Zhaojiang Lin, Andrea Jessee, Nirav Shah, Alex Betty, Yue Liu, Anuj Kumar, Wen-tau Yih, Xin Luna Dong
https://arxiv.org/abs/2509.25107

Knowledge Extraction on Semi-Structured Content: Does It Remain Relevant for Question Answering in the Era of LLMs?
The advent of Large Language Models (LLMs) has significantly advanced web-based Question Answering (QA) systems over semi-structured content, raising questions about the continued utility of knowledge extraction for question answering. This paper investigates the value of triple extraction in this new paradigm by extending an existing benchmark with knowledge extraction annotations and evaluating commercial and open-source LLMs of varying sizes. Our results show that web-scale knowledge extract…

POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency
Ashim Dahal, Ankit Ghimire, Saydul Akbar Murad, Nick Rahimi
https://arxiv.org/abs/2510.01009

POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency
Video Question Answering (VQA) with Large Vision Language Models (LVLMs) has gained significant traction in research ever since the Flamingo was introduced by Deepmind. Recent advancements in large context/long video question answering have allowed VQA tasks to have context window of 1500+ frames. However, this only leads to 50 seconds of video footage without losing any significant information. We introduce POVQA, a data-efficient pipeline that compresses each second of video into a single tem…

Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window
Qiaoyu Tang, Hao Xiang, Le Yu, Bowen Yu, Yaojie Lu, Xianpei Han, Le Sun, WenJuan Zhang, Pengbo Wang, Shixuan Liu, Zhenru Zhang, Jianhong Tu, Hongyu Lin, Junyang Lin
https://arxiv.org/abs/2510.08276

Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window
While recent advances in reasoning models have demonstrated cognitive behaviors through reinforcement learning, existing approaches struggle to invoke deep reasoning capabilities in multi-turn agents with long-horizon interactions. We propose DeepMiner, a novel framework that elicits such abilities by introducing high-difficulty training tasks and dynamic context window. DeepMiner presents a reverse construction method to generate complex but verifiable question-answer pairs from authentic web …