Tootfinder

See the Forest and the Trees: A Synergistic Reasoning Framework for Knowledge-Based Visual Question Answering
Junjie Wang, Yunhan Tang, Yijie Wang, Zhihao Yuan, Huan Wang, Yangfan He, Bin Li
https://arxiv.org/abs/2507.17659

See the Forest and the Trees: A Synergistic Reasoning Framework for Knowledge-Based Visual Question Answering
Multimodal Large Language Models (MLLMs) have pushed the frontiers of Knowledge-Based Visual Question Answering (KBVQA), yet their reasoning is fundamentally bottlenecked by a reliance on uni-dimensional evidence. This "seeing only the trees, but not the forest" approach prevents robust, multi-faceted understanding. Inspired by the principle of seeing both the forest and trees, we propose Synergos-VQA, a novel synergistic reasoning framework. At its core, Synergos-VQA concurrently generates and…

Flavor SU(3) analysis of the charmless semileptonic $B \to PV\ell^ \nu_\ell$ decays
Yi Qiao, Jin-Huan Sheng, Yuan-Guo Xu, Ru-Min Wang
https://arxiv.org/abs/2507.17537

Flavor SU(3) analysis of the charmless semileptonic $B \to PV\ell^+ν_\ell$ decays
All charmless $B \to PV\ell^+ν_\ell$ ($P$ denotes light pseudoscalar meson and $V$ denotes vector meson) decays have not been experimentally observed to date, but some of them might be measured in the near future. The charmless $B \to PV\ell^+ν_\ell$ decays with the axial-vector ($A$) resonance states, the tensor ($T$) resonance states and the excited vector ($V_{E,D}$) resonance states are studied based on flavor SU(3) analysis in this work, where $V_E$ contains $\{ρ(1450), K^*(1410), ω(14…

Hmm, really? https://www.msn.com/en-us/money/markets/the-us-economy-is-regaining-its-swagger/ar-AA1IXrFT

Retrieval Enhanced Feedback via In-context Neural Error-book
Jongyeop Hyun, Bumsoo Kim
https://arxiv.org/abs/2508.16313 https://arxiv.org/pdf/2508.16313

Retrieval Enhanced Feedback via In-context Neural Error-book
Recent advancements in Large Language Models (LLMs) have significantly improved reasoning capabilities, with in-context learning (ICL) emerging as a key technique for adaptation without retraining. While previous works have focused on leveraging correct examples, recent research highlights the importance of learning from errors to enhance performance. However, existing methods lack a structured framework for analyzing and mitigating errors, particularly in Multimodal Large Language Models (MLLM…

The Illusion of Readiness: Stress Testing Large Frontier Models on Multimodal Medical Benchmarks
Yu Gu, Jingjing Fu, Xiaodong Liu, Jeya Maria Jose Valanarasu, Noel Codella, Reuben Tan, Qianchu Liu, Ying Jin, Sheng Zhang, Jinyu Wang, Rui Wang, Lei Song, Guanghui Qin, Naoto Usuyama, Cliff Wong, Cheng Hao, Hohin Lee, Praneeth Sanapathi, Sarah Hilado, Bian Jiang, Javier Alvarez-Valle, Mu Wei, Jianfeng Gao, Eric Horvitz, Matt Lungren, Hoifung Poon, Paul Vozila

The Illusion of Readiness: Stress Testing Large Frontier Models on Multimodal Medical Benchmarks
Large frontier models like GPT-5 now achieve top scores on medical benchmarks. But our stress tests tell a different story. Leading systems often guess correctly even when key inputs like images are removed, flip answers under trivial prompt changes, and fabricate convincing yet flawed reasoning. These aren't glitches; they expose how today's benchmarks reward test-taking tricks over medical understanding. We evaluate six flagship models across six widely used benchmarks and find that high lead…

Crosslisted article(s) found for eess.SY. https://arxiv.org/list/eess.SY/new
[1/1]:
- A Counterfactual Reasoning Framework for Fault Diagnosis in Robot Perception Systems
Haeyoon Han, Mahdi Taheri, Soon-Jo Chung, Fred Y. Hadaegh

A Chain-of-thought Reasoning Breast Ultrasound Dataset Covering All Histopathology Categories
Haojun Yu, Youcheng Li, Zihan Niu, Nan Zhang, Xuantong Gong, Huan Li, Zhiying Zou, Haifeng Qi, Zhenxiao Cao, Zijie Lan, Xingjian Yuan, Jiating He, Haokai Zhang, Shengtao Zhang, Zicheng Wang, Dong Wang, Ziwei Zhao, Congying Chen, Yong Wang, Wangyan Qin, Qingli Zhu
https…

A Chain-of-thought Reasoning Breast Ultrasound Dataset Covering All Histopathology Categories
Breast ultrasound (BUS) is an essential tool for diagnosing breast lesions, with millions of examinations per year. However, publicly available high-quality BUS benchmarks for AI development are limited in data scale and annotation richness. In this work, we present BUS-CoT, a BUS dataset for chain-of-thought (CoT) reasoning analysis, which contains 11,439 images of 10,019 lesions from 4,838 patients and covers all 99 histopathology types. To facilitate research on incentivizing CoT reasoning, …

Adaptive Fast-and-Slow Visual Program Reasoning for Long-Form VideoQA
Chenglin Li, Feng Han, FengTao, Ruilin Li, Qianglong Chen, Jingqi Tong, Yin Zhang, Jiaqi Wang
https://arxiv.org/abs/2509.17743

Adaptive Fast-and-Slow Visual Program Reasoning for Long-Form VideoQA
Large language models (LLMs) have shown promise in generating program workflows for visual tasks. However, previous approaches often rely on closed-source models, lack systematic reasoning, and struggle with long-form video question answering (videoQA). To address these challenges, we introduce the FS-VisPR framework, an adaptive visual program reasoning approach that balances fast reasoning for simple queries with slow reasoning for difficult ones. First, we design efficient visual modules (e.…

Robust Denoising Neural Reranker for Recommender Systems
Wenyu Mao, Shuchang Liu, Hailan Yang, Xiaobei Wang, Xiaoyu Yang, Xu Gao, Xiang Li, Lantao Hu, Han Li, Kun Gai, An Zhang, Xiang Wang
https://arxiv.org/abs/2509.18736

Adrienne Jones-McAllister told News 12 Long Island that she was undergoing an MRI on her knee
when she asked the technician to get her husband, Keith McAllister, to help her get off the table.
She said she called out to him.
The man, 61, entered the MRI room while a scan was underway
The machine’s strong magnetic force drew him in by the metallic chain around his neck, according to a release from the Nassau County Police Department.
He died Thursday afternoon

Man dies after heavy weight-training chain around neck pulls him into MRI machine
A man whose large metallic weight-training chain around his neck pulled him into an MRI machine in New York after he wandered into the room has died. Nassau County police on Long Island say the 61-year-old man died Thursday afternoon, a day after he entered a room while a Magnetic Resonance Imaging scan was underway at Nassau Open MRI. The police department said in a statement that the strong magnetic force drew him in by his metallic chain. Authorities did not release his name. A person who an…