Tootfinder

Can Argus Judge Them All? Comparing VLMs Across Domains
Harsh Joshi, Gautam Siddharth Kashyap, Rafiq Ali, Ebad Shabbir, Niharika Jain, Sarthak Jain, Jiechao Gao, Usman Naseem
https://arxiv.org/abs/2507.01042

Can Argus Judge Them All? Comparing VLMs Across Domains
Vision-Language Models (VLMs) are advancing multimodal AI, yet their performance consistency across tasks is underexamined. We benchmark CLIP, BLIP, and LXMERT across diverse datasets spanning retrieval, captioning, and reasoning. Our evaluation includes task accuracy, generation quality, efficiency, and a novel Cross-Dataset Consistency (CDC) metric. CLIP shows strongest generalization (CDC: 0.92), BLIP excels on curated data, and LXMERT leads in structured reasoning. These results expose trad…

Satellite and Mobile Phone Data Reveal How Violence Affects Seasonal Migration in Afghanistan
Xiao Hui Tai, Suraj R. Nair, Shikhar Mehra, Joshua E. Blumenstock
https://arxiv.org/abs/2507.00279

Satellite and Mobile Phone Data Reveal How Violence Affects Seasonal Migration in Afghanistan
Seasonal migration plays a critical role in stabilizing rural economies and sustaining the livelihoods of agricultural households. Violence and civil conflict have long been thought to disrupt these labor flows, but this hypothesis has historically been hard to test given the lack of reliable data on migration in conflict zones. Focusing on Afghanistan in the 8-year period prior to the Taliban's takeover in 2021, we first demonstrate how satellite imagery can be used to infer the timing of the …

Test-Time Consistency in Vision Language Models
Shih-Han Chou, Shivam Chandhok, James J. Little, Leonid Sigal
https://arxiv.org/abs/2506.22395 https://

Test-Time Consistency in Vision Language Models
Vision-Language Models (VLMs) have achieved impressive performance across a wide range of multimodal tasks, yet they often exhibit inconsistent behavior when faced with semantically equivalent inputs, undermining their reliability and robustness. Recent benchmarks, such as MM-R3, highlight that even state-of-the-art VLMs can produce divergent predictions across semantically equivalent inputs, despite maintaining high average accuracy. Prior work addresses this issue by modifying model architect…

This https://arxiv.org/abs/2505.13455 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Exploring Emotional Synchrony in Dyadic Interactions: The Role of Speech Conditions in Facial and Vocal Affective Alignment
Understanding how humans express and synchronize emotions across multiple communication channels particularly facial expressions and speech has significant implications for emotion recognition systems and human computer interaction. Motivated by the notion that non-overlapping speech promotes clearer emotional coordination, while overlapping speech disrupts synchrony, this study examines how these conversational dynamics shape the spatial and temporal alignment of arousal and valence across fac…

Can Common VLMs Rival Medical VLMs? Evaluation and Strategic Insights
Yuan Zhong, Ruinan Jin, Xiaoxiao Li, Qi Dou
https://arxiv.org/abs/2506.17337 https://…

Can Common VLMs Rival Medical VLMs? Evaluation and Strategic Insights
Medical vision-language models (VLMs) leverage large-scale pretraining for diverse imaging tasks but require substantial computational and data resources. Meanwhile, common or general-purpose VLMs (e.g., CLIP, LLaVA), though not trained for medical use, show promise with fine-tuning. This raises a key question: Can efficient fine-tuned common VLMs rival generalist medical VLMs for solving specific medical imaging tasks? This study systematically evaluates common and medical VLMs across disease …

Blackstone agrees to acquire a majority stake in NetBrain, valuing the Burlington, Massachusetts-based network operations and automation company at $750M (Ryan Gould/Bloomberg)
https://www.bloomberg.com/news/articles/2025-07-…

A Benchmark Dataset and Evaluation Framework for Vietnamese Large Language Models in Customer Support
Long S. T. Nguyen, Truong P. Hua, Thanh M. Nguyen, Toan Q. Pham, Nam K. Ngo, An X. Nguyen, Nghi D. M. Pham, Nghia H. Nguyen, Tho T. Quan
https://arxiv.org/abs/2507.22542

A Benchmark Dataset and Evaluation Framework for Vietnamese Large Language Models in Customer Support
With the rapid growth of Artificial Intelligence, Large Language Models (LLMs) have become essential for Question Answering (QA) systems, improving efficiency and reducing human workload in customer service. The emergence of Vietnamese LLMs (ViLLMs) highlights lightweight open-source models as a practical choice for their accuracy, efficiency, and privacy benefits. However, domain-specific evaluations remain limited, and the absence of benchmark datasets reflecting real customer interactions ma…

A young female bear caused a stir after wandering out of the forest and into the leafy suburbs of the Lithuanian capital.
For two days, the brown bear ambled through the neighborhoods of Vilnius,
trotted across highways and explored backyards
— all while being chased by onlookers with smartphones and, eventually, drones.
The government then issued a permit for the bear to be shot and killed.
That did not go down well with Lithuania’s hunters who refused, aware …

Lithuanian hunters refuse government request to shoot a wild bear in the capital
Lithuanian hunters have refused to shoot a wild bear that was spotted roaming around the Lithuanian capital of Vilnius and criticized the government for issuing a permit to kill a member of the protected species. The Lithuanian Association of Hunters and Fishermen says in a statement it is shocked by the decision of the Environment Ministry to shoot the bear. The bear now seems to be out of danger as it was spotted on Wednesday walking through forested areas well outside the city. A government …

MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
Xi Chen, Mingkang Zhu, Shaoteng Liu, Xiaoyang Wu, Xiaogang Xu, Yu Liu, Xiang Bai, Hengshuang Zhao
https://arxiv.org/abs/2506.22434

MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
This work explores enabling Chain-of-Thought (CoT) reasoning to link visual cues across multiple images. A straightforward solution is to adapt rule-based reinforcement learning for Vision-Language Models (VLMs). However, such methods typically rely on manually curated question-answer pairs, which can be particularly challenging when dealing with fine grained visual details and complex logic across images. Inspired by self-supervised visual representation learning, we observe that images contai…

MoCHA: Advanced Vision-Language Reasoning with MoE Connector and Hierarchical Group Attention
Yuqi Pang, Bowen Yang, Yun Cao, Fan Rong, Xiaoyu Li, Chen He
https://arxiv.org/abs/2507.22805

MoCHA: Advanced Vision-Language Reasoning with MoE Connector and Hierarchical Group Attention
Vision large language models (VLLMs) are focusing primarily on handling complex and fine-grained visual information by incorporating advanced vision encoders and scaling up visual models. However, these approaches face high training and inference costs, as well as challenges in extracting visual details, effectively bridging across modalities. In this work, we propose a novel visual framework, MoCHA, to address these issues. Our framework integrates four vision backbones (i.e., CLIP, SigLIP, DI…