…View arXiv page View PDF Project page GitHub 4 Add to collection Community TRON introduces a generator–verifier framework for visual reasoning RL, where Python-based environments continuously generate new images, questions…
…We study this question and propose AgentFugue, a collective reasoning framework built around a shared reasoning hub . As peer agents explore the same task in parallel, the hub records concise notes on…
…What Drives Delegation and Trust in Human-Computer Cooperative Question Answering? Published on May 27 Submitted by Maharshi Gor on Jun 2 QANTA Authors: Maharshi Gor , , , , , , Abstract Human-AI collaboration in question…
…questions are designed to be hint-free, ensuring that no key evidence is disclosed to models before answering. View arXiv page View PDF Project page GitHub 56 Add to collection Community This…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct We study the personal camera roll visual question answering setting. In this setting, a conversational AI assistant can access a user's personal camera…
…View arXiv page View PDF Project page Add to collection Community We introduce HakushoBench , a challenging Japanese chart and table visual question answering (VQA) benchmark for evaluating vision-language models (VLMs). To…
…Each question carries a query timestamp and an evidence interval, and at evaluation, the model sees only the prefix preceding the query. Questions span four levels of increasing abstraction: instantaneous egocentric perception…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Multimodal Large Language Models (MLLMs) have demonstrated significant achievements in general visual question answering (VQA) tasks. However, they remain brittle on mechanical engineering drawings…
…We propose GridProbe, an efficient training-free posterior-probing inference paradigm that scores evidence in answer space using a frozen VLM's own reasoning and then selects question-relevant frames adaptively, resulting…
…We also found that models do not use videos effectively to reason about the questions, as a single image related to the question leads to similar performance as passing a full video…