Tootfinder

Effective Training Data Synthesis for Improving MLLM Chart Understanding
Yuwei Yang, Zeyu Zhang, Yunzhong Hou, Zhuowan Li, Gaowen Liu, Ali Payani, Yuan-Sen Ting, Liang Zheng
https://arxiv.org/abs/2508.06492

Effective Training Data Synthesis for Improving MLLM Chart Understanding
Being able to effectively read scientific plots, or chart understanding, is a central part toward building effective agents for science. However, existing multimodal large language models (MLLMs), especially open-source ones, are still falling behind with a typical success rate of 30%-50% on challenging benchmarks. Previous studies on fine-tuning MLLMs with synthetic charts are often restricted by their inadequate similarity to the real charts, which could compromise model training and performa…

From Kardar-Parisi-Zhang scaling to soliton proliferation in Josephson junction arrays
Mikheil Tsitsishvili, Reinhold Egger, Karsten Flensberg, Sebastian Diehl
https://arxiv.org/abs/2509.08479

From Kardar-Parisi-Zhang scaling to soliton proliferation in Josephson junction arrays
We propose Josephson junction arrays as realistic platforms for observing nonequilibrium scaling laws characterizing the Kardar-Parisi-Zhang (KPZ) universality class, and space-time soliton proliferation. Focusing on a two-chain ladder geometry, we perform numerical simulations for the roughness function. Together with analytical arguments, our results predict KPZ scaling at intermediate time scales, extending over sufficiently long time scales to be observable, followed by a crossover to the a…

TrackVLA : Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
Jiahang Liu, Yunpeng Qi, Jiazhao Zhang, Minghan Li, Shaoan Wang, Kui Wu, Hanjing Ye, Hong Zhang, Zhibo Chen, Fangwei Zhong, Zhizheng Zhang, He Wang
https://arxiv.org/abs/2510.07134

TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
Embodied Visual Tracking (EVT) is a fundamental ability that underpins practical applications, such as companion robots, guidance robots and service assistants, where continuously following moving targets is essential. Recent advances have enabled language-guided tracking in complex and unstructured scenes. However, existing approaches lack explicit spatial reasoning and effective temporal memory, causing failures under severe occlusions or in the presence of similar-looking distractors. To add…

A Meat-Summer Night's Dream: A Tangible Design Fiction Exploration of Eating Biohybrid Flying Robots
Ziming Wang, Yiqian Wu, Qingxiao Zheng, Shihan Zhang, Ned Barker, Morten Fjeld
https://arxiv.org/abs/2510.06507

A Meat-Summer Night's Dream: A Tangible Design Fiction Exploration of Eating Biohybrid Flying Robots
What if future dining involved eating robots? We explore this question through a playful and poetic experiential dinner theater: a tangible design fiction staged as a 2052 Paris restaurant where diners consume a biohybrid flying robot in place of the banned delicacy of ortolan bunting. Moving beyond textual or visual speculation, our ``dinner-in-the-drama'' combined performance, ritual, and multisensory immersion to provoke reflection on sustainability, ethics, and cultural identity. Six partic…

Bidirectional Representations Augmented Autoregressive Biological Sequence Generation:Application in De Novo Peptide Sequencing
Xiang Zhang, Jiaqi Wei, Zijie Qiu, Sheng Xu, Zhi Jin, ZhiQiang Gao, Nanqing Dong, Siqi Sun
https://arxiv.org/abs/2510.08169

Bidirectional Representations Augmented Autoregressive Biological Sequence Generation:Application in De Novo Peptide Sequencing
Autoregressive (AR) models, common in sequence generation, are limited in many biological tasks such as de novo peptide sequencing and protein modeling by their unidirectional nature, failing to capture crucial global bidirectional token dependencies. Non-Autoregressive (NAR) models offer holistic, bidirectional representations but face challenges with generative coherence and scalability. To transcend this, we propose a hybrid framework enhancing AR generation by dynamically integrating rich c…

Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narratives
Prathamesh Vasudeo Naik, Naresh Kumar Dintakurthi, Zhanghao Hu, Yue Wang, Robby Qiu
https://arxiv.org/abs/2509.08380

Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narratives
Generating regulatorily compliant Suspicious Activity Report (SAR) remains a high-cost, low-scalability bottleneck in Anti-Money Laundering (AML) workflows. While large language models (LLMs) offer promising fluency, they suffer from factual hallucination, limited crime typology alignment, and poor explainability -- posing unacceptable risks in compliance-critical domains. This paper introduces Co-Investigator AI, an agentic framework optimized to produce Suspicious Activity Reports (SARs) sign…

Memory Retrieval and Consolidation in Large Language Models through Function Tokens
Shaohua Zhang, Yuan Lin, Hang Li
https://arxiv.org/abs/2510.08203 https://

Memory Retrieval and Consolidation in Large Language Models through Function Tokens
The remarkable success of large language models (LLMs) stems from their ability to consolidate vast amounts of knowledge into the memory during pre-training and to retrieve it from the memory during inference, enabling advanced capabilities such as knowledge memorization, instruction-following and reasoning. However, the mechanisms of memory retrieval and consolidation in LLMs remain poorly understood. In this paper, we propose the function token hypothesis to explain the workings of LLMs: Duri…

InstructX: Towards Unified Visual Editing with MLLM Guidance
Chong Mou, Qichao Sun, Yanze Wu, Pengze Zhang, Xinghui Li, Fulong Ye, Songtao Zhao, Qian He
https://arxiv.org/abs/2510.08485

InstructX: Towards Unified Visual Editing with MLLM Guidance
With recent advances in Multimodal Large Language Models (MLLMs) showing strong visual understanding and reasoning, interest is growing in using them to improve the editing performance of diffusion models. Despite rapid progress, most studies lack an in-depth analysis of MLLM design choices. Moreover, the integration of MLLMs and diffusion models remains an open challenge in some difficult tasks, such as video editing. In this paper, we present InstructX, a unified framework for image and video…

Mediator-Guided Multi-Agent Collaboration among Open-Source Models for Medical Decision-Making
Kaitao Chen, Mianxin Liu, Daoming Zong, Chaoyue Ding, Shaohao Rui, Yankai Jiang, Mu Zhou, Xiaosong Wang
https://arxiv.org/abs/2508.05996

Mediator-Guided Multi-Agent Collaboration among Open-Source Models for Medical Decision-Making
Complex medical decision-making involves cooperative workflows operated by different clinicians. Designing AI multi-agent systems can expedite and augment human-level clinical decision-making. Existing multi-agent researches primarily focus on language-only tasks, yet their extension to multimodal scenarios remains challenging. A blind combination of diverse vision-language models (VLMs) can amplify an erroneous outcome interpretation. VLMs in general are less capable in instruction following a…

Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts
Rochana Prih Hastuti, Rian Adam Rajagede, Mansour Al Ghanim, Mengxin Zheng, Qian Lou
https://arxiv.org/abs/2509.07755 …

Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts
As large language models (LLMs) adapted to sensitive domains such as medicine, their fluency raises safety risks, particularly regarding provenance and accountability. Watermarking embeds detectable patterns to mitigate these risks, yet its reliability in medical contexts remains untested. Existing benchmarks focus on detection-quality tradeoffs, overlooking factual risks under low-entropy settings often exploited by watermarking's reweighting strategy. We propose a medical-focused evaluation w…