Accepted System Demonstrations Papers

• OpenRLHF: A Ray-based Easy-to-use, Scalable and High-performance RLHF Framework
  Bin Chen, Hao Chen, Haoran Wang, Haotian Xu, Jason Klein Liu, Jian Hu, Songlin Jiang, Wei Shen, Weixun Wang, Wenkai Fang, Xianyu, Xibin Wu, Yu Cao, LiuYiming
• EasyDistill: A Comprehensive Toolkit for Effective Knowledge Distillation of Large Language Models
  Chengyu Wang, Jun Huang, Junbing Yan, Wenrui Cai, Yuanhao Yue
• CafGa: Customizing Feature Attributions to Explain Language Models
  Alan David Boyle, Furui Cheng, Mennatallah El-Assady, Vilém Zouhar
• SLACKAGENTS: SCALABLE COLLABORATION OF MULTIPLE AI AGENTS IN WORKSPACES
  Caiming Xiong, Huan Wang, Jianguo Zhang, Juntao Tan, Shelby Heinecke, Silvio Savarese, Weiran Yao, Zhiwei Liu, Zuxin Liu, Frank Wang
• InTriage: Intelligent Telephone Triage in Pre-Hospital Emergency Care
  Dehan Hong, Hao Fei, Kai He, Marcus Eng Hock Ong, Mengling Feng, Qika Lin, Eng Siong Chng
• EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models
  Guozhou Zheng, Haoming Xu, Huajun Chen, Mengru Wang, Ningyu Zhang, Shuxun Wang, Xinle Deng, Yunzhi Yao, Ziwen Xu, kewei Xu
• AERA Chat: An Interactive Platform for Automated Explainable Student Answer Assessment
  Artem Bobrov, Cesare Aloisi, Jiazheng Li, Runcong Zhao, Yulan He
• Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization
  Damien Riquet, Gabriel Loiseau, Marc Tommasi, Maxime Meyer, Damien Sileo
• SpiritRAG: A Q&A System for Religion and Spirituality in the United Nations Archive
  Anastassia Shaitarova, Fabian Winiger, Gerold Schneider, Nianlong Gu, Patrick Montjourides, Yingqiang Gao
• KMatrix-2: A Comprehensive Heterogeneous Knowledge Collaborative Enhancement Toolkit for Large Language Model
  Jun Zhao, Kang Liu, Kun Luo, Shizhu He, Wangtao Sun, XueYou Zhang, Ziyang Huang, di wu, shun wu, yuanxiaowei
• EvoAgentX: An Automated Framework for Evolving Agentic Workflows
  Jinyuan Fang, Siwei Liu, Yingxu Wang, Zaiqiao Meng
• ResearStudio: A Human-intervenable Framework for Building Controllable Deep Research Agents
  Linyi Yang, Yixuan Weng
• PresentAgent: Multimodal Agent for Presentation Video Generation
  Biao Wu, Jingwei Shi, Ling Chen, Meng Fang, Yang Zhao, Yanjie Liang, Zeyu Zhang
• PDFMathTranslate: Scientific Document Translation Preserving Layouts
  Chang Chu, Rongxin Ouyang, Xiangyao Ma, Zhikuang Xin
• Open Political Corpora: Structuring, Searching, and Analyzing Political Text Collections with PoliCorp
  Muhammad Ahsan Shahid, Nina Smirnova, Philipp Mayr
• LAD: LoRA-Adapted Diffusion
  Ayoub Bagheri, Ruurd Jan Anthonius Kuiper, Bram van Es, Lars de Groot
• UnityAI Guard: Pioneering Toxicity Detection Across Low-Resource Indian Languages
  Adithya Ananth, Birudugadda Srivibhav, Daksh Jain, Eshwar Dhande, Himanshu Beniwal, Kuldeep, Mayank Singh, Pavan Deekshith Doddi, Reddybathuni Venkat, Rohit Kumar
• CrowdAgent: Multi-Agent Managed Multi-Source Annotation System
  Changjie Fan, Haobo Wang, Junbo Zhao, Maosheng Qin, Mingxuan Xia, Minmin Lin, Renyu Zhu, Runze Wu, Zhen Zhu, Chenchenkai, Lu Xu
• LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators
  Gabriel Chua, Leanne Tan, Roy Ka-Wei Lee, Ziyu Ge
• Pico: A Modular Framework for Hypothesis-Driven Small Language Model Research
  David Demitri Africa, Paula Buttery, Richard Diehl Martinez, Ryan Daniels, Suchir Salhan, Yuval Weiss
• DistaLs: a Comprehensive Collection of Language Distance Measures
  Esther Ploeger, Rob van der Goot, Tanja Samardzic, Verena Blaschke
• MASA: A Modular Framework for LLM-Driven Multi-Agent Systems for Autoformalization
  Andre Freitas, Lan Zhang, Marco Valentino
• SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains
  Daniel Smolyak, Krithika Ramesh, Margrét V. Bjarnadóttir, Nupoor Gandhi, Ritu Agarwal, Zihao Zhao, Anjalie Field
• Open-Theatre: An Open-Source Toolkit for LLM-based Interactive Drama
  Hongqiu Wu, Tianyang Xu, Weiqi Wu, hai zhao
• End-to-End Multilingual Automatic Dubbing via Duration-based Translation with Large Language Models
  Hyun-Sik Won, DongJin Jeong, Hyunkyu Choi, Jinwon Kim
• Sanskrit Voyager: Unified Web Platform for Interactive Reading and Linguistic Analysis of Sanskrit Texts
  Danilo Croce, Giacomo De Luca, Roberto Basili
• AutoIntent: AutoML for Text Classification
  Darina Rustamova, Denis Kuznetsov, Ilya Alekseev, Roman Solomatin
• PledgeTracker: A System for Monitoring the Fulfilment of Pledges
  Andreas Vlachos, David Corney, Michael Sejr Schlichtkrull, Yulong Chen, Zhenyun Deng, Andrew Dudfield, Nasim Asl
• Bratly: A Python Extension for BRAT Functionalities
  Christian Lovis, Jamil Zaghir, Jean-Philippe Goldman, Mina Bjelogrlic, Nikola Bjelogrlic
• SciClaims: An End-to-End Generative System for Biomedical Claim Analysis
  Jose Manuel Gomez-Perez, Raúl Ortega
• LingConv: An Interactive Toolkit for Controlled Paraphrase Generation with Linguistic Attribute Control
  Hadi Amiri, Mohamed Elgaar
• BAREC Demo: Resources and Tools for Sentence-level Arabic Readability Assessment
  Hanada Taha, Khalid Elmadani, Kinda Altarbouch, Nizar Habash, Ossama Obeid
• TRACE: Training and Inference-Time Interpretability Analysis for Language Models
  Andre Freitas, Danilo Carvalho, Nura Aljaafari
• Synthetic Data for Evaluation: Supporting LLM-as-a-Judge Workflows with EvalAssist
  Elizabeth M. Daly, Erik Miehling, Hyo Jin Do, Jasmina Gajcin, Martín Santillán Cooper, Michael Desmond, Qian Pan, Werner Geyer, Zahra Ashktorab
• TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs
  Alfy Samuel, Alperen Öziş, Anoop Kumar, Daben Liu, Duygu Nur Yaldiz, Hayrettin Eren Yildiz, Mitash Ashish Shah, Sai Praneeth Karimireddy, Amir Avestimehr, Sungmin Kang, Yavuz Faruk Bakman, Zhiqi Huang
• Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents
  Jingyuan Wang, Qiyu Sun, Richong Zhang, Shiqi Li, Yaowei Zheng, Yuchen Gong, Ziyang Miao
• The iRead4Skills Intelligent Complexity Analyzer
  Alejandro Catala, David Antunes, Elodie Vanzeveren, Eugénio Ribeiro, Jorge Baptista, Marcos Garcia, Raquel Amaro, Thibault Bañeras-Roux, Thomas François, Wafa Aissa, Mario Izquierdo-Álvarez
• TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability
  Ameya Godbole, James Flemings, Johnny Wei, Krishna P. Gummadi, Mohammad Aflah Khan, Robin Jia, Willie Neiswanger, Ryan Wang
• AM4DSP: Argumentation Mining in Structured Decentralized Discussion Platforms for Deliberative Democracy
  Anna De Liddo, Elena Cabrio, Lucas Anastasiou, Serena Villata, Sofiane Elguendouze, Erwan Hain
• GLiNER2: Schema-Driven Multi-Task Learning for Structured Information Extraction
  Gil Pasternak, Urchade Zaratiana
• Automated Evidence Extraction and Scoring for Corporate Climate Policy Engagement: A Multilingual RAG Approach
  Chiara Colesanti Senni, Imene kolli, Markus Leippold, Saeid Vaghefi, Shantam Raj
• LaTeXMT: Machine Translation for LaTeX Documents
  Calvin Hoy, Georg Moser, Samuel Frontull
• MALLM: Multi-Agent Large Language Models Framework
  Bela Gipp, Jan Philip Wahle, Jonas Becker, Lars Benedikt Kaesberg, Niklas Bauer, Terry Ruas
• RadEval: A framework for radiology text evaluation
  Dave Van Veen, David W Eyre, Fatemeh Haghighi, Javid Abderezaei, Jean-Benoit Delbrouck, Justin Xu, Xi Zhang, Zaiqiao Meng, Ali Ganjizadeh, Eric Brattain, Julie Bauml, Roger Boodoo
• Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree
  Sam Johnson, Thai Le, Viet Pham
• LangVAE and LangSpace: Building and Probing for Language Model VAEs
  Andre Freitas, Danilo Carvalho, Harriet Unsworth, Yingji Zhang
• AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysis
  Callie C. Liao, Duoduo Liao, Sai Surya Gadiraju
• ROBOTO2: An Interactive System and Dataset for LLM-assisted Clinical Trial Risk of Bias Assessment
  Anthony Hevia, Lucy Lu Wang, Nguyen Thanh Tam, Sanjana Chintalapati, Terry P Klassen, Veronica Ka Wai Lai
• GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models
  Ananda Sreenidhi, Bhavani Sai Praneeth Varma Mantina, Fei Yuan, Hengyu Luo, Joseph Attieh, Jörg Tiedemann, Mengjie Wang, Ona de Gibert, Peiqin Lin, Raúl Vázquez, Samea Yusofi, Sawal Devkota, Shaoxiong Ji, Xu Huang, Zihao Li
• AIPOM: Agent-aware Interactive Planning for Multi-Agent Systems
  Chen Shen, Dan Zhang, Estevam Hruschka, Hannah Kim, Kushan Mitra
• Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification
  Chenfei Xiong, Dirk Hovy, Donya Rooein, Elliott Ash, Jingwei Ni, Lorena Calvo-Bartolomé, Markus Leippold, Mennatallah El-Assady, Vilém Zouhar, Yu Fan, Alexander Hoyle, MRINMAYA SACHAN
• SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks
  Adamenko Pavel, Aidar Valeev, Alena Fenogenova, Dmitrii Babaev, Ivan Lopatin, Ivanov Mikhail, Pavel Zadorozhny, Rodion Levichev, Valentin Malykh
• AgentDiagnose: An Open Toolkit for Diagnosing LLM Agent Trajectories
  Apurva Gandhi, Graham Neubig, Tianyue Ou, Wanyao Guo, Xiang Yue
• BioGraphia: A LLM-Assisted Biological Pathway Graph Annotation Platform
  Adam Officer, Angela Chen, Lei Li, Sumin Jo, Xi Xu, Yufei Huang
• From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens
  Daniel Wei, Eric Haoran Huang, Haoyue Shi, Hala Sheta, Ilia Alenabi, Jiajun Hong, Jialin Yang, Jiawei Zhou, Ruoxi Ning, Ryker Lin, Shuyu Wu, Ziqiao Ma
• MedTutor: A Retrieval-Augmented LLM System for Case-Based Medical Education
  Arman Cohan, Dongsuk Jang, Sophie Chheang, Ziyao Shangguan, Anurag Gupta, Jan T Czerminski, Kyle Tegtmeyer
• AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning
  Chi Chen, Chongyi Wang, Haotian Chen, Maosong Sun, Shenzhi Yang, Wang Xu, Xin Cong, Yankai Lin, Yaxi Lu, Yesai Wu, Yuan Yao, Yupeng Huo, Zhiyuan Liu, Zhong Zhang, Zhongwu Zhai, 司函, Yikun Fu
• MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models
  Caiming Xiong, Haolin Chen, Huan Wang, Jianguo Zhang, Jielin Qiu, Shelby Heinecke, Shiyu Wang, Weiran Yao, Zhiwei Liu, Zuxin Liu, silvio savarese, Roshan Ram
• PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation
  Eliya Habba, Gabriel Stanovsky, Gili Lior, Noam Dahan
• ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning
  Ao Sun, Ching Wing Kwok, Jianyuan Zhan, Takatomo Saito, Wei Dai, Xudong Xiao, Yian Wang, Yichen Lu, Zongheng Wu, Jiaen LIU, SICHENG LAI, Sheng fu
• Quest2DataAgent: Automating End-to-End Scientific Data Collection
  Ethan A. Brown, Sobin Alosious, Tengfei Luo, Tianyu Yang, Xiangliang Zhang, Yuhan Liu, Jason R. Rohr
• Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support
  Anastasiia Derzhanskaia, Christin Seifert, Jan Trienes, Jörg Schlötterer, Markus Mühling, Roland Schwarzkopf
• GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer
  Ahmed Nesar Tahsin Choudhury, Mahmudul Hasan, Md. Mahmudul Hasan, Md Mosaddek Khan
• LearnLens: LLM-Enabled Personalised, Curriculum-Grounded Feedback with Educators in the Loop
  Artem Bobrov, Cesare Aloisi, Jiazheng Li, Runcong Zhao, Yulan He
• GraphMind: Interactive Novelty Assessment System for Accelerating Scientific Discovery
  Italo Luis da Silva, Lin Gui, Yulan He, hanqi yan
• SciSketch: An Open-source Framework for Automated Schematic Diagram Generation in Scientific Papers
  Arman Cohan, Chen Zhao, Kaiyan Zhang, Manasi Patwardhan, Yilun Zhao, Zihang Wang
• Alpha-GPT: Human-AI Interactive Alpha Mining for Quantitative Investment
  Hang Yuan, Heung-Yeung Shum, Jian Guo, Leon Zhou, Lionel Ni, Saizhuo Wang
• o-MEGA: Optimized Methods for Explanation Generation and Analysis
  Andrej Ridzik, Jaroslav Kopčan, Marcel Veselý, Martin Tamajka, Qiwei Peng, Ľuboš Kriš
• Interactive Training: Feedback-Driven Neural Network Optimization
  Wentao Zhang, Yang Young Lu, Yuntian Deng
• OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model
  Chen Wang, Chengqing Zong, Jiajun Zhang, Jinqiao Wang, Jun Lin, Lingxiang Wu, Tianyu Peng, Wen Yang
• TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents
  Fenghai Li, Haofei Yu, Jiaxun Zhang, Keyang Xuan, Kunlun Zhu, Kyle Richardson, Ziheng Qi, Zijie Lei, Jiaxuan You
• ConfReady: A RAG based Assistant and Dataset for Conference Checklist Responses
  Agam Shah, Kosha Bheda, Michael Galarnyk, Prasun Banerjee, Rutwik Routu, Sudheer Chava, Vidhyakshaya Kannan
• LLM$\times$MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System
  Haoyu Wang, Jie Zhou, Maosong Sun, Shuo Wang, Siyu Lin, Yu Chao, Zhiyuan Liu, Zhu Zhang, Zihan Zhou, xiaorong wang
• DVAGen: Dynamic Vocabulary Augmented Generation
  Jiahao Kuang, Jie Wang, Nuowei Liu, Tao Ji, Wei Du, Xiaoling Wang, Yuanbin Wu
• PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization
  Dawei Xiang, Kexin Chu, Tianqi Ding, Wei Zhang, Wenyan Xu, Zixu Shen
• Metamo: Empowering Large Language Models with Psychological Distortion Detection for Cognition-aware Coaching
  HAJIME HOTTA, Manh-Cuong Phan, Minh-Tien Nguyen, Le Huu Loi
• MathBuddy: A Multimodal System for Affective Math Tutoring
  Dacia Braca, Debanjana Kar, Leopold Böss, Nina Christine Hubig, Yufang Hou, Philipp Wintersberger, Sebastian Maximilian Dennerlein