| Time | Event | Title | Authors & Speakers |
|---|---|---|---|
| 09:30–09:55 | Coffee and Arrivals | ||
| 09:55–10:00 | Introduction | Prof. Yulan He | |
| 10:00–10:45 | Invited Talk 1 (Chair: Linhai Zhang) | From Language to Perception: Emergent Multimodal Reasoning in Foundation Models | Che Liu (Imperial College London) |
| 10:45–11:45 | Paper Session 1 LLM Reasoning (Chair: Lin Gui) | MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale | Jiawei Guo, Tianyu Zheng, Yizhi Li, Yuelin Bai, Bo Li, Yubo Wang, King Zhu, Graham Neubig, Wenhu Chen, Xiang Yue |
| Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration | Qinglin Zhu, Runcong Zhao, Hanqi Yan, Yulan He, Yudong Chen, Lin Gui | ||
| Temporal Reasoning for Timeline Summarisation in Social Media | Jiayu Song, Mahmud Elahi Akhter, Dana Atzil-Slonim, Maria Liakata | ||
| Position: LLMs Need a Bayesian Meta-Reasoning Framework for More Robust and Generalizable Reasoning | Hanqi Yan, Linhai Zhang, Jiazheng Li, Zhenyi Shen, Yulan He | ||
| 11:45–12:00 | Coffee Break | ||
| 12:00–12:45 | Paper Session 2 AI & Social Science (Chair: Runcong Zhao) | Catching Stray Balls: Football, fandom, and the impact on digital discourse | Mark J. Hill |
| Reproducibility: The New Frontier in AI Governance | Israel Mason-Williams, Gabryel Mason-Williams | ||
| EnigmaToM: Improve LLMs’ Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States | Hainiu Xu, Siya Qi, Jiazheng Li, Yuxiang Zhou, Jinhua Du, Caroline Catmur, Yulan He | ||
| 12:45–14:00 | Lunch | ||
| 14:00–14:45 | Invited Talk 2 (Chair: Hanqi Yan) | Your Next-Token Prediction and Transformers Are Biased for Long-Context Modeling | Yifei Wang (Massachusetts Institute of Technology) (remote) |
| 14:45–15:30 | Paper Session 3 LLM & QA (Chair: Linhai Zhang) | PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA | Xinyu Wang, Yanzheng Xiang, Lin Gui, Yulan He |
| Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice Questions | Ruizhe Li, Yanjun Gao | ||
| Assessing the Reasoning Capabilities of LLMs in the context of Evidence-based Claim Verification | John Dougrez-Lewis, Mahmud Elahi Akhter, Federico Ruggeri, Sebastian Löbbers, Yulan He, Maria Liakata | ||
| 15:30–15:45 | Coffee Break | ||
| 15:45–16:30 | Paper Session 4 LLM & RL (Chair: Hanqi Yan) | NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning | Wei Liu, Siya Qi, Xinyu Wang, Chen Qian, Yali Du, Yulan He |
| M³HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality | Ziyan Wang, Zhicheng Zhang, Fei Fang, Yali Du | ||
| Less for More: Enhanced Feedback-aligned Mixed LLMs for Molecule Caption Generation and Fine-Grained NLI Evaluation | Dimitris Gkoumas, Maria Liakata | ||
| 16:30–17:30 | Paper Session 5 LLM Mix-up (Chair: Yulan He) | Evaluating LLMs' Assessment of Mixed-Context Hallucination Through the Lens of Summarization | Siya Qi, Rui Cao, Yulan He, Zheng Yuan |
| PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation | Linhai Zhang, Jialong Wu, Deyu Zhou, Yulan He | ||
| Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering | Zhanghao Hu, Hanqi Yan, Qinglin Zhu, Zhenyi Shen, Yulan He, Lin Gui | ||
| MuPT: A Generative Symbolic Music Pretrained Transformer | Xingwei Qu, Yuelin Bai, Yinghao Ma, Ziya Zhou, Ka Man Lo, Jiaheng Liu, Ruibin Yuan, Lejun Min, Xueling Liu, Tianyu Zhang, Xinrun Du, Shuyue Guo, Yiming Liang, Yizhi Li, Shangda Wu, Junting Zhou, Tianyu Zheng, Ziyang Ma, Fengze Han, Wei Xue, Gus Xia, Emmanouil Benetos, Xiang Yue, Chenghua Lin, Xu Tan, Stephen W. Huang, Jie Fu, Ge Zhang | ||
| 17:30–17:35 | Wrap-Up | Prof. Yulan He | |
*Bold denotes speaker for session