Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environmentsby…
VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Databy Xuefeng Du, Reshmi Ghosh, Robert Sim,…
COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Modelsby Divyanshu Daiya, Damon…
Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Methodby Bikang Pan, Wei Huang, Ye…
BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Searchby Linzhuang…
Counterfactual Token Generation in Large Language Modelsby Ivi Chatzi, Nina Corvelo Benz, Eleni Straitouri, Stratis…
Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selectionby Matteo Zecchin, Sangwoo Park, Osvaldo SimeoneFirst submitted…
Federated Large Language Models: Current Progress and Future Directionsby Yuhang Yao, Jianyi Zhang, Junda Wu,…
Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarkingby Benjamin Feuer, Micah Goldblum,…
Visual Prompting in Multimodal Large Language Models: A Surveyby Junda Wu, Zhehao Zhang, Yu Xia,…