Increasing the Difficulty of Automatically Generated Questions via Reinforcement Learning with Synthetic Preferenceby William Thorne,…
Rewriting Conversational Utterances with Instructed Large Language Modelsby Elnara Galimzhanova, Cristina Ioana Muntean, Franco Maria…
PAR: Prompt-Aware Token Reduction Method for Efficient Large Multimodal Modelsby Yingen Liu, Fan Wu, Ruihui…
SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layersby Viktoriia Chekalina, Anna Rudenko, Gleb…
Weak-eval-Strong: Evaluating and Eliciting Lateral Thinking of LLMs with Situation Puzzlesby Qi Chen, Bowen Zhang,…
Uncovering Factor Level Preferences to Improve Human-Model Alignmentby Juhyun Oh, Eunsu Kim, Jiseon Kim, Wenda…
Personal Intelligence System UniLM: Hybrid On-Device Small Language Model and Server-Based Large Language Model for…
PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Samplingby Xudong…
Core Tokensets for Data-efficient Sequential Training of Transformersby Subarnaduti Paul, Manuel Brack, Patrick Schramowski, Kristian…
Beyond Captioning: Task-Specific Prompting for Improved VLM Performance in Mathematical Reasoningby Ayush Singh, Mansi Gupta,…