AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learningby Minghao Chen, Yihang Li,…
Devil’s Advocate: Anticipatory Reflection for LLM Agentsby Haoyu Wang, Tao Li, Zhiwei Deng, Dan Roth,…
Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformersby Chau Pham, Bryan A. PlummerFirst submitted to arxiv…
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Trainingby Wenyu Du,…
Are Long-LLMs A Necessity For Long-Context Tasks?by Hongjin Qian, Zheng Liu, Peitian Zhang, Kelong Mao,…
V-Zen: Efficient GUI Understanding and Precise Grounding With A Novel Multimodal LLMby Abdur Rahman, Rajat…
Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verificationby Yuxuan Guo, Shaohui Peng, Jiaming Guo,…
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Searchby Nicola…
Language-Driven Interactive Traffic Trajectory Generationby Junkai Xia, Chenxin Xu, Qingyao Xu, Chen Xie, Yanfeng Wang,…
Text-guided 3D Human Motion Generation with Keyframe-based Parallel Skip Transformerby Zichen Geng, Caren Han, Zeeshan…