47 citations · 60 across the 36 of their papers we have counts for
8 papers · 1 filter
Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning
Qi Sun, Pengfei Hong, Tej Deep Pala +4
Traditional reinforcement learning-based robotic control methods are often task-specific and fail to generalize across diverse environments or unseen objects and instructions. Visu…
An Evolved Universal Transformer Memory
Edoardo Cetin, Qi Sun, Tianyu Zhao +1
Prior methods propose to offset the escalating costs of modern foundation models by dropping specific parts of their contexts with hand-designed rules, while attempting to preserve…
Can-Do! A Dataset and Neuro-Symbolic Grounded Framework for Embodied Planning with Large Multimodal Models
Yew Ken Chia, Qi Sun, Lidong Bing +1
Large multimodal models have demonstrated impressive problem-solving abilities in vision and language tasks, and have the potential to encode extensive world knowledge. However, it…
Transformer Layers as Painters
Qi Sun, Marc Pickett, Aakash Kumar Nain +1
Despite their nearly universal adoption for large language models, the internal workings of transformers are not well understood. We aim to better understand the impact of removing…
MM-InstructEval: Zero-Shot Evaluation of (Multimodal) Large Language Models on Multimodal Reasoning Tasks
Xiaocui Yang, Wenfang Wu, Shi Feng +7
The emergence of multimodal large language models (MLLMs) has triggered extensive research in model evaluation. While existing evaluation studies primarily focus on unimodal (visio…
Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code
Taishi Nakamura, Mayank Mishra, Simone Tedeschi +42
Pretrained language models are an integral part of AI applications, but their high computational cost for training limits accessibility. Initiatives such as Bloom and StarCoder aim…
Evolutionary Optimization of Model Merging Recipes
Takuya Akiba, Makoto Shing, Yujin Tang +2
Large language models (LLMs) have become increasingly capable, but their development often requires substantial computational resources. While model merging has emerged as a cost-e…
Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction
Qi Sun, Kun Huang, Xiaocui Yang +3
Document-level Relation Triplet Extraction (DocRTE) is a fundamental task in information systems that aims to simultaneously extract entities with semantic relations from a documen…