While next-token prediction is considered a promising path towards artificial general
intelligence, it has struggled to excel in multimodal tasks, which are still dominated by …

Parameter-efficient transfer learning (PETL) has emerged as a flourishing research field for
adapting large pre-trained models to downstream tasks, greatly reducing trainable …

Colonoscopy is currently one of the most sensitive screening methods for colorectal cancer.
This study investigates the frontiers of intelligent colonoscopy techniques and their …

Building on the foundations of language modeling in natural language processing, Next
Token Prediction (NTP) has evolved into a versatile training objective for machine learning …

Chain-of-Thought (CoT) prompting elicits large language models (LLMs) to produce a series
of intermediate reasoning steps before arriving at the final answer. However, when …

The remarkable success of Large Language Models (LLMs) has extended to the multimodal
domain, achieving outstanding performance in image understanding and generation …

The rapid advance of Large Language Models (LLMs) has catalyzed the development of
Vision-Language Models (VLMs). Monolithic VLMs, which avoid modality-specific encoders …

Scaling the input image resolution is essential for enhancing the performance of Vision
Language Models (VLMs), particularly in text-rich image understanding tasks. However …

The standard practice for developing contemporary MLLMs is to feed features from vision
encoder (s) into the LLM and train with natural language supervision. In this work, we posit …

We present an efficient encoder-free approach for video-language understanding that
achieves competitive performance while significantly reducing computational overhead …