OmChat: A Recipe to Train Multimodal Language Models with Strong Long Context and Video Understanding

We introduce OmChat, a model designed to excel in handling long contexts and video understanding tasks. OmChat's new architecture standardizes how different visual inputs are processed, making it more efficient and adaptable. It uses a dynamic vision encoding process to effectively handle images of various resolutions, capturing fine details across a range of image qualities. OmChat utilizes an active progressive multimodal pretraining strategy, which gradually increases the model's capacity for long contexts and enhances its overall abilities. By selecting high-quality data during training, OmChat learns from the most relevant and informative data points. With support for a context length of up to 512K, OmChat demonstrates promising performance in tasks involving multiple images and videos, outperforming most open-source models in these benchmarks. Additionally, OmChat proposes a prompting strategy for unifying complex multimodal inputs including single image text, multi-image text and videos, and achieving competitive performance on single-image benchmarks. To further evaluate the model's capabilities, we proposed a benchmark dataset named Temporal Visual Needle in a Haystack. This dataset assesses OmChat's ability to comprehend temporal visual details within long videos. Our analysis highlights several key factors contributing to OmChat's success: support for any-aspect high image resolution, the active progressive pretraining strategy, and high-quality supervised fine-tuning datasets. This report provides a detailed overview of OmChat's capabilities and the strategies that enhance its performance in visual understanding.

OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer

Recent advancements in Large Language Models (LLMs) have expanded their capabilities to multimodal contexts, including comprehensive video understanding. However, processing extensive videos such as 24-hour CCTV footage or full-length films presents significant challenges due to the vast data and processing demands. Traditional methods, like extracting key frames or converting frames to text, often result in substantial information loss. To address these shortcomings, we develop OmAgent, efficiently stores and retrieves relevant video frames for specific queries, preserving the detailed content of videos. Additionally, it features an Divide-and-Conquer Loop capable of autonomous reasoning, dynamically invoking APIs and tools to enhance query processing and accuracy. This approach ensures robust video understanding, significantly reducing information loss. Experimental results affirm OmAgent's efficacy in handling various types of videos and complex tasks. Moreover, we have endowed it with greater autonomy and a robust tool-calling system, enabling it to accomplish even more intricate tasks.

Plug-in UL-CSI-Assisted Precoder Upsampling Approach in Cellular FDD Systems

Acquiring downlink channel state information (CSI) is crucial for optimizing performance in massive Multiple Input Multiple Output (MIMO) systems operating under Frequency-Division Duplexing (FDD). Most cellular wireless communication systems employ codebook-based precoder designs, which offer advantages such as simpler, more efficient feedback mechanisms and reduced feedback overhead. Common codebook-based approaches include Type II and eType II precoding methods defined in the 3GPP standards. Feedback in these systems is typically standardized per subband (SB), allowing user equipment (UE) to select the optimal precoder from the codebook for each SB, thereby reducing feedback overhead. However, this subband-level feedback resolution may not suffice for frequency-selective channels. This paper addresses this issue by introducing an uplink CSI-assisted precoder upsampling module deployed at the gNodeB. This module upsamples SB-level precoders to resource block (RB)-level precoders, acting as a plug-in compatible with existing gNodeB or base stations.