4 papers
SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning
Jitesh Jain, Jialuo Li, Zixian Ma +7
As humans, we are natural any-horizon reasoners, i.e., we can decide whether to iteratively skim long videos or watch short ones in full when necessary for a given task. With this…
AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory
Jitesh Jain, Shubham Maheshwari, Ning Yu +2
Riding on the success of LLMs with retrieval-augmented generation (RAG), there has been a growing interest in augmenting agent systems with external memory databases. However, the…
Slow-Fast Architecture for Video Multi-Modal Large Language Models
Min Shi, Shihao Wang, Chieh-Yun Chen +6
Balancing temporal resolution and spatial detail under limited compute budget remains a key challenge for video-based multi-modal large language models (MLLMs). Existing methods ty…
Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
Jitesh Jain, Zhengyuan Yang, Humphrey Shi +2
In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often…