5 papers
STRIVE: Structured Spatiotemporal Exploration for Reinforcement Learning in Video Question Answering
Emad Bahrami, Olga Zatsarynna, Parth Pathak +3
We introduce STRIVE (SpatioTemporal Reinforcement with Importance-aware Variant Exploration), a structured reinforcement learning framework for video question answering. While grou…
Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices
Saeid Ghafouri, Mohsen Fayyaz, Xiangchen Li +4
Real-time multi-label video classification on embedded devices is constrained by limited compute and energy budgets. Yet, video streams exhibit structural properties such as label…
DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding
Tanveer Hannan, Dimitrios Mallios, Parth Pathak +5
Large Vision-Language Models (LVLMs) have demonstrated strong multimodal reasoning capabilities on long and complex documents. However, their high memory footprint makes them impra…
Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders
Ali Rasekh, Erfan Bagheri Soula, Omid Daliran +2
Despite significant advances in Multimodal Large Language Models (MLLMs), understanding complex temporal dynamics in videos remains a major challenge. Our experiments show that cur…
DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights
Liana Mikaelyan, Ayyoob Imani, Mathew Salvaris +2
We introduce DeltaLLM, a new post-training compression technique to reduce the memory footprint of LLMs. We propose an alternative way of structuring LLMs with weight sharing betwe…