6 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…
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…
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…
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…
Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encoding
Niloofar Azizi, Mohsen Fayyaz, Horst Bischof
Understanding human behavior fundamentally relies on accurate 3D human pose estimation. Graph Convolutional Networks (GCNs) have recently shown promising advancements, delivering s…