6 papers
Incentivizing Vision Language Models to Search for Long Video Question Answering
Harsh Goel, S P Sharan, Sahil Shah +4
We introduce VSeek, an agentic framework that transforms long-video question answering (LVQA) from a passive, single-pass perception task into a multi-turn retrieval process. VSeek…
We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback
Minkyu Choi, S P Sharan, Harsh Goel +2
Current text-to-video (T2V) generation models are increasingly popular due to their ability to produce coherent videos from textual prompts. However, these models often struggle to…
Mixture-of-Experts Models in Vision: Routing, Optimization, and Generalization
Adam Rokah, Daniel Veress, Caleb Caulk +1
Mixture-of-Experts (MoE) architectures enable conditional computation by routing inputs to multiple expert subnetworks and are often motivated as a mechanism for scaling large lang…
NeuS-QA: Grounding Long-Form Video Understanding in Temporal Logic and Neuro-Symbolic Reasoning
Sahil Shah, S P Sharan, Harsh Goel +5
While vision-language models (VLMs) excel at tasks involving single images or short videos, they still struggle with Long Video Question Answering (LVQA) due to its demand for comp…
A Challenge to Build Neuro-Symbolic Video Agents
Sahil Shah, Harsh Goel, Sai Shankar Narasimhan +4
Modern video understanding systems excel at tasks such as scene classification, object detection, and short video retrieval. However, as video analysis becomes increasingly central…
Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification
S P Sharan, Minkyu Choi, Sahil Shah +3
Recent advancements in text-to-video models such as Sora, Gen-3, MovieGen, and CogVideoX are pushing the boundaries of synthetic video generation, with adoption seen in fields like…