8 papers
Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models
Pardis Taghavi, Reza Langari, Gaurav Pandey
Training-free block-sparse attention can accelerate video transformers, but row-wise attention concentration does not by itself specify an executable sparse operator. Queries shari…
From Numbers to Judgment: Specialist LLM Agents and Reinforcement Learning for European Listed Real Estate
Pardis Taghavi, Santosh Bhavani
We study whether the localized numerical operations and integrative judgments of financial analysis benefit from the same form of LLM specialization. Larix maps a 16-lens European…
MODEST: Multi-Optics Depth-of-Field Stereo Dataset
Nisarg K. Trivedi, Vinayak A. Belludi, Vinayaka A. Belludi +1
Training and evaluation of state-of-the-art computer vision algorithms for reliable shallow depth of field (DoF) rendering and defocus deblurring remain constrained by a persistent…
Spec Kit Agents: Context-Grounded Agentic Workflows
Pardis Taghavi, Santosh Bhavani
Spec-driven development (SDD) with AI coding agents provides a structured workflow, but agents often remain "context blind" in large, evolving repositories, leading to hallucinated…
Training a Student Expert via Semi-Supervised Foundation Model Distillation
Pardis Taghavi, Tian Liu, Renjie Li +2
Foundation models deliver strong perception but are often too computationally heavy to deploy, and adapting them typically requires costly annotations. We introduce a semi-supervis…
The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics
Xiangbo Gao, Mingyang Wu, Siyuan Yang +4
While recent generative video models have achieved remarkable visual realism and are being explored as world models, true physical simulation requires mastering both space and time…