7 citations · 9 across the 7 of their papers we have counts for
8 papers
Rubric Rewards from Item Response Theory
Milad Yazdani, Yaser Souri, Xiren Zhou +4
Many language tasks have no single answer that can be checked automatically. Rubrics provide criteria for judging responses to these tasks. For reinforcement learning, the resultin…
ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction
Amirhossein Abaskohi, Yuhang He, Peter West +3
Computer-use agents (CUAs) rely on visual observations of graphical user interfaces, where each screenshot is encoded into a large number of visual tokens. As interaction trajector…
OS-Marathon: Benchmarking Computer-Use Agents on Vast-Horizon, Repetitive Tasks
Jing Wu, Wenjie Ai, Daphne Barretto +7
Vast-horizon, repetitive workflows are common in daily routines, e.g., processing expense reports from a stack of receipts, organising a collection of PDF annotations into structur…
WebSTAR: Scalable Data Synthesis for Computer Use Agents with Step-Level Filtering
Yifei He, Pranit Chawla, Yaser Souri +2
Computer use agents (CUAs) can operate real-world digital interfaces but remain difficult to train due to the high cost of graphical user interface (GUI) interaction and the scarci…
Turn Down the Noise: Leveraging Diffusion Models for Test-time Adaptation via Pseudo-label Ensembling
Mrigank Raman, Rohan Shah, Akash Kannan +1
The goal of test-time adaptation is to adapt a source-pretrained model to a continuously changing target domain without relying on any source data. Typically, this is either done b…
Bridging the Gap: Exploring the Capabilities of Bridge-Architectures for Complex Visual Reasoning Tasks
Kousik Rajesh, Mrigank Raman, Mohammed Asad Karim +1
In recent times there has been a surge of multi-modal architectures based on Large Language Models, which leverage the zero shot generation capabilities of LLMs and project image e…
HateProof: Are Hateful Meme Detection Systems really Robust?
Piush Aggarwal, Pranit Chawla, Mithun Das +4
Exploiting social media to spread hate has tremendously increased over the years. Lately, multi-modal hateful content such as memes has drawn relatively more traction than uni-moda…
SAC: Semantic Attention Composition for Text-Conditioned Image Retrieval
Surgan Jandial, Pinkesh Badjatiya, Pranit Chawla +3
The ability to efficiently search for images is essential for improving the user experiences across various products. Incorporating user feedback, via multi-modal inputs, to naviga…