Author

Ankan Deria

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

WorldGuide: Goal-Directed Video World Model for Procedural Task Execution

Video generators and video-based world models can synthesize plausible visual trajectories, but long-horizon procedural tasks require generation to adapt to what has actually been produced. A model must determine the next action from its generated state, execute that action, and recognize when the task is complete. Ope...

Ankan Deria, Komal Kumar, Hisham Cholakkal et al. · 0 citations

Preprint Aug 2026

Training-Free Speech-Centric Omni Understanding with Frozen VLMs

Training-Free Omni is introduced, a plug-and-play framework that converts a frozen VLM into a speech-centric omni model without architectural modification, or multimodal re-alignment, and shows that strong speech-centric omni understanding can often be obtained through modular audio-to-language routing rather than cost...

Ankan Deria, H. Rasheed, Xi-Lin He et al. · 0 citations