Apratim Bhattacharyya
@apratimbh.bsky.social
ML Researcher, Qualcomm AI Research | Postdoc, University of Tübingen | PhD, Max Planck Institute for Informatics | AI Assistants, Multi-modal LLMs, Autonomous Driving
🚨Submit by 1st May @cvprconference.bsky.social: extended abstracts on streaming vision-language models, real-time activity understanding, grounding, ego-centric video understanding, language and robot learning. Contributions are encouraged to include a demo!
👉Details: varworkshop.github.io/calls/
👉Details: varworkshop.github.io/calls/
April 28, 2025 at 9:45 PM
🚨Submit by 1st May @cvprconference.bsky.social: extended abstracts on streaming vision-language models, real-time activity understanding, grounding, ego-centric video understanding, language and robot learning. Contributions are encouraged to include a demo!
👉Details: varworkshop.github.io/calls/
👉Details: varworkshop.github.io/calls/
🚨We present in "Enhancing Hallucination Detection through Noise Injection" [https://arxiv.org/pdf/2502.03799], an efficient approach to detect hallucinations in LLMs, within a Bayesian framework.
TL; DR - We use noise injection to capture both epistemic and aleatoric uncertainty!
TL; DR - We use noise injection to capture both epistemic and aleatoric uncertainty!
February 11, 2025 at 10:01 PM
🚨We present in "Enhancing Hallucination Detection through Noise Injection" [https://arxiv.org/pdf/2502.03799], an efficient approach to detect hallucinations in LLMs, within a Bayesian framework.
TL; DR - We use noise injection to capture both epistemic and aleatoric uncertainty!
TL; DR - We use noise injection to capture both epistemic and aleatoric uncertainty!
Join us at the CVPR 2025 Workshop on Vision-based Assistants in the Real-world (VAR) and tackle one of AI's biggest challenges: building systems that can comprehend and reason about dynamic, real-world scenes.
Workshop Page: varworkshop.github.io
Workshop Page: varworkshop.github.io
January 21, 2025 at 6:43 PM
Join us at the CVPR 2025 Workshop on Vision-based Assistants in the Real-world (VAR) and tackle one of AI's biggest challenges: building systems that can comprehend and reason about dynamic, real-world scenes.
Workshop Page: varworkshop.github.io
Workshop Page: varworkshop.github.io
🚨Check out our new work on distilling reasoning skills from LLMs into efficient driving policies, to deal with critical "long-tail" scenarios.
arXiv: arxiv.org/abs/2501.09757
arXiv: arxiv.org/abs/2501.09757
January 17, 2025 at 8:26 PM
🚨Check out our new work on distilling reasoning skills from LLMs into efficient driving policies, to deal with critical "long-tail" scenarios.
arXiv: arxiv.org/abs/2501.09757
arXiv: arxiv.org/abs/2501.09757