Ramraj Chandradevan (@cramraj8) 's Twitter Profile
Ramraj Chandradevan

@cramraj8

CS PhD student @ Emory University

ID: 98379596

calendar_today21-12-2009 13:35:19

29 Tweet

153 Followers

1,1K Following

SystemsNerd (@__vishwanath__) 's Twitter Profile Photo

link.springer.com/article/10.100… My undergrad research work is finally online! We optimized pattern storage and recall of auto-associative networks with the help of Dentate Gyrus! #research #neuro

SystemsNerd (@__vishwanath__) 's Twitter Profile Photo

🚨Attn Everyone🚨 My collaborators and I have been working on a project whose main aim is to identify the design principles behind #microservices. We would like to invite participants who have experience in working with microservices. #AcademicTwitter

Eugene Yang (@eyangtw) 's Twitter Profile Photo

Happy to share that our paper entitled "C3: Continued Pretraining with Contrastive Weak Supervision for Cross-Language Ad-Hoc Retrieval" (w/ Suraj Nair Ramraj Chandradevan Rebecca Iglesias-Flores and Doug Oard) at SIGIR 2025! Preprint coming shortly :)

Eugene Yang (@eyangtw) 's Twitter Profile Photo

On Tuesday 3:30-5:00pm, I will be presenting a poster of "C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrieval" that I collaborated with Suraj Nair Ramraj Chandradevan Rebecca Iglesias-Flores and Doug Oard arxiv.org/abs/2204.11989

Eugene Yang (@eyangtw) 's Twitter Profile Photo

And in the same session, my collaborator Ramraj Chandradevan will present "Learning to Enrich Query Representation with Pseudo-Relevance Feedback for Cross-lingual Retrieval"!

Kaustubh Dholé (@kaustubhdhole) 's Twitter Profile Photo

Happy to share our Gradio based query gen. & retrieval interface (initially designed for IARPA BETTER) & generalized to explore E2E query generation & support HITL & IR annotations-Fire it up with this Colab & use it for your own retrieval tasks! github.com/emory-irlab/qu… 1/n

Sumit (@_reachsumit) 's Twitter Profile Photo

DUQGen: Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation Generates synthetic training data by clustering target documents, probabilistically sampling clusters and using LMs to produce diverse queries 📝arxiv.org/abs/2404.02489

DUQGen: Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation

Generates synthetic training data by clustering target documents, probabilistically sampling clusters and using LMs to produce diverse queries

📝arxiv.org/abs/2404.02489
Jathushan Rajasegaran (@brjathu) 's Twitter Profile Photo

An Empirical Study of Autoregressive Pre-training from Videos. paper: arxiv.org/pdf/2501.05453 website: brjathu.github.io/toto We empirically study autoregressive pre-training from videos. Our models are pre-trained on a diverse dataset of videos and images comprising over 1

An Empirical Study of Autoregressive Pre-training from Videos.

paper: arxiv.org/pdf/2501.05453
website: brjathu.github.io/toto

We empirically study autoregressive pre-training from videos. Our models are pre-trained on a diverse dataset of videos and images comprising over  1