Vibhor Agarwal

Ecstatic to share that our 2 full papers have been accepted at @TheWebConf 2022! Thanks to my supervisor @nishanthsastry for the guidance! Looking forward to do better work!😀 Paper details in separate tweets. #TheWebConf #WWW2022 #NLP

🚨Our paper on understanding Tracking, Profiling, and Personalization in Generative AI Assistants has been accepted @USENIXSecurity '25! (w/ @pcallejop, @ammandalari, @zubair_shafiq) Preprint: arxiv.org/pdf/2503.16586… Checkout the thread for more details! #usenix #GenAI

Hiring Lecturer in NLP: jobs.surrey.ac.uk/vacancy.aspx?r…. Lectureship position aligned with Nature Inspired Computing and Engineering (NICE) research group (lnkd.in/ew6xpiJm) within the CS. Happy to be contacted for discussing our research/strengths. #nlproc

🎉After much anticipation, I’m thrilled to share that I’m starting a new chapter as Research Scientist at @BellLabs in Cambridge! 🚀 I'll be working on NLP + Responsible AI research @soc_dynamics with @danielequercia. #newyear #newbeginnings

If you’re interested in Responsible AI research, apply for this summer internship at Bell Labs in the vibrant city of Cambridge!

2024 has been incredible: 15+ publications, and exciting progress in #ResponsibleAI 🎉 Check out our yearly newsletter for all the highlights and what’s next for 2025 social-dynamics.net/newsletter/202…

Recently, I completed a milestone of 100 citations on Google scholar! 😀 I know it's not a lot but it is a reminder to myself that it's just the beginning and I should keep working hard for impactful research. Have a look at my papers here: scholar.google.com/citations?user…

📢Paper accepted at @ACM_IMC_2024 How do Smart TVs profile viewing activity of its users? We look at the tracking conducted directly by the Smart TV platforms via ACR to understand privacy implications in UK vs US. @giaanselmi, @Homiefe, @pcallejop, @ammandalari, @zubair_shafiq

🚀 Excited to introduce MMSoc, our #ACL2024 benchmark for evaluating Multimodal Large Language Models (MLLMs) in social media analysis! 🌐 🔗 Paper: arxiv.org/abs/2402.14154 🤗 Benchmark: huggingface.co/collections/Ah…

With everyone using LLMs to generate code, papers like this one are needed to study the impact of hallucinations. Makes me wonder if "hallucination removal" will be a code maintenance issue down the road. @vibhoragarwall, Pei, Alamir, @xiaomoliu arxiv.org/abs/2408.08333

🤔Do you know LLMs can hallucinate even during code generation? Excited to present our research "CodeMirage: Hallucinations in Code Generated by LLMs" presented at AutoMates @IJCAIconf 2024. Paper: arxiv.org/pdf/2408.08333 #LLM #hallucination #codegeneration #ai #research #safety