Shafiq (raihanjoty.github.io) directs the NLP group's work on large language modeling (LLM) and generative AI. Some of his group's recent projects include SFR-RAG, SFR-Judge, SFR-RAG-Agent and xGen. He is also a tenured Associate Professor (currently on leave) in the School of Computer Science and Engineering (SCSE) at NTU. He was a founding manager of the Salesforce Research Asia (Singapore) lab. His research contributed to 35+ patents and more than 170+ papers in top-tier NLP and ML conferences and journals. He severed as a PC chair of SIGDIAL-2023, best paper award committee of ICLR-23, NAACL-22 and a (senior) area chair for all the NLP and ML conferences.
Post-training methods (RLVR, On-policy distillation) are Episode-local Language models are getting better at learning from feedback during post-training. In reinforcement learning with verifiable rewards (RLVR), a model tries a problem, a verifier checks…
What if launching an RL training run felt less like operating a GPU cluster and more like talking to a sharp research engineer in Slack? Training AI models is still strangely artisanal, involving…
Introduction Reinforcement Learning from Human or AI Feedback (RLHF, RLAIF) has become the standard recipe for aligning large language models (LLMs). But as we push into the agentic era — where models call…
VIBEPASS, a new benchmark, reveals a fundamental weakness in modern AI coding assistants: even with near-perfect scores on code generation tasks, frontier models falter when it comes to finding and fixing subtle bugs…
AI agents that rely on web search are vulnerable to “well poisoning” attacks, where adversaries publish fabricated but authoritative-sounding content designed to be retrieved during search. Think “AI Slop” for agents. Our research…
