NLP Researcher Stony Brook University Views my own.
Joined April 2011
- Tweets3.5K
- Following640
- Followers1.7K
- Likes5.5K
Pinned Tweet
Interested in Autonomous coding agents? Check out AppWorld, a labor of love from @harsh3vedi et al. Provides an execution environment & a challenging benchmark for interactive coding agents on complex everyday tasks over common apps. @stonybrooknlp #ACL2024 @aclmeeting #NLProc.
🔥 Autonomous AI Assistants (e.g., #googleio2024, #WWDC24) and coding agents (e.g., #Devin, #SWEAgent) have garnered a lot of attention recently. We can envision coding agents autonomously completing complex day-to-day tasks across apps using APIs on our behalf. But how can we develop & benchmark them in a rigorous & reproducible manner?
🚀 Introducing AppWorld: 🌎a simulated world environment where agents can write code to interact with many apps via APIs on behalf of people 📊a benchmark of complex tasks defined on it, and 🧪a robust evaluation framework for assessing agent’s goal completion.
📢 To appear as an #ACL2024 paper 🌎💻🧑🤝🧑 “AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents” #NLProc #ai #AIagents
📜 arxiv.org/abs/2407.18901 (paper)
🌐 appworld.dev for code, blog, data (tasks, APIs, trajectories) explorer, interactive playground, leaderboard & more!
Niranjan retweeted
ChatGPT several times where's best to go for spring break? It recommends Barcelona almost every time.
This isn't a fluke. RL training rewards one best answer, so the model learns to commit to one mode and repeat it.
Meet Multi-Answer RL: a simple RL method that trains LMs to reason through and output a distribution of answers in a single generation. [1/N]
Niranjan retweeted
🚨New paper on AI & Copyright
👨⚖️Courts have credited LLM companies' claims that safety alignment prevents reproduction of copyrighted expression.
But what if fine-tuning on a simple writing task ruins it all?
Worse : Fine-tuning on a single author's books (e.g., Murakami) unlocks verbatim recall of copyrighted books from 30+ unrelated authors, sometimes as high as 90%.
Joint work with @niloofar_mire (@LTIatCMU), Jane Ginsburg ( @ColumbiaLaw) and my amazing PhD student @irisiris_l (@sbucompsc )
(1/n)🧵
Niranjan retweeted
Slightly late but excited to share that I defended my PhD @stonybrooknlp in Dec ’25. Grateful for my time at there, thankful to people I met along the way & extremely happy about the work I did with everyone! Excited for my next adventure as a postdoc @osunlp @hhsun1 @ysu_nlp
Niranjan retweeted
McGill University (@mcgillu) has many open faculty and postdoctoral positions with generous funding packages, thanks to Impact+ grants, which are investing $2 billion to attract global talent to Canada 🇨🇦🇨🇦🇨🇦.
Associate/Full Professor: $8 million startup package
Assistant Professor: $600K startup package
Postdoc: $70K (starting salary)
If you are interested and work in the space of AI/ML/NLP/LLMs, please reach out to me.
#AI #NLProc #ML
Niranjan retweeted
Deeply happy and honored to be elected as an ACL Fellow -- and to be a part of the respected cohort of this+past years' fellows (congrats everyone)! 🙏
All the credit (and sincere gratitude) to all my amazing students, postdocs, collaborators, mentors, and family! 🤗💙
Niranjan retweeted
@nikita_soni_ and co are organizing a great shared task at SemEval 2026. Make sure to submit your systems!
@SemEvalWorkshop 2026 Task2 Live!! Go participate #NLProc @aclmeeting
Build personalized, ecologically valid, emotionally intelligent systems! Rare opportunity to study lived emotions via self-reported & longitudinal experiences
Evaluation begins Jan 10
tinyurl.com/semeval26task2
Niranjan retweeted
@SemEvalWorkshop 2026 Task2 Live!! Go participate #NLProc @aclmeeting
Build personalized, ecologically valid, emotionally intelligent systems! Rare opportunity to study lived emotions via self-reported & longitudinal experiences
Evaluation begins Jan 10
tinyurl.com/semeval26task2
Niranjan retweeted
1/ Hiring PhD students at CMU SCS (LTI/MLD) for Fall 2026 (Deadline 12/10) 🎓
I work on open, reliable LMs: augmented LMs & agents (RAG, tool use, deep research), safety (hallucinations, copyright), and AI for science, code & multilinguality & open to bold new ideas!
FAQ in 🧵
Niranjan retweeted
Announcing 63 #AmazonResearchAwards recipients from 41 universities in 8 countries across 5 research areas. Awardees have access to 700+ Amazon public datasets and can utilize AWS AI/ML services and tools through AWS Promotional Credits. amazon.science/research-area…
Niranjan retweeted
I am recruiting students at TTIC! Apply by Dec 9
Pursue a fully-funded and personalized PhD in #computerscience with world-class faculty as mentors, a 4:1 student-to-faculty ratio, and in the vibrant city of Chicago. Learn more and apply by Dec. 9 (NO FEE): buff.ly/Qw8njWB
If you are interested in SLM based multi-agent systems check this paper led by @bsbijoy2050. This @aaclmeeting paper shows how you can train efficient and effective SLM based small agents on the AppWorld benchmark. Work supported by a @SUNY-@IBM collaboration grant.
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more
It was a joy to have been part of your journey @harsh3vedi. Learnt so much from you and through your projects. Looking forward to seeing the next phase in your journey.
🚨 Late Life update
🎓 I defended my thesis (AppWorld, IRCoT, MuSiQue, DiRe, TeaBReaC) & joined @allen_ai as a research scientist earlier this year
🙏 Deeply grateful to my awesome advisor @b_niranjan mentors @tusharkhot @Ashish_S_AI, committee members @HAndySchwartz @OwenRambow @sameer_, many collaborators, @stonybrooknlp labmates, friends & family
🤝If you want to collaborate, DMs are open! I’m interested in (tool-use, coding, web) agents and environments
🌎 We've many exciting releases on the AppWorld front coming up. Stay tuned! Or DM if you can help! 🙂
Niranjan retweeted
🚨 Late Life update
🎓 I defended my thesis (AppWorld, IRCoT, MuSiQue, DiRe, TeaBReaC) & joined @allen_ai as a research scientist earlier this year
🙏 Deeply grateful to my awesome advisor @b_niranjan mentors @tusharkhot @Ashish_S_AI, committee members @HAndySchwartz @OwenRambow @sameer_, many collaborators, @stonybrooknlp labmates, friends & family
🤝If you want to collaborate, DMs are open! I’m interested in (tool-use, coding, web) agents and environments
🌎 We've many exciting releases on the AppWorld front coming up. Stay tuned! Or DM if you can help! 🙂
Thanks @gregd_nlp for visiting @sbucompsc and the broader NLP and AI group here. And welcome to right coast :-).
Niranjan retweeted
Excited to share that QUDsim has been accepted to #COLM2025!! 🎉🎉
Niranjan retweeted
🚨 New paper alert! 🚨
📢 Announcing MuSciClaims, a multimodal claim verification benchmark for heterogeneous, information-rich scientific figures. Such verification is crucial for evaluating scientific hypotheses & ensuring trust and reproducibility in results. 1/6 #NLProc
Niranjan retweeted
Paper: arxiv.org/abs/2506.04585
I'm excited to explore multimodal reasoning in scientific domains that require deep expertise and hyper specialization.
Many thanks to my wonderful collaborators on this paper @bandhammanikant @msaquibhasan @apoorva_kashi @MKoupaee @b_niranjan 6/6
