Excited to share that our work, #MonteCLoRA, has officially been merged into the #HuggingFace PEFT library! π₯³ https://t.co/1411PsNGwc
Build #peft from source to use it right away! π
π Paper: https://t.co/vPAvMvYsrb
π€ Docs: https://t.co/fHtm0NW4BM
π§π· #LCS2 goes to #Rio π§π· Presenting our paper where we move beyond memoryless personalization β modeling user preferences as action-conditioned geometric walks with memory for better, user-aligned summaries. See you at #Riocentro π #Personalization#RepresentationLearning
Happy to announce that our paper has been accepted to #ICLR2026! π
π Beyond Markovian Drifts: Action-Biased Geometric Walks with Memory for Personalized Summarization
π₯ Parthiv Chatterjee, Asish Batha, Tashvi Patel, @sourish_rygbee, @Tanmoy_Chak
Congratulations to all authors!
π Paper: https://t.co/AJKJ8G1Fp6
β¨Current multimodal LLMs donβt truly see math diagrams -- they approximate. We introduce SpatialMath, which bridges perception and reasoning, enabling more reliable visual mathematical problem-solving.
π #EACL2026 Sneak Peak Alert π
We're excited to share a paper that we are presenting at #EACL2026 in #Morocco!
π Can LLMs Reason over Extended Multilingual Contexts? Towards Long-Context Evaluation Beyond Retrieval over Haystacks
π₯ @AmeyHengle@prasNLP Soham Dan @Tanmoy_Chak
π Key Findings:
- Reasoning fails before retrieval
- Multilingual gap is real
- Effective context <30%: LLMs utilize only a fraction of their claimed context window
- RAG helps, but not enough
- Uncertainty reasoning is hardest
π’ New Media Feature π’ We are pleased to share that Prof. Tanmoy Chakraborty @Tanmoy_Chak was recently invited to Insight, a program on @sansad_tv, to speak on the growing challenges posed by #AIGenerated synthetic content.
#ResponsibleAI#PublicPolicy
https://t.co/ckn8kjp6XM
π New Podcast Alert ποΈ
Prof. Tanmoy Chakraborty @Tanmoy_Chak joins Rudraditya on The Inner Circle With Rudraditya podcast for a sharp, no-hype conversation on the realities, risks, and future of AI. #AI#MachineLearning#SLM#AIGovernance#NLProc
https://t.co/KSUw5bYoge
β¨ Huge thanks to all collaborators and participants whose lived experiences shaped this work. We hope this contributes toward accessible, scalable, and culturally resonant digital mental health solutions, especially in low-resource settings.
π New Paper Alert π We're excited to share that our paper "Here for You: A Co-Designed Mental Health Screening App for Indian University Students " has been accepted for publication in #JMIR#FormativeResearch! π @Tanmoy_Chak
https://t.co/dHmRGDTdsJ
π Key Highlights (contd.)
- Ethical and regulatory alignment, including adherence to DPDP guidelines
- Demonstrates the power of the βnothing about us without usβ principle in digital mental health
Happy to announce that our paper has been accepted to #ICLR2026! π
π Beyond Markovian Drifts: Action-Biased Geometric Walks with Memory for Personalized Summarization
π₯ Parthiv Chatterjee, Asish Batha, Tashvi Patel, @sourish_rygbee, @Tanmoy_Chak
Congratulations to all authors!
π€ Keynote | Singapore Symposium on NLP #SSNLP @ #AAAI2026
π¨οΈ Enough of Scaling Laws! Let's Focus on Downscaling
π€ @Tanmoy_Chak
π A call to rethink scale focusing on efficient, interpretable, and adaptable #SmallLanguageModels that rival large models without prohibitive costs.
#LCS2 is ready for #AAAI2026 πΈπ¬ π¦
We are excited to be in Singapore this week to share our latest work across quantum-inspired NLP, brain-aligned AI, and efficient language models. If you're around #AAAI2026 or #SSNLP2026, drop by and say hello! #NLProc#AIResearch@Tanmoy_Chak
π Tutorial | #AAAI2026
π§βπ» Brain-Inspired AI 2.0: Aligning Language Models Across Languages and Modalities
π₯ Subba Reddy Oota, @Tanmoy_Chak, @ManishGuptaMG1, Raju S. Bapi
π§ Exploring the intersection of computational cognitive neuroscience and AI. #BrainInspiredAI#CognitiveAI