Raghuveer T

It was really fun to meet new people and discuss agent environments. Thanks to the workshop organizers for putting together such a great event! Here is the slide deck from the talk: shuyanzhou.com/assets/slides/…

👋 Hello #SanDiego! We are excited to present our latest work bridging Causal Inference and GenAI at #NeurIPS2025. For tackling unobserved confounders, come visit on Dec 5, 2025 at 11 AM PST. 📍Poster 2516 Coupling Generative Modeling and an Autoencoder with the Causal Bridge🧵👇

Our entire group has come to San Diego this week and we have a series of presentations at #NeurIPS! Come find us and chat about contrastive learning and LLM agents. @bhuwandhingra @raghavlite @syz0x1 @JunlinWang3 @RoyXie_ @DCirci

📢 New preprint announcement!! - Most image encoders are trained independently before being integrated into a VLM, resulting to generic, query-agnostic image representations that constrain downstream VLM performance. - 🚀 We introduce the Text-Guided Semantic Image Encoder (TIE), which produces query/image-conditioned image representations, enabling VLMs to operate on task-relevant image features. - Across nine image-to-text benchmarks, TIE-based VLMs achieve +1.5–1.3 average improvements, with gains of up to +6 points on DocVQA and InfoVQA. - Notably, despite using only half the image tokens, and therefore offering faster inference, TIE-based VLMs outperform their standard counterparts. Paper: arxiv.org/abs/2511.20770

Excited to be in Montreal this week for COLM 2025! I have two papers accepted this year: 1️⃣ The Unlearning Mirage, a dynamic framework for evaluating LLM unlearning. 2️⃣ With @Harsh_N_Lalai10, using 20 Questions as a creative framework to systematically evaluate geographical bias in LLMs. Check out the individual threads!

Breaking the Batch Barrier (B3) was accepted as a Spotlight presentation at NeurIPS 2025. Do check it out!!

📢 New Preprint from @raghavlite on Multimodal Contrastive Learning: Breaking the Batch Barrier (B3) 📢 TL;DR: Smart batch mining based on community detection achieves state of the art on the MMEB benchmark. Preprint: arxiv.org/pdf/2505.11293 Code: github.com/raghavlite/B3

I will be presenting ✨GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings✨at #NAACL2025! We propose a simple and effective training-free inference time method to achive high quality embeddings - Beats other trainig-free methods by upto 4 points on STS benchmark. - Notable gains over training-free, unsupervised methods on the MTEB benchmark - Robust to prompt perturbations Link: arxiv.org/pdf/2410.14635 📅 4/30, Wed, 2:00-3:30 Hall 3 Happy to chat more about embeddings and my current research!

I just published Tips for Writing NLP Papers link.medium.com/uBPPpR5yiCb I wrote it for my students so I don't have to sound like a broken record (and edit papers for the same issues over and over again 😃). But some of you might find it useful too.

For very long, OntoNotes has served as the most important benchmark for coreference resolution. We are happy to present "LongtoNotes" that extends OntoNotes to up to 8X longer documents. Paper : arxiv.org/abs/2210.03650

@buzzganesh @coling2020 @mageed @laksvs Awesome. Keep rocking

Stoked to have my first acceptance during PhD at @coling2020 Automatic Detection of Machine Generated Text: A Critical Survey w @mageed, @laksvs We - survey detectors for English - categorize false +ve errors of RoBERTa (SoTA) & more - discuss future directions arXiving soon