Raghuveer T (@raghavlite) profile picture

PhD Student at Duke University; Intern at @Meta FAIR.

India
Joined December 2014
Photo by Raghuveer T (@raghavlite)
Raghuveer T retweeted
Muse Spark 1.3 is rolling out today with frontier performance almost too cheap to meter. This is the biggest jump we've made so far on coding and agentic work. Try it in Muse Code and our API. Next up 🍉 and Muse Spark open weights releases coming soon.
1,437
1,594
1,228
19,829
3,812,489
Raghuveer T retweeted
Happy to share that I have been selected as a Cosmos grantee for 2026 under the theme of Human Autonomy! @danish037 and I will be working on building an open-source AI detector. Thanks to @cosmos_inst for the support!
9
5
1
60
3,874
New preprint from @ghazalkhn and @raghavlite! The dominant paradigm for multimodal document retrieval has been to represent pdf pages as image inputs to a VLM. We show that this approach is suboptimal for text-rich scientific documents. With the same VLM, keeping text as tokens and interleaving with figure images leads to better performance than page-level images -- despite not being trained on such sequences! Text embeddings alone also handle figure-based queries quite well -- by using captions and in-text references. Overall, text-based embeddings are still quite effective for multimodal retrieval! Lots more interesting findings in the paper: arxiv.org/pdf/2604.18508
4
1
16
3,034
Raghuveer T retweeted
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…
Invited Talk 6 "Towards Future-proof Benchmarks for Digital Agents" from Shuyan Zhou @syz0x1 (Duke University)
3
9
61
7,276
👋 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🧵👇
1
1
2
115
Raghuveer T retweeted
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
10
1
24
4,321
📢 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
5
1
19
1,789
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!
16
1
35
4,373
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
2
7
985
📢 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
2
4
4
18
6,010
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!
1
1
12
478
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.
24
225
12
963
101,512
Raghuveer T retweeted
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
1
7
3
69