Aniket Rege
@wregss
PhD-ing @WisconsinCS and @AIatMeta | MS at @uwcse/@RAIVNLab | Ex @nvidiaai and @samsungresearch. He/Him
With all the recent hype around 🪆Matryoshka Representation Learning 🪆(Thanks @OpenAI !), I finally put my longstanding plan of writing a detailed blog about MRL to action aniketrege.github.io/blog/2024/mrl/ This blog is NOT a paper walkthrough (see @RitvikRastogi19 for that!) (1/7)
Culturally representative text to image models are surfing in to #iccv2025 🌊🏖️☀️ see you all in Hawaii!!
Training text-to-image models? Want your models to represent cultures across the globe but don't know how to systematically evaluate them? Introducing ⚕️CuRe⚕️ a new benchmark and scoring suite for cultural representativeness through the lens of information gain (1/10)
LLaVA-Prumerge, the first work of Visual Token Reduction for MLLM, finally got accepted after being cited 146 times since last year. Congrats to the team! @yuzhang_shang @yong_jae_lee See how to do MLLM inference much cheaper while holding performance. llava-prumerge.github.io
visual tokens in current large multimodal models are spatially redundant, indicated by the sparse attention maps. LLaVA-PruMerge proposes to first prune and then merge visual tokens, which can compress the visual tokens by 18 times (14 times on MME/TextVQA) on average while…
Had a fantastic time at #CVPR2025 and my spotlight talk on culturally representative T2I models at the DemoDiv workshop was definitely the highlight Thanks @polkirichenko and all the organizers, attendees and panelists for a super engaging & thought provoking workshop!
🚨 I'll be giving a short contributed talk about CuRe at CVPR 's DemoDiv workshop today (06/11) at 10 AM! Please drop by, I'd love to chat 😁 x.com/polkirichenko/…
did a (big) thing 🙃 still going to be running my brand practice, but now outta london! looking to take on projects in jun/jul (+ beyond), so if there's founders, investors, tech ppl u know and would like to connect me with, that'd be v kind <3 work at snehasanks.com
Check out this cool work from our lab!
🚨Our new paper: VisualToolAgent (VisTA) 🚨 Visual agents learn to use tools—no prompts or supervision! ✅RL via GRPO ✅Decoupled agent/reasoner (e.g. GPT-4o) ✅Strong OoD generalization 📊ChartQA, Geometry3K, BlindTest, MathVerse 🔗oodbag.github.io/vista_web/ 🧵👇
Stop by CVPR poster #330 in Hall D for a chat about heterogenous and culturally representative generative models!
Training text-to-image models? Want your models to represent cultures across the globe but don't know how to systematically evaluate them? Introducing ⚕️CuRe⚕️ a new benchmark and scoring suite for cultural representativeness through the lens of information gain (1/10)
Started from: seeing saturating retrieval accuracy curves with increasing embedding size on ImageNet after training a *single* ResNet-50 Now we here: "MRL Support" as a column in state-of-the-art embedding models 🥹🪆
🚀 Proud to introduce the Qwen3-Embedding and Qwen3-Reranker Series – setting new standards in multilingual text embedding and relevance ranking! ✨ Highlights: ✅ Available in 0.6B / 4B / 8B versions ✅ Supports 119 languages ✅ State-of-the-Art performance on MMTEB , MTEB ,…
Matryoshka-powered elasticity for the win! 🪆🚀 Excited to try Gemma 3n on my next smart fridge 🤓
Pocket powerhouse admist I/O awesomeness! Gemma 3n E4B & E2B are insane models, optimized for on-device while rivaling frontier models. It's a 🪆Matryoshka Transformer (MatFormer)🪆: Natively elastic b/w 4B & 2B pareto-optimally! ⭐️: free models with ZERO training cost! 🧵👇
Pocket powerhouse admist I/O awesomeness! Gemma 3n E4B & E2B are insane models, optimized for on-device while rivaling frontier models. It's a 🪆Matryoshka Transformer (MatFormer)🪆: Natively elastic b/w 4B & 2B pareto-optimally! ⭐️: free models with ZERO training cost! 🧵👇