Adhiraj Ghosh
@adhirajghosh.bsky.social
ELLIS PhD, University of Tübingen | Data-centric Vision and Language @bethgelab.bsky.social Website: adhirajghosh.github.io Twitter: https://x.com/adhiraj_ghosh98
Excited to be in Vienna for #ACL2025 🇦🇹!You'll find @dziadzio.bsky.social and I by our ONEBench poster, so do drop by! 🗓️Wed, July 30, 11-12:30 CET 📍Hall 4/5 I’m also excited to talk about lifelong and personalised benchmarking, data curation and vision-language in general! Let’s connect!
Why More Researchers Should be Content Creators Just trying something new! I recorded one of my recent talks, sharing what I learned from starting as a small content creator. youtu.be/0W_7tJtGcMI We all benefit when there are more content creators!
I'm in Nashville this week attending #CVPR2025. Excited to discuss post-training VLMs and diffusion models!
🏆ONEBench accepted to ACL main! ✨ Stay tuned for the official leaderboard and real-time personalised benchmarking release! If you’re attending ACL or are generally interested in the future of foundation model benchmarking, happy to talk! #ACL2025NLP #ACL2025 @aclmeeting.bsky.social
Adhiraj Ghosh@adhirajghosh.bsky.social · 2y ago🚨Looking to test your foundation model on an arbitrary and open-ended set of capabilities, not explicitly captured by static benchmarks? 🚨 Check out ✨ONEBench✨, where we show how sample-level evaluation is the solution. 🔎 arxiv.org/abs/2412.06745
🧠 Keeping LLMs factually up to date is a common motivation for knowledge editing. But what would it actually take to support this in practice at the scale and speed the real world demands? We explore this question and really push the limits of lifelong knowledge editing in the wild. 👇
Check out our newest paper! As always, it was super fun working on this with @prasannamayil.bsky.social
Prasanna Mayilvahanan@prasannamayil.bsky.social · last yr.New preprint out! 🎉 How does LLM training loss translate to downstream performance? We show that pretraining data and tokenizer shape loss-to-loss scaling, while architecture and other factors play a surprisingly minor role! brendel-group.github.io/llm-line/ 🧵1/8
🚨Great Models Think Alike and this Undermines AI Oversight🚨 New paper quantifies LM similarity (1) LLM-as-a-judge favor more similar models🤥 (2) Complementary knowledge benefits Weak-to-Strong Generalization☯️ (3) More capable models have more correlated failures 📈🙀 🧵👇
Fuck it, today we're open-sourcing the codebase used to train SmolVLM from scratch on 256 H100s 🔥 Inspired by our team's effort to open-source DeepSeek's R1, we are releasing the training and evaluation code on top of the weights 🫡 Now you can train any SmolVLM—or create your own custom VLMs!
NLI Improves Compositionality in Vision-Language Models is accepted to #ICLR2025! CECE enables interpretability and achieves significant improvements in hard compositional benchmarks without fine-tuning (e.g., Winoground, EqBen) and alignment (e.g., DrawBench, EditBench). + info: cece-vlm.github.io
📄 New Paper: "How to Merge Your Multimodal Models Over Time?" arxiv.org/abs/2412.06712 Model merging assumes all finetuned models are available at once. But what if they need to be created over time? We study Temporal Model Merging through the TIME framework to find out! 🧵
How to Merge Your Multimodal Models Over Time?
Model merging combines multiple expert models - finetuned from a base foundation model on diverse tasks and domains - into a single, more capable model. However, most existing model merging approaches...
arxiv.org
How do we benchmark the vast capabilities of foundation models? Introducing ONEBench – a unifying benchmark to test them all, led by @adhirajghosh.bsky.social and @dziadzio.bsky.social!⬇️ Sample-level benchmarks could be the new generation- reusable, recombinable & evaluate lots of capabilities!
Adhiraj Ghosh@adhirajghosh.bsky.social · 2y ago🚨Looking to test your foundation model on an arbitrary and open-ended set of capabilities, not explicitly captured by static benchmarks? 🚨 Check out ✨ONEBench✨, where we show how sample-level evaluation is the solution. 🔎 arxiv.org/abs/2412.06745
🚨Looking to test your foundation model on an arbitrary and open-ended set of capabilities, not explicitly captured by static benchmarks? 🚨 Check out ✨ONEBench✨, where we show how sample-level evaluation is the solution. 🔎 arxiv.org/abs/2412.06745
🚀New Paper: Active Data Curation Effectively Distills Multimodal Models arxiv.org/abs/2411.18674 Smol models are all the rage these days & knowledge distillation (KD) is key for model compression! We show how data curation can effectively distill to yield SoTA FLOP-efficient {C/Sig}LIPs!! 🧵👇
Excited to test it out, could be a blessing for large-scale projects!
Andi@andimara.bsky.social · 2y agoLet's go! We are releasing SmolVLM, a smol 2B VLM built for on-device inference that outperforms all models at similar GPU RAM usage and tokens throughputs. SmolVLM can be fine-tuned on a Google collab and be run on a laptop! Or process millions of documents with a consumer GPU!
I've found starter packs on NLP, vision, graphics, etc. But personally, I would love to know and hear from researchers working on vision-language. So, let me know if you'd like to join this starter pack, would be happy to add! go.bsky.app/TENRRBb
