Today at @iclr-conf.bsky.social, come chat with @changho.bsky.social about what types of data drive weak-to-strong generalization!

Tons of model weights available, but what else can we do besides prediction? 🤔 Introducing Grad-Mimic! A new data selection framework using well-trained model’s weights to find high-value samples for foundation models. Boost data curation & data efficiency!

First up at #NeurIPS2024 from our group, our work on labeling via programmatic distillation (a spotlight!). Label your data orders of magnitude faster and cheaper — come join us today at Poster Session 2 East for a demo!

💥💥 Just touched down in Vancouver for #NeurIPS2024! 🇨🇦 I'll be here till Dec 14, to present two papers SpatialEval and GAD (details in thread🧵), happy to chat about agentic framework and reasoning for LLMs and multimodal LLMs (DM is open)! 🤝

Ever wondered if constrained decoding changes how LLMs actually behave? We proved it does - and came up with a new solution to fix the distribution distortion problem.
🤝 Stop by our poster this Thursday (Dec 12) or just DM us!
⏰ 11AM - 2PM PST
📍 East Exhibit Hall A-C #4911
neurips.cc/virtual/2024...