Sidak Pal Singh
51 posts
@unregularized
Research Scientist at Google DeepMind, working on Gemini. (prev. PhD at ETH Zürich & MPI-IS Tübingen.) No second-hand opinions. They are absolutely my own ;)
This is Gemini 3: our most intelligent model that helps you learn, build and plan anything. It comes with state-of-the-art reasoning capabilities, world-leading multimodal understanding, and enables new agentic coding experiences. 🧵
A few numbers from my PhD: 8 first-author top-conference (CVPR/ICCV/ECCV) papers 100% acceptance rate per paper 80% acceptance rate per submission 1 invited long talk at CVPR tutorial 5 top-conf demos (acceptance rate 100% vs ~30% average) ~2k GitHub stars
1/ 🚨 New paper alert! 🚨 We explore a key question in deep learning: Can independently trained Transformers be linearly connected in weight space — without a loss barrier? Yes — if you uncover their rich symmetries. 📄 arXiv: arxiv.org/abs/2506.22712
Ever wondered how the optimization trajectories are like when training neural nets & LLMs🤔? Do they contain a lot of twists 💃 and turns, or does the direction largely remain the same🛣️? We explore this in our work for LLMs (upto 12B params) + ResNets on ImageNet. Key findings👇
Ever wondered how the loss landscape of Transformers differs from that of other architectures? Or which Transformer components make its loss landscape unique? With @unregularized & @f_dangel, we explore this via the Hessian in our #ICLR2025 spotlight paper! Key insights👇 1/8
🚀 Introducing NSA: A Hardware-Aligned and Natively Trainable Sparse Attention mechanism for ultra-fast long-context training & inference! Core components of NSA: • Dynamic hierarchical sparse strategy • Coarse-grained token compression • Fine-grained token selection 💡 With optimized design for modern hardware, NSA speeds up inference while reducing pre-training costs—without compromising performance. It matches or outperforms Full Attention models on general benchmarks, long-context tasks, and instruction-based reasoning. 📖 For more details, check out our paper here: arxiv.org/abs/2502.11089
@kellerjordan0 Yes, but with your older code (with warmup and w/o scaling by number of elements). Also this could be seed dependent, etc. Take it with very huge grain of salt.
Source: papercopilot.com/paper-list/neu…
Review requirements! (And 10pg limit!)
