Rick Lamers
3.9K posts
@ricklamers
👨💻 AI Researcher @NVIDIA. Ex-Groq. Occasional angel investor. Opinions are my own.
“RL directly for effective, harness harmonized, problem decomposition” may get us ridiculously good solving machines I like it
You mean the actual issue is not having AI labs in Europe? Surprising.
27x faster Attention Residuals!!! 🚀 We implemented Block AttnRes as a pip-installable package. !pip install flash-attn-res No annoying kernel nonsense. No compile/autograd plumbing. Call it like a regular PyTorch op. It just works. Methodology: 🔹 fused triton kernels 🔹 batched attention over residual blocks 🔹 online-softmax merge 🔹 flash attention-style split-KV reduction Thanks @LLMenjoyer and @cartesia for the support and guidance✌️
OpenAI’s GPT-5.5 is the second model to complete one of our multi-step cyber-attack simulations end-to-end 🧵
Mistral Medium 3.5 is out and it's a dense 128B model
1/🚀 Excited to announce Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation! We built an omni model utilizing direct patch embedding layers for raw image inputs and achieves SOTA in multimodal understanding AND generation. Paper: huggingface.co/papers/2604.24… Code: github.com/facebookresear… Thanks to all the co-authors! @__Johanan, @wmren993, @xiaoke_shawn_h, @ShoufaChen, @TianhongLi6, Mengzhao Chen, Yatai Ji, Sen He, Jonas Schult, Belinda Zeng, Tao Xiang, @WenhuChen, Ping Luo, @LukeZettlemoyer!
New work with @AlecRad and @DavidDuvenaud: Have you ever dreamed of talking to someone from the past? Introducing talkie, a 13B model trained only on pre-1931 text. Vintage models should help us to understand how LMs generalize (e.g., can we teach talkie to code?). Thread:
