Organization card: lab description from futuremls.org

README.md

@@ -8,19 +8,17 @@ pinned: false
 
 # FutureMLS Lab
 
-## Models
+The **Future Machine Learning & Systems Lab** is a nonprofit research lab working where machine learning meets computer systems. Foundation models are remarkably capable but costly to train and serve. Our mission is to close the gap between model capability and the real-world cost of deploying it.
 
-| Model | Base model | Format | Size |
-|---|---|---|---:|
-| [flint-nvfp4-coldgptq](https://huggingface.co/FutureMLS-Lab/flint-nvfp4-coldgptq) | [RecursiveSI/flint](https://huggingface.co/RecursiveSI/flint) | NVFP4 (W4A4) routed experts, BF16 elsewhere | 23.5 GB (BF16: 79.6 GB) |
+We pursue algorithm–system co-design in four connected directions:
 
-### flint-nvfp4-coldgptq
+- **Efficient ML architecture**: speculator and attention design
+- **Efficient post-training**: loss design, reinforcement learning and quantization
+- **Efficient post-training engines**: post-training and inference systems
+- **Agents**: coding agents and AI for science
 
-B300, SGLang 0.5.16 with `flint_sglang` 0.1.4, the model's default sampling. Generation length counts completion tokens,
-reasoning included.
+Our work spans methods, models, kernels, runtimes and serving systems. It is open source, reproducible and built to be used.
 
-| Benchmark | Accuracy, BF16 → NVFP4 | Generation length p50 / p90 (tokens), BF16 → NVFP4 |
-|---|---:|---:|
-| GSM8K, 1,319 questions | 96.1 → 96.0 | 451 / 2,796 → 459 / 3,004 |
-| GPQA Diamond, 198 questions × 3 samples | 69.2 → 68.9 | 6,718 / 30,918 → 7,440 / 30,553 |
-| AIME 2026, 30 problems × 16 samples | 84.4 → 83.8 | 7,927 / 32,768 → 8,294 / 32,768 |
+**Selected projects:** [OSCAR](https://futuremls.org/projects/oscar.html), 2-bit KV-cache quantization (NeurIPS 2026) · [CARE](https://futuremls.org/projects/care.html), covariance-aware conversion to Multi-Head Latent Attention (ICLR 2026) · [Taylor-Calibrate](https://futuremls.org/projects/taylor-calibrate.html), hybrid linear-attention distillation
+
+Founder & PI: [Zhongzhu (Charlie) Zhou](https://zhongzhuzhou.org/) · [Website](https://futuremls.org/) · [GitHub](https://github.com/FutureMLS-Lab) · [zhongzhu@futuremls.org](mailto:zhongzhu@futuremls.org)