-
Scaling test-time compute
📈602Boost LLM answers with flexible test‑time search strategies
-
FineWeb: decanting the web for the finest text data at scale
🍷1.45kExplore and download the FineWeb web‑scale text dataset
-
The Ultra-Scale Playbook
🌌4.05kThe ultimate guide to training LLM on large GPU Clusters
-
FineVision: Open Data is All You Need
📝236A new open-source dataset for training VLMs
ldwang
ldwang
AI & ML interests
LLM, MLLM, Infra
Recent Activity
upvoted a paper 25 minutes ago
MotionVLA: Vision-Language-Action Model for Humanoid Motion upvoted a paper 25 minutes ago
MassAlloc Attention: Let Attention Allocate Its Own Compute upvoted a paper 26 minutes ago
CoWindow Attention: Full Causal Coverage Is a Collective PropertyOrganizations
-
Scaling test-time compute
📈602Boost LLM answers with flexible test‑time search strategies
-
FineWeb: decanting the web for the finest text data at scale
🍷1.45kExplore and download the FineWeb web‑scale text dataset
-
The Ultra-Scale Playbook
🌌4.05kThe ultimate guide to training LLM on large GPU Clusters
-
FineVision: Open Data is All You Need
📝236A new open-source dataset for training VLMs
Misc tools for llm & vlm.