-
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Paper • 2602.10693 • Published • 216 -
Flash-KMeans: Fast and Memory-Efficient Exact K-Means
Paper • 2603.09229 • Published • 61 -
DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
Paper • 2603.11076 • Published • 4
Akki
hc99
AI & ML interests
None yet
Recent Activity
updated
a collection
about 1 hour ago
to read updated
a collection
1 day ago
to read upvoted an article 18 days ago
GGML and llama.cpp join HF to ensure the long-term progress of Local AI Organizations
