Llama-3.1-8B-Base
PulseAugur coverage of Llama-3.1-8B-Base — every cluster mentioning Llama-3.1-8B-Base across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New platform DataFlex-RL finds no consistent gains from RLVR data policies
Researchers have developed DataFlex-RL, a new platform designed to evaluate data policies for reinforcement learning with verifiable rewards (RLVR). Initial experiments using Qwen2.5-7B-Base across 12 benchmarks showed …
-
DataFlex-RL finds uniform sampling matches adaptive policies in RLVR
A new evaluation platform called DataFlex-RL has been developed to assess data policies for reinforcement learning with verifiable rewards (RLVR). Research using this platform indicates that simple uniform sampling of t…
-
New K-12 knowledge graph benchmarks LLM curriculum cognition
Researchers have developed K12-KGraph, a novel knowledge graph designed to evaluate and train large language models (LLMs) specifically for K-12 education. This graph, derived from official textbooks, captures curriculu…