AI Research / Writing Evaluation / RLHF
Meta AI research on RL-XAR, a method for training language models toward expert-level writing using expert-aligned rubrics and reinforcement learning. The page explains the problem, the rubric-learning loop, and experiments on paper sections, story writing, and Wikipedia-style text.
This is a substantive AI research page with a clear technical contribution, concrete method description, and multiple visible experiment sections. It is directly relevant to AI builders working on evaluation, reward design, and writing models, and there is enough evidence here for a useful directory listing.
The crawl shows the paper narrative and results overview, but not a full implementation, code release, benchmark table, or reproducible setup details. From this page alone, a visitor cannot tell whether there is public code, model access, or a downloadable paper/poster.
Last evaluated 17 days ago. Current rank #1942. Up 2 spots in the rankings.
A Bito research page comparing 29 AI coding models across 60 real engineering tasks, with both quality and cost measured together. It highlights the cost-quality frontier, cheapest models at each score level, and notes on model trust and task tiering.
An autonomous research system that runs on a single workstation and aggressively checks its own claims with adversarial self-verification, replication, and calibration audits.
An MCP-based research agent that searches live web data through SQL and publishes reports with the full query and tool trajectory.
Uno is a research repository for speeding up LLM inference with discrete diffusion and lossless multi-token decoding. The repo includes inference, training, and evaluation code, plus installation steps, checkpoints, and example workflows.
