Evaluation Benchmark

Bilibili Tech

Nov 5, 2024 · Artificial Intelligence

Bilibili's In-House Role-Playing Large Language Model: Architecture, Training Stages, Evaluation, and Demonstrations

Bilibili’s in‑house role‑playing large language model, built on the Index architecture and refined through pre‑training, supervised fine‑tuning, and preference optimization (PPO and DPO), achieved top scores on the Chinese CharacterEval benchmark, surpassing rivals while incorporating safety alignment and showcasing consistent, personality‑driven dialogue examples.

Evaluation BenchmarkLarge Language ModelSupervised Fine-tuning

0 likes · 13 min read

Bilibili's In-House Role-Playing Large Language Model: Architecture, Training Stages, Evaluation, and Demonstrations

DataFunTalk

Jan 12, 2023 · Artificial Intelligence

Tencent AI Lab's Advances in High‑Fidelity 3D Face Digitization and Evaluation

This article presents Tencent AI Lab's recent research on efficient 3D face digitization—including single‑photo, multi‑photo, and RGB‑D selfie pipelines—describes a detailed production workflow, introduces a new evaluation benchmark (REALY), and shares insights from a technical Q&A session.

3D face reconstructionAI LabDifferentiable Rendering

0 likes · 11 min read

Tencent AI Lab's Advances in High‑Fidelity 3D Face Digitization and Evaluation