BestHub
Sign in
Bilibili Tech
Author

Bilibili Tech

Provides introductions and tutorials on Bilibili-related technologies.

401
Articles
0
Likes
2.2k
Views
0
Comments
Recent Articles

Latest from Bilibili Tech

100 recent articles max
Bilibili Tech
Bilibili Tech
Jul 1, 2026 · Artificial Intelligence

FATE Series (SABER & CASTER) Debuts at ACL 2026: Advanced LLM Reasoning

At ACL 2026 in San Diego, Bilibili’s tech team introduced the FATE series—SABER, which reduces overthinking in LLMs with a token‑budgeted switchable training, and CASTER, a community‑aware evaluation system built on Social‑CoT and the MEDEA framework that outperforms GPT‑5.2 and Claude‑4.5‑Opus on the new CASTER‑Bench, while also promoting the B‑UP talent recruitment program.

LLMMultimodal EvaluationSocial CoT
0 likes · 10 min read
FATE Series (SABER & CASTER) Debuts at ACL 2026: Advanced LLM Reasoning
Bilibili Tech
Bilibili Tech
Jun 12, 2026 · Artificial Intelligence

A New UGC Video Evaluation Paradigm Built on 17 Billion Real User Interactions

The paper introduces CASTER, a multimodal AI system that uses Social‑CoT reasoning and the MEDEA framework to simulate diverse audience reactions, benchmarked on the large‑scale CASTER‑Bench dataset, and demonstrates superior performance over GPT‑5.2, Claude‑4.5‑Opus, and traditional VQA methods while already being deployed on Bilibili.

Community resonanceSocial CoTUGC video evaluation
0 likes · 9 min read
A New UGC Video Evaluation Paradigm Built on 17 Billion Real User Interactions
Bilibili Tech
Bilibili Tech
May 27, 2026 · Artificial Intelligence

How to Use A2UI + Vue to Enable Large Models to Generate Interactive Interfaces

This article details how a unified AI assistant framework built for Bilibili's advertising business evolves from plain text output to generating fully interactive UI by leveraging Google’s A2UI protocol, a custom Vue renderer, double‑validation mechanisms, SSE dual‑channel streaming, and a wrapper component system, providing concrete examples and architectural diagrams.

A2UIAgentGenerative UI
0 likes · 17 min read
How to Use A2UI + Vue to Enable Large Models to Generate Interactive Interfaces
Bilibili Tech
Bilibili Tech
May 15, 2026 · Frontend Development

Building an AI‑Powered Frontend Development Workflow with Bili‑FE

This article details how the Bili‑FE team evolved prompt engineering into a Harness Engineering workflow, creating a structured .workflow knowledge base and a series of AI‑driven commands that automate the entire frontend development lifecycle from requirement preprocessing to testing and mock generation.

AIAutomationFrontend
0 likes · 20 min read
Building an AI‑Powered Frontend Development Workflow with Bili‑FE
Bilibili Tech
Bilibili Tech
Apr 14, 2026 · Artificial Intelligence

Can 10% of Instruction Data Match Full-Scale Fine-Tuning? The SPICE Solution

The SPICE method leverages Fisher Information Matrix submodularity and a novel gradient‑conflict penalty to select a small, high‑quality subset of instruction‑tuning data, achieving comparable or superior performance to full‑data fine‑tuning while dramatically reducing training cost.

Fisher informationGradient ConflictInstruction Tuning
0 likes · 13 min read
Can 10% of Instruction Data Match Full-Scale Fine-Tuning? The SPICE Solution
Bilibili Tech
Bilibili Tech
Mar 31, 2026 · Artificial Intelligence

Can AI Generate Real‑Time, Editable Motion Graphics? Inside Neon Vibe Motion

This article examines Neon Vibe Motion, an open‑source platform that lets users describe motion effects in natural language, uses LLMs to generate executable Canvas/WebGL code with adjustable parameters, and details the architecture, workflow, prompt engineering, and export options that enable real‑time, controllable motion graphics.

AI motion graphicsCanvas 2DLLM code generation
0 likes · 25 min read
Can AI Generate Real‑Time, Editable Motion Graphics? Inside Neon Vibe Motion
Bilibili Tech
Bilibili Tech
Mar 12, 2026 · Frontend Development

Turning Canvas Snapshots into Real Video Cards with ProseMirror

This article recounts Bilibili’s evolution from using Canvas‑based screenshot tricks to render video cards in the Quill editor to adopting ProseMirror with Tiptap, detailing the technical debt, the new schema and NodeView architecture, performance optimizations, batch link validation, and strategies for backward compatibility and real‑time interactive components.

FrontendPerformanceProseMirror
0 likes · 17 min read
Turning Canvas Snapshots into Real Video Cards with ProseMirror
Bilibili Tech
Bilibili Tech
Feb 13, 2026 · Artificial Intelligence

Self-Forcing: Turning Global Video Diffusion into Causal Streaming for Long-Form Generation

This article examines the Wan2.1 video diffusion model, identifies its scalability bottlenecks for long and real‑time video generation, and introduces the Self‑Forcing causal framework together with sequence‑parallel and RoPE optimizations that achieve sub‑second latency and up to 1.5× speed‑up on modern GPUs.

GPU OptimizationVideo Diffusioncausal inference
0 likes · 14 min read
Self-Forcing: Turning Global Video Diffusion into Causal Streaming for Long-Form Generation
Bilibili Tech
Bilibili Tech
Jan 28, 2026 · Artificial Intelligence

Boosting Video Generation Inference: Full Graph Compilation with torch.compile

This article examines the challenges of optimizing video generation model inference, moving from operator-level tweaks to full-graph compilation using torch.compile, and details systematic strategies to eliminate Graph Breaks, handle dynamic shapes, KV-Cache indexing, and Python-side caches, achieving a 47.6% speedup on a 14B model without accuracy loss.

AIInference Accelerationgraph optimization
0 likes · 14 min read
Boosting Video Generation Inference: Full Graph Compilation with torch.compile