Provides introductions and tutorials on Bilibili-related technologies.
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.
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.
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.
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.
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.
SABER introduces a reinforcement‑learning framework that lets large language models dynamically switch among four token‑budgeted reasoning modes, dramatically cutting inference length while preserving or improving accuracy across math, code, and logic tasks.
This article details how we built an AI‑tool ecosystem by evolving a basic online JS cloud‑function platform into a unified, reusable capability layer that integrates with Flowise, LangChain StructuredTool, and the Model Context Protocol (MCP) to provide secure, cross‑platform tool calls for agents.
This article details the design and deployment of a multi‑layer LLM system that automatically reads massive creator group chats, extracts structured insights, mitigates hallucinations with dual‑model verification, uses few‑shot prompting for stable output, and delivers real‑time risk alerts and operational reports.
This article explains what an AI Agent is, distinguishes it from traditional workflows, and demonstrates how to build and customize agents using the Go‑based Blades framework, covering core concepts, code examples, five workflow patterns, best‑practice guidelines, and reference resources.
This article analyzes the current bottlenecks of Bilibili's private messaging service, explains the technical challenges of massive data volume and traffic spikes, and presents a comprehensive multi‑layer architecture upgrade—including cache strategies, BFF refactoring, database sharding, and consistency mechanisms—to ensure scalability and reliability.
