alignment | BestHub

DataFunTalk

Nov 11, 2024 · Artificial Intelligence

OpenAI VP Lilian Weng Departs and Shares Full AI Safety Talk Transcript

The article reports the departure of OpenAI research VP Lilian Weng, provides the full transcript of her recent AI safety and alignment presentation at a Bilibili event, and discusses broader concerns about OpenAI's safety culture, reinforcement learning from human feedback, and the importance of collective involvement in AI safety.

AI SafetyMachine LearningOpenAI

0 likes · 10 min read

OpenAI VP Lilian Weng Departs and Shares Full AI Safety Talk Transcript

DaTaobao Tech

Jul 19, 2024 · Artificial Intelligence

Practices and Techniques for Vertical Domain Large Language Models

Vertical domain large language models, fine‑tuned on specialized data, deliver higher expertise and task performance, but require continual knowledge updates and careful alignment; techniques such as BPO‑guided instruction tuning (+1.8% accuracy), Reflexion‑based Text2API (+4% API correctness), advanced RAG preprocessing, and SFT combined with ORPO (+5.2% gain) demonstrate notable improvements while underscoring remaining challenges and collaborative opportunities.

AIRAGSFT

0 likes · 9 min read

Practices and Techniques for Vertical Domain Large Language Models

Bilibili Tech

Jun 14, 2024 · Artificial Intelligence

Technical Report on the Index-1.9B Series: Model Variants, Pre‑training Optimizations, and Alignment Experiments

The report presents the open‑source Index‑1.9B family—base, pure, chat, and character variants—detailing benchmark results, pre‑training optimizations such as a normalized LM‑Head and deeper‑slim architectures, the importance of modest instruction data, alignment via SFT/DPO, role‑play enhancements with RAG, and acknowledges remaining safety and factual limitations.

LLMalignmentevaluation

0 likes · 15 min read

Technical Report on the Index-1.9B Series: Model Variants, Pre‑training Optimizations, and Alignment Experiments

DataFunTalk

Apr 6, 2023 · Artificial Intelligence

A Comprehensive Survey of Large Language Models: Background, Capabilities, Key Technologies, and Future Directions

This article reviews the rapid progress of large language models (LLMs), covering their historical development, scaling laws, emergent abilities, core technologies such as training and alignment, resource ecosystems, evaluation methods, safety concerns, and prospective research challenges.

AI researchLLMPrompt Engineering

0 likes · 21 min read

A Comprehensive Survey of Large Language Models: Background, Capabilities, Key Technologies, and Future Directions

DataFunTalk

Mar 16, 2023 · Artificial Intelligence

Technical Optimizations and Breakthroughs of GPT‑4: Multimodal Capabilities, Alignment Strategies, and Predictable Scaling

The article summarizes the technical innovations behind GPT‑4, highlighting its multimodal abilities, improved alignment methods, scaling‑law‑based performance prediction, and remaining limitations, while referencing the official OpenAI technical report and community analyses.

AI researchGPT-4alignment

0 likes · 10 min read

Technical Optimizations and Breakthroughs of GPT‑4: Multimodal Capabilities, Alignment Strategies, and Predictable Scaling

Laravel Tech Community

Feb 9, 2023 · Artificial Intelligence

Understanding ChatGPT: Architecture, Training Strategies, and Alignment Challenges

This article explains how ChatGPT builds on GPT‑3, describes the supervised‑plus‑reinforcement learning (RLHF) pipeline that fine‑tunes the model, compares model capability with consistency, and discusses the performance evaluation and remaining limitations of large language models.

ChatGPTRLHFalignment

0 likes · 15 min read

Understanding ChatGPT: Architecture, Training Strategies, and Alignment Challenges

Zhengtong Technical Team

Dec 30, 2022 · Frontend Development

Implementation of Component Drag‑and‑Drop in the Wukong Low‑Code Visual Platform

This article explains how the Wukong low‑code visual platform implements component drag‑and‑drop, covering material‑to‑canvas dragging, intra‑canvas movement, resizing via eight handles, alignment guide generation, performance optimizations using CSS transforms, and component encapsulation with Vue 3.

Vue3alignmentcomponent

0 likes · 14 min read

Implementation of Component Drag‑and‑Drop in the Wukong Low‑Code Visual Platform

Tencent Cloud Developer

Apr 27, 2022 · Artificial Intelligence

Alignment-Uniformity Representation Learning for Zero-shot Video Classification (AURL)

The AURL framework, presented by Pu Shi, introduces alignment‑uniformity aware representation learning for zero‑shot video classification, achieving up to 28 % top‑1 accuracy gains on UCF101 and HMDB51, and has already boosted business metrics in Tencent’s advertising, search, and video‑channel recommendation systems.

alignmentcomputer visiondeep learning

0 likes · 19 min read

Alignment-Uniformity Representation Learning for Zero-shot Video Classification (AURL)

Kuaishou Tech

Apr 1, 2022 · Fundamentals

Understanding Glyph Metrics and Text Layout in the Y‑tech Cangjie Engine

This article explains the core concepts of glyph metrics, horizontal and vertical text layout, kerning, line breaking, and alignment techniques used by the Y‑tech Cangjie engine to provide rich text effects for video editing applications.

RenderingText LayoutTypography

0 likes · 7 min read

Understanding Glyph Metrics and Text Layout in the Y‑tech Cangjie Engine