[AI Researcher & Software Engineer]

Yap Wei Herng

Passionate about artificial intelligence, machine learning, and software development. Sharing insights from research and practical experience.

Focus

Research Areas

Artificial Intelligence

Machine learning, deep learning, neural networks, and intelligent systems.

Software Engineering

Best practices, architecture patterns, and modern development methodologies.

Research & Development

Exploring cutting-edge technologies and innovative solutions.

Latest

Recent Posts

18 Publications
(4 min read)

Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting

Introduction Background Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities, known as catastrophic forgetting. This phenomenon has been observed in both supervised fine-tuning (SFT) for instruction following and reinforcement learning (RL) for preference alignment. However, the comparative susceptibility of SFT and RL...

Catastrophic-Forgetting LLM Reinforcement-Learning
Read Article
(7 min read)

Agent-based Automated Claim Matching with Instruction-following LLMs

Introduction Background Automated fact-checking pipelines rely on claim matching to identify claims that can be verified using the same evidence or fact-check. This task is crucial for scaling fact-checking efforts, as it helps in grouping related claims for efficient verification. Previous work has framed claim matching as a ranking problem...

LLM Agent
Read Article
(3 min read)

mHC: Manifold-Constrained Hyper-Connections

Introduction Background Deep neural network architectures have evolved significantly since the introduction of ResNets in 2016, with residual connections becoming a cornerstone of modern models like Transformers and large language models (LLMs). Hyper-Connections (HC) extended this paradigm by expanding the residual stream width and diversifying connectivity patterns, yielding performance gains...

Architecture Training
Read Article
(3 min read)

ConfTuner: Training Large Language Models to Express Their Confidence Verbally

Introduction Background Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as science, law, and healthcare, where accurate expressions of uncertainty are essential for reliability and trust. However, current LLMs often generate incorrect answers with high confidence, a phenomenon known as overconfidence. This undermines trust and poses challenges...

Inference
Read Article
View All Posts