Changdae Oh

changdae's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted an article about 1 month ago

view article

Article

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

• 

Feb 11

•

94

upvoted 5 papers 3 months ago

Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

Paper • 2510.07242 • Published Oct 8 • 30

Infusing Theory of Mind into Socially Intelligent LLM Agents

Paper • 2509.22887 • Published Sep 26 • 5

LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals

Paper • 2509.21875 • Published Sep 26 • 9

Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment

Paper • 2509.23564 • Published Sep 28 • 7

Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding

Paper • 2509.23050 • Published Sep 27 • 14

upvoted 2 papers 7 months ago

MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems

Paper • 2505.18943 • Published May 25 • 24

Visual Instruction Bottleneck Tuning

Paper • 2505.13946 • Published May 20 • 10

upvoted 4 papers 10 months ago

DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation

Paper • 2410.03782 • Published Oct 3, 2024 • 1

Can Your Uncertainty Scores Detect Hallucinated Entity?

Paper • 2502.11948 • Published Feb 17 • 3

Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations

Paper • 2501.19066 • Published Jan 31 • 13

How to Steer LLM Latents for Hallucination Detection?

Paper • 2503.01917 • Published Mar 1 • 11