Daniel Huynh's picture

Daniel Huynh PRO

dhuynh95

·

dhuynh95

AI & ML interests

None yet

Recent Activity

upvoted a paper 4 days ago

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos

updated a collection 4 days ago

upvoted a paper 4 days ago

Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong

View all activity

Articles

Open-source embeddings and LLMs outperform Gemini and OpenAI for Web Navigation while being faster and cheaper

Automatic Hallucination detection with SelfCheckGPT NLI

StarCoder Memorization Experiment Highlights Privacy Risks of Fine-Tuning On Code

Introducing BlindChat, an open-source and privacy-by-design Conversational AI fully in-browser

AI Total Cost of Ownership Calculator: Evaluate the cost of in-house AI deployment vs AI APIs

Organizations

dhuynh95's activity

upvoted a paper 4 days ago

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos

Paper • 2501.09781 • Published 10 days ago • 21

updated a collection 4 days ago

cool-papers

62 items • Updated 4 days ago

upvoted a paper 4 days ago

Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong

Paper • 2501.09775 • Published 10 days ago • 26

updated a collection 4 days ago

cool-papers

62 items • Updated 4 days ago

upvoted a paper 4 days ago

MLLM-as-a-Judge for Image Safety without Human Labeling

Paper • 2501.00192 • Published 26 days ago • 25

updated a collection 4 days ago

cool-papers

62 items • Updated 4 days ago

upvoted a paper 4 days ago

Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives

Paper • 2501.04003 • Published 19 days ago • 24

updated a collection 4 days ago

cool-papers

62 items • Updated 4 days ago

upvoted a paper 4 days ago

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

Paper • 2412.19723 • Published 30 days ago • 81

updated a collection 4 days ago

cool-papers

62 items • Updated 4 days ago

upvoted 2 papers 4 days ago

Demystifying Domain-adaptive Post-training for Financial LLMs

Paper • 2501.04961 • Published 17 days ago • 11

ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding

Paper • 2501.05452 • Published 17 days ago • 15

updated a collection 4 days ago

cool-papers

62 items • Updated 4 days ago

liked a Space about 2 months ago

QwQ-32B-Preview

QwQ-32B-Preview

updated a collection 2 months ago

cool-papers

62 items • Updated 4 days ago

upvoted 2 papers 2 months ago

Stronger Models are NOT Stronger Teachers for Instruction Tuning

Paper • 2411.07133 • Published Nov 11, 2024 • 35

Autoregressive Models in Vision: A Survey

Paper • 2411.05902 • Published Nov 8, 2024 • 17

updated a collection 2 months ago

cool-papers

62 items • Updated 4 days ago

liked a model 2 months ago

microsoft/OmniParser

Image-Text-to-Text • Updated Dec 2, 2024 • 1.33k • 1.54k