corpus.blog
56,966 blogs · [ { "id": "01a0872a-8774-714d-97ce-64ad3f4ed07d", "title": "PageGuide: Browser Extension to Assist Users in Navigating a Webpage and Locating Information", "url": "https://anhnguyen.me/2026/pageguide/", "published_at": "2026-04-06T22:37:06+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad3fa1c908", "title": "SketchVLM: Vision-Language Models Can Annotate Images to Explain Thoughts and Guide Users", "url": "https://anhnguyen.me/2026/sketchvlm/", "published_at": "2026-04-06T22:00:24+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad403573b1", "title": "Improving Human Verification of LLM Reasoning through Interactive Explanation Interfaces", "url": "https://anhnguyen.me/2026/interactive-llm/", "published_at": "2026-01-22T20:00:21+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad40558721", "title": "Understanding Generative AI Capabilities in Everyday Image Editing Tasks", "url": "https://anhnguyen.me/2026/genai-vs-humans/", "published_at": "2026-01-20T23:18:27+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad40627293", "title": "Vision Language Models are Biased", "url": "https://anhnguyen.me/2026/vlms-are-biased/", "published_at": "2026-01-02T06:24:36+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad411d9317", "title": "TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models", "url": "https://anhnguyen.me/2025/transformer-attention-bottlenecks/", "published_at": "2025-05-31T05:08:20+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad41b54f96", "title": "Interpretable LLM-based Table Question Answering", "url": "https://anhnguyen.me/2025/plan-of-sqls/", "published_at": "2025-05-31T04:39:11+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad42abf7fb", "title": "Improving zero-shot object-level change detection by incorporating visual correspondence", "url": "https://anhnguyen.me/2025/change-detection-correspondence/", "published_at": "2025-05-31T04:23:13+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad439fa564", "title": "HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs", "url": "https://anhnguyen.me/2025/hot/", "published_at": "2025-05-31T03:28:57+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad43c359be", "title": "B-score: Detecting biases in large language models using response history", "url": "https://anhnguyen.me/2025/b-score/", "published_at": "2025-05-30T18:23:50+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad4456b76f", "title": "Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers", "url": "https://anhnguyen.me/2024/face-id-vit/", "published_at": "2024-11-08T14:48:24+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad44bc320e", "title": "PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans", "url": "https://anhnguyen.me/2024/pcnn/", "published_at": "2024-08-06T20:40:47+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad45451258", "title": "Vision Language Models Are Blind", "url": "https://anhnguyen.me/2024/vlms-are-blind/", "published_at": "2024-07-10T22:15:19+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad458cd04d", "title": "PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck", "url": "https://anhnguyen.me/2024/peeb/", "published_at": "2024-05-03T18:24:49+00:00" }, { "id": "01a0872a-8774-714d-97ce-64ad45a1e3b4", "title": "GlitchBench: Can large multimodal models detect video game glitches?", "url": "https://anhnguyen.me/2024/glitchbench/", "published_at": "2024-04-10T18:50:57+00:00" } ] posts Claim your blog
Back to anhnguyen.me
Blog · corpus.blog/blogs/anhnguyen.me/posts

anhnguyen.me

anhnguyen.me

2026

PageGuide: Browser Extension to Assist Users in Navigating a Webpage and Locating Informationoriginal ↗
6 Apr 2026
SketchVLM: Vision-Language Models Can Annotate Images to Explain Thoughts and Guide Usersoriginal ↗
6 Apr 2026
Improving Human Verification of LLM Reasoning through Interactive Explanation Interfacesoriginal ↗
22 Jan 2026
Understanding Generative AI Capabilities in Everyday Image Editing Tasksoriginal ↗
20 Jan 2026
Vision Language Models are Biasedoriginal ↗
2 Jan 2026

2025

TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Modelsoriginal ↗
31 May 2025
Interpretable LLM-based Table Question Answeringoriginal ↗
31 May 2025
Improving zero-shot object-level change detection by incorporating visual correspondenceoriginal ↗
31 May 2025
HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputsoriginal ↗
31 May 2025
B-score: Detecting biases in large language models using response historyoriginal ↗
30 May 2025

2024

Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformersoriginal ↗
8 Nov 2024
PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humansoriginal ↗
6 Aug 2024
Vision Language Models Are Blindoriginal ↗
10 Jul 2024
PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneckoriginal ↗
3 May 2024
GlitchBench: Can large multimodal models detect video game glitches?original ↗
10 Apr 2024