Guangyao Dou

gydou's activity

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

upvoted a paper 3 days ago

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge

Paper • 2608.12218 • Published 5 days ago • 5

upvoted a paper 9 days ago

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

Paper • 2608.06301 • Published 11 days ago • 34

upvoted a paper about 2 months ago

DAR: Deontic Reasoning with Agentic Harnesses

Paper • 2606.05009 • Published Jun 3 • 6

authored 6 papers 2 months ago

Machine Unlearning in Generative AI: A Survey

Paper • 2407.20516 • Published Jul 30, 2024

Towards Safer Large Language Models through Machine Unlearning

Paper • 2402.10058 • Published Jun 5, 2024

Avoiding Copyright Infringement via Large Language Model Unlearning

Paper • 2406.10952 • Published Feb 11, 2025

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models

Paper • 2502.15910 • Published Jul 23, 2025

DAR: Deontic Reasoning with Agentic Harnesses

Paper • 2606.05009 • Published Jun 3 • 6

Steering Multimodal Large Language Models Decoding for Context-Aware Safety

Paper • 2509.19212 • Published Sep 23, 2025

upvoted a paper 2 months ago

Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher

Paper • 2606.01000 • Published May 31 • 6

updated a dataset 2 months ago

gydou/DeonticBench

Viewer • Updated Jun 4 • 6.48k • 430 • 8

submitted a paper to Daily Papers 2 months ago

DAR: Deontic Reasoning with Agentic Harnesses

Paper • 2606.05009 • Published Jun 3 • 6

liked a Space 4 months ago

Running

3.98k

The Ultra-Scale Playbook

🌌

3.98k

The ultimate guide to training LLM on large GPU Clusters

upvoted 2 papers 4 months ago

Many-Tier Instruction Hierarchy in LLM Agents

Paper • 2604.09443 • Published Apr 10 • 16

DeonticBench: A Benchmark for Reasoning over Rules

Paper • 2604.04443 • Published Apr 6 • 9

submitted a paper to Daily Papers 4 months ago

DeonticBench: A Benchmark for Reasoning over Rules

Paper • 2604.04443 • Published Apr 6 • 9

authored 2 papers 4 months ago

Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench

Paper • 2410.22108 • Published Oct 29, 2024 • 1

DeonticBench: A Benchmark for Reasoning over Rules

Paper • 2604.04443 • Published Apr 6 • 9

published a dataset 5 months ago

gydou/DeonticBench

Viewer • Updated Jun 4 • 6.48k • 430 • 8

updated a model almost 2 years ago

ImageToGPSproject/HF_custom_new_ImageToGPSproject_base_resnet18

11.2M • Updated Nov 12, 2024