Albert Yin

AlbertYin

8 7

https://albert-y1n.github.io/

AI & ML interests

LLM

Recent Activity

liked a model 6 days ago

AlbertYin/agentdojo_attacker_qwen3_4b_5.6_terra

upvoted a paper 14 days ago

GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis

upvoted a paper 15 days ago

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

View all activity

Organizations

None yet

liked a model 6 days ago

AlbertYin/agentdojo_attacker_qwen3_4b_5.6_terra

4B • Updated Aug 24 • 43 • 1

upvoted a paper 14 days ago

GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis

Paper • 2609.38923 • Published 16 days ago • 125

upvoted a paper 15 days ago

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

Paper • 2603.13026 • Published Jul 23 • 2

updated a collection 19 days ago

PIForge Attackers

Collection

Released RL prompt injection attacker checkpoints from PIForge and PISmith. • 9 items • Updated 19 days ago

liked a model 22 days ago

mindlab-research/Macaron-V1.1

Text Generation • 753B • Updated 23 days ago • 468 • 11

upvoted a paper about 1 month ago

Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation

Paper • 2609.11115 • Published Sep 10 • 165

updated a model about 1 month ago

AlbertYin/agentdojo_attacker_qwen3_4b_muse_spark

4B • Updated Sep 7 • 26

published a model about 1 month ago

AlbertYin/agentdojo_attacker_qwen3_4b_muse_spark

4B • Updated Sep 7 • 26

upvoted a paper about 1 month ago

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published Sep 3 • 212

updated a model about 2 months ago

AlbertYin/agentdojo_attacker_qwen3_4b_5.6_terra_dev

4B • Updated Aug 31 • 10

published a model about 2 months ago