arxiv:2606.01286
Aaron Li
aaronjli
·
AI & ML interests
Deep Learning, Interpretability, Computational Neuroscience
Recent Activity
authored a paper 1 day ago
Certifying LLM Safety against Adversarial Prompting authored a paper 1 day ago
BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution upvoted a paper 1 day ago
BenchEvolver: Frontier Task Synthesis via Solution-Centric EvolutionOrganizations
models 5
aaronjli/w2s_llama3-8b-instruct_gpt2-xl_boolq_fp16
8B • Updated • 2
aaronjli/w2s_llama3-8b-instruct_gpt2-large_boolq_fp16
8B • Updated • 3
aaronjli/w2s_llama3-8b-instruct_gpt2-medium_boolq_fp16
8B • Updated • 2
aaronjli/w2s_llama3-8b-instruct_gpt2-small_boolq_fp16
8B • Updated • 2
aaronjli/w2s_llama3-8b-instruct_qwen1.5-0.5b_boolq_fp16
8B • Updated • 1