Zixuan Weng

YukinoAsuna's activity

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

authored 2 papers about 24 hours ago

Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs

Paper • 2610.13078 • Published 14 days ago • 2

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs

Paper • 2502.19820 • Published Feb 27, 2025

upvoted 3 papers 1 day ago

Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs

Paper • 2610.13078 • Published 14 days ago • 2

Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research

Paper • 2610.24944 • Published 5 days ago • 19

Scaling Parameter-Efficient Fine-Tuning for Brain Encoding

Paper • 2610.26802 • Published 4 days ago • 242

upvoted a paper about 2 months ago

SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation

Paper • 2608.21500 • Published Aug 21 • 41

liked a model 3 months ago

zai-org/GLM-5.2

Text Generation • 753B • Updated Sep 1 • 345k • • 5.18k

upvoted 2 papers 7 months ago

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Paper • 2604.05091 • Published Apr 6 • 45

Emergent Social Intelligence Risks in Generative Multi-Agent Systems

Paper • 2603.27771 • Published Mar 29 • 50

liked 2 models 9 months ago

failspy/llama-3-70B-Instruct-abliterated

Text Generation • 71B • Updated May 7, 2024 • 8.57k • • 152

dphn/Dolphin3.0-Llama3.1-8B

8B • Updated Apr 14, 2025 • 3.39k • 407

upvoted a paper about 1 year ago

Building a Foundational Guardrail for General Agentic Systems via Synthetic Data

Paper • 2510.09781 • Published Oct 10, 2025 • 27

updated a model about 2 years ago

YukinoAsuna/test_trainer

Text Classification • 0.1B • Updated Sep 10, 2024 • 4