徐伯阳

biangbiang888

9 9

·

AI & ML interests

AI alignment, jailbreak detection, red teaming, model robustness, safety evaluation

Recent Activity

liked a model 2 days ago

imwizard/redteaming_model_flanT5_classification_2

liked a model 2 days ago

brao/llama-2-7b-hallucination_detection

liked a model 2 days ago

leomaurodesenv/bert-base-uncased-jailbreakv-28k

View all activity

Organizations

None yet

upvoted 2 papers 2 days ago

Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures

Paper • 2609.29429 • Published 8 days ago • 23

WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation

Paper • 2609.30221 • Published 8 days ago • 46

upvoted 3 papers 3 days ago

Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

Paper • 2609.27334 • Published 9 days ago • 51

FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation

Paper • 2609.27657 • Published 9 days ago • 9

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published about 1 month ago • 494

upvoted a paper 4 days ago

ALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning

Paper • 2609.22323 • Published 16 days ago • 10

upvoted 2 papers 8 days ago

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents

Paper • 2609.23986 • Published 11 days ago • 28

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

Paper • 2609.22068 • Published 14 days ago • 138

upvoted a paper 9 days ago

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Paper • 2609.20511 • Published 15 days ago • 110