Hao Zhou
3 papers · Latest:
Cryptography & Security
Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
Safety Anchor introduces Safety Bottleneck Regularization (SBR) to defend LLMs against harmful fine-tuning by anchoring hidden states in the unembedding layer.
2605.05995
Human-Computer InteractionBATON: A Multimodal Benchmark for Bidirectional Automation Transition Observation in Naturalistic Driving
BATON is a new multimodal dataset and benchmark for predicting driver handover and takeover events in naturalistic automated driving.
2604.07263
Natural Language ProcessingGemini: A Family of Highly Capable Multimodal Models
Gemini is a new family of multimodal AI models excelling in image, audio, video, and text understanding, achieving state-of-the-art results across numerous benchmarks including human-expert level on MMLU.
2312.11805
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.