AI.info

Zhangyang Wang

Explore Zhangyang Wang on AI.info.

• Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems
• Neurosymbolic LoRA: Why and When to Tune Weights vs. Rewrite Prompts
• Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration
• The Path Not Taken: RLVR Provably Learns Off the Principals
• One Token Embedding Is Enough to Deadlock Your Large Reasoning Model