5 papers
Leaky Students: Membership Inference against On-Policy Distillation
Zhexi Lu, Mingzhi Zhu, Stacy Patterson +1
On-policy distillation (OPD) trains a student to match a teacher's next-token distributions on student-generated trajectories. However, privileged information supplied to the teach…
Multi-task Code LLMs: Data Mix or Model Merge?
Mingzhi Zhu, Boris Sobolev, Rahul Krishna +3
Recent research advocates deploying smaller, specialized code LLMs in agentic frameworks alongside frontier models, sparking interest in efficient strategies for multi-task learnin…
ESCA: Enabling Seamless Codec Avatar Execution through Algorithm and Hardware Co-Optimization for Virtual Reality
Mingzhi Zhu, Ding Shang, Sai Qian Zhang
Photorealistic Codec Avatars (PCA), which generate high-fidelity human face renderings, are increasingly being used in Virtual Reality (VR) environments to enable immersive communi…
GhostShell: Streaming LLM Function Calls for Concurrent Embodied Programming
Jian Gong, Youwei Huang, Bo Yuan +16
We present GhostShell, a novel approach that leverages Large Language Models (LLMs) for streaming and concurrent behavioral programming in embodied systems. In contrast to predefin…
Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing
Boyuan Chen, Mingzhi Zhu, Brendan Dolan-Gavitt +2
The rapid advancement of large language models (LLMs) has significantly improved code completion tasks, yet the trade-off between accuracy and computational cost remains a critical…