4 papers
DemoPSD: Disagreement-Modulated Policy Self-Distillation
Yunhe Li, Hao Shi, Wenhao Liu +5
On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the stud…
VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio
Hao Zhang, Qinran Lin, Linqi Song +1
Vision-language models like CLIP can provide rich semantic priors for open-vocabulary object detection. However, jointly integrating both textual and visual knowledge into detectio…
ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models
Wenhao Liu, Hao Shi, Yunhe Li +7
Long chain-of-thought (CoT) trajectories in large language model (LLM) reasoning cause severe inference bottlenecks due to rapid key-value (KV) cache growth. Current decoding-time…
Flexible Coded Distributed Convolution Computing for Enhanced Straggler Resilience and Numerical Stability in Distributed CNNs
Shuo Tan, Rui Liu, Xuesong Han +4
Deploying Convolutional Neural Networks (CNNs) on resource-constrained devices necessitates efficient management of computational resources, often via distributed environments susc…