3 papers
cs.LG2026
AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning
Changhai Zhou, Shiyang Zhang, Yuhua Zhou +5
Quantization followed by parameter-efficient fine-tuning has emerged as a promising paradigm for downstream adaptation under tight GPU memory constraints. However, this sequential…
cs.CV2026
SoulX-FlashHead: Oracle-guided Generation of Infinite Real-time Streaming Talking Heads
Tan Yu, Qian Qiao, Le Shen +9
Achieving a balance between high-fidelity visual quality and low-latency streaming remains a formidable challenge in audio-driven portrait generation. Existing large-scale models o…
cs.LG2026
Balancing Fidelity and Plasticity: Aligning Mixed-Precision Fine-Tuning with Linguistic Hierarchies
Changhai Zhou, Shiyang Zhang, Yuhua Zhou +5
Deploying and fine-tuning Large Language Models (LLMs) on resource-constrained edge devices requires navigating a strict trade-off between memory footprint and task performance. Wh…