Picture for Xihui Lin

Xihui Lin

Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs

Add code
Mar 03, 2025
Viaarxiv icon

A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts

Add code
Oct 02, 2024
Figure 1 for A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts
Figure 2 for A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts
Figure 3 for A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts
Figure 4 for A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts
Viaarxiv icon

Efficient LLM Training and Serving with Heterogeneous Context Sharding among Attention Heads

Add code
Jul 25, 2024
Figure 1 for Efficient LLM Training and Serving with Heterogeneous Context Sharding among Attention Heads
Figure 2 for Efficient LLM Training and Serving with Heterogeneous Context Sharding among Attention Heads
Figure 3 for Efficient LLM Training and Serving with Heterogeneous Context Sharding among Attention Heads
Figure 4 for Efficient LLM Training and Serving with Heterogeneous Context Sharding among Attention Heads
Viaarxiv icon

The Hitchhiker's Guide to Human Alignment with *PO

Add code
Jul 21, 2024
Viaarxiv icon