RSQ: Learning from Important Tokens Leads to Better Quantized LLMs
Paper
•
2503.01820
•
Published
•
2
Yi-Lin Sung
a2889184
AI & ML interests
None yet
Recent Activity
authored
a paper
about 2 months ago
Unified Coarse-to-Fine Alignment for Video-Text Retrieval
authored
a paper
about 2 months ago
Merge, Then Compress: Demystify Efficient SMoE with Hints from Its
Routing Policy
authored
a paper
about 2 months ago
ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language
Models
Organizations
None yet