Taming LLMs by Scaling Learning Rates with Gradient Grouping
Paper • 2506.01049 • Published • 40
lupinsyli
lupinsyli
·
AI & ML interests
LLM / VLM research
Recent Activity
upvoted a paper 16 days ago
Taming LLMs by Scaling Learning Rates with Gradient GroupingOrganizations
None yet
upvoted 4
papers 16 days ago
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper • 2504.00999 • Published • 98
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
Paper • 2605.21195 • Published • 20
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
Paper • 2607.04033 • Published • 76