Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time
Paper
•
2408.13233
•
Published
•
23
•
4
Literate Goggles
literate-goggles
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 19 hours ago
InstructTTSEval: Benchmarking Complex Natural-Language Instruction
Following in Text-to-Speech Systems
upvoted
a
paper
2 days ago
Qwen3-TTS Technical Report
upvoted
a
paper
8 days ago
TiDAR: Think in Diffusion, Talk in Autoregression
Organizations
None yet