Nested Learning: The Illusion of Deep Learning Architectures
Paper • 2512.24695 • Published • 48
Tullus Augustus
TULLUS
·
AI & ML interests
The Goal Is Simple = Sharing Is Caring, If you see unique or rare model listed here consider it a Top Tier High End Release by their respective Developers and Teams. I leave all original names / base space. (RSI) is cool.
Recent Activity
new activity about 13 hours ago
TULLUS/Instella-MoE-16B-A3B-Think:Gated MLA context memory scaling and vocabulary tax on 2.8B active compute liked a model 1 day ago
LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct updated a Space 1 day ago
TULLUS/bebop-space-jazz-stationOrganizations
None yet
upvoted 6
papers 3 days ago
LiteAttention: A Temporal Sparse Attention for Diffusion Transformers
Paper • 2511.11062 • Published • 34
Continuous Thought Machines
Paper • 2505.05522 • Published • 16
TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models
Paper • 2501.16937 • Published • 9
FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language
Paper • 2506.20920 • Published • 80
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
Paper • 2510.08697 • Published • 41
upvoted a paper 4 days ago
upvoted an article 11 days ago
Article
VLM Run Gateway: Run open-weight OCR, VLM and vision models behind one API
vlm-run
• • 6 upvoted a collection 12 days ago
upvoted a paper 12 days ago
upvoted an article 12 days ago
Article
TurboQuant Quantization Explained
lucifertrj
• • 5 upvoted a paper 13 days ago
upvoted a collection 13 days ago
upvoted an article 13 days ago
Article
Give Your Coding Agents a Memory You Own
dacorvo
• • 108