Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
Paper • 2607.07386 • Published • 10
🔄 In a Training Loop
Urro
urroxyz
AI & ML interests
computational linguistics major 🤖🔎ðŸ”
i am autistic. if i come off rude, i probably didn't mean to. please feel free to ask me for clarification.
Recent Activity
upvoted a paper 2 days ago
Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity updated a collection 2 days ago
WTF GENIUS PAPERSOrganizations
upvoted 6
papers 2 days ago
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
Paper • 2607.07708 • Published • 83
Stronger Normalization-Free Transformers
Paper • 2512.10938 • Published • 25
T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground
Paper • 2512.10430 • Published • 121
Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules
Paper • 2512.02892 • Published • 14
Learning Unmasking Policies for Diffusion Language Models
Paper • 2512.09106 • Published • 13
upvoted 6
papers 3 days ago
PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages
Paper • 2607.05992 • Published • 6
KVpop -- Key-Value Cache Compression with Predictive Online Pruning
Paper • 2607.05061 • Published • 20
Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding
Paper • 2607.05722 • Published • 11
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Paper • 2607.05147 • Published • 30
TREK: Distill to Explore, Reinforce to Refine
Paper • 2607.05339 • Published • 8
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Paper • 2607.02980 • Published • 61
upvoted a changelog 4 days ago
Hugging Face Changelog
Filter Models page by Hardware
• 155
upvoted 2
papers 4 days ago
upvoted a paper 5 days ago
upvoted 4
papers 7 days ago
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
Paper • 2607.00152 • Published • 8
WARP: Weight-Space Analysis for Recovering Training Data Portfolios
Paper • 2607.01686 • Published • 9
Denser neq Better: Limits of On-Policy Self-Distillation for Continual Post-Training
Paper • 2607.01763 • Published • 10
DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation
Paper • 2606.29961 • Published • 10