Maglev: Sliding Recurrent Memory
Paper • 2608.02870 • Published • 5
🔄 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
updated a collection about 2 hours ago
WTF GENIUS PAPERS upvoted a paper about 2 hours ago
Maglev: Sliding Recurrent Memory updated a collection about 2 hours ago
WTF GENIUS PAPERSOrganizations
upvoted 2
papers about 2 hours ago
upvoted 5
papers 1 day ago
ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization
Paper • 2608.11045 • Published • 3
Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing
Paper • 2608.11660 • Published • 4
Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning
Paper • 2607.29211 • Published • 3
SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models
Paper • 2608.10538 • Published • 5
Full-bandwidth transformer
Paper • 2608.08888 • Published • 10
upvoted a paper 2 days ago
upvoted 3
papers 3 days ago
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Paper • 2608.09819 • Published • 331
Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation
Paper • 2608.10812 • Published • 12
On-Policy Self-Distillation without Any Supervision
Paper • 2608.06296 • Published • 202
upvoted 4
papers 4 days ago
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss
Paper • 2608.03796 • Published • 14
OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching
Paper • 2608.08097 • Published • 24
SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation
Paper • 2608.04419 • Published • 27
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
Paper • 2608.09888 • Published • 614
upvoted a paper 5 days ago
upvoted 4
papers 7 days ago
Lngram: N-gram Conditional Memory in Latent Space
Paper • 2605.24869 • Published • 1
Beyond Conditional Computation: Retrieval-Augmented Genomic Foundation Models with Gengram
Paper • 2601.22203 • Published • 2
Interpretable MEG Decoding of Perceived Speech: Cortical Sources and the Stimulus Features That Drive Retrieval
Paper • 2608.01481 • Published • 69
Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replay
Paper • 2608.05784 • Published • 28