Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
Paper • 2610.42147 • Published • 2
🤝 Open to Collab
Urro
urroxyz
AI & ML interests
computational linguistics major 🤖🔎🔠
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 10 hours ago
WTF GENIUS PAPERS upvoted a paper about 10 hours ago
Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention upvoted a paper about 10 hours ago
R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization LoopOrganizations
upvoted 7
papers about 10 hours ago
R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop
Paper • 2610.22740 • Published • 97
On the Origin and Evolution of Training-Inference Mismatch in LLM Reinforcement Learning
Paper • 2610.40945 • Published • 10
When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications
Paper • 2610.40256 • Published • 9
MemSteer: Turning User Histories into Supervision for Agent Memory Optimization
Paper • 2610.39276 • Published • 6
Follow the Gradient: Tracing Safety Degradation Back to Training Data
Paper • 2610.37481 • Published • 29
Think Twice: The Metis-1.6 Technical Report
Paper • 2610.37903 • Published • 4
upvoted 4
papers 1 day ago
Building Auditable AI Text Detectors with Sparse Autoencoders
Paper • 2610.30006 • Published • 16
TenetBench: A Clause-Anchored Russian Corpus for Evaluating Language Models against Professional Codes of Ethics
Paper • 2610.29477 • Published • 22
Every Weight Is a Path of Shared Discrete Decisions
Paper • 2610.31931 • Published • 27
On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models
Paper • 2610.32770 • Published • 49
upvoted 9
papers 3 days ago
Instruction Capacity: Behavior and Degradation of Language Models under Controlled Load
Paper • 2610.36095 • Published • 4
Scaling Lean Theorem Proving for Real-World Code Verification
Paper • 2610.38174 • Published • 7
CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models
Paper • 2610.21143 • Published • 15
Glance: The Generator Is Its Own Reranker
Paper • 2610.40454 • Published • 15
Broken on Arrival: Non-Functional Quantized LLM Artifacts in Public Model Registries and How to Catch Them
Paper • 2609.05881 • Published • 7
Your LR Schedule May Not Be Principled: Effective Learning Rate Scheduling in Weight-Normalized Training
Paper • 2610.40362 • Published • 16
Your Benchmark Is an Empirical Measure Over Difficulty
Paper • 2610.29927 • Published • 167
WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training
Paper • 2610.37161 • Published • 66
A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
Paper • 2610.38568 • Published • 92