Hölder Policy Optimisation
Paper • 2605.12058 • Published • 16
Urro PRO
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 about 5 hours ago
Hölder Policy Optimisation updated a collection about 5 hours ago
WTF GENIUS PAPERS upvoted a paper about 5 hours ago
Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVROrganizations
upvoted 4
papers about 5 hours ago
Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR
Paper • 2605.15726 • Published • 25
Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding
Paper • 2605.02290 • Published • 32
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
Paper • 2605.11739 • Published • 49
upvoted 3
papers 3 days ago
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning
Paper • 2605.14386 • Published • 54
Long Context Pre-Training with Lighthouse Attention
Paper • 2605.06554 • Published • 23
Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
Paper • 2605.13301 • Published • 149
upvoted an article 3 days ago
Article
Unlocking asynchronicity in continuous batching
- +1
ror, pcuenq, ariG23498
• • 45 upvoted 7
papers 3 days ago
PreScam: A Benchmark for Predicting Scam Progression from Early Conversations
Paper • 2605.12243 • Published • 2
LLM-based Detection of Manipulative Political Narratives
Paper • 2605.14354 • Published • 3
Ideology Prediction of German Political Texts
Paper • 2605.14352 • Published • 3
Dynamic Latent Routing
Paper • 2605.14323 • Published • 4
PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution
Paper • 2605.13027 • Published • 6
Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning
Paper • 2605.11458 • Published • 5
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
Paper • 2605.06527 • Published • 42
upvoted 5
papers 4 days ago
From Pixels to Concepts: Do Segmentation Models Understand What They Segment?
Paper • 2605.09591 • Published • 2
The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs
Paper • 2605.08737 • Published • 3
FeatCal: Feature Calibration for Post-Merging Models
Paper • 2605.13030 • Published • 7
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
Paper • 2605.12825 • Published • 11
Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
Paper • 2605.13511 • Published • 30