Urro

urroxyz's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 20 papers about 10 hours ago

Reinforcement Learning from Meta-Evaluation: Aligning Language Models Without Ground-Truth Labels

Paper • 2601.21268 • Published 5 days ago • 2

FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning

Paper • 2601.19001 • Published 7 days ago • 3

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units

Paper • 2601.21996 • Published 4 days ago • 4

ECO: Quantized Training without Full-Precision Master Weights

Paper • 2601.22101 • Published 4 days ago • 6

KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices

Paper • 2601.21579 • Published 5 days ago • 6

Beyond Imitation: Reinforcement Learning for Active Latent Planning

Paper • 2601.21598 • Published 5 days ago • 9

Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts

Paper • 2601.22156 • Published 4 days ago • 10

Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening

Paper • 2601.21590 • Published 5 days ago • 12

Self-Improving Pretraining: using post-trained models to pretrain better models

Paper • 2601.21343 • Published 5 days ago • 14

Language-based Trial and Error Falls Behind in the Era of Experience

Paper • 2601.21754 • Published 4 days ago • 16

Shaping capabilities with token-level data filtering

Paper • 2601.21571 • Published 5 days ago • 20

Discovering Hidden Gems in Model Repositories

Paper • 2601.22157 • Published 4 days ago • 20

ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation

Paper • 2601.21420 • Published 5 days ago • 38

Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization

Paper • 2601.21358 • Published 5 days ago • 5

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published 3 days ago • 34

Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification

Paper • 2601.22642 • Published 4 days ago • 7

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment

Paper • 2601.20218 • Published 6 days ago • 10

SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization

Paper • 2601.22491 • Published 4 days ago • 11

FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation

Paper • 2601.23182 • Published 3 days ago • 18

ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought

Paper • 2601.23184 • Published 3 days ago • 12