euclaise

euclaise's activity

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

upvoted an article 2 days ago

view article

Article

Differential Transformer V2

• 

Jan 20

•

42

upvoted 4 papers 4 days ago

2Mamba2Furious: Linear in Complexity, Competitive in Accuracy

Paper • 2602.17363 • Published 6 days ago • 7

Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts

Paper • 2602.13367 • Published 12 days ago • 29

On Surprising Effectiveness of Masking Updates in Adaptive Optimizers

Paper • 2602.15322 • Published 8 days ago • 9

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

Paper • 2602.13515 • Published 11 days ago • 42

upvoted 4 papers 11 days ago

Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum

Paper • 2510.00526 • Published Oct 1, 2025 • 10

Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning

Paper • 2602.08382 • Published 16 days ago • 10

When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning

Paper • 2602.10560 • Published 14 days ago • 28

Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models

Paper • 2602.12036 • Published 13 days ago • 96

upvoted 2 papers 13 days ago

Prism: Spectral-Aware Block-Sparse Attention

Paper • 2602.08426 • Published 16 days ago • 35

iGRPO: Self-Feedback-Driven LLM Reasoning

Paper • 2602.09000 • Published 15 days ago • 15

upvoted a paper 21 days ago

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

Paper • 2602.01058 • Published 24 days ago • 41

upvoted 5 papers 23 days ago

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

Paper • 2601.22156 • Published 26 days ago • 13

Discovering Hidden Gems in Model Repositories

Paper • 2601.22157 • Published 26 days ago • 22

iFSQ: Improving FSQ for Image Generation with 1 Line of Code

Paper • 2601.17124 • Published Jan 23 • 33

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

Paper • 2601.21420 • Published 27 days ago • 42

Scaling Embeddings Outperforms Scaling Experts in Language Models

Paper • 2601.21204 • Published 27 days ago • 100

upvoted 3 papers 26 days ago

Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models

Paper • 2601.14152 • Published Jan 20 • 5

The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models

Paper • 2601.15165 • Published Jan 21 • 72

Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers

Paper • 2601.17367 • Published Jan 24 • 33