euclaise

euclaise's activity

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

upvoted 3 papers 4 days ago

Online Vector Quantized Attention

Paper • 2602.03922 • Published 29 days ago • 1

Softmax Linear Attention: Reclaiming Global Competition

Paper • 2602.01744 • Published about 1 month ago • 1

Test-Time Training with KV Binding Is Secretly Linear Attention

Paper • 2602.21204 • Published 8 days ago • 29

upvoted 3 papers 7 days ago

On the "Induction Bias" in Sequence Models

Paper • 2602.18333 • Published 12 days ago • 4

Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking

Paper • 2602.21196 • Published 8 days ago • 3

One-step Language Modeling via Continuous Denoising

Paper • 2602.16813 • Published 14 days ago • 4

upvoted an article 10 days ago

view article

Article

Differential Transformer V2

• 

Jan 20

•

42

upvoted a paper 11 days ago

2Mamba2Furious: Linear in Complexity, Competitive in Accuracy

Paper • 2602.17363 • Published 13 days ago • 7

upvoted 3 papers 12 days ago

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

Paper • 2602.13367 • Published 19 days ago • 31

On Surprising Effectiveness of Masking Updates in Adaptive Optimizers

Paper • 2602.15322 • Published 16 days ago • 9

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

Paper • 2602.13515 • Published 19 days ago • 43

upvoted 4 papers 19 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 23 days ago • 10

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

Paper • 2602.10560 • Published 21 days ago • 29

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

Paper • 2602.12036 • Published 20 days ago • 93

upvoted 2 papers 21 days ago

Prism: Spectral-Aware Block-Sparse Attention

Paper • 2602.08426 • Published 23 days ago • 36

iGRPO: Self-Feedback-Driven LLM Reasoning

Paper • 2602.09000 • Published 23 days ago • 16

upvoted a paper 29 days ago

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

Paper • 2602.01058 • Published Feb 1 • 41

upvoted 2 papers about 1 month ago

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

Paper • 2601.22156 • Published Jan 29 • 13

Discovering Hidden Gems in Model Repositories

Paper • 2601.22157 • Published Jan 29 • 22