Article
🚀 DTS: A Candidate for the Best Parallel Reasoning in LLMs
•
13
dooho lee
BlueYellowGreen
AI & ML interests
None yet
Recent Activity
upvoted
an
article
about 18 hours ago
🚀 DTS: A Candidate for the Best Parallel Reasoning in LLMs
upvoted
a
paper
about 18 hours ago
LLaDA2.1: Speeding Up Text Diffusion via Token Editing
upvoted
a
paper
about 18 hours ago
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
Organizations
None yet
upvoted
an
article
about 18 hours ago
upvoted
4
papers
about 18 hours ago
LLaDA2.1: Speeding Up Text Diffusion via Token Editing
Paper
•
2602.08676
•
Published
•
58
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
Paper
•
2602.05400
•
Published
•
295
When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning
Paper
•
2602.10560
•
Published
•
22
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Paper
•
2602.10604
•
Published
•
147
upvoted
5
articles
1 day ago
Article
Performant local mixture-of-experts CPU inference with GPU acceleration in llama.cpp
•
10
Article
Fine-Tuning FunctionGemma on TPU to Create a Virtual Fitness Coach in 10 Minutes, $0.50
•
13
Article
CRAFT: Continuous Reasoning and Agentic Feedback Tuning
•
66
Article
From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output
•
18
Article
Training Qwen3 VL to label bbox : synthetic data, environment and training analysis
•
5
upvoted
4
papers
2 days ago
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
Paper
•
2602.06717
•
Published
•
68
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger
Paper
•
2602.08222
•
Published
•
237
QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining
Paper
•
2602.07085
•
Published
•
178
Covo-Audio Technical Report
Paper
•
2602.09823
•
Published
•
8
upvoted
4
papers
10 days ago
Shaping capabilities with token-level data filtering
Paper
•
2601.21571
•
Published
•
26
ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation
Paper
•
2601.21420
•
Published
•
42
Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives
Paper
•
2601.20833
•
Published
•
175
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
Paper
•
2601.22975
•
Published
•
96
upvoted
2
papers
14 days ago