Jade

euclaise's activity

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

upvoted 4 papers 2 days ago

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

Paper • 2506.05209 • Published 21 days ago • 41

Play to Generalize: Learning to Reason Through Game Play

Paper • 2506.08011 • Published 17 days ago • 15

ReDit: Reward Dithering for Improved LLM Policy Optimization

Paper • 2506.18631 • Published 3 days ago • 7

SeqPE: Transformer with Sequential Position Encoding

Paper • 2506.13277 • Published 10 days ago • 5

upvoted 7 papers 9 days ago

Through the Valley: Path to Effective Long CoT Training for Small Language Models

Paper • 2506.07712 • Published 17 days ago • 18

Reinforcement Pre-Training

Paper • 2506.08007 • Published 17 days ago • 230

Institutional Books 1.0: A 242B token dataset from Harvard Library's collections, refined for accuracy and usability

Paper • 2506.08300 • Published 17 days ago • 8

Comment on The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity

Paper • 2506.09250 • Published 16 days ago • 27

BOW: Bottlenecked Next Word Exploration

Paper • 2506.13502 • Published 10 days ago • 2

A Technical Study into Small Reasoning Language Models

Paper • 2506.13404 • Published 10 days ago • 9

Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency

Paper • 2506.08343 • Published 17 days ago • 46

upvoted 3 papers 19 days ago

Frankentext: Stitching random text fragments into long-form narratives

Paper • 2505.18128 • Published May 23 • 3

SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models

Paper • 2506.04180 • Published 22 days ago • 32

OpenThoughts: Data Recipes for Reasoning Models

Paper • 2506.04178 • Published 22 days ago • 41

upvoted 6 papers 27 days ago

How new data permeates LLM knowledge and how to dilute it

Paper • 2504.09522 • Published Apr 13 • 8

BLEUBERI: BLEU is a surprisingly effective reward for instruction following

Paper • 2505.11080 • Published May 16 • 5

Text Generation Beyond Discrete Token Sampling

Paper • 2505.14827 • Published May 20 • 10

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space

Paper • 2505.15778 • Published May 21 • 17

Hybrid Latent Reasoning via Reinforcement Learning

Paper • 2505.18454 • Published May 24 • 5

HoPE: Hybrid of Position Embedding for Length Generalization in Vision-Language Models

Paper • 2505.20444 • Published May 26 • 3