Scratch to Scale

scratchtoscale's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

epappas 

authored a paper 16 days ago

What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document

Paper • 2610.04128 • Published 20 days ago • 12

dsouzadaniel 

authored 2 papers about 1 month ago

Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning

Paper • 2609.10445 • Published Sep 9 • 34

The Culture Funnel: You Can't Align What isn't in the Data

Paper • 2606.13808 • Published Jun 11

epappas 

authored 2 papers about 1 month ago

Privacy Failure in Split-LLM Training, The Returned Gradient Nullifies the Decoys

Paper • 2609.04382 • Published Sep 3 • 5

Covenant-72B: Pre-Training a 72B LLM with Trustless Peers Over-the-Internet

Paper • 2603.08163 • Published Mar 9 • 5

eliebak 

authored 2 papers about 2 months ago

Prime Agent: A Self-Improving RLM Harness

Paper • 2608.23552 • Published Aug 24 • 57

How Can We Synthesize High-Quality Pretraining Data? A Systematic Study of Prompt Design, Generator Model, and Source Data

Paper • 2604.13977 • Published Apr 15 • 3

nemocbb 

authored a paper 2 months ago

DCAS: Decoupling CLI Agent Scaffolding to Internalize Planning across Scaffolds

Paper • 2608.06113 • Published Aug 6 • 18

nemocbb 

submitted a paper to Daily Papers 2 months ago

DCAS: Decoupling CLI Agent Scaffolding to Internalize Planning across Scaffolds

Paper • 2608.06113 • Published Aug 6 • 18

nemocbb 

submitted 2 papers to Daily Papers 3 months ago

SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch

Paper • 2607.27167 • Published Jul 29 • 20

MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis

Paper • 2607.27146 • Published Jul 29 • 30

nemocbb 

authored 2 papers 3 months ago

SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch

Paper • 2607.27167 • Published Jul 29 • 20

MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis

Paper • 2607.27146 • Published Jul 29 • 30

woojun-jung 

authored a paper 6 months ago

QEVA: A Reference-Free Evaluation Metric for Narrative Video Summarization with Multimodal Question Answering

Paper • 2604.24052 • Published Apr 27

roeybc 

authored a paper 8 months ago

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Paper • 2602.12670 • Published Feb 13 • 68

chansung 

authored a paper 8 months ago

TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models

Paper • 2602.15449 • Published Feb 17 • 7

chansung 

submitted a paper to Daily Papers 8 months ago

TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models

Paper • 2602.15449 • Published Feb 17 • 7

epappas 

authored a paper 10 months ago

Incentivizing Permissionless Distributed Learning of LLMs

Paper • 2505.21684 • Published May 27, 2025 • 1

eliebak 

submitted a paper to Daily Papers 10 months ago

SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations

Paper • 2512.14080 • Published Dec 16, 2025 • 10

woojun-jung 

authored a paper 10 months ago

Visual Funnel: Resolving Contextual Blindness in Multimodal Large Language Models

Paper • 2512.10362 • Published Dec 11, 2025 • 2