Paul S PRO

SuperPauly's activity

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

upvoted a paper 16 days ago

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

Paper • 2609.09153 • Published 19 days ago • 42

upvoted a paper 28 days ago

Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents

Paper • 2607.08716 • Published Jul 9 • 14

upvoted 2 papers about 1 month ago

Prime Agent: A Self-Improving RLM Harness

Paper • 2608.23552 • Published Aug 24 • 56

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

Paper • 2608.15089 • Published Aug 15 • 448

upvoted 2 papers 3 months ago

Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs

Paper • 2604.00824 • Published Apr 6 • 1

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

Paper • 2607.02512 • Published Jul 2 • 308

upvoted a collection 3 months ago

Android Models

Collection

LiteRT models that can run on Android • 17 items • Updated Jul 26 • 277

upvoted 3 papers 4 months ago

metaTextGrad: Automatically optimizing language model optimizers

Paper • 2505.18524 • Published Oct 22, 2025 • 2

Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills

Paper • 2604.05333 • Published Apr 7 • 22

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Paper • 2605.23904 • Published May 22 • 264

upvoted a paper 5 months ago

DFlash: Block Diffusion for Flash Speculative Decoding

Paper • 2602.06036 • Published Feb 5 • 99

upvoted 2 collections 5 months ago

DFlash

Collection

Block Diffusion for Flash Speculative Decoding • 23 items • Updated 14 days ago • 156

Ternary Bonsai

Collection

1.58-bit Bonsai models • 9 items • Updated Jun 4 • 108

upvoted 4 collections over 1 year ago

Recurrent Models

Collection

These are checkpoints for recurrent LLMs developed to scale test-time compute by recurring in latent space. • 15 items • Updated Feb 25 • 12

LoRI Adapters

Collection

LoRI adapters for natural language understanding, code generation, mathematical reasoning, and safety alignment, based on LLaMA-3-8B and Mistral-7B. • 39 items • Updated Feb 25 • 5

Gemstone Models

Collection

Our 22 open source Gemstone models for scaling laws range from 50M to 2B parameters, spanning 11 widths from 256 to 3072 and 18 depths from 3 to 80. • 66 items • Updated Mar 2 • 11

Tiny Models

Collection

8 items • Updated Apr 7, 2025 • 9

upvoted a paper over 1 year ago

UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Paper • 2501.12326 • Published Jan 21, 2025 • 64