J C

dark-pen

·

AI & ML interests

None yet

Recent Activity

liked a model 2 minutes ago

distil-labs/distil-qwen3.5-4b-invoice-decision

liked a model 2 minutes ago

distil-labs/distil-qwen3.5-0.8b-invoice-triage

liked a model 2 minutes ago

distil-labs/distil-qwen3.5-4b-invoice-grounded-decision

View all activity

Organizations

upvoted a paper about 1 hour ago

CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents

Paper • 2603.17829 • Published Mar 18 • 1

upvoted a collection about 1 hour ago

CodeScout

RL-trained code search agents (1.7B, 4B, 14B) that outperform 2–18× larger models using only a Unix terminal. 📄 arxiv.org/abs/2603.17829 • 12 items • Updated Mar 19 • 10

upvoted 2 papers about 2 hours ago

SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features

Paper • 2509.16098 • Published Sep 19, 2025 • 1

Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO

Paper • 2511.13288 • Published Nov 17, 2025 • 20

upvoted a collection about 2 hours ago

UniDoc-RL

4 items • Updated Apr 17 • 1

upvoted 8 papers about 2 hours ago

OBLIQ-IR: Training a Dense Retriever for Oblique Queries

Paper • 2609.29649 • Published 25 days ago • 1

What Makes Interaction Trajectories Effective for Training Terminal Agents?

Paper • 2606.03461 • Published Jun 2 • 4

LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents

Paper • 2608.17393 • Published Aug 18 • 27

SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments

Paper • 2610.12611 • Published 8 days ago • 106

Multi-Stream Attention Residuals

Paper • 2610.13630 • Published 7 days ago • 44

An Empirical Study of Harness Design for Coding Agents

Paper • 2609.20804 • Published 29 days ago • 95

Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method

Paper • 2609.35965 • Published 9 days ago • 12

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published Sep 14 • 106

upvoted an article about 2 hours ago

Article

Detecting Machine-Generated Code: Unveiling Patterns in AI-Generated Programming

YerbaPage

•

Jul 2, 2025

• 3

upvoted a collection about 3 hours ago

UIBK-Embedding-V1

1 item • Updated 5 days ago • 1

upvoted an article about 4 hours ago

Article

Tokenmaxxing BERT: 50x faster tokenization

huggingface

•

about 10 hours ago

• 31

upvoted 2 collections about 4 hours ago

Simulation RL Envs

Real-world work rebuilt as deterministic RL simulations from seed data. Part 1: PortSimEnv v1, berth planning at the Port of Barcelona. • 6 items • Updated 2 days ago • 2

SmolDataEnvs Multi-harness RL

Try the three environments, follow the tutorial, and explore the datasets, models and historical RL/SFT results. • 22 items • Updated 8 days ago • 4

upvoted a paper about 4 hours ago

SemBridge: Language Transfer in Sparse Encoders via Multilingual Semantic Bridges

Paper • 2605.26002 • Published May 25 • 6

upvoted a paper about 5 hours ago

Towards Retrieving Interaction Spaces for Agentic Search

Paper • 2606.06880 • Published Jun 5 • 6