Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
Paper • 2608.30821 • Published • 122
dooho lee
BlueYellowGreen
AI & ML interests
None yet
Recent Activity
upvoted a paper 9 days ago
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling upvoted a paper 9 days ago
Language Models Can Control Their Own Attention upvoted a paper 9 days ago
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?Organizations
None yet
upvoted 6
papers 9 days ago
Language Models Can Control Their Own Attention
Paper • 2609.02737 • Published • 75
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Paper • 2609.01437 • Published • 269
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Paper • 2609.02749 • Published • 555
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Paper • 2609.04148 • Published • 295
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
Paper • 2609.04199 • Published • 385
upvoted 4
articles 10 days ago
Article
NeoMME: an efficient Multimodal-native and Multilingual Encoder
Hcompany
• • 103 Article
Training a coding model to paint watercolours with TRL and OpenEnv
sergiopaniego
• • 68 Article
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
- +1
iamleonie, burtenshaw, sergiopaniego
• • 117 Article
Open Yap 1K: 1,000 hours of full-duplex natural conversation, free for commercial use
TheAgenticDataCompany
• • 13 upvoted 4
papers 15 days ago
On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability
Paper • 2608.30320 • Published • 59
Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement
Paper • 2608.31046 • Published • 157
StudentSim: Training LLM-based Student Simulators
Paper • 2609.01591 • Published • 493
DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution
Paper • 2608.31106 • Published • 102
upvoted a paper 24 days ago
upvoted 5
papers about 1 month ago
MiniMind-O Technical Report: An Open Small-Scale Speech-Native Omni Model
Paper • 2605.03937 • Published • 4
Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models
Paper • 2606.25041 • Published • 125
Agentic Abstention: Do Agents Know When to Stop Instead of Act?
Paper • 2606.28733 • Published • 152
DOPD: Dual On-policy Distillation
Paper • 2606.30626 • Published • 117
Dockerless: Environment-Free Program Verifier for Coding Agents
Paper • 2606.28436 • Published • 118