Stoney Kang

sikang99's activity

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

upvoted 2 papers about 9 hours ago

Generative Visual Code Mobile World Models

Paper • 2602.01576 • Published 2 days ago • 27

Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

Paper • 2602.00919 • Published 4 days ago • 188

upvoted a collection 1 day ago

Open-AgentRL

Collection

RLAnything & DemyAgent: Open-Source RL for LLMs and Agentic Scenarios • 12 items • Updated 1 day ago • 5

upvoted 3 papers 1 day ago

RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System

Paper • 2602.02488 • Published 2 days ago • 27

Causal World Modeling for Robot Control

Paper • 2601.21998 • Published 6 days ago • 27

PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction

Paper • 2601.22046 • Published 6 days ago • 21

upvoted 4 papers 2 days ago

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published 5 days ago • 73

DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation

Paper • 2601.22904 • Published 5 days ago • 11

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment

Paper • 2601.20218 • Published 7 days ago • 15

PaperBanana: Automating Academic Illustration for AI Scientists

Paper • 2601.23265 • Published 5 days ago • 84

upvoted 2 collections 4 days ago

RADIO

Collection

A collection of Foundation Vision Models that combine multiple models (CLIP, DINOv2, SAM, etc.). • 18 items • Updated 6 days ago • 29

Open Coding Agents

Collection

11 items • Updated 1 day ago • 40

upvoted 6 papers 5 days ago

MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources

Paper • 2601.22054 • Published 6 days ago • 5

Self-Improving Pretraining: using post-trained models to pretrain better models

Paper • 2601.21343 • Published 6 days ago • 14

DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents

Paper • 2601.20975 • Published 7 days ago • 9

Qwen3-ASR Technical Report

Paper • 2601.21337 • Published 6 days ago • 30

DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation

Paper • 2601.22153 • Published 6 days ago • 68

Advancing Open-source World Models

Paper • 2601.20540 • Published 7 days ago • 111

upvoted 2 papers 6 days ago

Linear representations in language models can change dramatically over a conversation

Paper • 2601.20834 • Published 7 days ago • 21

SERA: Soft-Verified Efficient Repository Agents

Paper • 2601.20789 • Published 7 days ago • 11