Yi Jung

YJ-142150's activity

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

upvoted 3 papers about 10 hours ago

Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction

Paper • 2610.12299 • Published 1 day ago • 40

In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks

Paper • 2609.38173 • Published 11 days ago • 41

AgentGarten: Code Worlds for Evolving Agents

Paper • 2610.12374 • Published 1 day ago • 128

upvoted 4 papers 1 day ago

WorldSonus: Bringing Sound to Worlds

Paper • 2610.08760 • Published 4 days ago • 33

DecepEval: A Benchmark for Evaluating Deception in LLM Agents

Paper • 2610.07967 • Published 4 days ago • 48

Tetris3D: 3D Scene Generation With Objects That Fit Together

Paper • 2610.10539 • Published 3 days ago • 44

GRACE: Generation-aware latent compression for efficient video generation

Paper • 2610.10524 • Published 3 days ago • 75

upvoted 2 papers 7 days ago

ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization

Paper • 2610.00906 • Published 9 days ago • 83

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 9 days ago • 105

upvoted 6 papers 8 days ago

World Observer: Joint Actor-Observer Generation for Persistent World Modeling

Paper • 2610.02162 • Published 9 days ago • 88

More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models

Paper • 2609.38827 • Published 10 days ago • 61

EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery

Paper • 2609.40340 • Published 10 days ago • 111

Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering

Paper • 2609.38177 • Published 11 days ago • 73

Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training

Paper • 2609.40111 • Published 10 days ago • 51

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published 10 days ago • 119

upvoted 5 papers 9 days ago

WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms

Paper • 2609.38121 • Published 11 days ago • 26

SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video

Paper • 2609.37969 • Published 11 days ago • 43

Raven: The Harness of Harnesses for Composable Agentic Intelligence

Paper • 2609.33439 • Published 13 days ago • 672

VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models

Paper • 2609.32607 • Published 14 days ago • 134

MaLiang-Harness: A Programmable Path to Image and Video Generation

Paper • 2609.34309 • Published 12 days ago • 341