Seojun Baek

seojunb's activity

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

upvoted 8 papers about 20 hours ago

RynnWorld-Latent: A Cross-Embodiment World Model Conditioned on Universal Latent Actions

Paper • 2610.36791 • Published 6 days ago • 12

OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images

Paper • 2610.35684 • Published 7 days ago • 121

LaLa-World: Scaling Latent World Models with Natural Language Actions

Paper • 2610.27851 • Published 12 days ago • 51

VibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation

Paper • 2610.35864 • Published 6 days ago • 20

RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation

Paper • 2610.27782 • Published 13 days ago • 10

AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark

Paper • 2610.31466 • Published 11 days ago • 19

PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations

Paper • 2610.37381 • Published 6 days ago • 156

Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes

Paper • 2610.32749 • Published 10 days ago • 124

upvoted a paper 3 days ago

SearchHorizonBench: A Benchmark for Search Value in AI Agents

Paper • 2610.34714 • Published 7 days ago • 12

upvoted 4 papers 4 days ago

More Memory, Better Videos? A Controlled Study of Visual Memory in Long-Video Generation

Paper • 2610.35001 • Published 7 days ago • 20

WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control

Paper • 2610.33135 • Published 10 days ago • 51

CausalAlign: Causal Alignment of Video Generation Models for Consistent Ego-Motion

Paper • 2610.29915 • Published 12 days ago • 18

AV-FABLE: Audio-Visual Manipulation Forensics in Long-Form Videos

Paper • 2610.33413 • Published 9 days ago • 45

upvoted 2 papers 5 days ago

RynnUnify: Towards Unified Embodied Brain

Paper • 2610.32965 • Published 10 days ago • 56

FLOMSS: Generative Music Source Separation by Flow Matching

Paper • 2610.17821 • Published 19 days ago • 14

upvoted 5 papers 6 days ago

Self-Distilling Future Video Representations for World Action Models

Paper • 2610.30320 • Published 12 days ago • 48

Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos

Paper • 2610.30866 • Published 11 days ago • 18

Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V

Paper • 2610.28416 • Published 13 days ago • 41

Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation

Paper • 2610.30926 • Published 10 days ago • 51

Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation

Paper • 2610.31305 • Published 11 days ago • 22