Seojun Baek

seojunb's activity

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

upvoted 2 papers about 15 hours ago

WorldLine: Action-Driven Visual Simulation for Robotic Manipulation

Paper • 2609.38059 • Published 4 days ago • 24

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

Paper • 2609.34309 • Published 5 days ago • 400

upvoted 3 papers about 16 hours ago

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

Paper • 2609.37969 • Published 4 days ago • 34

LongLive-Plug: Once-for-All Distillation for Video Generation

Paper • 2609.38154 • Published 4 days ago • 34

VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models

Paper • 2609.32607 • Published 7 days ago • 144

upvoted 2 papers 2 days ago

VideoPhysEdit: Physical Counterfactual Video Editing via Rigid-Body Physical Scene Reconstruction

Paper • 2609.35134 • Published 5 days ago • 19

SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning

Paper • 2609.33616 • Published 6 days ago • 25

upvoted a paper 3 days ago

TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent

Paper • 2609.27277 • Published 10 days ago • 32

upvoted 4 papers 4 days ago

ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation

Paper • 2609.28923 • Published 9 days ago • 10

AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation

Paper • 2609.29816 • Published 9 days ago • 12

Training Object Permanence in World Models

Paper • 2609.28654 • Published 10 days ago • 240

WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation

Paper • 2609.30221 • Published 9 days ago • 46

upvoted 4 papers 5 days ago

RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling

Paper • 2609.22947 • Published 14 days ago • 42

All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation

Paper • 2609.27901 • Published 10 days ago • 22

The Past Frames the Future: Memory for Autoregressive Video Generation

Paper • 2609.28466 • Published 10 days ago • 64

MemoryAthena: Adaptive Routing over Latent and Generated Memories

Paper • 2609.25853 • Published 11 days ago • 12

upvoted 4 papers 6 days ago

Streaming Video Editing with Easy Adaptation

Paper • 2609.24788 • Published 12 days ago • 15

OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation

Paper • 2609.22069 • Published 15 days ago • 37

VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention

Paper • 2609.15810 • Published 19 days ago • 51

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

Paper • 2609.21465 • Published 15 days ago • 150