Taekyung Ki

taekyungki's activity

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

upvoted a paper 3 days ago

MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs

Paper • 2606.30026 • Published 15 days ago • 6

upvoted a paper 23 days ago

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

Paper • 2606.19531 • Published 27 days ago • 22

upvoted a paper 27 days ago

JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence

Paper • 2606.14777 • Published Jun 10 • 211

upvoted 7 papers about 1 month ago

Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization

Paper • 2606.11180 • Published Jun 9 • 36

Latent Spatial Memory for Video World Models

Paper • 2606.09828 • Published Jun 8 • 71

VideoMDM: Towards 3D Human Motion Generation From 2D Supervision

Paper • 2606.13364 • Published Jun 11 • 20

Flash-WAM: Modality-Aware Distillation for World Action Models

Paper • 2606.05254 • Published Jun 3 • 7

World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis

Paper • 2606.05979 • Published Jun 4 • 9

TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

Paper • 2606.04743 • Published Jun 3 • 47

HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents

Paper • 2605.17873 • Published May 18 • 12

upvoted 7 papers about 2 months ago

OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources

Paper • 2605.29250 • Published May 28 • 80

Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents

Paper • 2605.28775 • Published May 27 • 38

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Paper • 2605.28774 • Published May 27 • 93

TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction

Paper • 2605.26115 • Published May 25 • 52

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

Paper • 2605.27365 • Published May 26 • 145

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

Paper • 2605.20258 • Published May 18 • 30

Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR

Paper • 2605.15726 • Published May 15 • 35

upvoted 3 papers 2 months ago

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

Paper • 2605.09063 • Published May 9 • 82

CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models

Paper • 2605.08735 • Published May 9 • 71

Representation Fréchet Loss for Visual Generation

Paper • 2604.28190 • Published Apr 30 • 32