Geuntaek Lim

geuntaek's activity

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

upvoted 2 papers 3 days ago

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

Paper • 2610.27851 • Published 5 days ago • 43

Reading, Writing, Sharing, and Interacting with the World through Video

Paper • 2610.31668 • Published 4 days ago • 8

upvoted 2 papers 10 days ago

DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding

Paper • 2610.19849 • Published 12 days ago • 42

OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding

Paper • 2610.18829 • Published 13 days ago • 747

upvoted a paper 12 days ago

PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos

Paper • 2609.38377 • Published 27 days ago • 15

upvoted a paper 20 days ago

Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers

Paper • 2610.00531 • Published 26 days ago • 63

upvoted a paper 21 days ago

Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It

Paper • 2609.36585 • Published 27 days ago • 42

upvoted a paper 26 days ago

OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?

Paper • 2609.38079 • Published 27 days ago • 57

upvoted a paper 27 days ago

Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge

Paper • 2609.34327 • Published 28 days ago • 41

upvoted a paper 28 days ago

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published Sep 25 • 121

upvoted a paper about 1 month ago

MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads

Paper • 2609.09206 • Published Sep 5 • 11

upvoted 6 papers 3 months ago

ChronoVision: Temporal Reasoning via Latent State Reconstruction

Paper • 2608.05631 • Published Aug 6 • 40

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 537

Self-Supervised Learning of Structured Dynamics from Videos

Paper • 2607.21576 • Published Jul 23 • 21

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

Paper • 2607.17423 • Published Jul 19 • 160

On-Policy Delta Distillation

Paper • 2607.15161 • Published Jul 16 • 38

4D Human-Scene Reconstruction from Low-Overlap Captures

Paper • 2607.09125 • Published Jul 10 • 52

upvoted 3 papers 4 months ago

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

Paper • 2601.16211 • Published Jul 2 • 51

Video-Oasis: Rethinking Evaluation of Video Understanding

Paper • 2603.29616 • Published Jul 2 • 66

Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts

Paper • 2607.00666 • Published Jul 1 • 24