LatentThinkingPKU

LatentThinking's activity

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

DogNeverSleep 

authored a paper about 23 hours ago

Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling

Paper • 2611.04916 • Published 2 days ago • 59

DogNeverSleep 

authored a paper 2 days ago

Reviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning

Paper • 2611.03602 • Published 3 days ago • 26

DogNeverSleep 

authored 4 papers 8 days ago

CodeCap-Bench: Can Code Serve as a Good Video Caption?

Paper • 2610.37341 • Published 9 days ago • 53

PIGEONS: Incremental Long-Video Captioning with Persistent Identity Gallery and Evolving Overarching Narrative Summary

Paper • 2610.16066 • Published 24 days ago

Beyond Zooming: Learning Multi-Tool Visual Reasoning for Ultra-High-Resolution Remote Sensing

Paper • 2607.25993 • Published Jul 28

ReBind: Multi-Reference Video Editing via Structured Instructions with Explicit Reference Relationships

Paper • 2607.14681 • Published Jul 16

DogNeverSleep 

submitted a paper to Daily Papers 8 days ago

CodeCap-Bench: Can Code Serve as a Good Video Caption?

Paper • 2610.37341 • Published 9 days ago • 53

DogNeverSleep 

authored a paper 13 days ago

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

Paper • 2610.30866 • Published 14 days ago • 14

DogNeverSleep 

submitted a paper to Daily Papers 13 days ago

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

Paper • 2610.30866 • Published 14 days ago • 14

DogNeverSleep 

authored 2 papers about 1 month ago

HiRAE: Hierarchical Representation Autoencoding with Residual Budgets

Paper • 2609.37775 • Published Sep 29 • 16

Think Before You Score: Thinking Reward Model for Visual Generation

Paper • 2609.37372 • Published Sep 29 • 58

DogNeverSleep 

submitted 2 papers to Daily Papers about 1 month ago

HiRAE: Hierarchical Representation Autoencoding with Residual Budgets

Paper • 2609.37775 • Published Sep 29 • 16

Think Before You Score: Thinking Reward Model for Visual Generation

Paper • 2609.37372 • Published Sep 29 • 58

DogNeverSleep 

authored a paper 3 months ago

FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory

Paper • 2608.04530 • Published Aug 5 • 10

DogNeverSleep 

submitted a paper to Daily Papers 3 months ago

FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory

Paper • 2608.04530 • Published Aug 5 • 10

DogNeverSleep 

authored a paper 3 months ago

OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models

Paper • 2608.03812 • Published Aug 4 • 18

DogNeverSleep 

submitted a paper to Daily Papers 3 months ago

OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models

Paper • 2608.03812 • Published Aug 4 • 18

DogNeverSleep 

authored 3 papers 3 months ago

RefCaptioner: Multi-Reference Image-Grounded Video Captioning

Paper • 2607.28509 • Published Jul 30 • 29

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

Paper • 2607.28595 • Published Jul 30 • 55

Flux-OPD: On-Policy Distillation with Evolving Contexts

Paper • 2607.28022 • Published Jul 30 • 45