LatentThinkingPKU

LatentThinking's activity

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

DogNeverSleep 

authored a paper 14 days ago

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

Paper • 2608.04530 • Published 15 days ago • 14

DogNeverSleep 

submitted a paper to Daily Papers 14 days ago

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

Paper • 2608.04530 • Published 15 days ago • 14

DogNeverSleep 

authored a paper 15 days ago

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

Paper • 2608.03812 • Published 16 days ago • 27

DogNeverSleep 

submitted a paper to Daily Papers 15 days ago

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

Paper • 2608.03812 • Published 16 days ago • 27

DogNeverSleep 

authored 3 papers 20 days ago

RefCaptioner: Multi-Reference Image-Grounded Video Captioning

Paper • 2607.28509 • Published 21 days ago • 30

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

Paper • 2607.28595 • Published 21 days ago • 55

Flux-OPD: On-Policy Distillation with Evolving Contexts

Paper • 2607.28022 • Published 21 days ago • 44

DogNeverSleep 

submitted 2 papers to Daily Papers 20 days ago

RefCaptioner: Multi-Reference Image-Grounded Video Captioning

Paper • 2607.28509 • Published 21 days ago • 30

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

Paper • 2607.28595 • Published 21 days ago • 55

THUdyh 

authored 2 papers 22 days ago

PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models

Paper • 2607.24957 • Published 24 days ago • 20

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 24 days ago • 496

DogNeverSleep 

authored 2 papers about 1 month ago

MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation

Paper • 2607.14189 • Published Jul 15 • 34

KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation

Paper • 2607.14202 • Published Jul 15 • 42

THUdyh 

authored a paper about 1 month ago

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Paper • 2607.14935 • Published Jul 16 • 172

DogNeverSleep 

submitted 2 papers to Daily Papers about 1 month ago

MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation

Paper • 2607.14189 • Published Jul 15 • 34

KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation

Paper • 2607.14202 • Published Jul 15 • 42

DogNeverSleep 

authored 2 papers about 2 months ago

CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales

Paper • 2606.21949 • Published Jun 20

DOPD: Dual On-policy Distillation

Paper • 2606.30626 • Published Jun 29 • 114

THUdyh 

authored 2 papers about 2 months ago

Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos

Paper • 2605.18984 • Published May 18 • 22

LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV

Paper • 2605.26244 • Published May 25 • 38