kak

Kaowai's activity

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

upvoted 3 papers 28 days ago

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding

Paper • 2606.02482 • Published 29 days ago • 36

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Paper • 2605.30611 • Published May 28 • 250

Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models

Paper • 2605.28132 • Published May 27 • 25

upvoted 7 papers about 1 month ago

SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation

Paper • 2605.22536 • Published May 21 • 28

WorldKV: Efficient World Memory with World Retrieval and Compression

Paper • 2605.22718 • Published May 21 • 42

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models

Paper • 2605.17672 • Published May 17 • 23

Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use

Paper • 2605.14038 • Published May 13 • 15

Lance: Unified Multimodal Modeling by Multi-Task Synergy

Paper • 2605.18678 • Published May 18 • 79

KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration

Paper • 2605.14278 • Published May 14 • 37

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

Paper • 2605.18739 • Published May 18 • 116

upvoted 4 papers about 2 months ago

Qwen-Image-VAE-2.0 Technical Report

Paper • 2605.13565 • Published May 13 • 62

Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling

Paper • 2605.13062 • Published May 13 • 33

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

Paper • 2605.13779 • Published May 13 • 223

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

Paper • 2605.13724 • Published May 13 • 105

upvoted 4 papers 3 months ago

Qianfan-OCR: A Unified End-to-End Model for Document Intelligence

Paper • 2603.13398 • Published Mar 11 • 155

Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation

Paper • 2603.16669 • Published Mar 17 • 70

Demystifing Video Reasoning

Paper • 2603.16870 • Published Mar 17 • 373

TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas

Paper • 2603.16448 • Published Mar 17 • 58

upvoted 2 papers 4 months ago

Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression

Paper • 2512.05081 • Published Dec 4, 2025 • 33

HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising

Paper • 2603.08703 • Published Mar 9 • 32