GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
Paper • 2609.24981 • Published • 78
Luo Zhang
Azhangluo77
AI & ML interests
Vision Language Model; MOE; RL
Recent Activity
upvoted a paper 28 days ago
GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation liked a Space 28 days ago
hugging-apps/qwen-image-2-1Organizations
None yet
upvoted 11
papers 28 days ago
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
Paper • 2609.26796 • Published • 37
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Paper • 2609.24972 • Published • 221
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling
Paper • 2609.19499 • Published • 37
What Does Privileged Information Add to On-Policy Self-Distillation?
Paper • 2609.20612 • Published • 36
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
Paper • 2609.20744 • Published • 54
JEPA-Anything: Learning Predictive Models across Different Worlds
Paper • 2609.20800 • Published • 79
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
Paper • 2609.20511 • Published • 143
Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model
Paper • 2609.18323 • Published • 116
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
Paper • 2609.20519 • Published • 142
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
Paper • 2609.19969 • Published • 231
upvoted an article 28 days ago
Article
Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community
- +3
pcuenq, lysandre, victor, julien-c, Jundot
• • 98 upvoted 3
papers over 1 year ago
Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents
Paper • 2505.24878 • Published • 23
Vision Language Models are Biased
Paper • 2505.23941 • Published • 23
Time Blindness: Why Video-Language Models Can't See What Humans Can?
Paper • 2505.24867 • Published • 82