Li Huanxing

lihuanxing's activity

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

upvoted a paper about 5 hours ago

Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation

Paper • 2610.30926 • Published 4 days ago • 189

upvoted 3 papers 1 day ago

DLite: History-free Speculative Decoding for Agentic AI

Paper • 2610.23787 • Published 10 days ago • 36

MemT-1.0: Towards Memory-Native Evolution

Paper • 2610.26825 • Published 7 days ago • 180

SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?

Paper • 2610.26659 • Published 7 days ago • 170

upvoted a paper 3 days ago

Cache Engineering for Agents

Paper • 2610.28577 • Published 6 days ago • 159

upvoted a paper 4 days ago

Co-Evolving Acting and Forecasting for Language Agents

Paper • 2610.20597 • Published 11 days ago • 15

upvoted a paper 5 days ago

Into the Unknown: Benchmarking AI agents on open scientific research problems

Paper • 2610.19159 • Published 13 days ago • 160

upvoted 2 papers 6 days ago

Velox: Spatial Memory Makes World Models Efficient

Paper • 2610.22311 • Published 11 days ago • 39

Virtual Head Attention

Paper • 2610.17959 • Published 13 days ago • 25

upvoted a paper 9 days ago

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

Paper • 2609.38169 • Published 27 days ago • 156

upvoted a paper 10 days ago

Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence

Paper • 2610.17656 • Published 13 days ago • 29

upvoted a paper 11 days ago

Multi-Stream Attention Residuals

Paper • 2610.13630 • Published 17 days ago • 52

upvoted 2 papers 12 days ago

One Model to Loop Them All: Elastic Latent Recurrence for Language Models

Paper • 2610.12582 • Published 18 days ago • 19

Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models

Paper • 2610.08966 • Published 18 days ago • 27

upvoted a paper 14 days ago

RunningTab: Direct Workspace Interaction with Environment-Side Tabs

Paper • 2610.10444 • Published 19 days ago • 44

upvoted 3 papers 16 days ago

Towards Looped Models Done Right, Part II: Rethinking at Fixed Points

Paper • 2610.06833 • Published 21 days ago • 36

Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs

Paper • 2609.32259 • Published 27 days ago • 104

Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment

Paper • 2609.38972 • Published 26 days ago • 30

upvoted 2 papers 17 days ago

Learning Functional Subspaces for Neural Network Compression

Paper • 2609.40127 • Published 26 days ago • 26

SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving

Paper • 2609.34117 • Published 28 days ago • 25