Junhan ZHU

Alrightlone's activity

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

upvoted a paper about 21 hours ago

DMax: Aggressive Parallel Decoding for dLLMs

Paper • 2604.08302 • Published 2 days ago • 29

upvoted a paper 1 day ago

INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling

Paper • 2604.07209 • Published 3 days ago • 26

upvoted a paper 4 days ago

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published 5 days ago • 98

upvoted a paper 5 days ago

Token Warping Helps MLLMs Look from Nearby Viewpoints

Paper • 2604.02870 • Published 8 days ago • 30

updated a model 9 days ago

Alrightlone/minimind-63M-full-sft-Junhan

Text Generation • 63.9M • Updated 9 days ago • 317

published a model 9 days ago

Alrightlone/minimind-63M-full-sft-Junhan

Text Generation • 63.9M • Updated 9 days ago • 317

upvoted a paper 9 days ago

HippoCamp: Benchmarking Contextual Agents on Personal Computers

Paper • 2604.01221 • Published 10 days ago • 27

upvoted an article 14 days ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

Mar 5

•

109

upvoted a paper 18 days ago

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Paper • 2603.19312 • Published 28 days ago • 24

liked a dataset 22 days ago

KD-TAO/LVOmniBench

Updated 8 days ago • 1.62k • 8

upvoted a paper 22 days ago

LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs

Paper • 2603.19217 • Published 23 days ago • 28

upvoted 4 papers 24 days ago

When Does Sparsity Mitigate the Curse of Depth in LLMs

Paper • 2603.15389 • Published 26 days ago • 5

Attention Residuals

Paper • 2603.15031 • Published 26 days ago • 178

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

Paper • 2603.15612 • Published 26 days ago • 152

Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation

Paper • 2603.16669 • Published 25 days ago • 70

upvoted a paper 28 days ago

Flash-KMeans: Fast and Memory-Efficient Exact K-Means

Paper • 2603.09229 • Published Mar 10 • 82

upvoted a collection about 1 month ago

DICE

Collection

A series of diffusion language models tailored for CUDA kernel generation. • 4 items • Updated Feb 13 • 3

upvoted a paper about 1 month ago

The Trinity of Consistency as a Defining Principle for General World Models

Paper • 2602.23152 • Published Feb 26 • 201

liked a model about 2 months ago

microsoft/TRELLIS.2-4B

Image-to-3D • Updated Dec 27, 2025 • 746

upvoted a paper about 2 months ago

dVoting: Fast Voting for dLLMs

Paper • 2602.12153 • Published Feb 12 • 22