Junhan ZHU

Alrightlone's activity

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

upvoted a paper about 24 hours ago

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

Paper • 2603.19217 • Published 1 day ago • 26

upvoted 4 papers 3 days ago

When Does Sparsity Mitigate the Curse of Depth in LLMs

Paper • 2603.15389 • Published 5 days ago • 5

Attention Residuals

Paper • 2603.15031 • Published 5 days ago • 127

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

Paper • 2603.15612 • Published 5 days ago • 145

Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation

Paper • 2603.16669 • Published 4 days ago • 68

upvoted a paper 7 days ago

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

Paper • 2603.09229 • Published 11 days ago • 79

upvoted a collection 17 days ago

DICE

Collection

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

upvoted a paper 22 days ago

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

Paper • 2602.23152 • Published 23 days ago • 198

upvoted a paper about 1 month ago

dVoting: Fast Voting for dLLMs

Paper • 2602.12153 • Published Feb 12 • 21

upvoted a collection about 1 month ago

NEO1_0

Collection

From Pixels to Words -- Towards Native Vision-Language Primitives at Scale • 7 items • Updated Jan 27 • 9

upvoted a collection about 2 months ago

Waypoint-1

Collection

The first real time diffusion world model designed for consumer hardware • 3 items • Updated Jan 30 • 8

upvoted 2 papers 2 months ago

Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights

Paper • 2512.01816 • Published Dec 1, 2025 • 94

Reconstructing 4D Spatial Intelligence: A Survey

Paper • 2507.21045 • Published Jul 28, 2025 • 38

upvoted 7 papers 3 months ago

Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems

Paper • 2512.24385 • Published Dec 30, 2025 • 8

Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation

Paper • 2512.23705 • Published Dec 29, 2025 • 45

OmniAgent: Audio-Guided Active Perception Agent for Omnimodal Audio-Video Understanding

Paper • 2512.23646 • Published Dec 29, 2025 • 15

Autoregressive Image Generation with Randomized Parallel Decoding

Paper • 2503.10568 • Published Mar 13, 2025 • 9

Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View

Paper • 2503.12553 • Published Mar 16, 2025 • 8

Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps

Paper • 2505.18675 • Published May 24, 2025 • 26

DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models

Paper • 2411.15024 • Published Nov 22, 2024 • 2