Zhiyuan Li
- Papers
- 10
Cite
Notes
Only stored in your browser.
Authored papers
10PersonaLive! Expressive Portrait Image Animation for Live Streaming
arXiv 2025
UWSAM: Segment Anything Model Guided Underwater Instance Segmentation and A Large-scale Benchmark Dataset
arXiv 2025
Megrez-Omni Technical Report
arXiv 2025
Kimi Linear: An Expressive, Efficient Attention Architecture
arXiv 2025
RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion
arXiv 2024
On-Device Language Models: A Comprehensive Review
arXiv 2024
A Survey of RWKV
arXiv 2024
Multimodal Causal Reasoning Benchmark: Challenging Vision Large Language Models to Infer Causal Links Between Siamese Images
arXiv 2024
Adam Exploits $\ell_\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity
arXiv 2024
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
arXiv 2023
Affiliations
Frequent co-authors
10from 10 papers