Open to Collab

Zhenglin Cheng (SII) PRO

kenshinn

AI & ML interests

SII is an institution dedicated to innovation in education and research in the field of Al. Zhenglin Cheng is a part of SII, focusing on unified multimodal models and few-step generation.

Recent Activity

upvoted a paper 1 day ago

Self-Adversarial One Step Generation via Condition Shifting

upvoted a paper 3 days ago

Structured Causal Video Reasoning via Multi-Objective Alignment

upvoted a paper 8 days ago

Memory Intelligence Agent

View all activity

Organizations

upvoted a paper 1 day ago

Self-Adversarial One Step Generation via Condition Shifting

Paper • 2604.12322 • Published 2 days ago • 12

upvoted a paper 3 days ago

Structured Causal Video Reasoning via Multi-Objective Alignment

Paper • 2604.04415 • Published 10 days ago • 9

upvoted a paper 8 days ago

Memory Intelligence Agent

Paper • 2604.04503 • Published 10 days ago • 56

upvoted a paper 29 days ago

Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training

Paper • 2603.16139 • Published about 1 month ago • 32

upvoted a paper about 1 month ago

Mode Seeking meets Mean Seeking for Fast Long Video Generation

Paper • 2602.24289 • Published Feb 27 • 41

upvoted a paper about 2 months ago

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published Feb 23 • 519

upvoted 2 papers 2 months ago

DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Paper • 2602.12205 • Published Feb 12 • 81

UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

Paper • 2602.02437 • Published Feb 2 • 80

upvoted a collection 4 months ago

TwinFlow

Collection

A collection of TwinFlow-accelerated diffusion models • 4 items • Updated 22 days ago • 6

upvoted a paper 4 months ago

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Paper • 2512.05150 • Published Dec 3, 2025 • 76

upvoted a paper 6 months ago

UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation

Paper • 2510.18701 • Published Oct 21, 2025 • 68

upvoted 2 papers 10 months ago

LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs

Paper • 2506.14429 • Published Jun 17, 2025 • 44

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better

Paper • 2506.09040 • Published Jun 10, 2025 • 34

upvoted a paper 11 months ago

Unified Continuous Generative Models

Paper • 2505.07447 • Published May 12, 2025 • 42

upvoted a paper 12 months ago

Packing Input Frame Context in Next-Frame Prediction Models for Video Generation

Paper • 2504.12626 • Published Apr 17, 2025 • 51

upvoted a paper about 1 year ago

Unified Reward Model for Multimodal Understanding and Generation

Paper • 2503.05236 • Published Mar 7, 2025 • 124

upvoted 4 papers over 1 year ago

GPT-4o System Card

Paper • 2410.21276 • Published Oct 25, 2024 • 87

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Paper • 2410.13848 • Published Oct 17, 2024 • 36

Baichuan-Omni Technical Report

Paper • 2410.08565 • Published Oct 11, 2024 • 87

B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests

Paper • 2409.08692 • Published Sep 13, 2024 • 27

Zhenglin Cheng (SII) PRO

AI & ML interests

Recent Activity

Organizations

kenshinn's activity