Yuhang Zang PRO

yuhangzang's activity

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

upvoted a paper 1 day ago

FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation

Paper • 2601.23182 • Published 4 days ago • 18

upvoted a collection 2 days ago

UnifiedReward Flex

Collection

7 items • Updated about 16 hours ago • 3

upvoted a collection 15 days ago

LightOnOCR-2 🦉

Collection

LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family • 12 items • Updated 13 days ago • 20

upvoted a collection about 1 month ago

RoPE++

Collection

19 items • Updated Dec 9, 2025 • 2

upvoted a paper about 2 months ago

Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs

Paper • 2512.07525 • Published Dec 8, 2025 • 59

upvoted 3 papers 2 months ago

ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning

Paper • 2512.05111 • Published Dec 4, 2025 • 49

ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation

Paper • 2512.03036 • Published Dec 2, 2025 • 22

Think Visually, Reason Textually: Vision-Language Synergy in ARC

Paper • 2511.15703 • Published Nov 19, 2025 • 9

upvoted 3 papers 3 months ago

Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning

Paper • 2510.27606 • Published Oct 31, 2025 • 29

STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence

Paper • 2510.24693 • Published Oct 28, 2025 • 19

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

Paper • 2510.18701 • Published Oct 21, 2025 • 67

upvoted 5 papers 4 months ago

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

Paper • 2510.08673 • Published Oct 9, 2025 • 126

G^2RPO: Granular GRPO for Precise Reward in Flow Models

Paper • 2510.01982 • Published Oct 2, 2025 • 7

SPARK: Synergistic Policy And Reward Co-Evolving Framework

Paper • 2509.22624 • Published Sep 26, 2025 • 18

CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning

Paper • 2509.22647 • Published Sep 26, 2025 • 33

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Paper • 2509.22186 • Published Sep 26, 2025 • 143

upvoted 3 collections 4 months ago

CapRL

Collection

Data & Models for CapRL1.0 series &2.0 series • 10 items • Updated Dec 25, 2025 • 6

Spark-Collection

Collection

Spark-Collection • 2 items • Updated Sep 29, 2025 • 2

SIM-CoT: Supervised Implicit Chain-of-Thought

Collection

Official checkpoint repository of "SIM-CoT: Supervised Implicit Chain-of-Thought" • 6 items • Updated Sep 28, 2025 • 2

upvoted a paper 4 months ago

SIM-CoT: Supervised Implicit Chain-of-Thought

Paper • 2509.20317 • Published Sep 24, 2025 • 42