Xiaoji Zheng

Student-Xiaoji's activity

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

upvoted a paper 1 day ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Paper • 2601.05242 • Published 3 days ago • 130

upvoted a paper 3 days ago

Choreographing a World of Dynamic Objects

Paper • 2601.04194 • Published 4 days ago • 12

upvoted 2 papers 4 days ago

NitroGen: An Open Foundation Model for Generalist Gaming Agents

Paper • 2601.02427 • Published 7 days ago • 35

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published 5 days ago • 87

upvoted a paper 5 days ago

NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

Paper • 2601.00393 • Published 10 days ago • 109

upvoted 3 papers 9 days ago

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation

Paper • 2512.24551 • Published 12 days ago • 18

GR-Dexter Technical Report

Paper • 2512.24210 • Published 12 days ago • 21

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published 11 days ago • 236

upvoted 2 papers 17 days ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published 24 days ago • 93

DreaMontage: Arbitrary Frame-Guided One-Shot Video Generation

Paper • 2512.21252 • Published 18 days ago • 34

upvoted 2 papers 18 days ago

StoryMem: Multi-shot Long Video Storytelling with Memory

Paper • 2512.19539 • Published 20 days ago • 17

LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry

Paper • 2512.19629 • Published 20 days ago • 25

upvoted 3 papers 19 days ago

An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges

Paper • 2512.11362 • Published about 1 month ago • 21

Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience

Paper • 2512.17260 • Published 23 days ago • 48

PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence

Paper • 2512.16793 • Published 24 days ago • 72

upvoted 5 papers 22 days ago

Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

Paper • 2512.16912 • Published 24 days ago • 10

JustRL: Scaling a 1.5B LLM with a Simple RL Recipe

Paper • 2512.16649 • Published 24 days ago • 24

The World is Your Canvas: Painting Promptable Events with Reference Images, Trajectories, and Text

Paper • 2512.16924 • Published 24 days ago • 25

Next-Embedding Prediction Makes Strong Vision Learners

Paper • 2512.16922 • Published 24 days ago • 83

LLaDA2.0: Scaling Up Diffusion Language Models to 100B

Paper • 2512.15745 • Published Dec 10, 2025 • 78