Xie Jiahui

xiejiahui's activity

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

upvoted 2 papers 4 days ago

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Paper • 2608.16859 • Published 15 days ago • 339

Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models

Paper • 2608.25518 • Published 6 days ago • 187

upvoted a paper 11 days ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 12 days ago • 273

upvoted a paper 20 days ago

The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows

Paper • 2608.06714 • Published 25 days ago • 10

upvoted a paper about 2 months ago

Attending to Multimodal Generation One Token at a Time

Paper • 2607.03738 • Published Jul 4 • 10

upvoted 2 papers 3 months ago

ABot-Earth 0.5: Generative 3D Earth Model

Paper • 2606.09967 • Published Jun 8 • 488

LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents

Paper • 2605.29559 • Published May 28 • 17

upvoted 3 papers 4 months ago

Reinforcing Multimodal Reasoning Against Visual Degradation

Paper • 2605.09262 • Published May 10 • 7

FASH-iCNN: Making Editorial Fashion Identity Inspectable Through Multimodal CNN Probing

Paper • 2604.26186 • Published Apr 29 • 3

Recursive Multi-Agent Systems

Paper • 2604.25917 • Published Apr 28 • 290

upvoted 9 papers 5 months ago

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time

Paper • 2604.11626 • Published Apr 13 • 103

Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models

Paper • 2604.10949 • Published Apr 13 • 40

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Paper • 2604.06628 • Published Apr 8 • 330

An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU

Paper • 2603.16428 • Published Mar 17 • 51

Terminal Agents Suffice for Enterprise Automation

Paper • 2604.00073 • Published Mar 31 • 100

NearID: Identity Representation Learning via Near-identity Distractors

Paper • 2604.01973 • Published Apr 2 • 33

Text Data Integration

Paper • 2603.27055 • Published Mar 28 • 8

Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning

Paper • 2603.22758 • Published Mar 24 • 4

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

Paper • 2603.25716 • Published Mar 26 • 158

upvoted a paper 6 months ago

Demystifing Video Reasoning

Paper • 2603.16870 • Published Mar 17 • 373