Ji Xie PRO

sanaka87's activity

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

upvoted a paper 2 days ago

Execution Before Memory: Diagnosing Memory Failures in Video World Models

Paper • 2610.23542 • Published 6 days ago • 33

upvoted a paper 6 days ago

WorldCast: Exploring Intelligent Visual Generation in World State Prediction

Paper • 2610.20731 • Published 8 days ago • 38

upvoted a paper 15 days ago

EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation

Paper • 2610.07969 • Published 16 days ago • 22

upvoted a paper 20 days ago

Hierarchical Continuous Diffusion Language Models

Paper • 2610.02193 • Published 21 days ago • 92

upvoted a paper 21 days ago

ThinkV2V: Unleashing the Reasoning Capability of MLLMs for Instruction-Guided Video Editing

Paper • 2609.38541 • Published 23 days ago • 33

upvoted 3 papers 22 days ago

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

Paper • 2609.38155 • Published 23 days ago • 116

OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?

Paper • 2609.38079 • Published 23 days ago • 57

Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning

Paper • 2609.35767 • Published 24 days ago • 50

upvoted a paper 23 days ago

TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces

Paper • 2609.33295 • Published 25 days ago • 72

upvoted a collection 23 days ago

OmniTaskonomy

Collection

OmniTaskonomy probes when generation helps understanding. Check our project page here: https://omni-taskonomy.github.io/ • 3 items • Updated 22 days ago • 2

upvoted a paper 28 days ago

PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing

Paper • 2609.23784 • Published Sep 20 • 16

upvoted a paper 29 days ago

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

Paper • 2609.24984 • Published about 1 month ago • 161

upvoted 3 papers about 1 month ago

OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation

Paper • 2609.22069 • Published Sep 18 • 38

L2P: Unlocking Latent Potential for Pixel Generation

Paper • 2605.12013 • Published May 12 • 37

Paint-Anything: Unified Any-Color Control for Image Generation and Editing

Paper • 2609.20816 • Published Sep 17 • 57

upvoted a paper 3 months ago

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Paper • 2607.27380 • Published Jul 29 • 60

upvoted a paper 4 months ago

Echo-Memory: A Controlled Study of Memory in Action World Models

Paper • 2606.09803 • Published Jun 8 • 33

upvoted 3 papers 6 months ago

ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents

Paper • 2604.23781 • Published Apr 26 • 34

UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models

Paper • 2604.17565 • Published Apr 19 • 10

RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details

Paper • 2604.06870 • Published Apr 8 • 44