Xianghao Kong

refkxh's activity

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

upvoted a collection 3 days ago

SolarWM

Collection

Family-specific checkpoints, released data, and paper for SolarWM long-horizon interactive video world models. • 7 items • Updated 11 days ago • 10

liked a model 3 days ago

junchaoh-cs/SolarWM-H3-33B

Updated 2 days ago • 10

authored a paper 12 days ago

Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout

Paper • 2609.09123 • Published 14 days ago • 55

upvoted a paper 12 days ago

Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout

Paper • 2609.09123 • Published 14 days ago • 55

authored 2 papers 18 days ago

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

Paper • 2604.10949 • Published Apr 13 • 15

SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models

Paper • 2609.02886 • Published 20 days ago • 117

upvoted a paper 19 days ago

SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models

Paper • 2609.02886 • Published 20 days ago • 117

liked a dataset 19 days ago

junchaoh-cs/SolarWM-Data

Updated 19 days ago • 13.8k • 45

upvoted a paper 27 days ago

EchoWM: Open and Enterable Omnimodal World Models

Paper • 2608.23189 • Published 29 days ago • 79

upvoted 2 papers about 1 month ago

Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning

Paper • 2608.03571 • Published Aug 6 • 47

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

Paper • 2608.03573 • Published Aug 6 • 61

upvoted a paper 3 months ago

EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots

Paper • 2607.02646 • Published Jul 2 • 26

authored a paper 3 months ago

Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning

Paper • 2606.27828 • Published Jun 26 • 26

upvoted 2 papers 3 months ago

Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning

Paper • 2606.27828 • Published Jun 26 • 26

OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics

Paper • 2606.09826 • Published Jun 8 • 20

upvoted a paper 4 months ago

EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation

Paper • 2605.23271 • Published May 22 • 31

liked a dataset 4 months ago

Enderfga/Mira

Preview • Updated Dec 18, 2025 • 390 • 2

authored a paper 5 months ago

UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors

Paper • 2605.00658 • Published May 1 • 87

upvoted a paper 5 months ago

UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors

Paper • 2605.00658 • Published May 1 • 87

authored a paper 6 months ago

Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models

Paper • 2603.17051 • Published Mar 17 • 69