Xianghao Kong

refkxh's activity

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

upvoted a paper about 10 hours ago

What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?

Paper • 2611.06483 • Published 1 day ago • 29

upvoted a paper 11 days ago

Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation

Paper • 2610.30926 • Published 14 days ago • 29

upvoted a paper 16 days ago

SolarRenderer: Few-Step Generative Reference Rendering

Paper • 2610.28630 • Published 17 days ago • 52

upvoted a paper 17 days ago

MT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion

Paper • 2610.25404 • Published 19 days ago • 40

upvoted a paper 21 days ago

Orbia: Do Generated Videos Form a Consistent 3D World?

Paper • 2610.20693 • Published 23 days ago • 33

upvoted a paper 22 days ago

RAR: Rate-Adaptive Rollout for Time-Consistent Interactive World Models

Paper • 2610.16302 • Published 24 days ago • 13

upvoted a collection about 2 months ago

SolarWM

Collection

Family-specific checkpoints, released data, and paper for SolarWM long-horizon interactive video world models. • 7 items • Updated Sep 10 • 12

liked a model about 2 months ago

junchaoh-cs/SolarWM-H3-33B

Updated about 9 hours ago • 17

authored a paper about 2 months ago

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

Paper • 2609.09123 • Published Sep 8 • 27

upvoted a paper about 2 months ago

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

Paper • 2609.09123 • Published Sep 8 • 27

authored 2 papers 2 months ago

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

Paper • 2604.10949 • Published Apr 13 • 14

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

Paper • 2609.02886 • Published Sep 2 • 114

upvoted a paper 2 months ago

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

Paper • 2609.02886 • Published Sep 2 • 114

liked a dataset 2 months ago

junchaoh-cs/SolarWM-Data

Updated Sep 3 • 11.9k • 54

upvoted a paper 2 months ago

EchoWM: Open and Enterable Omnimodal World Models

Paper • 2608.23189 • Published Aug 24 • 82

upvoted 2 papers 3 months ago

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

Paper • 2608.03571 • Published Aug 6 • 42

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

Paper • 2608.03573 • Published Aug 6 • 56

upvoted a paper 4 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 4 months ago

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

Paper • 2606.27828 • Published Jun 26 • 26

upvoted a paper 4 months ago

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

Paper • 2606.27828 • Published Jun 26 • 26