Lin Haoran

liha5y's activity

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

upvoted a paper about 14 hours ago

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

Paper • 2607.25659 • Published 3 days ago • 73

upvoted 2 papers 1 day ago

Progress Reward Modeling for Robotic Learning: A Comprehensive Survey

Paper • 2607.21655 • Published 9 days ago • 191

HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone

Paper • 2607.25895 • Published 3 days ago • 141

upvoted 2 papers 8 days ago

DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines

Paper • 2607.16617 • Published 13 days ago • 137

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

Paper • 2607.19191 • Published 9 days ago • 304

upvoted 2 papers 9 days ago

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

Paper • 2607.17977 • Published 11 days ago • 197

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

Paper • 2607.17423 • Published 12 days ago • 166

upvoted 2 papers 12 days ago

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published 23 days ago • 139

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Paper • 2607.14952 • Published 15 days ago • 203

upvoted a paper 13 days ago

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Paper • 2607.14935 • Published 15 days ago • 170

upvoted 2 papers 14 days ago

X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras

Paper • 2607.12993 • Published 17 days ago • 131

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Paper • 2607.12463 • Published 17 days ago • 108

upvoted a paper 15 days ago

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Paper • 2607.13285 • Published 17 days ago • 227

upvoted 2 papers 22 days ago

RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation

Paper • 2607.06558 • Published 24 days ago • 79

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Paper • 2607.06559 • Published 24 days ago • 95

upvoted a paper 23 days ago

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

Paper • 2607.04033 • Published 27 days ago • 76

upvoted 2 papers 24 days ago

PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

Paper • 2607.05373 • Published 25 days ago • 66

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Paper • 2606.29526 • Published Jun 28 • 170

upvoted a paper 27 days ago

Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models

Paper • 2606.19297 • Published Jun 17 • 80

upvoted a paper about 1 month ago

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

Paper • 2606.17162 • Published Jun 15 • 177