Kanghui Tian

KangHui2200's activity

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

upvoted 4 papers 3 days ago

Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation

Paper • 2507.23440 • Published Jul 31, 2025 • 2

Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm

Paper • 2511.04570 • Published Nov 6, 2025 • 243

STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules

Paper • 2601.03537 • Published Jan 7 • 1

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published Mar 15 • 319

upvoted a paper 4 days ago

CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL

Paper • 2609.39533 • Published 15 days ago • 19

upvoted a paper 29 days ago

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Paper • 2609.18708 • Published about 1 month ago • 85

upvoted a paper 4 months ago

InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning

Paper • 2606.12195 • Published Jun 10 • 25

upvoted a paper 5 months ago

KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration

Paper • 2605.14278 • Published May 14 • 36