Kanghui Tian

KangHui2200's activity

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

upvoted a paper about 16 hours ago

MIRA: A Multimodal Illustrated Deep Research Agent for Controllable Reports

Paper • 2610.25926 • Published 18 days ago • 20

liked 2 datasets about 16 hours ago

MIRA-MMDeepResearch/MIRA-General-Data-20K

Viewer • Updated 3 days ago • 21.5k • 59 • 1

MIRA-MMDeepResearch/MIRA-Harness-Data-4K

Viewer • Updated 3 days ago • 3.4k • 119 • 1

liked a model about 16 hours ago

MIRA-MMDeepResearch/MIRA-SFT-35B-A3B

Image-Text-to-Text • 665k • Updated 4 days ago • 26 • 2

upvoted a paper about 16 hours ago

Turns Matter: Advancing Streaming Video RL via Turn-Level Credit

Paper • 2611.06728 • Published 2 days ago • 121

upvoted 4 papers 24 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 • 241

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 • 303

upvoted a paper 25 days ago

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

Paper • 2609.39533 • Published Oct 1 • 20

upvoted a paper about 2 months ago

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Paper • 2609.18708 • Published Sep 16 • 56

upvoted a paper 5 months ago

InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning

Paper • 2606.12195 • Published Jun 10 • 24

upvoted a paper 6 months ago

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

Paper • 2605.14278 • Published May 14 • 36