Shaobai Jiang

shaobaij's activity

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

upvoted a paper about 16 hours ago

Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training

Paper • 2507.05386 • Published Jul 7, 2025 • 1

upvoted 2 papers about 21 hours ago

SWE-Universe: Scale Real-World Verifiable Environments to Millions

Paper • 2602.02361 • Published 3 days ago • 54

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

Paper • 2602.01058 • Published 5 days ago • 38

upvoted 3 papers 2 days ago

Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models

Paper • 2601.22060 • Published 7 days ago • 144

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published 6 days ago • 79

How AI Impacts Skill Formation

Paper • 2601.20245 • Published 9 days ago • 8

upvoted 9 papers 3 days ago

Qwen3-ASR Technical Report

Paper • 2601.21337 • Published 8 days ago • 33

Kimi K2.5: Visual Agentic Intelligence

Paper • 2602.02276 • Published 3 days ago • 193

Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery

Paper • 2601.20088 • Published 9 days ago • 1

DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation

Paper • 2601.22153 • Published 7 days ago • 68

ECO: Quantized Training without Full-Precision Master Weights

Paper • 2601.22101 • Published 7 days ago • 6

FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale

Paper • 2601.22146 • Published 7 days ago • 8

Corrective Diffusion Language Models

Paper • 2512.15596 • Published Dec 17, 2025 • 1

JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion

Paper • 2601.22143 • Published 7 days ago • 6

STEP3-VL-10B Technical Report

Paper • 2601.09668 • Published 22 days ago • 193

upvoted 4 papers 4 days ago

Reasoning Models Generate Societies of Thought

Paper • 2601.10825 • Published 21 days ago • 14

Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives

Paper • 2601.20833 • Published 8 days ago • 171

K2-V2: A 360-Open, Reasoning-Enhanced LLM

Paper • 2512.06201 • Published Dec 5, 2025 • 2

LongCat-Image Technical Report

Paper • 2512.07584 • Published Dec 8, 2025 • 23

upvoted a paper 5 days ago

ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation

Paper • 2601.21420 • Published 7 days ago • 41