Jiaya Jia

Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning

Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents

VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning

RePlan: Reasoning-Guided Region Planning for Complex Instruction-Based Image Editing

DreamOmni2: Multimodal Instruction-based Editing and Generation

Guided Sampling in Reinforcement Learning for LLM Reasoning

From Noisy Traces to Stable Gradients: Bias--Variance Optimized Preference Optimization for Aligning Large Reasoning Models

SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought Exploration

Elevating Large Language Models with Module-of-Thought

MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech

Don’t Lose the Thread: Empowering Long-Horizon LLM Agents with Cognitive Resource Self-Allocation

DynamicBench: Evaluating Real-Time Report Generation in Large Language Models

Multi-Scale Group Relative Policy Optimization for Large Language Models

End-to-End QA Construction Pipeline for Continual Pre-training of Large Language Models

IndustryGPT: A Large Language Model for Industrial Domain-Specific Question Answering

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning

Training-Free Efficient Video Generation via Dynamic Token Carving

GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning

DLoFT: Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning

MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation

Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization

Effective LLM Knowledge Learning Requires Rethinking Generalization

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs