robin zhang
Chevolier
·
AI & ML interests
None yet
Recent Activity
updated
a collection
about 15 hours ago
Image Generation
updated
a collection
about 15 hours ago
Multimodal
updated
a collection
about 15 hours ago
Reasoning
Organizations
None yet
Reasoning
-
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Paper • 2509.07980 • Published • 101 -
Tree Search for LLM Agent Reinforcement Learning
Paper • 2509.21240 • Published • 87 -
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Paper • 2512.01374 • Published • 83 -
How Far Are We from Genuinely Useful Deep Research Agents?
Paper • 2512.01948 • Published • 50
VLA
-
π_RL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
Paper • 2510.25889 • Published • 64 -
Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model
Paper • 2510.27607 • Published • 8 -
A Survey on Efficient Vision-Language-Action Models
Paper • 2510.24795 • Published • 5 -
Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach
Paper • 2512.02834 • Published • 38
Multimodal
-
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization
Paper • 2510.08540 • Published • 109 -
Diffusion Transformers with Representation Autoencoders
Paper • 2510.11690 • Published • 165 -
Spotlight on Token Perception for Multimodal Reinforcement Learning
Paper • 2510.09285 • Published • 36 -
Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation
Paper • 2510.17354 • Published • 33
Agent
-
Agent Learning via Early Experience
Paper • 2510.08558 • Published • 266 -
Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
Paper • 2510.08002 • Published • 23 -
Self-Improving LLM Agents at Test-Time
Paper • 2510.07841 • Published • 9 -
The Denario project: Deep knowledge AI agents for scientific discovery
Paper • 2510.26887 • Published • 6
Image Generation
-
Seedream 4.0: Toward Next-generation Multimodal Image Generation
Paper • 2509.20427 • Published • 80 -
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Paper • 2511.22699 • Published • 169 -
RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards
Paper • 2512.00473 • Published • 17
Recommendation
Video Generation
-
UniVideo: Unified Understanding, Generation, and Editing for Videos
Paper • 2510.08377 • Published • 70 -
LongLive: Real-time Interactive Long Video Generation
Paper • 2509.22622 • Published • 184 -
HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
Paper • 2509.08519 • Published • 128
LLM
-
Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning
Paper • 2510.03259 • Published • 57 -
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
Paper • 2510.07242 • Published • 30 -
First Try Matters: Revisiting the Role of Reflection in Reasoning Models
Paper • 2510.08308 • Published • 24 -
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Paper • 2510.03222 • Published • 75
World Model
Image Generation
-
Seedream 4.0: Toward Next-generation Multimodal Image Generation
Paper • 2509.20427 • Published • 80 -
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Paper • 2511.22699 • Published • 169 -
RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards
Paper • 2512.00473 • Published • 17
Reasoning
-
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Paper • 2509.07980 • Published • 101 -
Tree Search for LLM Agent Reinforcement Learning
Paper • 2509.21240 • Published • 87 -
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Paper • 2512.01374 • Published • 83 -
How Far Are We from Genuinely Useful Deep Research Agents?
Paper • 2512.01948 • Published • 50
Recommendation
VLA
-
π_RL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
Paper • 2510.25889 • Published • 64 -
Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model
Paper • 2510.27607 • Published • 8 -
A Survey on Efficient Vision-Language-Action Models
Paper • 2510.24795 • Published • 5 -
Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach
Paper • 2512.02834 • Published • 38
Video Generation
-
UniVideo: Unified Understanding, Generation, and Editing for Videos
Paper • 2510.08377 • Published • 70 -
LongLive: Real-time Interactive Long Video Generation
Paper • 2509.22622 • Published • 184 -
HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
Paper • 2509.08519 • Published • 128
Multimodal
-
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization
Paper • 2510.08540 • Published • 109 -
Diffusion Transformers with Representation Autoencoders
Paper • 2510.11690 • Published • 165 -
Spotlight on Token Perception for Multimodal Reinforcement Learning
Paper • 2510.09285 • Published • 36 -
Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation
Paper • 2510.17354 • Published • 33
LLM
-
Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning
Paper • 2510.03259 • Published • 57 -
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
Paper • 2510.07242 • Published • 30 -
First Try Matters: Revisiting the Role of Reflection in Reasoning Models
Paper • 2510.08308 • Published • 24 -
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Paper • 2510.03222 • Published • 75
Agent
-
Agent Learning via Early Experience
Paper • 2510.08558 • Published • 266 -
Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
Paper • 2510.08002 • Published • 23 -
Self-Improving LLM Agents at Test-Time
Paper • 2510.07841 • Published • 9 -
The Denario project: Deep knowledge AI agents for scientific discovery
Paper • 2510.26887 • Published • 6