Xiangji Zeng
zengxiangji
AI & ML interests
None yet
Recent Activity
liked
a model
8 days ago
deepseek-ai/DeepSeek-OCR
liked
a model
14 days ago
Kwaipilot/KAT-Dev-72B-Exp
updated
a collection
15 days ago
reinforcement-learning
Organizations
None yet
agent
edge-inference
reinforcement-learning
-
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning
Paper • 2506.04207 • Published • 48 -
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
Paper • 2504.11468 • Published • 30 -
RLPR: Extrapolating RLVR to General Domains without Verifiers
Paper • 2506.18254 • Published • 31 -
Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
Paper • 2507.05255 • Published • 74
chain-of-thought
reasoning
context-engineering
-
A Survey of Context Engineering for Large Language Models
Paper • 2507.13334 • Published • 257 -
Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers
Paper • 2506.23918 • Published • 88 -
Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning
Paper • 2507.16784 • Published • 120 -
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Paper • 2510.04618 • Published • 109
aigc
representation-learning
inference-optimization
brain
reasoning
agent
context-engineering
-
A Survey of Context Engineering for Large Language Models
Paper • 2507.13334 • Published • 257 -
Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers
Paper • 2506.23918 • Published • 88 -
Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning
Paper • 2507.16784 • Published • 120 -
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Paper • 2510.04618 • Published • 109
edge-inference
aigc
reinforcement-learning
-
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning
Paper • 2506.04207 • Published • 48 -
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
Paper • 2504.11468 • Published • 30 -
RLPR: Extrapolating RLVR to General Domains without Verifiers
Paper • 2506.18254 • Published • 31 -
Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
Paper • 2507.05255 • Published • 74
representation-learning
chain-of-thought
inference-optimization