Jinyang Wu

Jinyang23's activity

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

authored 2 papers about 2 hours ago

Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism

Paper • 2601.05524 • Published 20 days ago

Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning

Paper • 2601.20209 • Published 1 day ago • 9

updated 3 models about 7 hours ago

Jinyang23/Spark-1.5B-ALFWorld

Reinforcement Learning • 2B • Updated about 7 hours ago

Jinyang23/Spark-1.5B-WebShop

Reinforcement Learning • 2B • Updated about 7 hours ago

Jinyang23/Spark-1.5B-ScienceWorld

Reinforcement Learning • 2B • Updated about 7 hours ago

published 3 models about 8 hours ago

Jinyang23/Spark-1.5B-ALFWorld

Reinforcement Learning • 2B • Updated about 7 hours ago

Jinyang23/Spark-1.5B-WebShop

Reinforcement Learning • 2B • Updated about 7 hours ago

Jinyang23/Spark-1.5B-ScienceWorld

Reinforcement Learning • 2B • Updated about 7 hours ago

upvoted a paper about 8 hours ago

Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning

Paper • 2601.20209 • Published 1 day ago • 9

submitted a paper to Daily Papers about 8 hours ago

Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning

Paper • 2601.20209 • Published 1 day ago • 9

upvoted 2 papers 14 days ago

MAXS: Meta-Adaptive Exploration with LLM Agents

Paper • 2601.09259 • Published 15 days ago • 95

A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation

Paper • 2601.09274 • Published 15 days ago • 84

authored a paper 21 days ago

Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning

Paper • 2601.03872 • Published 22 days ago • 42

upvoted a paper 21 days ago

Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning

Paper • 2601.03872 • Published 22 days ago • 42

submitted a paper to Daily Papers 21 days ago

Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning

Paper • 2601.03872 • Published 22 days ago • 42

upvoted a paper about 1 month ago

HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices

Paper • 2512.14052 • Published Dec 16, 2025 • 42

submitted a paper to Daily Papers about 1 month ago

HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices

Paper • 2512.14052 • Published Dec 16, 2025 • 42

upvoted a paper about 2 months ago

From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks

Paper • 2512.02580 • Published Dec 2, 2025 • 28

commented a paper about 2 months ago

From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks

Paper • 2512.02580 • Published Dec 2, 2025 • 28 •

2

upvoted a paper 4 months ago

Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints

Paper • 2510.08549 • Published Oct 9, 2025 • 7