StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents
Paper • 2607.22798 • Published • 55
AI & ML interests
Large Language Models
Recent Activity
View all activity
ZiyangÂ
authored a
paper 1 day ago
ZiyangÂ
submitted a
paper to Daily Papers 1 day ago
tangmenÂ
authored a
paper 20 days ago
tangmenÂ
submitted a
paper to Daily Papers 21 days ago
tangmenÂ
submitted a
paper to Daily Papers about 1 month ago
tangmenÂ
authored 9
papers about 1 month ago
RubricBench: Aligning Model-Generated Rubrics with Human Standards
Paper • 2603.01562 • Published • 64
OffSeeker: Online Reinforcement Learning Is Not All You Need for Deep Research Agents
Paper • 2601.18467 • Published • 1
Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models
Paper • 2603.01571 • Published • 34
AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent
Paper • 2512.20745 • Published
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
Paper • 2505.15431 • Published • 2
Towards a Unified Paradigm: Integrating Recommendation Systems as a New Language in Large Models
Paper • 2412.16933 • Published
Multimodal Dialogue Response Generation
Paper • 2110.08515 • Published
WizardLM: Empowering Large Language Models to Follow Complex Instructions
Paper • 2304.12244 • Published • 14
VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct
Paper • 2606.23543 • Published • 6
haipeng1Â
authored 4
papers about 1 month ago
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
Paper • 2308.09583 • Published • 8
Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena
Paper • 2407.10627 • Published
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
Paper • 2505.15431 • Published • 2
AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent
Paper • 2512.20745 • Published
haipeng1Â
submitted a
paper to Daily Papers about 1 month ago
haipeng1Â
authored a
paper about 1 month ago