Ping Nie
- Papers
- 20
Cite
Notes
Only stored in your browser.
Authored papers
20Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
arXiv 2026
ClawBench: Can AI Agents Complete Everyday Online Tasks?
arXiv 2026
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
arXiv 2026
RewardHarness: Self-Evolving Agentic Post-Training
arXiv 2026
Watch Before You Answer: Learning from Visually Grounded Post-Training
arXiv 2026
Context Forcing: Consistent Autoregressive Video Generation with Long Context
arXiv 2026
ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks
arXiv 2026
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
arXiv 2026
VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction
arXiv 2026
VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
arXiv 2025
Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining
arXiv 2025
VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation
arXiv 2025
StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs
arXiv 2025
BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
arXiv 2025
ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations
arXiv 2025
VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search
arXiv 2025
VisCoder2: Building Multi-Language Visualization Coding Agents
arXiv 2025
VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation
arXiv 2025
BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions
arXiv 2025
Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem
arXiv 2025
Affiliations
Frequent co-authors
10from 20 papers