AI.info

Wentao Zhang

Explore Wentao Zhang on AI.info.

• Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs
• Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs
• TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning
• EthicMind: A Risk-Aware Framework for Ethical-Emotional Alignment in Multi-Turn Dialogue
• BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents
• GENIUS: Generative Fluid Intelligence Evaluation Suite
• AD-MIR: Bridging the Gap from Perception to Persuasion in Advertising Video Understanding via Structured Reasoning
• Towards Automated Kernel Generation in the Era of LLMs
• GIFT: Reconciling Post-Training Objectives via Variational Finite-Temperature Gibbs Initialization
• GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models
• Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
• Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation
• DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM
• VABench: A Comprehensive Benchmark for Audio-Video Generation
• AICC: Parse HTML Finer, Make Models Better -- A 7.3T AI-Ready Corpus Built by a Model-Based HTML Parser
• Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL
• Jarvis: Towards Personalized AI Assistant via Personal KV-Cache Retrieval
• Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks
• LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding
• Towards Adaptable Humanoid Control via Adaptive Motion Tracking
• PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System