AI.info

Xin Zhang

Explore Xin Zhang on AI.info.

• SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
• PeakFlow: Peak-Guided Coarse-to-Refined Modeling for EEG-Based Dynamic Affective Trajectory Prediction
• WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
• LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion
• STAGE: A Full-Screenplay Benchmark for Reasoning over Evolving Stories
• X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests
• RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios
• CityRiSE: Reasoning Urban Socio-Economic Status in Large Vision-Language Models via Reinforcement Learning
• StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answering