Yingxue Zhang

One Demo Is All It Takes: Planning Domain Derivation with LLMs from A Single Demonstration

Uncertainty-Aware Gaussian Map for Vision-Language Navigation

OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning

From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Training Retrieval-Augmented Generation Agents

When Engineering Outruns Intelligence: Rethinking Instruction-Guided Navigation

A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic

Plan2Evolve: LLM Self-Evolution for Improved Planning Capability via Automated Domain Generation

Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling

It Takes Two: Your GRPO Is Secretly DPO

C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning

Hint Marginalization for Improved Reasoning in Large Language Models

The Graph's Apprentice: Teaching an LLM Low-Level Knowledge for Circuit Quality Estimation

ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models