Yang Gao

24

Papers

183

Total Citations

Papers (24)

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

NeurIPS 2025arXiv

Digital Life Project: Autonomous 3D Characters with Social Intelligence

SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters

Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving

ViT-Calibrator: Decision Stream Calibration for Vision Transformer

Angle Robustness Unmanned Aerial Vehicle Navigation in GNSS-Denied Scenarios

Multi-Agent Reinforcement Learning with Communication-Constrained Priors

NeurIPS 2025arXiv

Beyond Mandatory Federations: Balancing Egoism, Utilitarianism and Egalitarianism in Mixed-Motive Games

Large Language Models Enhanced Personalized Graph Neural Architecture Search in Federated Learning

DGA-GNN: Dynamic Grouping Aggregation GNN for Fraud Detection

PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidance

Weakly Supervised Multimodal Affordance Grounding for Egocentric Images

Optimistic Value Instructors for Cooperative Multi-Agent Reinforcement Learning

Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning

HOIAnimator: Generating Text-prompt Human-object Animations using Novel Perceptive Diffusion Models

Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation

Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation

Safe and Robust Subgame Exploitation in Imperfect Information Games

EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data

Enhancing Few-Shot Class-Incremental Learning via Training-Free Bi-Level Modality Calibration

Dynamic Multi-Layer Null Space Projection for Vision-Language Continual Learning

Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos

Adapting In-Domain Few-Shot Segmentation to New Domains without Source Domain Retraining

NATRA: Noise-Agnostic Framework for Trajectory Prediction with Noisy Observations