Author

Haifeng Wang

Observed names: Wang, HaiFeng, Wang, Haifeng

Institutions: Chinese Academy of Sciences, Baidu (China)

Observed institutions: Chinese Academy of Sciences, Baidu (China)

OpenAlex ID: A5125251827

ERNIE 5.0 Technical Report

2026 · Wang, Haifeng, Wu, Hua, et al. · arXiv (Cornell University) · 2

PDF

Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs

2026 · Ren, Zixuan, Lu, Jinliang, et al. · arXiv (Cornell University)

PDF

SimReg: Achieving Higher Performance in the Pretraining via Embedding Similarity Regularization

2026 · Sun, Yan, Wang, Guoxia, et al. · arXiv (Cornell University)

PDF

Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping

2026 · Chen, Yao, Chen, Yilong, et al. · arXiv (Cornell University)

PDF

Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models

2026 · Pan, Jiadong, Li, Liang, et al. · arXiv (Cornell University)

PDF

Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation

2026 · Chen, Yilong, Gu, Naibin, et al. · arXiv (Cornell University)

PDF

Eureka-Audio: Triggering Audio Intelligence in Compact Language Models

2026 · Zhang, Dan, Lei, Yishu, et al. · arXiv (Cornell University)

PDF

RRAttention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference

2026 · Liu, Siran, Wang, Guoxia, et al. · arXiv (Cornell University)

PDF

OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution

2026 · Zhang, Le, Xiao, Yixiong, et al. · arXiv (Cornell University)

PDF

CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation

2026 · Hu, Jing, Zhu, Danxiang, et al. · arXiv (Cornell University)

PDF

Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models

2026 · Sun, Shaoning, Cai, Mingzhu, et al. · arXiv (Cornell University)

PDF

VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction

2026 · Ji, Longbin, Liu, Xiaoxiong, et al. · arXiv (Cornell University)

PDF

MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free

2026 · Lei, Yishu, He, Shuwei, et al. · arXiv (Cornell University)

PDF

LifeMem: Enabling Lifelong Experience Reuse for LLM Agents

2026 · Yuli Qiu, Yutong Li, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

PDF

Works count: 16

Citation count: 2

H-index: 1

I10-index: