Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Wei Deng

Wei Deng

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Vision×1NLP×1Info Retrieval×1

Frequent co-authors

Xianlin Zhang1×
Mengshi Qi1×
Han Zhang1×
Zihao Tang1×
Xin Yu1×
Xiao Liu1×

Research Timeline

2026
Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory

The paper introduces RHELM, a new benchmark designed to test LLMs' long-term memory by simulating realistic, complex, and evolving dialogues that integrate multiple heterogeneous data sources.

Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models

The paper proposes an agentic pipeline for spatial reasoning by introducing a dynamic cognitive map and Spatial Assertion Codes (SAC), achieving state-of-the-art performance on complex spatial tasks.

Highlighted terms show continued research focus across papers

Papers

cs.CVRecentJun 1, 2026

Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models

Wei Deng, Xianlin Zhang, Mengshi Qi

The paper proposes an agentic pipeline for spatial reasoning by introducing a dynamic cognitive map and Spatial Assertion Codes (SAC), achieving state-of-the-art performance on complex spatial tasks.

View →
cs.CLcs.IRRecentMay 29, 2026

Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory

Han Zhang, Zihao Tang, Xin Yu, Xiao Liu +7 more

The paper introduces RHELM, a new benchmark designed to test LLMs' long-term memory by simulating realistic, complex, and evolving dialogues that integrate multiple heterogeneous data sources.

View →