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

Jie Feng

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×2Signal Processing×1Systems and Control×1Vision×1NLP×1

Frequent co-authors

Xiangyu Li1×
Bodong Shang1×
Junchao Ma1×
Qingqing Wu1×
Deshuang Huang1×
Tianhui Liu1×

Research Timeline

2026
Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling

The paper introduces Graph-Distance Contribution Reward (GDCR) and Step Advantage Policy Optimization (SAPO) to provide fine-grained, step-level credit assignment for agentic search by modeling world knowledge as a latent graph.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes

The paper introduces SpatialAct, a challenging benchmark that reveals a significant 'reasoning-to-action gap,' showing that current VLMs struggle to maintain coherent spatial understanding and perform reliable actions in multi-turn 3D environments.

Fundamentals of NOMA in Low-Earth Orbit Coordinated Multi-Satellite Networks

This paper investigates the downlink performance of CoMS-NOMA networks from a system-level perspective.

Highlighted terms show continued research focus across papers

Papers

eess.SPeess.SYEmpiricalRecentJun 9, 2026

Fundamentals of NOMA in Low-Earth Orbit Coordinated Multi-Satellite Networks

Xiangyu Li, Bodong Shang, Junchao Ma, Qingqing Wu +2 more

This paper investigates the downlink performance of CoMS-NOMA networks from a system-level perspective.

View →
cs.CVcs.AIcs.CLRecentMay 29, 2026

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes

Tianhui Liu, Jie Feng, Zhiheng Zheng, Shengyuan Wang +5 more

The paper introduces SpatialAct, a challenging benchmark that reveals a significant 'reasoning-to-action gap,' showing that current VLMs struggle to maintain coherent spatial understanding and perform…

View →
cs.AIRecentMay 28, 2026

Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling

Yuchen Liu, Yingjie Feng, Lixiong Qin, Jiasi Chen +4 more

The paper introduces Graph-Distance Contribution Reward (GDCR) and Step Advantage Policy Optimization (SAPO) to provide fine-grained, step-level credit assignment for agentic search by modeling world…

View →