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

Song Wang

6 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

6
26

Top categories

AI×5ML×2Vision×1Distributed×1Software Eng.×1Robotics×1Crypto×1

Frequent co-authors

Fuyuan Qian2×
Menglong Zhang2×
Quanying Liu2×
Xuanzhi Liu1×
Xinyi Wu1×
Hang Pan1×

Research Timeline

2026
SafeDream: Safety World Model for Proactive Early Jailbreak Detection

SAFEDREAM introduces a lightweight, external world-model framework that proactively detects multi-turn jailbreak attacks by modeling cumulative safety erosion and predicting early failure points.

Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning

The paper proposes a novel framework combining behavior-invariant task representation learning and a Transformer-based world model to achieve robust generalization in offline meta-reinforcement learning, particularly in sparse-reward settings.

Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning

The paper proposes a novel framework combining behavior-invariant task representation learning and a Transformer-based world model to achieve robust generalization in offline meta-reinforcement learning, particularly in sparse-reward settings.

ARP: Enhancing Quantized Skill Abstractions via Visual Alignment and Iterative Refinement for Robotic Manipulation

This paper proposes a new framework, Aligned Refinement Policy (ARP), to learn visuomotor policies for long-horizon manipulation tasks.

JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models

JoyNexus is a multi-tenant service for VLA model supervised fine-tuning, reinforcement learning, and evaluation, which decouples services, introduces group batching, and improves training efficiency.

ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos

ClearGS improves 3D Gaussian Splatting from handheld videos with uneven viewpoint coverage and mixed frame quality.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIEmpiricalRecentSep 25, 2026

ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos

Xuanzhi Liu, Xinyi Wu, Hang Pan, Wensi Huang +3 more

ClearGS improves 3D Gaussian Splatting from handheld videos with uneven viewpoint coverage and mixed frame quality.

View →
cs.DCcs.AIcs.SEEmpirical
Recent
Jul 17, 2026

JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models

Haoran Sun, Wentao Zhang, Junyang Hua, Hedan Yang +17 more

JoyNexus is a multi-tenant service for VLA model supervised fine-tuning, reinforcement learning, and evaluation, which decouples services, introduces group batching, and improves training efficiency.

View →
cs.ROEmpiricalRecentJun 21, 2026

ARP: Enhancing Quantized Skill Abstractions via Visual Alignment and Iterative Refinement for Robotic Manipulation

Yuntian Wang, Zesheng Jia, Yuhui Duan, Qibing Wang +4 more

This paper proposes a new framework, Aligned Refinement Policy (ARP), to learn visuomotor policies for long-horizon manipulation tasks.

View →
cs.LGcs.AIRecentMay 30, 2026

Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning

Fuyuan Qian, Menglong Zhang, Song Wang, Quanying Liu

The paper proposes a novel framework combining behavior-invariant task representation learning and a Transformer-based world model to achieve robust generalization in offline meta-reinforcement learni…

View →
cs.LGcs.AIRecentMay 30, 2026

Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning

Fuyuan Qian, Menglong Zhang, Song Wang, Quanying Liu

The paper proposes a novel framework combining behavior-invariant task representation learning and a Transformer-based world model to achieve robust generalization in offline meta-reinforcement learni…

View →
cs.CRcs.AIApr 18, 2026

SafeDream: Safety World Model for Proactive Early Jailbreak Detection

Bo Yan, Weikai Lin, Yada Zhu, Song Wang

SAFEDREAM introduces a lightweight, external world-model framework that proactively detects multi-turn jailbreak attacks by modeling cumulative safety erosion and predicting early failure points.

View →