CORTEXA
← Browse
arxivcs.ROcs.AI2026-07-01

DART-VLN: Test-Time Memory Decay and Anti-Loop Regularization for Discrete Vision-Language Navigation

Shaoheng Zhang, Zhichen Li, Jie Mei

Memory-based agents for discrete vision-language navigation (VLN) operate under partial observability and can exhibit systematic inference-time failures even with strong pretrained backbones. We focus on two recurring problems: stale historical evidence during memory readout and inefficient local backtracking during action selection. We present DART-VLN, a training-free inference-time framework that combines Test-Time Memory Decay, which reweights stale and redundant memory slots without modifying their stored content, with Anti-Loop Regularization, a lightweight next-hop penalty that discourages immediate reversals. DART-VLN introduces no learnable parameters and leaves the navigation backbone unchanged. Experiments on R2R and REVERIE show that memory decay consistently preserves or improves task performance while reducing runtime. Adding anti-loop regularization further shortens trajectories, reduces local backtracking, and achieves the best overall balance between navigation quality and efficiency among the evaluated GridMM variants. These results indicate that lightweight inference-time control can improve the reliability and efficiency of memory-based discrete VLN without retraining.

View free PDFSource page

Related papers

arxivcs.ROcs.AI2026-07-23

VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method

Jiabin Lou, Haopeng Wang, Yuanshuai Wang, Xinyu Liu, Xuxin Lv, Yuxin Guo, et al.

Vision-and-Language Navigation (VLN) enables embodied agents to follow natural-language instructions. However, route-level instructions commonly encode spatial priors, such as orientation, distance, and layout, that are not explicitly available from onboard sensing at deployment…

View free PDFSource page
arxivcs.ROcs.AI2026-07-31

ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency

Wenda Yu, Tianshi Wang, Fengling Li, Xin Li, Jingjing Li, Lei Zhu

Vision-language-action (VLA) policies achieve strong performance in robotic manipulation but remain vulnerable to runtime disturbances that break the temporal alignment among visual observations, robot states, and executed actions. We introduce ActFovea, a plug-and-play safeguard…

View free PDFSource page
arxivcs.LGcs.AIcs.MAcs.RO2026-07-23

Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections

Gil Lifshits, Igal Bilik, Gilad Katz

Coordinating autonomous vehicles at unsignalized intersections remains a critical challenge for multi-agent reinforcement learning (MARL) systems, which typically struggle with combinatorial action spaces, reliance on privileged information, or rigid agent designs. We propose Mas…

View free PDFSource page
arxivcs.ROcs.AIeess.SY2026-07-31

FBFM: A Training-Free Asynchronous Feedback Mechanism for Flow-Matching in World-Action Models Execution

Peize Li, Ruimeng Zhang, Ru Zhang, Cong Huang, Kai Chen, Shanghang Zhang

Although world-action models (WAMs) enhance long-horizon robot control by predicting visual evolution before acting, long-horizon reliability demands repeated re-grounding in real observations--not recursive rollout. Existing WAMs address this by refreshing history or KV cache wi…

View free PDFSource page
arxivcs.ROcs.AI2026-07-31

CLIFT: Turning Gemini Robotics On-Device into Humanoid Specialists via Non-Invasive Closed-Loop Iterative Fine-Tuning

Yuxin Chen, Hari Srikanth, Nathan Jew, Menglin Wu, Pengcheng Wang, Junli Ren, et al.

While robot foundation models are growing increasingly capable, the strongest models are typically trained on proprietary data and remain closed-source, limiting downstream users' ability to adapt them to new tasks, embodiments, and deployment settings. Following the LLM communit…

View free PDFSource page
arxivcs.ROcs.AIcs.CLcs.CV2026-07-23

GS-Agent: Creating 4D Physical Worlds With Generative Simulation

Hongxin Zhang, Chunru Lin, Junyan Li, Zhou Xian, Tsun-Hsuan Wang, Chuang Gan

Creating dynamic and physically realistic 4D worlds from natural language descriptions is both fascinating and challenging. Traditional computer graphics methods rely on manual creation, requiring extensive human effort to fine-tune materials, motions, and visual fidelity. Recent…

View free PDFSource page