Skip to content
VLA 線 · 查看同日 AI 報告 →查看同日 AI 报告 →
VLA 研究日報 Pulsar
LIVE
— AI 線今日無資料 —— AI 线今日无资料 —

VLA 研究日報VLA 研究日报

共 40 篇

🔧 技術技术

📖 背景閱讀背景阅读

VLA [Department of Computer Science, University of North Carolina at Chapel Hill]

Sensing Which Modality Matters: Evidence-Gated Regularization for Robust VLA Policies

Yue Yang et al. · arXiv:2609.03142v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies fuse multimodal sensory inputs, but training on limited and homogeneous robot demonstrations encourages spurious inter-sensor correlations rather than task-relevant signal, a failure we term modality entanglement. Under real-world occlusions and distractors, this manifests as nuisance sensitivity to corruption of uninformative sensors and single-modality insufficiency when only one informative sensor remains in

VLA [Tsinghua University]

WISE: World-model-guided Imagination Scheduling for Efficient Post-training of Vision-Language-Action Models

Chenhao Zhang et al. · arXiv:2609.03681v1 Announce Type: new Abstract: Post-training VLA policies typically rely on supervised fine-tuning with costly expert demonstrations or reinforcement learning with expensive and potentially unstable real-world exploration. World models offer a promising alternative by evaluating candidate behaviors through imagined futures, yet effective post-training requires more than accurate prediction: imagination must be scheduled where it is useful, bounded within reliable horizons, and t

VLA [Liber AI Research]

Semantic Bayesian World Models

Tommaso Soru · 观点文章,主张知识图谱的确定性断言与基础模型的概率推理需要融合构成语义贝叶斯世界模型;无机器人实验。

VLA [Purdue University]

Latent Energy Action Planning with World Models

Phu Pham et al. · arXiv:2609.03294v1 Announce Type: new Abstract: Latent world models support efficient model predictive control from high-dimensional observations, yet optimizing a single learned latent objective can favor action sequences whose decoder-predicted terminal descriptor does not match the goal descriptor. We introduce Latent Energy Action Planning (LEAP), which treats the complete action horizon as a differentiable variable and optimizes it through a frozen LeWorldModel (LeWM). LEAP couples terminal