Manipulation, locomotion, sim-to-real transfer and autonomous driving: learning systems that have to survive physics.
arXiv:2609.24137v1 Announce Type: cross Abstract: Traditional data systems face profound limitations in the AI era, relying on human-crafted pipelines, lacking semantic understanding of heterogeneous...
arXiv:2609.24246v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable progress in natural language understanding, yet their effectiveness in specialized fields like astro...
The paper investigates an agentic framework for open‑world fake image detection that combines specialist detectors with per‑detector triage, prompting, and conflict‑aware evidence arbitration. Experiments across six configurations and three multimodal large language model backbones reveal that naive detector fusion yields high false‑positive rates, while triage and prompting consistently filter unreliable evidence. The most significant improvement comes from the reasoning component: a stronger judge markedly outperforms a weaker one, especially under distribution shift, and overall manipulation recall is nearly saturated, highlighting that the key challenge lies in calibrating trust and arbitrating conflicting forensic evidence rather than detecting manipulations themselves.
arXiv:2410.14606v3 Announce Type: replace Abstract: Learning from a stream of experience as it arrives, also known as streaming learning, is a core part of natural learning. However, reliable streami...
arXiv:2609.11737v2 Announce Type: replace-cross Abstract: Collective intelligence depends not only on the capabilities of individual members, but also on how those members are organized. Yet artifici...
arXiv:2609.23184v1 Announce Type: new Abstract: Embodied world models learn to predict future physical dynamics from visual observations and control signals, where physical knowledge is implicitly en...
The paper proposes a method to distill world‑model representations into compact Vision‑Language‑Action (VLA) policies. By adding a single feature‑alignment term during VLA training, a frozen world model’s internal features are cached and the student policy learns to match them, eliminating the need for a generative future‑rolling component. The resulting lightweight policy runs in 32 ms on an RTX 5090, achieving high performance on LIBERO and RoboCasa‑GR1, and transfers effectively to real robotic hardware.
arXiv:2609.24621v1 Announce Type: cross Abstract: Tactile sensing is increasingly being incorporated into learning-based robotic manipulation, yet many existing approaches rely on spatially distribut...
arXiv:2603.18532v3 Announce Type: replace-cross Abstract: The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for f...
arXiv:2609.24193v1 Announce Type: new Abstract: Pedestrian head orientation recognition plays an important role in autonomous driving by providing valuable cues for understanding pedestrian attention...
Standard deployment-ready object detectors for autonomous vehicles degrade in adverse weather and lighting conditions without being trained on extensive domain-specific data. While large-scale vision...
We focus on human-robot collaborative transport, a challenging task of broad relevance spanning logistics, manufacturing, and the home, in which a user and a robot work together to relocate a large or...
Autonomous parking in nonconvex and narrow environments remains challenging. Although optimal-control methods can explicitly enforce vehicle dynamics and collision constraints, nonconvexity compromise...
Robotic foundation models achieve impressive performance on standard manipulation benchmarks, yet these evaluations typically assume clean, timely, and consistent visual observations throughout execut...
Evaluating world models requires assessing both the quality of the worlds they generate and their consistency and responsiveness under exploration, interaction, and modification. We introduce HappyWor...
Deploying language-conditioned manipulation without a dedicated GPU requires efficient inference and action chunks that cover the delay between policy queries. We present vla.simd, a CPU inference eng...
Continual learning, the ability to learn from sequential experience while retaining and adapting prior knowledge, is central to intelligent systems operating in changing environments. However, convent...
Traditional data systems face profound limitations in the AI era, relying on human-crafted pipelines, lacking semantic understanding of heterogeneous data, and operating through rigid, reactive proces...
The paper proposes using ultrathin metalenses to physically encode metric depth cues into two polarized optical wavefronts, enabling accurate monocular depth estimation. By aligning a pretrained depth foundation model with these optical signals through direct fine‑tuning, and by creating a simulation pipeline to generate realistic metalens responses from RGB‑D data, the authors bridge the gap between nanophotonics and learned depth priors. Experiments show that this method surpasses conventional monocular metric depth estimation and depth‑from‑defocus baselines.
The paper introduces Jarvis, an offline, edge‑deployable voice assistant designed for autonomous racecars. It combines speech recognition, synthesis, and a lightweight text‑to‑command classifier fine‑tuned from the Mistral 7B model to provide high‑level behavioral commands. Experiments show 97.63 % intent recognition accuracy with an average latency of 1.39 s, outperforming larger online‑hosted models and enabling quick response times for time‑critical driving tasks.