ROBOMARKET
Stay Informed
Daily coverage from 6108 trusted sources — robotics, AI agents, and industry analysis for the GCC.
Last Updated: 10:00 PM (18m ago)
Auto-refresh every 2 hours
M3-Former: Multimodal Transformer with Mixture-of-Experts for Long-Term Vessel Trajectory Prediction
arXiv:2609.10559v1 Announce Type: new Abstract: To address the challenges of behavioral multimodality, limited semantic utilization, and long-term error accumulation in vessel trajectory prediction, this paper proposes M3-Former, a multimodal trajectory prediction framework enhanced by large language models (LLMs). The proposed framework incorporates vessel static attributes and navigational intent as semantic priors for long-term trajectory modeling. Specifically, a unified multimodal representation space is constructed, in which static semantic information is encoded by a pre-trained LLM and aligned with dynamic trajectory features through self-attention. To jointly capture global route planning and local motion variations, a dual-granularity Mixture-of-Experts (MoE) architecture is introduced, where sequence-level experts model global navigation trends and token-level experts refine fine-grained maneuvering behaviors. In addition, a Steering-Weighted Cross-Entropy loss is designed t
Halo: Improving forecast accuracy through heteroscedastic estimation
arXiv:2609.10589v1 Announce Type: new Abstract: Heteroscedastic forecasting, where a network estimates a scale parameter alongside a location parameter, is normally motivated by uncertainty quantification. This paper shows it also improves the point estimate, in contrast to reported negative results for heteroscedastic estimation outside time series. Halo is a modification that reuses an existing deep forecaster's architecture, giving it a second output for the scale of its implied distribution and training it under the matching negative log likelihood. Adapting three state-of-the-art models --- a transformer, a graph network paired with a variational autoencoder, and a single-layer convolutional network --- under both Gaussian and Laplacian losses demonstrates the phenomenon. On the five electricity price markets of a standard forecasting benchmark, Halo improves MSE and MAE in 28 of 30 model-market-metric comparisons, cutting average MSE by 2.6% to 16.5% and average MAE by 1.7% to 11
HuRo: Robotizing Human Videos for Scalable VLA Pretraining
arXiv:2609.10706v1 Announce Type: new Abstract: Human video datasets have emerged as a compelling alternative to expensive real-robot data, offering rich diversity at scale. To bridge the human-to-robot embodiment gap, existing approaches either robotize videos in task-matched settings or address observation and action alignment separately at scale. In this work, we systematically examine whether robotized human videos can provide effective and scalable supervision for pretraining vision-language-action (VLA) policies. To this end, we develop a robotization pipeline that converts heterogeneous human videos into robot-aligned observations and action trajectories while inferring missing intermediate signals across annotation levels. Using this pipeline, we construct the HuRo dataset, comprising about 630K robotized episodes and 142M processed frames from five human-video sources. Across four real-world manipulation tasks, increasing robotized pretraining scale improves overall completion
Bagaimana AI Mengubah Cara Saya Bekerja (dan Bisa Mengubah Cara Kamu Juga)
Jam 9 malam. Laptop masih menyala. To-do list belum juga mengecil.Continue reading on Medium »
Reverse-Engineering Claude Web's MicroVM: Uncovering Anthropic's Hidden Antspace
Comments
The Destination of Power Without a Vision, and the Future of Humans and Artificial Intelligence
A look back at history reveals that human beings have exhibited a surprisingly consistent weakness when it comes to how they use power and Continue reading on Medium »
Ukraine Is Finding New Ways to Make Russia Pay
I want you to picture a vault. It s not a physical one, but a legal and financial architecture holding nearly 210 billion in Russian Continue reading on Medium »
The Room You End Up In
Something went wrong with the AI deployment you championed. The output was wrong, or the volume was wrong, or the wrong people got the Continue reading on Medium »
OpenAI considers slowing advanced AI development, Sam Altman tells employees
Comments
WaterTwin AI: When Water Data Becomes a Decision
From abnormal water usage to evidence-backed action with Gemini, Google ADK, and a system that knows when to abstainContinue reading on Medium »
The Next Checkout Problem Is Not Intelligence. It Is Authority.
AI shopping agents promise convenience. The harder question begins after the recommendation.Continue reading on Medium »
Sean Carroll explains the biggest ideas in the universe – Full Interview [video]
Comments