arXiv:2602.11337v1 Announce Type: new Abstract: Deploying robots at scale demands robustness to the long tail of everyday situations. The countless variations in scene layout, object geometry, and task specifications that characterize real environments are vast and underrepresented in existing robot benchmarks. Measuring this level of generalization requires infrastructure at a scale and diversity that physical evaluation alone cannot provide. We introduce MolmoSpaces, a fully open ecosystem to support large-scale benchmarking of robot policies. MolmoSpaces consists of over 230k […]

Ver mais

arXiv:2604.08646v1 Announce Type: new Abstract: Instruction-based video editing is a natural way to control video content with text, but adapting a video generation model into an editor usually appears data-hungry. At the same time, high-quality video editing data remains scarce. In this paper, we show that a video generation backbone can become a strong video editor without large scale video editing data. We present InsEdit, an instruction-based editing model built on HunyuanVideo-1.5. InsEdit combines a visual editing architecture […]

Ver mais

arXiv:2603.00656v1 Announce Type: new Abstract: Real-world user requests to LLM agents are often underspecified. Agents must interact to acquire missing information and make correct downstream decisions. However, current multi-turn GRPO-based methods often rely on trajectory-level reward computation, which leads to credit assignment problems and insufficient advantage signals within rollout groups. A feasible approach is to identify valuable interaction turns at a fine granularity to drive more targeted learning. To address this, we introduce InfoPO (Information-Driven Policy Optimization), which […]

Ver mais

arXiv:2602.09254v1 Announce Type: new Abstract: Bystander privacy in smart homes has been widely studied in Western contexts, yet it remains underexplored in non-Western countries such as China. In this study, we analyze 49 Chinese smart home apps using a mixed-methods approach, including privacy policy review, UX/UI evaluation, and assessment of Apple App Store privacy labels. While most apps nominally comply with national regulations, we identify significant gaps between written policies and actual implementation. Our traceability analysis highlights inconsistencies […]

Ver mais

arXiv:2601.18128v1 Announce Type: new Abstract: High-dimensional data often exhibit variation that can be captured by lower dimensional factors. For high-dimensional data from multiple studies or environments, one goal is to understand which underlying factors are common to all studies, and which factors are study or environment-specific. As a particular example, we consider platelet gene expression data from patients in different disease groups. In this data, factors correspond to clusters of genes which are co-expressed; we may expect some […]

Ver mais

Large Language Models (LLMs) often incur an alignment tax: safety post-training can reduce general utility (e.g., reasoning and coding). We argue that this tax primarily arises from continual-learning-style forgetting in sequential alignment, where distribution shift and conflicting objectives cause safety updates to overwrite pre-trained competencies. Accordingly, we cast safety alignment as a continual learning (CL) problem that must balance plasticity (acquiring safety constraints) and stability (preserving general abilities). We propose Orthogonal Gradient Projection for Safety Alignment (OGPSA), a […]

Ver mais

Optimally trading-off exploration and exploitation is the holy grail of reinforcement learning as it promises maximal data-efficiency for solving any task. Bayes-optimal agents achieve this, but obtaining the belief-state and performing planning are both typically intractable. Although deep learning methods can greatly help in scaling this computation, existing methods are still costly to train. To accelerate this, this paper proposes a variational framework for learning and planning in Bayes-adaptive Markov decision processes that coalesces variational belief learning, sequential […]

Ver mais

How are you, hacker? 🪐 What’s happening in tech today, February 13, 2026? The HackerNoon Newsletter brings the HackerNoon homepage straight to your inbox. On this day, we present you with these top quality stories. From OpenClaw After the Hype: A Real-World Test of a “Do-Anything” AI Assistant to AI Coding Tip 006 – Review Every Line Before You Commit, let’s dive right in. OpenClaw After the Hype: A Real-World Test of a “Do-Anything” AI Assistant By @navigatingnoise […]

Ver mais