February 2026

arXiv:2602.00929v1 Announce Type: new Abstract: Humans learn abstractions and use them to plan efficiently to quickly generalize across tasks — an ability that remains challenging for state-of-the-art large language model (LLM) agents and deep reinforcement learning (RL) systems. Inspired by the cognitive science of how people form abstractions and intuitive theories of their world knowledge, Theory-Based RL (TBRL) systems, such as TheoryCoder, exhibit strong generalization through effective use of abstractions. However, they heavily rely on human-provided abstractions and […]

Ver mais

arXiv:2602.00927v1 Announce Type: new Abstract: Training LLMs to think and reason for longer has become a key ingredient in building state-of-the-art models that can solve complex problems previously out of reach. Recent efforts pursue this in different ways, such as RL fine-tuning to elicit long CoT or scaling latent reasoning through architectural recurrence. This makes reasoning length an important scaling knob. In this work, we identify a novel phenomenon (both theoretically and experimentally): under outcome-only supervision, out-of-distribution (OOD) […]

Ver mais

arXiv:2602.00924v1 Announce Type: new Abstract: Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack of alignment between learned features and human semantics. In this paper, we address these limitations by adapting unconstrained feature models-a mathematical framework from neural collapse theory-and by supervising the task. We supervise (decoder-only) SAEs to reconstruct feature vectors by jointly learning […]

Ver mais

arXiv:2602.00923v1 Announce Type: new Abstract: The challenge of generating reliable local plans has long hindered practical applications in highly cluttered and dynamic environments. Key fundamental bottlenecks include acquiring large-scale expert demonstrations across diverse scenes and improving learning efficiency with limited data. This paper proposes SanD-Planner, a sample-efficient diffusion-based local planner that conducts depth image-based imitation learning within the clamped B-spline space. By operating within this compact space, the proposed algorithm inherently yields smooth outputs with bounded prediction errors […]

Ver mais

arXiv:2602.00919v1 Announce Type: new Abstract: We introduce Green-VLA, a staged Vision-Language-Action (VLA) framework for real-world deployment on the Green humanoid robot while maintaining generalization across diverse embodiments. Green-VLA follows a five stage curriculum: (L0) foundational VLMs, (L1) multimodal grounding, (R0) multi-embodiment pretraining, (R1) embodiment-specific adaptation, and (R2) reinforcement-learning (RL) policy alignment. We couple a scalable data-processing pipeline (3,000 hours of demonstrations) with temporal alignment and quality filtering, and use a unified, embodiment-aware action interface enabling a single policy […]

Ver mais

arXiv:2602.00918v1 Announce Type: new Abstract: Early Classification of Time Series (ECTS) addresses decision-making problems in which predictions must be made as early as possible while maintaining high accuracy. Most existing ECTS methods assume that the time-dependent decision costs governing the learning objective are known, fixed, and correctly specified. In practice, however, these costs are often uncertain and may change over time, leading to mismatches between training-time and deployment-time objectives. In this paper, we study ECTS under two practically […]

Ver mais

arXiv:2602.00915v1 Announce Type: new Abstract: Cross-embodiment dexterous grasping aims to generate stable and diverse grasps for robotic hands with heterogeneous kinematic structures. Existing methods are often tailored to specific hand designs and fail to generalize to unseen hand morphologies outside the training distribution. To address these limitations, we propose textbf{UniMorphGrasp}, a diffusion-based framework that incorporates hand morphological information into the grasp generation process for unified cross-embodiment grasp synthesis. The proposed approach maps grasps from diverse robotic hands into […]

Ver mais

arXiv:2602.00914v1 Announce Type: new Abstract: We present a lightweight multimodal baseline for emotion recognition in conversations using the SemEval-2024 Task 3 dataset built from the sitcom Friends. The goal of this report is not to propose a novel state-of-the-art method, but to document an accessible reference implementation that combines (i) a transformer-based text classifier and (ii) a self-supervised speech representation model, with a simple late-fusion ensemble. We report the baseline setup and empirical results obtained under a limited […]

Ver mais

arXiv:2602.00913v1 Announce Type: new Abstract: Sentence-level human value detection is typically framed as multi-label classification over Schwartz values, but it remains unclear whether Schwartz higher-order (HO) categories provide usable structure. We study this under a strict compute-frugal budget (single 8 GB GPU) on ValueEval’24 / ValuesML (74K English sentences). We compare (i) direct supervised transformers, (ii) HO$rightarrow$values pipelines that enforce the hierarchy with hard masks, and (iii) Presence$rightarrow$HO$rightarrow$values cascades, alongside low-cost add-ons (lexica, short context, topics), label-wise threshold […]

Ver mais

arXiv:2602.00912v1 Announce Type: new Abstract: Recent initiatives advocating responsible, transparent research assessment have intensified the call to use open research information rather than proprietary databases. This study evaluates the coverage and citation representation of publications recorded in the Current Research Information Systems (CRIS), all instances of the IRIS software platform, of six Italian universities within OpenCitations, a community-owned open infrastructure. Using persistent identifiers (DOIs, PMIDs, and ISBNs) specified in the IRIS installations involved, we matched the publications recorded […]

Ver mais