arXiv:2604.16916v1 Announce Type: new Abstract: Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making tasks, such as multiple-choice questions (MCQs), where abstention is discouraged or unavailable. We identify a systematic failure mode in this setting: reformulating harmful requests as forced-choice MCQs, where all options are unsafe, can systematically bypass refusal behavior, even in models that […]

Ver mais

The most dangerous advice in academia is “just start writing.” It sounds noble. It sounds productive. It is also a lie. Telling a graduate student to “just write” without a structure is like telling a construction crew to “just build” without a blueprint. You might end up with walls, but they won’t hold a roof. You will spend six months pouring concrete only to realize you forgot the plumbing. I see this every year. Brilliant students freeze. They […]

Ver mais

In this tutorial: You will understand that Exploration vs Exploitation is not a button, it is not “epsilon“, but a real data collection strategy, which decides what the agent can learn and how good it can become. You will see why the training reward can lie to you, why an agent without exploration can look “better” on the graph, but actually be weaker in reality. You will learn where exploration actually occurs in an Markov Decision Process(MDP), not […]

Ver mais

Unsupervised pre-training can equip reinforcement learning agents with prior knowledge and accelerate learning in downstream tasks. A promising direction, grounded in human development, investigates agents that learn by setting and pursuing their own goals. The core challenge lies in how to effectively generate, select, and learn from such goals. Our focus is on broad distributions of downstream tasks where solving every task zero-shot is infeasible. Such settings naturally arise when the target tasks lie outside of the pre-training […]

Ver mais

arXiv:2602.22343v1 Announce Type: new Abstract: As interfaces evolve from static user pathways to dynamic human-AI collaboration, no standard methods exist for selecting appropriate interface patterns based on user needs and task complexity. Existing frameworks only provide guiding principles for designing AI agent capabilities. We propose a dimensional framework based on workflow complexity, AI autonomy, and AI reasoning to guide the design of context-aware, scalable AI interfaces aka modalities (e.g., prompt bars, split screens, full screens, etc.). The framework […]

Ver mais

arXiv:2603.00606v1 Announce Type: new Abstract: Accurate 3D hand pose and pressure sensing is essential for immersive human-computer interaction, yet simultaneously achieving both in mobile scenarios remains a significant challenge. We present WristPP, a camera-based wrist-worn system that estimates 3D hand pose and per-vertex pressure from a single wide-FOV RGB frame in real time. A Vision Transformer (ViT) backbone with joint-aligned tokens predicts Hand-VQVAE codebook indices for mesh recovery, while an extrinsics-conditioned branch jointly estimates per-vertex pressure. On a […]

Ver mais

AI agents are already too human. Not in the romantic sense, not because they love or fear or dream, but in the more banal and frustrating one. The current implementations keep showing their human origin again and again: lack of stringency, lack of patience, lack of focus. Faced with an awkward task, they drift towards the familiar. Faced with hard constraints, they start negotiating with reality. — Andreas Påhlsson-Notini, Less human AI agents, please. Tags: ai-agents, coding-agents, ai

Ver mais

arXiv:2604.24767v1 Announce Type: new Abstract: Congenital heart disease (CHD) is the most common type of birth defect, impacting about 1% of live births worldwide. Echocardiography, the gold-standard diagnostic method, is costly and inaccessible in low-resource settings. Diagnosis is delayed due to limited skilled experts, whose ability to interpret pathological patterns varies significantly, causing inter- and intra-clinician variability. Therefore, we present a new method for a more accessible diagnostic modality, the digital stethoscope, to detect CHDs. Our method is […]

Ver mais

arXiv:2603.03418v1 Announce Type: new Abstract: Recently, DeepSeek has invented the manifold-constrained hyper-connection (mHC) approach which has demonstrated significant improvements over the traditional residual connection in deep learning models cite{xie2026mhc}. Nevertheless, this approach has not been tailor-designed for improving hyperspectral image (HSI) classification. This paper presents a clustering-guided mHC Mamba model (mHC-HSI) for enhanced HSI classification, with the following contributions. First, to improve spatial-spectral feature learning, we design a novel clustering-guided Mamba module, based on the mHC framework, that […]

Ver mais

LLM role-playing, i.e., using LLMs to simulate specific personas, has emerged as a key capability in various applications, such as companionship, content creation, and digital games. While current models effectively capture character tones and knowledge, simulating the inner thoughts behind their behaviors remains a challenge. Towards cognitive simulation in LLM role-play, previous efforts mainly suffer from two deficiencies: data with high-quality reasoning traces, and reliable reward signals aligned with human preferences. In this paper, we propose HER, a […]

Ver mais