technocracy

arXiv:2602.07197v1 Announce Type: new Abstract: Deep Neural Networks (DNNs) are vulnerable to backdoor attacks. Due to the nature of Machine Learning as a Service (MLaaS) applications, black-box defenses are more practical than white-box methods, yet existing purification techniques suffer from key limitations: a lack of justification for specific transformations, dataset dependency, high computational overhead, and a neglect of frequency-domain transformations. This paper conducts a preliminary study on various image transformations, identifying down-upscaling as the most effective backdoor trigger […]

Ver mais

Hi I’m currently looking to use DQN to implement an ai that plays yugioh (a two player card game), but have had basically no experience with Ml. I don’t know if I am underestimating the complexity of this, given how complex yugioh is, but with how big the size of the state that needs to be fed in is, along with the number of actions that need to be mapped (possibly around 120 total possible moves, though obviously […]

Ver mais

Visual reinforcement learning is appealing for robotics but expensive — off-policy methods are sample-efficient yet slow; on-policy methods parallelize well but waste samples. Recent work has shown that off-policy methods can train faster than on-policy methods in wall-clock time for state-based control. Extending this to vision remains challenging, where high-dimensional input images complicate training dynamics and introduce substantial storage and encoding overhead. To address these challenges, we introduce Squint, a visual Soft Actor Critic method that achieves faster […]

Ver mais

The point of the blackmail exercise was to have something to describe to policymakers—results that are visceral enough to land with people, and make misalignment risk actually salient in practice for people who had never thought about it before. — A member of Anthropic’s alignment-science team, as told to Gideon Lewis-Kraus Tags: ai-ethics, anthropic, claude, generative-ai, ai, llms

Ver mais

arXiv:2602.07139v1 Announce Type: new Abstract: Millimeter-Wave (mmWave) radar enables camera-free gesture recognition for Internet of Things (IoT) interfaces, with robustness to lighting variations and partial occlusions. However, recent studies reveal that its data can inadvertently encode biometric signatures, raising critical privacy challenges for IoT applications. In particular, we demonstrate that mmWave radar point cloud data can leak identity-related information in the absence of explicit identity labels. To address this risk, we propose {ImmCOGNITO}, a graph-based autoencoder that transforms […]

Ver mais

arXiv:2602.21273v1 Announce Type: new Abstract: Generating multi-frame, action-rich visual narratives without fine-tuning faces a threefold tension: action text faithfulness, subject identity fidelity, and cross-frame background continuity. We propose StoryTailor, a zero-shot pipeline that runs on a single RTX 4090 (24 GB) and produces temporally coherent, identity-preserving image sequences from a long narrative prompt, per-subject references, and grounding boxes. Three synergistic modules drive the system: Gaussian-Centered Attention (GCA) to dynamically focus on each subject core and ease grounding-box overlaps; […]

Ver mais

arXiv:2510.00479v2 Announce Type: replace-cross Abstract: We numerically investigate the feasibility and limits of jointly estimating flow fields and unknown particle properties (e.g., position, size, and density) from Lagrangian particle tracking (LPT) data. LPT offers time-resolved, volumetric measurements of particle trajectories, which are markers of the carrier fluid motion. However, experimental tracks are spatially sparse and potentially noisy, and the problem of reconstructing flow fields may be further complicated by inertial particle transport, such that particle slip velocities must […]

Ver mais

arXiv:2604.15379v1 Announce Type: new Abstract: Modern GPUs adopt chiplet-based designs with multiple private cache hierarchies, but current programming models (CUDA/HIP) expose a flat execution hierarchy that cannot express chiplet-level locality or synchronization. This mismatch leads to redundant memory traffic and poor cache utilization in memory-bound workloads such as LLM inference. We present Fleet, a multi-level task model that maps computation to memory scopes. Fleet introduces Chiplet-tasks, a new abstraction that binds work and data to a chiplet and […]

Ver mais

arXiv:2601.22242v1 Announce Type: new Abstract: A driving algorithm that aligns with good human driving practices, or at the very least collaborates effectively with human drivers, is crucial for developing safe and efficient autonomous vehicles. In practice, two main approaches are commonly adopted: (i) supervised or imitation learning, which requires comprehensive naturalistic driving data capturing all states that influence a vehicle’s decisions and corresponding actions, and (ii) reinforcement learning (RL), where the simulated driving environment either matches or is […]

Ver mais