Off Active
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Activation-Based Active Learning for In-Context Learning: Challenges and Insights
Announce Type: new Abstract: Deep active learning has previously been explored for LLM in-context sample selection, but not with methods that utilise recent advances in understanding of transformer activations. In this paper, we test the hypothesis that model activations could provide a fine-grained signal to optimise the selection of in-context examples. We present the most comprehensive analysis to date of MLP activation-based deep active learning methods applied to in-context learning,...
ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning
arXiv:2505.21457v2 Announce Type: replace Abstract: Active vision, also known as active perception, refers to actively selecting where and how to look in order to gather task-relevant information. It is a critical component of efficient perception and decision-making in humans and advanced embodied agents. With the rise of Multimodal Large Language Models (MLLMs) as central planners in robotic systems, the lack of methods for equipping MLLMs with active perception has become a key gap.
MATraM: A Multi-Activity Transport and Mobility Agent-Based Model for Activity Modifications
arXiv:2605.30547v1 Announce Type: new Abstract: This paper introduces the Multi-Activity Transport & Mobility (MATraM) Agent-Based Model (ABM), a novel framework designed to advance activity-based transport modelling by incorporating dynamic activity adaptation. Traditional transport models simulate system performance using varying levels of abstraction, including flow-based, queue-based, and interaction-based mobility representations. While these approaches differ in their treatment of...
LastAct: Trajectory-Guided Latest-Activity Localization for Real-Time Smart-Home Activity Recognition
arXiv:2606.00260v2 Announce Type: replace Abstract: Human Activity Recognition (HAR) from ambient sensors enables smart-home applications such as health monitoring and assisted living. In realistic deployments, however, sensor events arrive as a continuous stream and activity boundaries are unknown. Sliding-window inference therefore produces many windows that straddle transitions and contain mixed activities, creating boundary contamination that violates the pre-segmented instance...
The Geometry of Activity Cliffs: Representation Dependence and Multi-Scale Characterization of Activity Landscapes
Announce Type: cross Abstract: Activity cliffs, structurally similar compounds with large potency differences, are widely treated as intrinsic features of chemical datasets. We argue that apart from target biology, much of our cliff understanding is a consequence of the geometry induced by the chosen molecular representation, not a property of a molecule pair itself. We designed a six-step pipeline to systematically test this hypothesis.
The Geometry of Activity Cliffs: Representation Dependence and Multi-Scale Characterization of Activity Landscapes
Announce Type: cross Abstract: Activity cliffs, structurally similar compounds with large potency differences, are widely treated as intrinsic features of chemical datasets. We argue that apart from target biology, much of our cliff understanding is a consequence of the geometry induced by the chosen molecular representation, not a property of a molecule pair itself. We designed a six-step pipeline to systematically test this hypothesis.
Structure of an active FlhA ring reveals allosteric coupling between substrate specificity and export engine activation
The bacterial flagellar type III secretion system transports structural subunits in a defined order to assemble the flagellum. FlhA is the core component of this nanomachine; its transmembrane domain functions as an ion-driven export engine and its cytoplasmic domain connected by a flexible linker forms a nonameric ring that controls substrate selection. The coupling mechanism of these activities has remained unclear because the transmembrane domain has resisted structural analysis.
Measuring Maximum Activations in Open Large Language Models
arXiv:2605.15572v2 Announce Type: replace Abstract: The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characterized outlier features and massive activations on pre-2024 LLaMA-style models, and the downstream activation-quantization stack inherits that picture without revisiting it for the post-LLaMA open-model boom. We ask the deployment-oriented question: how large can activations get in modern...
SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks
Announce Type: replace Abstract: The choice of activation function plays a critical role in neural networks, yet most architectures still rely on fixed, uniform activation functions across all neurons. We introduce SmartMixed, a novel two-phase training strategy that allows networks to learn optimal per-neuron activation functions while preserving computational efficiency at inference. In the first phase, neurons adaptively select from a pool of candidate activation functions (ReLU, Sigmoid,...
Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation
arXiv:2606.08682v1 Announce Type: new Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs). By constructing a steering vector from examples of a target behavior and injecting it into intermediate activations during inference, activation steering enables flexible behavioral control while avoiding the permanent parameter updates required by finetuning. Meanwhile, recent work has identified emergent...