arXiv:2604.25370v2 Announce Type: replace-cross Abstract: The release of GPT-image-2 by OpenAI marks a watershed moment in AI-generated imagery: the boundary between photographic reality and synthetic content has never been more difficult to discern. We introduce the GPT-Image-2 Twitter Dataset, the first published dataset of GPT-image-2 generated images, sourced from publicly available Twitter/X posts in the […]
RouteFormer: A Transformer-Based Routing Framework for Autonomous Vehicles
arXiv:2504.05407v2 Announce Type: replace-cross Abstract: Autonomous surveillance missions in Internet of Things (IoT) networks often involve solving NP-hard combinatorial optimization problems to ensure efficient resource utilization. To address the limitations of conventional heuristics in dynamic environments, we propose RouteFormer, a novel framework for single-agent routing in graph-based terrains. RouteFormer creates a synergy between the global […]
A Harmonic Mean Formulation of Average Reward Reinforcement Learning in SMDPs
arXiv:2605.04880v1 Announce Type: cross Abstract: Recent research has revived and amplified interest in algorithms for undiscounted average reward reinforcement learning in infinite-horizon, non-episodic (continuing) tasks. Semi-Markov decision processes (SMDPs) are of particular interest. In SMDPs, discrete actions stochastically generate both rewards and durations, and the objective is to optimize the average reward rate. Existing algorithms […]
Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Network
arXiv:2511.01553v2 Announce Type: replace-cross Abstract: AI systems on edge devices require online continual learning — adapting to non-stationary streams and unfamiliar classes without catastrophic forgetting — under strict power constraints. We present CLP-SNN, a spiking neural network with a self-normalizing local learning rule and a spike-driven neural state machine for autonomous on-chip learning, implemented on […]
Less Is More: Engineering Challenges of On-Device Small Language Model Integration in a Mobile Application
arXiv:2604.24636v2 Announce Type: replace-cross Abstract: On-device Small Language Models (SLMs) promise fully offline, private AI experiences for mobile users (no cloud dependency, no data leaving the device). But is this promise achievable in practice? This paper presents a longitudinal practitioner case study documenting the engineering challenges of integrating SLMs (Gemma 4 E2B, 2.6B parameters; Qwen3 […]
Norm Anchors Make Model Edits Last
arXiv:2602.02543v3 Announce Type: replace-cross Abstract: Sequential Locate-and-Edit (L&E) model editing can fail abruptly after many edits. We identify and formalize this failure as a positive norm-feedback loop, in which solved value vectors and edited MLP weights progressively amplify each other, degrading edit quality and eventually collapsing model capabilities. Our analysis shows that this feedback can […]
Anticipating Innovation Using Large Language Models
arXiv:2605.04875v1 Announce Type: cross Abstract: Forecasting innovation, intended as the emergence of new technological combinations, is a fundamental challenge for science and policy. We show that forthcoming combinations leave an early trace in the collective language of patents, with predictive signals detectable even decades in advance. We show that signal is not attributable to any […]
Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers
arXiv:2603.17771v2 Announce Type: replace-cross Abstract: Attention sinks and massive activations are recurring and closely related phenomena in Transformer models. Existing explanations have largely focused on the forward pass, yet in pre-norm Transformers, large residual-stream norms play only an indirect forward role because sublayers operate on normalized inputs. We study this relationship from the perspective of […]
CAP: Controllable Alignment Prompting for Unlearning in LLMs
arXiv:2604.21251v3 Announce Type: replace-cross Abstract: Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensitive information, necessitating selective knowledge unlearning for regulatory compliance and ethical safety. However, existing parameter-modifying methods face fundamental limitations: high computational costs, uncontrollable forgetting boundaries, and strict dependency on model weight access. These constraints render them impractical for closed-source […]
Co-Learning Port-Hamiltonian Systems and Optimal Energy-Shaping Control
arXiv:2604.26172v2 Announce Type: replace-cross Abstract: We develop a physics-informed learning framework for energy-shaping control of port-Hamiltonian (pH) systems from trajectory data. The proposed approach co-learns a pH system model and an optimal energy-balancing passivity-based controller (EB-PBC) through alternating optimization with policy-aware data collection. At each iteration, the system model is refined using trajectory data collected […]
Assessing Cognitive Effort in L2 Idiomatic Processing: An Eye-Tracking Dataset
arXiv:2605.04857v1 Announce Type: cross Abstract: This paper presents the development and validation of an eye-tracking dataset designed to investigate how second-language (L2) learners process idiomatic expressions. While native speakers often rely on direct retrieval of figurative meanings, L2 speakers frequently adopt a literal-first approach, which incurs measurable cognitive costs. This resource captures these costs through […]
AutoOR: Scalably Post-training LLMs to Autoformalize Operations Research Problems
arXiv:2604.16804v2 Announce Type: replace-cross Abstract: Optimization problems are central to decision-making in manufacturing, logistics, scheduling, and other industrial settings. Translating complicated descriptions of these problems into solver-ready formulations requires specialized operations research (OR) expertise, making it hard to scale. We present AutoOR, a scalable synthetic data generation and reinforcement learning pipeline that trains LLMs to […]