Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 24504v1 Announce Type: new Abstract: We discuss reasons why the scaling exponents of current Large Language Models (LLMs) applications are indicating an unsustainable regime in terms of energy resources.
arXiv:2606. 24237v1 Announce Type: new Abstract: Federated Graph Learning facilitates collaborative graph modeling across distributed clients while preserving data privacy.
arXiv:2601. 22548v4 Announce Type: replace-cross Abstract: Recent research has shown that large language models (LLMs) favor their own outputs when acting as judges, undermining the integrity of automated post-training and evaluation workflows.
arXiv:2606. 24575v1 Announce Type: new Abstract: Modern finance relies heavily on complex machine learning models to find patterns in the stock market.
arXiv:2606. 24231v1 Announce Type: new Abstract: Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are confined to a fixed action vocabulary, while anchor-based methods generate proposals dynamically yet suffer from sparse supervision constrained to a single ground-truth trajectory.
arXiv:2606. 24459v1 Announce Type: new Abstract: Bearing fault diagnosis faces critical challenges when dataset heterogeneity, operating condition variations, and limited labeled data occur simultaneously in industrial environments.
arXiv:2606. 22974v2 Announce Type: replace Abstract: Recent work on preference elicitation in large language models (LLMs) has demonstrated that, when given a series of choices between two outcomes, LLMs reveal a coherent, model-specific utility structure.
arXiv:2602. 15245v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL)-based biomechanical simulations have the potential to revolutionise HCI research and interaction design, but currently lack usability and interpretability.
arXiv:2606. 24164v1 Announce Type: cross Abstract: Recent end-to-end models for EEG-guided target speech extraction report impressive results, underscoring potential for neuro-steered hearing technologies.
arXiv:2508. 16420v3 Announce Type: replace Abstract: Target-conditioned sequence models provide a simple interface for controllable offline decision making, but the requested target return can be an unreliable control signal, especially when the target return lies in underrepresented regions of the dataset.
arXiv:2606. 24046v1 Announce Type: cross Abstract: This work presents a machine learning framework that leverages an autoencoder (AE) for the efficient modeling of FinFET.
arXiv:2602. 02899v2 Announce Type: replace Abstract: Decentralized training is often regarded as inferior to centralized training because the consensus errors between workers are thought to undermine convergence and generalization.
arXiv:2606. 24601v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) addresses the problem of training multiple agents that pursue collaborative, competitive, or mixed objectives.
arXiv:2606. 23741v1 Announce Type: cross Abstract: Causal reasoning, which encompasses the discovery of causal structures and the inference of causal effects, is fundamental to data-driven decision making.
arXiv:2606. 23745v1 Announce Type: cross Abstract: We present JEDEL, a framework for generating synthesis-ready DNA-encoded libraries (DELs) directly from three-dimensional pharmacophore representations of active ligands.
arXiv:2606. 23983v1 Announce Type: cross Abstract: A single forward pass of a capable model is a fast, fluent, and unreliable problem-solver: it is right often enough to be useful and wrong often enough to be dangerous; in language models, such confident errors are known as hallucinations.
arXiv:2606. 21295v2 Announce Type: replace-cross Abstract: Existing sequence models, including RNNs, LSTMs, continuous-time networks, and Transformers, share a common structural principle: layer-wise dynamics, where all neurons in the same layer co-evolve through a shared parameterized operator, leaving individual neurons no freedom to evolve independently.
arXiv:2508. 12042v3 Announce Type: replace Abstract: Federated learning (FL) allows collaborative training of machine learning models across multiple parties without sharing raw data.
arXiv:2606. 24010v1 Announce Type: new Abstract: Multi-agent systems are widely used in safety-critical applications that require coordinated behavior under strict safety constraints.
arXiv:2606. 23991v1 Announce Type: new Abstract: What is an agent?