arXiv Machine Learning
Jun 15
Curvature-Guided Geometric Representation for Protein-Ligand Binding Affinity Prediction
arXiv:2606. 14159v1 Announce Type: new Abstract: Protein-ligand binding affinity (PLA) prediction is critical in drug discovery.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jun 15
The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training
arXiv:2603. 10444v2 Announce Type: replace-cross Abstract: FP4 training promises substantial memory and compute savings for large language models, but remains fragile because blockwise quantization is dictated by extreme activation magnitudes, which inflate dynamic range and compress long-tail signals.
arXiv Machine Learning
Jun 15
A Low-Rank Subspace Analysis of LLM Interventions
arXiv:2606. 14388v1 Announce Type: new Abstract: Interventions designed to modify a particular behavior in LLMs, such as refusal or sycophancy, often produce unintended changes in other behaviors.
arXiv AI
Jun 15
A Virtuous AI is an Existential Risk
arXiv:2606. 13739v1 Announce Type: cross Abstract: This paper examines trade-offs between AI safety and well-being relative to (i) one of the most promising methods for finetuning super-capable AIs, 'Constitutional AI', and (ii) one of the most influential approaches to understanding complex ethical decision making and the conditions for the well-being of rational agents, 'Virtue Ethics'.
arXiv Machine Learning
Jun 15
Private Prediction via PAC Privacy
arXiv:2601. 14033v2 Announce Type: replace Abstract: Machine learning models are increasingly served behind APIs.
arXiv AI
Jun 15
Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulation
arXiv:2606. 14188v1 Announce Type: cross Abstract: We present CORD-SLS, a real-time control method for safe deformable object manipulation, with a focus on ropes and cloth.
arXiv Machine Learning
Jun 15
Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning
arXiv:2606. 14130v1 Announce Type: new Abstract: Safe coordination problems surface in multi-agent reinforcement learning when global safety cannot be enforced by any agent unilaterally: the admissibility of one agent's action may depend on the dynamics of other agents.
arXiv AI
Jun 15
An interpretable unsupervised representation learning for high precision measurement in particle physics
arXiv:2511. 22246v2 Announce Type: replace-cross Abstract: Unsupervised learning has been widely applied to various tasks in particle physics.
arXiv AI
Jun 15
Morphology-Aware Sample Assignment: Overcoming IoU Insensitivity for Surface Defect Detection
arXiv:2606. 13723v1 Announce Type: cross Abstract: Intersection-over-Union (IoU), as a pivotal metric for evaluating the spatial alignment between candidate proposals and ground-truth annotations, directly determines the quality of positive sample sets and the training efficacy of visual detection models.
arXiv AI
Jun 15
Learning Developmental Scaffoldings to Guide Self-Organisation
arXiv:2605. 14998v3 Announce Type: replace Abstract: From subcellular structures to entire organisms, many natural systems generate complex organisation through self-organisation: local interactions that collectively give rise to global structure without any blueprint of the outcome.
arXiv AI
Jun 15
When Sample Selection Bias Precipitates Model Collapse
arXiv:2606. 13732v1 Announce Type: new Abstract: The proliferation of recursive training on synthetic data can alleviate data scarcity but risks model collapse, where repeated training erodes distributional tails and homogenizes outputs.
arXiv Machine Learning
Jun 15
NeST: Neuron Selective Tuning for LLM Safety
arXiv:2602. 16835v2 Announce Type: replace-cross Abstract: Safety alignment is essential for the responsible deployment of Large Language Models (LLMs).
arXiv Machine Learning
Jun 15
Neural Variability Enhances Artificial Network Robustness
arXiv:2606. 13801v1 Announce Type: new Abstract: Neural responses in cortex exhibit substantial trial-to-trial variability in response to repeated stimuli, while peripheral sensory neurons respond far more consistently, leading many to wonder whether stochasticity may carry meaning.
arXiv AI
Jun 15
Order Is Not Control: Driven-Dissipative Response Laws Across Artificial and Biological Systems
arXiv:2606. 12923v2 Announce Type: replace-cross Abstract: AI alignment, interpretability, steering, and neural perturbation studies identify order-inducing objects.
arXiv AI
Jun 15
Recovering Stranded Discrimination in Knowledge Tracing: Per-Item Bias Correction via Empirical-Bayes Shrinkage
arXiv:2606. 14123v1 Announce Type: cross Abstract: Deployed knowledge-tracing models are typically frozen after training, yet systematic per-item logit bias arises, from limited per-item expressivity in backbone architectures and from post-deployment shifts in item properties, degrading prediction quality.
arXiv AI
Jun 15
A Two-Stage Statistical Framework for Evaluating Associative Interference in Large Language Models
arXiv:2606. 14117v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly evaluated for bias using adaptations of human psychological paradigms, yet methodological limitations-particularly the conflation of refusal behavior with task performance-have hindered clear interpretation.
arXiv AI
Jun 15
FAConformer: Frequency-Aware Convolutional Transformer for Auditory Attention Decoding
arXiv:2606. 14120v1 Announce Type: cross Abstract: Auditory attention decoding (AAD) aims to infer the attended speaker from neural responses in multi-speaker acoustic environments and is a key problem for neuro-steered hearing systems.
arXiv AI
Jun 15
WorkBench Revisited: Workplace Agents Two Years On
arXiv:2606. 13715v1 Announce Type: new Abstract: The best agent on WorkBench in March 2024, GPT-4, completed 43% of tasks and took an unintended harmful action, such as emailing the wrong person, on 26% of them.
arXiv Machine Learning
Jun 15
Generative Modeling of Bach-Style Symbolic Music: A Comparative Study of Autoregressive, Latent-Variable, and Adversarial Approaches
arXiv:2606. 13626v2 Announce Type: replace-cross Abstract: We study generative modeling of Bach-style symbolic piano music using a shared MIDI corpus and three model families: autoregressive LSTMs with attention, latent-variable models including recurrent VAEs and vector-quantized VAEs, and generative adversarial networks.
arXiv Machine Learning
Jun 15
A Unified Framework for Structured Flow Modeling: From Representation to Verification and Model Discovery
arXiv:2605. 18250v3 Announce Type: replace-cross Abstract: Many dynamical systems can be described in terms of structured flows combining source/sink behavior, cyclic dynamics, and topology-constrained transport.