Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 04335v1 Announce Type: new Abstract: The framework of robust Markov decision processes (RMDPs) allows the design of reinforcement learning agents that satisfy performance guarantees under worst-case transition dynamics.
arXiv:2606. 04920v1 Announce Type: new Abstract: Quantizing deep neural networks is essential for efficient inference on resource-constrained devices.
arXiv:2602. 19799v2 Announce Type: replace-cross Abstract: Despite recent algorithmic advances, we still lack principled ways to leverage the well-documented rescaling symmetries in ReLU neural network parameters.
arXiv:2606. 04613v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) struggle when applied to medical image-text data, yet the tools available to diagnose this failure remain limited.
arXiv:2606. 04168v1 Announce Type: new Abstract: Safety alignment in large language models (LLMs) is fragile in part because it is often shallow: fine-tuning mainly reshapes the model's behavior near the first few output tokens.
arXiv:2602. 19101v2 Announce Type: replace-cross Abstract: Value alignment of Large Language Models (LLMs) requires us to empirically measure these models' actual, acquired representation of value.
arXiv:2605. 07032v2 Announce Type: replace-cross Abstract: The evolution of generative models from next-token predictors to autonomous engines of complex systems necessitates rigorous safety hardening.
arXiv:2605. 24602v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) frequently suffer from object hallucinations, yet the visual perceptual mechanism underlying this failure remains poorly understood.
arXiv:2512. 16919v2 Announce Type: replace-cross Abstract: Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving.
arXiv:2606. 04812v1 Announce Type: cross Abstract: Guaranteeing safety is critical to the deployment of reinforcement learning (RL) agents in the real-world, especially as policies learned using deep RL may demonstrate susceptibility to transition perturbations that result in unknown or unsafe behaviour.
arXiv:2606. 04656v1 Announce Type: cross Abstract: Object detection is a safety-critical component of autonomous driving.
arXiv:2606. 04143v1 Announce Type: cross Abstract: Accurate flood forecasting is essential for mitigating disaster risks and protecting communities.
arXiv:2602. 01146v2 Announce Type: replace Abstract: Conversational assistants are increasingly integrating long-term memory with large language models (LLMs).
arXiv:2606. 04373v1 Announce Type: cross Abstract: Data-Free Quantization (DFQ) addresses data security concerns by synthesizing samples, without accessing real data.
arXiv:2601. 04051v3 Announce Type: replace Abstract: Symbolic regression aims to find symbolic expressions that describe datasets.
arXiv:2605. 07724v2 Announce Type: replace-cross Abstract: Recursive retraining of generative models poses a critical representation challenge: when synthetic outputs are curated based on a fixed reward signal, the model tends to collapse onto a narrow set of outputs that over-optimize that objective.
arXiv:2605. 16331v2 Announce Type: replace-cross Abstract: Protein language models are increasingly used to guide experimental and clinical decisions, yet it is often unclear whether a confident prediction reflects recognition of biological evidence or retrieval of a statistical default.
arXiv:2605. 19294v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) policies increasingly rely on asynchronous inference to hide large-model latency behind ongoing robot motion.
arXiv:2606. 04384v1 Announce Type: new Abstract: Machine learning's reliance on sensitive data necessitates privacy-preserving techniques like Differentially Private Stochastic Gradient Descent (DPSGD).
arXiv:2606. 04486v1 Announce Type: cross Abstract: Watermarking methods for language models have been studied extensively in the autoregressive setting, where tokens are generated sequentially.