Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 07176v1 Announce Type: cross Abstract: Developing foundation generative models for endoscopy is limited by the gap between natural and clinical images and the computational cost of training large Diffusion Transformers.
arXiv:2608. 06511v1 Announce Type: new Abstract: Adaptive data-cleaning methods replace manual filtering thresholds with data-driven partitions.
arXiv:2608. 07328v1 Announce Type: cross Abstract: Hardware failures require legged robots to rapidly reorganize coordination and gait timing to maintain stability and mobility.
arXiv:2511. 09432v2 Announce Type: replace Abstract: Machine learning (ML) models achieve remarkable performance but remain hard to interpret due to their scale and complexity.
arXiv:2608. 06400v1 Announce Type: new Abstract: Reward models are central to learning from human preferences, yet identifying what drives their predictions remains challenging.
arXiv:2608. 06984v1 Announce Type: cross Abstract: Modern agent harnesses persist state across tasks and sessions through persistent carriers like memory, skills, tools, and shared artifacts.
arXiv:2605. 00123v3 Announce Type: replace Abstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts.
arXiv:2604. 21827v2 Announce Type: replace Abstract: In accomplishing complex tasks, human cognition typically progresses from abstract to concrete (e.
arXiv:2608. 06402v1 Announce Type: new Abstract: Community detection is a fundamental task in graph analytics that aims to identify cohesive groups of entities with similar behaviors or interests.
arXiv:2510. 19399v2 Announce Type: replace Abstract: Spectral bias, the tendency of neural networks to learn low-frequency features first, is a well-known issue with many training algorithms for physics-informed neural networks (PINNs).
arXiv:2608. 05726v1 Announce Type: cross Abstract: Large Language Models (LLMs) are often used as evaluators of text quality, known as LLM-as-a-Judge, which can outperform conventional automatic evaluation metrics that rely on reference texts.
arXiv:2608. 06631v1 Announce Type: cross Abstract: Cryptanalytic extraction has been demonstrated for ReLU networks, for networks using componentwise activations such as GELU or SiLU, and for a Transformer's final projection matrix.
arXiv:2608. 06766v1 Announce Type: cross Abstract: Training changes a network's predictions while allocating task-relevant structure across its internal units.
arXiv:2608. 07068v1 Announce Type: new Abstract: Long-horizon agents accumulate growing contexts during interaction, impairing performance and stability.
arXiv:2608. 06792v1 Announce Type: cross Abstract: Foundation model(FM) for recommendation has shown strong ability to model long-horizon sequential user behavior.
arXiv:2605. 01720v3 Announce Type: replace-cross Abstract: Existing large-scale sign language resources typically provide supervision only at the level of raw video-text alignment and are often produced in laboratory settings.
arXiv:2608. 06564v1 Announce Type: new Abstract: Quantization is how large language models are actually deployed, and below four bits it is known to hurt.
arXiv:2608. 07154v1 Announce Type: cross Abstract: Open-source robotics and foundation models have lowered the barrier to embodied AI, yet language-guided laboratory automation still requires reliable alignment from instructions and observations to safe actions.
arXiv:2606. 08531v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly evolving from simple text-based interaction systems into LLM agents that can maintain memory, use tools, access external environments, and execute tasks.
arXiv:2608. 07192v1 Announce Type: new Abstract: Low-resolution infrared (IR) array sensors represent an interesting solution for privacy-preserving human sensing in embedded systems.