Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2601. 11541v2 Announce Type: replace-cross Abstract: To address the scalability of feedback in computer science while mitigating the privacy and cost limitations of commercial Large Language Models (LLMs), this study evaluates a locally hosted Small Language Model (SLM).
arXiv:2507. 09751v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but exhibit problems with logical consistency in their output.
arXiv:2606. 09132v1 Announce Type: new Abstract: Visual Language Models (VLMs) have gained significant popularity due to their remarkable ability.
arXiv:2606. 07640v1 Announce Type: cross Abstract: This study investigates the trade-offs between fidelity, privacy, and utility in synthetic data generation under conditions of data scarcity and privacy sensitivity.
arXiv:2601. 19082v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, coordinate, and act on behalf of users.
arXiv:2606. 08405v1 Announce Type: new Abstract: While data-intensive deep reinforcement learning can optimize complex control policies, scientific discovery in physical systems fundamentally requires an interpretable chain of reasoning that connects physical evidence to structured control architectures.
arXiv:2606. 08063v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in visual understanding, yet their performance degrades significantly under real-world visual corruptions.
arXiv:2606. 08016v1 Announce Type: cross Abstract: Current image editing software often hinges on fixed filters or expert tuning, leaving a gap between amateur users' intent and outcomes.
arXiv:2606. 09475v1 Announce Type: new Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misaligned behavior.
arXiv:2601. 04266v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are widely deployed in safety-critical embodied AI applications such as robotics.
arXiv:2512. 07355v2 Announce Type: replace Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge.
arXiv:2606. 08021v1 Announce Type: cross Abstract: As large language model (LLM) agents are integrated into autonomous cloud operations, distributed systems face a semantic reliability problem: proposer agents can generate production mutations, such as modifying IAM policies, opening firewall security groups, or executing data exports, that are syntactically valid and statically authorized but operationally unsafe.
arXiv:2606. 09315v1 Announce Type: cross Abstract: BCI-to-agent pipelines turn decoded neural activity into an authorization channel for tool-use agents, exposing a new attack surface we call \emph{brain-prompt injection}: signal-side perturbations, context-only injections, and adaptive dual-decoder attacks can all change the routed action while EEG-side or text-side monitors remain blind.
arXiv:2606. 09749v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks.
arXiv:2604. 09967v2 Announce Type: replace-cross Abstract: Muon has emerged as a promising optimizer for large-scale foundation model pre-training by exploiting the matrix structure of neural network updates through iterative orthogonalization.
arXiv:2605. 21028v2 Announce Type: replace-cross Abstract: Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks as long-range anchors.
arXiv:2606. 07706v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated strong performance across multimodal tasks, yet their safety robustness remains an open challenge.
arXiv:2606. 09377v1 Announce Type: cross Abstract: Formal neural network verification -- proving that a network satisfies safety properties for \emph{all} inputs in a specified domain -- is bounded in practice by GPU memory: standard implementations of bound-propagation algorithms (IBP, CROWN, $\alpha$-CROWN) require weight and relaxation-coefficient matrices to reside entirely on one accelerator.
arXiv:2604. 04251v2 Announce Type: replace Abstract: Intelligent tutoring systems increasingly rely on reinforcement learning to personalise instruction, yet optimising for observable engagement signals can systematically decouple learner activity from genuine knowledge acquisition.
arXiv:2605. 17254v3 Announce Type: replace Abstract: Property prediction and inverse structural design of catalytic materials are typically modeled as two independent tasks: the former predicts target properties from given structures, whereas the latter generates candidate structures according to desired properties.