Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2604. 02765v2 Announce Type: replace Abstract: Class-incremental learning (CIL) is commonly evaluated under predefined schedules with fixed or nearly equal class increments, leaving irregular class-arrival scenarios underexplored.
arXiv:2608. 16259v1 Announce Type: cross Abstract: The rapid progress of image generation models calls for AI-generated image (AIGI) detectors that are not only accurate but also explainable and reliable.
arXiv:2510. 22819v3 Announce Type: replace Abstract: The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly important, as it captures the learner's actual decisions and describes the evolution of the learning process over time.
arXiv:2509. 21514v4 Announce Type: replace Abstract: Research on Knowledge Tracing (KT) models traditionally focuses on improving predictive accuracy.
arXiv:2608. 15901v1 Announce Type: cross Abstract: Continual learning regularizers like EWC fight forgetting by penalizing changes from previous-task parameters with per-parameter importance, typically diagonal Fisher values.
arXiv:2507. 19894v2 Announce Type: replace Abstract: With the rapid advancement of generative models, privacy, copyright, safety, and reliability risks have attracted growing attention.
arXiv:2604. 06628v2 Announce Type: replace Abstract: A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes.
arXiv:2501. 12147v2 Announce Type: replace-cross Abstract: Selecting appropriate training data is crucial for instruction fine-tuning of large language models (LLMs), which aims to (1) elicit strong capabilities, and (2) achieve balanced performance across different tasks.
The paper argues that AI governance should rely on ISO-like interoperability protocols rather than solely on jurisdiction-specific laws. It proposes standardized AI nutrition labels that include metrics for bias, energy usage, and data provenance to enable machine‑readable risk communication across borders. These protocols aim to reduce regulatory fragmentation, lower barriers for SMEs, and build public trust while allowing modular evolution with technology.
arXiv:2608. 16324v1 Announce Type: cross Abstract: We present LaGSplat (Latent Lagrangian Gaussian Splatting), a framework that infers interactive, physics-governed dynamics from one or a few monocular videos.
arXiv:2608. 15980v1 Announce Type: cross Abstract: Preference benchmarks are built by hiring annotators, and the identity of those annotators is treated as an implementation detail.
OGX (Open GenAI Stack) is an open‑source AI application server and Python library that implements the APIs of major frontier labs such as OpenAI, Anthropic, and Google, allowing developers to build agentic AI applications against a single API surface. It supports a wide range of inference providers, vector store backends, and safety backends, and includes a Kubernetes Operator for production deployment. OGX is used as the self‑hosted, model‑agnostic backend for AI‑powered developer tools like Claude Code, Codex CLI, OpenCode, and OpenHands, and has garnered significant community engagement with over 8,400 GitHub stars, 242 contributors, and 4,000 commits.
arXiv:2608. 16513v1 Announce Type: cross Abstract: Recent advances in diffusion models and Transformer architectures have led to significant progress in text-to-video generation.
arXiv:2608. 14711v1 Announce Type: new Abstract: AI coding agent benchmarks rank agents with the Chen et al.
arXiv:2608. 15820v1 Announce Type: cross Abstract: We present QuantumPhaseNet, a gauge-covariant geometric and quantum-spectral extension of Transformer representations.
arXiv:2608. 14828v1 Announce Type: new Abstract: Aligning a language agent to several objectives at once is a persistent failure mode of preference-based training: when objectives are combined additively, optimization collapses onto whichever is cheapest to improve and sacrifices the rest, so a support agent learns to sound warm while giving no real help.
arXiv:2608. 15783v1 Announce Type: cross Abstract: In transfer-learning settings, a model derived from abundant surrogate labels may be deployed in a target population where gold-standard outcomes are unobserved.
arXiv:2608. 14992v1 Announce Type: new Abstract: Language-model systems increasingly read from stores they also write to, so a claim that was merely written earlier can return looking retrieved.
arXiv:2502. 11603v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit strong natural language understanding capabilities but also inherit and amplify societal biases, particularly gender bias, raising fairness concerns.
arXiv:2608. 15256v1 Announce Type: new Abstract: Collaborative training in distributed semantic communication (DSC) networks typically relies on decentralized federated learning (DFL).