Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
The rapid advancement of generative AI models is leading to more realistic deepfake media, encompassing the manipulation of audio, video, or both. This raises severe privacy and societal concerns.
A story about a broken printer, visual inductive bias, and why the race endedin a tie. The post Is Language Visual?
arXiv:2606. 13436v1 Announce Type: new Abstract: Evaluation in machine learning is typically treated as a neutral measurement process.
arXiv:2603. 10834v3 Announce Type: replace-cross Abstract: Understanding how neural networks rely on visual cues offers a human-interpretable view of their internal decision processes.
arXiv:2606. 12713v1 Announce Type: new Abstract: Claims that artificial general intelligence has already arrived and claims that it remains decades away are often defended from overlapping evidence.
arXiv:2603. 00610v3 Announce Type: replace-cross Abstract: While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind.
arXiv:2606. 12923v1 Announce Type: cross Abstract: AI alignment, interpretability, steering, and neural perturbation studies identify order-inducing objects.
arXiv:2606. 12886v1 Announce Type: cross Abstract: Interleaved thinking, where a unified multimodal model alternates between textual reasoning and visual generation, has shown promise on spatial and physical tasks.
arXiv:2602. 13379v2 Announce Type: replace-cross Abstract: LLM-based agents are becoming increasingly capable, yet their safety lags behind.
arXiv:2602. 00343v2 Announce Type: replace-cross Abstract: Federated learning (FL) enables collaborative model training over privacy-sensitive, distributed data, but its environmental impact is difficult to compare across studies due to inconsistent measurement boundaries and heterogeneous reporting.
arXiv:2602. 14367v2 Announce Type: replace-cross Abstract: The rapid evolution of Large Language Models has catalyzed a surge in scientific idea production, yet this leap has not been accompanied by a matching advance in idea evaluation.
arXiv:2606. 12443v1 Announce Type: cross Abstract: Social roles shape expectations, priorities, and judgments, yet it remains unclear how large language models (LLMs) associate occupational identities with broader cultural value patterns.
arXiv:2604. 07590v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) is widely used to ground large language models in external knowledge sources.
arXiv:2606. 12747v1 Announce Type: new Abstract: Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs.
arXiv:2602. 18154v2 Announce Type: replace-cross Abstract: Jailbreaking poses a significant risk to the deployment of Large Language Models (LLMs) and Vision Language Models (VLMs).
arXiv:2601. 04885v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) serve a global audience, alignment must transition from enforcing universal consensus to respecting cultural pluralism.
arXiv:2606. 13258v1 Announce Type: new Abstract: Gait-based Parkinson's disease assessment increasingly relies on heterogeneous sensors, but clinical systems rarely collect all modalities simultaneously.
arXiv:2606. 12871v1 Announce Type: new Abstract: Search Agents (SAs) typically leverage large language models (LLMs) to support complex information-seeking tasks by autonomously exploring web sources and synthesizing information into comprehensive responses.
arXiv:2606. 12657v1 Announce Type: new Abstract: Human mobility data is important for transportation, urban planning, and epidemic control, but large-scale trajectory collection is often costly and privacy-constrained, motivating realistic synthetic trajectory generation.
arXiv:2606. 12809v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are trained on massive multimodal data, making data unlearning increasingly important as data owners may request the removal of specific content.