arXiv:2509.14181v1 Announce Type: cross Abstract: Representation learning techniques like contrastive learning have long been explored in time series forecasting, mirroring their success in computer vision and natural language processing. Yet recent state-of-the-art (SOTA) forecasters seldom adopt these representation approaches because…
arXiv:2508.14689v2 Announce Type: replace-cross Abstract: Pre-trained foundation models have demonstrated remarkable success in audio, vision and language, yet their potential for general machine signal modeling with arbitrary sampling rates-covering acoustic, vibration, and other industrial sensor data-remains under-explored. In this work,…
arXiv:2509.13333v1 Announce Type: new Abstract: Large language models (LLMs) can internally distinguish between evaluation and deployment contexts, a behaviour known as emph{evaluation awareness}. This undermines AI safety evaluations, as models may conceal dangerous capabilities during testing. Prior work demonstrated this…
arXiv:2501.19301v2 Announce Type: replace-cross Abstract: The rapid advancement of Large Language Models (LLMs) has revolutionized text generation but also raised concerns about potential misuse, making detecting LLM-generated text (AI text) increasingly essential. While prior work has focused on identifying AI…
arXiv:2509.13352v1 Announce Type: new Abstract: Unmanned Aerial Vehicles (UAVs) are increasingly deployed in defense, surveillance, and disaster response, yet most systems remain confined to SAE Level 2–3 autonomy. Their reliance on rule-based control and narrow AI restricts adaptability in dynamic,…
arXiv:2509.13357v1 Announce Type: new Abstract: We propose semantic fusion, a lightweight scheme that augments a Transformer language model (LM) with a parallel, fuzzy-membership feature channel that encodes token-level semantics. Each token is represented by a vector of interpretable features (e.g.…
arXiv:2509.13347v1 Announce Type: new Abstract: The choice of action spaces is a critical yet unresolved challenge in developing capable, end-to-end trainable agents. This paper first presents a large-scale, systematic comparison of prominent abstracted action spaces and tokenizers for Vision-Language-Action (VLA)…
arXiv:2509.13351v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive capabilities across diverse tasks, yet their ability to perform structured symbolic planning remains limited, particularly in domains requiring formal representations like the Planning Domain Definition Language (PDDL). In…
arXiv:2509.13341v1 Announce Type: new Abstract: Training agents to act in embodied environments typically requires vast training data or access to accurate simulation, neither of which exists for many cases in the real world. Instead, world models are emerging as an…
arXiv:2509.13339v1 Announce Type: new Abstract: This position paper contends that modern AI research must adopt an antifragile perspective on safety — one in which the system’s capacity to guarantee long-term AI safety such as handling rare or out-of-distribution (OOD) events…
