arXiv:2512.18399v1 Announce Type: cross Abstract: Tokenization is a critical preprocessing step for large language models (LLMs), directly impacting training efficiency and downstream performance. General-purpose tokenizers trained predominantly on English and Latin-script languages exhibit suboptimal performance on morphologically rich languages such as Arabic, resulting in inflated token sequences and reduced compression efficiency. In this work, we […]
AI reasoning effort predicts human decision time in content moderation
arXiv:2508.20262v2 Announce Type: replace Abstract: Large language models can now generate intermediate reasoning steps before producing answers, improving performance on difficult problems by interactively developing solutions. This study uses a content moderation task to examine parallels between human decision times and model reasoning effort, measured using the length of the chain-of-thought (CoT). Across three frontier […]
ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling
arXiv:2402.06118v4 Announce Type: replace-cross Abstract: By combining natural language understanding, generation capabilities, and breadth of knowledge of large language models with image perception, recent large vision language models (LVLMs) have shown unprecedented visual reasoning capabilities. However, the generated text often suffers from inaccurate grounding in the visual input, resulting in errors such as hallucination of […]
Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement
arXiv:2510.22860v2 Announce Type: replace-cross Abstract: Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in neuroscience. While modern large language models (LLMs) are increasingly used to model neural responses to language, their internal representations are highly “entangled,” mixing information about lexicon, syntax, meaning, and reasoning. […]
An Exploration of Default Images in Text-to-Image Generation
arXiv:2505.09166v5 Announce Type: replace-cross Abstract: In the creative practice of text-to-image (TTI) generation, images are synthesized from textual prompts. By design, TTI models always yield an output, even if the prompt contains unknown terms. In this case, the model may generate default images: images that closely resemble each other across many unrelated prompts. Studying default […]
On the Koopman-Based Generalization Bounds for Multi-Task Deep Learning
arXiv:2512.19199v1 Announce Type: cross Abstract: The paper establishes generalization bounds for multitask deep neural networks using operator-theoretic techniques. The authors propose a tighter bound than those derived from conventional norm based methods by leveraging small condition numbers in the weight matrices and introducing a tailored Sobolev space as an expanded hypothesis space. This enhanced bound […]
TICL+: A Case Study On Speech In-Context Learning for Children’s Speech Recognition
arXiv:2512.18263v1 Announce Type: cross Abstract: Children’s speech recognition remains challenging due to substantial acoustic and linguistic variability, limited labeled data, and significant differences from adult speech. Speech foundation models can address these challenges through Speech In-Context Learning (SICL), allowing adaptation to new domains without fine-tuning. However, the effectiveness of SICL depends on how in-context examples […]
Rethinking Multi-Agent Intelligence Through the Lens of Small-World Networks
arXiv:2512.18094v1 Announce Type: new Abstract: Large language models (LLMs) have enabled multi-agent systems (MAS) in which multiple agents argue, critique, and coordinate to solve complex tasks, making communication topology a first-class design choice. Yet most existing LLM-based MAS either adopt fully connected graphs, simple sparse rings, or ad-hoc dynamic selection, with little structural guidance. In […]
Reinforcement Learning Position Control of a Quadrotor Using Soft Actor-Critic (SAC)
arXiv:2512.18333v1 Announce Type: cross Abstract: This paper proposes a new Reinforcement Learning (RL) based control architecture for quadrotors. With the literature focusing on controlling the four rotors’ RPMs directly, this paper aims to control the quadrotor’s thrust vector. The RL agent computes the percentage of overall thrust along the quadrotor’s z-axis along with the desired […]
The Subject of Emergent Misalignment in Superintelligence: An Anthropological, Cognitive Neuropsychological, Machine-Learning, and Ontological Perspective
arXiv:2512.17989v1 Announce Type: new Abstract: We examine the conceptual and ethical gaps in current representations of Superintelligence misalignment. We find throughout Superintelligence discourse an absent human subject, and an under-developed theorization of an “AI unconscious” that together are potentiality laying the groundwork for anti-social harm. With the rise of AI Safety that has both thematic […]