arXiv preprints from January 1, 2026 through September 12, 2026 — 04:09:00 EST
Recent advances in world models have shown promise for modeling future dynamics of environmental states, enabling agents to reason and act without accessing real environments. Current methods mainly perform single-step or fixed-horizon rollouts, leaving their potential for complex task planning under-exploited. We propose...
This chapter examines how data analytics can be leveraged to enhance immersive teacher simulations, situating this inquiry within the broader learning sciences discourse on embodied cognition, data-informed feedback, and teacher professional learning. It explores both conceptual foundations and empirical cases to illustrate how...
Complex decision-making by autonomous machines and algorithms could underpin the foundations of future society. Generative AI is emerging as a powerful engine for such transitions. However, we show that Generative AI-driven developments pose a critical pitfall: fairness concerns. In robotic applications, although intuitions about...
Current AI safety frameworks, which often treat harmfulness as binary, lack the flexibility to handle borderline cases where humans meaningfully disagree. To build more pluralistic systems, it is essential to move beyond consensus and instead understand where and why disagreements arise. We introduce PluriHarms, a benchmark designed...
Despite their growing adoption in education, LLMs remain misaligned with the core principle of effective tutoring: the dialogic construction of knowledge. We introduce ConvoLearn, a dataset of 2,134 semi-synthetic tutor-student dialogues operationalizing six dimensions of dialogic tutoring grounded in knowledge-building theory,...
Veterinary electronic health records (vEHRs) contain privacy-sensitive identifiers that limit secondary use. While PetEVAL provides a benchmark for veterinary de-identification, the domain remains low-resource. This study evaluates whether large language model (LLM)-generated synthetic narratives improve de-identification safety under...
IVF is one of the most widely used ANNS (Approximate Nearest Neighbors Search) methods in vector databases. The idea of redundant assignment is to assign a data vector to more than one IVF lists for reducing the chance of missing true neighbors in IVF search. However, the naive strategy, which selects the second IVF list based on the...
Policy optimization for large language models often suffers from sparse reward signals in multi-step reasoning tasks. Critic-free methods like GRPO assign a single normalized outcome reward to all tokens, providing limited guidance for intermediate reasoning . While Process Reward Models (PRMs) offer dense feedback, they risk...
Graphical User Interfaces (GUIs) are central to human-computer interaction, yet automating complex GUI tasks remains a major challenge for autonomous agents, largely due to a lack of scalable, high-quality training data. While recordings of human demonstrations offer a rich data source, they are typically long, unstructured, and lack...
Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary verification and revisions even if they have reached the correct answers. This limitation stems from the...
Multimodal fake news detection is crucial for mitigating adversarial misinformation. Existing methods, relying on static fusion or LLMs, face computational redundancy and hallucination risks due to weak visual foundations. To address this, we propose DIVER (Dynamic Iterative Visual Evidence Reasoning), a framework grounded in a...
Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs). Most prior work focuses on improving the efficiency of federated learning for LLMs (FedLLM). However, security in open federated environments, particularly defenses against malicious clients, remains underexplored. To...
The hardware-friendly implementation of transcendental functions remains a longstanding challenge in design automation. These functions, which cannot be expressed as finite combinations of algebraic operations, pose significant complexity in digital circuit design. This study introduces a novel approach, TranSC, that utilizes...
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, yet they remain constrained by the finite capacity of their context windows and the inherent difficulty of maintaining long-term factual consistency during multi-hop reasoning. While existing methods utilize context compression or...
As an important paradigm for enhancing the generation quality of Large Language Models (LLMs), retrieval-augmented generation (RAG) faces the two challenges regarding retrieval accuracy and computational efficiency. This paper presents a novel RAG framework called Bridge-RAG. To overcome the accuracy challenge, we introduce the...
Offline meta-reinforcement learning (OMRL) combines the strengths of learning from diverse datasets in offline RL with the adaptability to new tasks of meta-RL, promising safe and efficient knowledge acquisition by RL agents. However, OMRL still suffers extrapolation errors due to out-of-distribution (OOD) actions, compromised by...
Reliable learning of multimodal data (e.g., multi-omics) is a widely concerning issue, especially in safety-critical applications such as medical diagnosis. However, low-quality data induced by multimodal noise poses a major challenge in this domain, causing existing methods to suffer from two key limitations. First, they struggle to...
To meet the ever-increasing demand for computational efficiency, Neural Processing Units (NPUs) have become critical in modern AI infrastructure. However, unlocking their full potential requires developing high-performance compute kernels using vendor-specific Domain-Specific Languages (DSLs), a task that demands deep hardware...
Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from large language models to smaller student models; however, conventional supervised KD often suffers from a distribution mismatch between training and inference. While on-policy KD approaches attempt to mitigate this issue by learning directly from...
From Vision-Language-Action (VLA) systems to robotics, existing egocentric datasets primarily focus on action recognition tasks, while largely overlooking the inherent role of motion analysis in sports and other fast-movement scenarios. To bridge this gap, we propose a real-time motion focus recognition method that estimates the...
Code-switching is a pervasive phenomenon in multilingual communication, yet the robustness of large language models (LLMs) in mixed-language settings remains insufficiently understood. In this work, we present a comprehensive evaluation of LLM capabilities in understanding, reasoning over, and generating code-switched text. We...
Generating high-quality structured data such as JSON records, remains a fundamental challenge for large language models (LLMs), particularly when semantic richness must coexist with strict schema adherence. While autoregressive LLMs offer strong structural consistency, they often struggle with semantic variation and output diversity....
While Large Language Models (LLMs) can generate fluent text, producing high-quality creative stories remains challenging. Reinforcement Learning (RL) offers a promising solution but faces two critical obstacles: designing reliable reward signals for subjective storytelling quality and mitigating training instability. This paper...
Tool use, such as web search, has become a standard capability even in freely available large language models (LLMs). However, existing benchmarks evaluate temporal reasoning mainly in static, non-tool-using settings, which poorly reflect how LLMs perform temporal reasoning in practice. We introduce Time Puzzles, a constraint-based...
This paper investigates PASS-enabled downlink covert communication in the presence of distributed surveillance, where multiple wardens perform signal detection and fuse their local binary decisions via majority-voting rule. We consider a dual-waveguide architecture that simultaneously delivers covert information and randomized jamming...