Stay updated with the latest research and technology news
arXiv:2602.05014v2 Announce Type: replace Abstract: With the rapid progress of tool-using and agentic large language models (LLMs), Retrieval-Augmented Generation (RAG) is evolving from one-shot, passive...
arXiv:2602.05027v2 Announce Type: replace Abstract: Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs...
arXiv:2602.05088v2 Announce Type: replace Abstract: Millions now use generative AI chatbots for psychological support. Despite the promise related to availability and scale, the single most...
arXiv:2602.05183v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly trained in complex Reinforcement Learning, multi-agent environments, making it difficult to understand how behavior...
arXiv:2602.05204v2 Announce Type: replace Abstract: Accurate forecasting of extreme weather events such as heavy rainfall or storms is critical for risk management and disaster mitigation....
arXiv:2602.05281v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs)....
arXiv:2602.05305v2 Announce Type: replace Abstract: Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models. Block diffusion improves...
arXiv:2602.05353v2 Announce Type: replace Abstract: Large Language Models have shown strong capabilities in complex problem solving, yet many agentic systems remain difficult to interpret and...
arXiv:2602.05370v2 Announce Type: replace Abstract: Iterative Direct Preference Optimization has emerged as the state-of-the-art paradigm for aligning Large Language Models on reasoning tasks. Standard implementations...
arXiv:2602.05410v2 Announce Type: replace Abstract: Federated Learning (FL) aims to train a collaborative model while preserving data privacy. However, the distributed nature of this approach...
arXiv:2602.05424v2 Announce Type: replace Abstract: Knowledge graphs (KGs) have become a key ingredient supporting a variety of applications. Beyond the traditional triplet representation of facts...
arXiv:2602.05444v2 Announce Type: replace Abstract: Safety alignment mechanisms in Large Language Models (LLMs) often operate as latent internal states, obscuring the model's inherent capabilities. Building...
arXiv:2602.05448v2 Announce Type: replace Abstract: Selecting the top $m$ from $n$ items via expensive $k$-wise comparisons is fundamental to settings ranging from LLM-based document reranking...
arXiv:2602.05449v2 Announce Type: replace Abstract: While diffusion models have achieved great success in the field of video generation, this progress is accompanied by a rapidly...
arXiv:2602.05512v2 Announce Type: replace Abstract: Large Language Models (LLMs) excel at language understanding but remain limited in knowledge-intensive domains due to hallucinations, outdated information, and...
arXiv:2602.05527v2 Announce Type: replace Abstract: Task-specific microscopy datasets are often too small to train deep learning models that learn robust feature representations. Self-supervised learning (SSL)...
arXiv:2602.05538v2 Announce Type: replace Abstract: Accurate 3D person detection is critical for safety in applications such as robotics, industrial monitoring, and surveillance. This work presents...
arXiv:2602.05687v2 Announce Type: replace Abstract: Individuals are increasingly generating substantial personal health and lifestyle data, e.g. through wearables and smartphones. While such data could transform...
arXiv:2602.05703v2 Announce Type: replace Abstract: SEAL is a static analyser for the verification of programs that manipulate unbounded linked data structures. It is based on...
arXiv:2602.05735v2 Announce Type: replace Abstract: In the era of large foundation models, the quality of embeddings has become a central determinant of downstream task performance...
arXiv:2602.05754v2 Announce Type: replace Abstract: Pipeline parallelism enables training models that exceed single-device memory, but practical throughput remains limited by pipeline bubbles. Although parameter freezing...
arXiv:2602.05817v2 Announce Type: replace Abstract: The rapid expansion of Internet of Things (IoT) ecosystems has led to increasingly complex and heterogeneous network topologies. Traditional network...
arXiv:2602.05863v2 Announce Type: replace Abstract: While Group Relative Policy Optimization (GRPO) has emerged as a scalable framework for critic-free policy learning, extending it to settings...
arXiv:2602.05885v2 Announce Type: replace Abstract: High-quality kernel is critical for scalable AI systems, and enabling LLMs to generate such code would advance AI development. However,...