Stay updated with the latest research and technology news
arXiv:2602.01291v1 Announce Type: new Abstract: Recent advances in large language models have demonstrated impressive capabilities in mathematical formalization. However, existing benchmarks focus on logical verification...
arXiv:2602.01294v1 Announce Type: new Abstract: We propose a neuromorphic solver for the NP-hard Edge User Allocation problem using an attractor network with Winner-Takes-All (WTA) mechanism...
arXiv:2602.01295v1 Announce Type: new Abstract: We investigate episodic Markov Decision Processes with heavy-tailed feedback (HTMDPs). Existing approaches for HTMDPs are conservative in stochastic environments and...
arXiv:2602.01296v1 Announce Type: new Abstract: 3D line mapping from multi-view RGB images provides a compact and structured visual representation of scenes. We study the problem...
arXiv:2602.01297v1 Announce Type: new Abstract: Electronic medical records (EMRs), particularly in neurology, are inherently heterogeneous, sparse, and noisy, which poses significant challenges for large language...
arXiv:2602.01298v1 Announce Type: new Abstract: Image-based object removal often erases only the named target, leaving behind interaction evidence that renders the result semantically inconsistent. We...
arXiv:2602.01299v1 Announce Type: new Abstract: Ill-founded (or non-wellfounded) proof systems have emerged as a natural framework for inductive and coinductive reasoning. In such systems, soundness...
arXiv:2602.01301v1 Announce Type: new Abstract: Scalar extrapolation and convergence acceleration methods are central tools in numerical analysis for improving the efficiency of iterative algorithms and...
arXiv:2602.01303v1 Announce Type: new Abstract: Generating coherent visual stories requires maintaining subject identity across multiple images while preserving frame-specific semantics. Recent training-free methods concatenate identity...
arXiv:2602.01304v1 Announce Type: new Abstract: We often assume that agent-to-agent interaction will mirror human conversation. However, agents operate fundamentally differently. What if they could develop...
arXiv:2602.01305v1 Announce Type: new Abstract: Large multimodal models have enabled one-click storybook generation, where users provide a short description and receive a multi-page illustrated story....
arXiv:2602.01306v1 Announce Type: new Abstract: Maintaining visual and semantic consistency across frames is a key challenge in text-to-image storytelling. Existing training-free methods, such as One-Prompt-One-Story,...
arXiv:2602.01308v1 Announce Type: new Abstract: This work investigates the optimization instability of deep neural networks from a less-explored yet insightful perspective: the emergence and amplification...
arXiv:2602.01311v1 Announce Type: new Abstract: Workflow automation has become increasingly accessible through low-code platforms, enabling small organizations and individuals to improve operational efficiency without extensive...
arXiv:2602.01312v1 Announce Type: new Abstract: Data attribution, tracing a model's prediction back to specific training data, is an important tool for interpreting sophisticated AI models....
arXiv:2602.01313v1 Announce Type: new Abstract: Long-term conversational memory is essential for LLM-based assistants, yet existing benchmarks focus on dyadic, single-topic dialogues that fail to capture...
arXiv:2602.01315v1 Announce Type: new Abstract: In this article, we develop a fully discrete numerical scheme for the one-dimensional (1D) and two-dimensional (2D) viscous Burgers equations...
arXiv:2602.01317v1 Announce Type: new Abstract: Decentralized Finance (DeFi) has turned blockchains into financial infrastructure, allowing anyone to trade, lend, and build protocols without intermediaries, but...
arXiv:2602.01322v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have emerged as a promising method for interpreting neural network representations by decomposing activations into sparse combinations...
arXiv:2602.01326v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) present a compelling alternative to autoregressive models, offering flexible, any-order infilling without specialized prompting design. However,...
arXiv:2602.01329v1 Announce Type: new Abstract: Flow Matching (FM) has recently emerged as a powerful approach for high-quality visual generation. However, their prohibitively slow inference due...
arXiv:2602.01331v1 Announce Type: new Abstract: Contemporary large language model (LLM)-based multi-agent systems exhibit systematic advantages in deep research tasks, which emphasize iterative, vertically structured information...
arXiv:2602.01334v1 Announce Type: new Abstract: Vision tool-use reinforcement learning (RL) can equip vision-language models with visual operators such as crop-and-zoom and achieves strong performance gains,...
arXiv:2602.01335v1 Announce Type: new Abstract: A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impactful...