Stay updated with the latest research and technology news
arXiv:2506.21039v2 Announce Type: replace Abstract: Long-horizon goal-conditioned tasks pose fundamental challenges for reinforcement learning (RL), particularly when goals are distant and rewards are sparse. While...
arXiv:2506.23116v4 Announce Type: replace Abstract: User experience (UX) practices have evolved in stages and are entering a transformative phase (UX 3.0), driven by AI technologies...
arXiv:2507.12038v4 Announce Type: replace Abstract: In this work, we present a fast distributed algorithm for local potential problems: these are graph problems where the task...
arXiv:2507.13528v3 Announce Type: replace Abstract: TickTacking is a rhythm-based interface that allows users to control a pointer in a two-dimensional space through dual-button tapping. This...
arXiv:2507.18539v3 Announce Type: replace Abstract: K\"onig's lemma is a fundamental result about trees with countless applications in mathematics and computer science. In contrapositive form, it...
arXiv:2507.19634v3 Announce Type: replace Abstract: Recent advances in large language models have laid the foundation for multimodal LLMs (MLLMs), which unify text, speech, and vision...
arXiv:2507.23497v2 Announce Type: replace Abstract: Existing algorithms for explaining the outputs of image classifiers are based on a variety of approaches and produce explanations that...
arXiv:2508.05303v2 Announce Type: replace Abstract: We investigate the use of the Metropolis-Hastings algorithm to sample posterior distribution in a Bayesian inverse problem, where the likelihood...
arXiv:2508.08179v3 Announce Type: replace Abstract: Human motion generation has found widespread applications in AR/VR, film, sports, and medical rehabilitation, offering a cost-effective alternative to traditional...
arXiv:2508.08800v2 Announce Type: replace Abstract: We study robustness to agent malfunctions in cooperative multi-agent reinforcement learning (MARL), a failure mode that is critical in practice...
arXiv:2508.11603v3 Announce Type: replace Abstract: Text-driven 3D editing seeks to modify 3D scenes according to textual descriptions, and most existing approaches tackle this by adapting...
arXiv:2508.12026v2 Announce Type: replace Abstract: Bongard Problems (BPs) provide a challenging testbed for abstract visual reasoning (AVR), requiring models to identify visual concepts fromjust a...
arXiv:2508.13090v2 Announce Type: replace Abstract: The increasing penetration of distributed energy resources (DERs) brings opportunities and challenges to the operation of distribution systems. To ensure...
arXiv:2508.14292v2 Announce Type: replace Abstract: Tokenization shapes how language models perceive morphology and meaning in NLP, yet widely used frequency-driven subword tokenizers (e.g., Byte Pair...
arXiv:2509.04583v2 Announce Type: replace Abstract: We propose an instance-wise adaptive sampling framework for constructing compact and informative training datasets for supervised learning of inverse problem...
arXiv:2509.07825v2 Announce Type: replace Abstract: 3D object segmentation with Large Language Models (LLMs) has become a prevailing paradigm due to its broad semantics, task flexibility,...
arXiv:2509.09135v3 Announce Type: replace Abstract: Existing reinforcement learning (RL) methods struggle with complex dynamical systems that demand interactions at high frequencies or irregular time intervals....
arXiv:2509.11461v2 Announce Type: replace Abstract: Career exploration is uncertain, requiring decisions with limited information and unpredictable outcomes. While generative AI offers new opportunities for career...
arXiv:2509.16072v3 Announce Type: replace Abstract: Language-conditioned robotic manipulation in open-world settings requires not only accurate task execution but also the ability to detect failures for...
arXiv:2509.19877v4 Announce Type: replace Abstract: Deep learning methods for electronic-structure Hamiltonian prediction has offered significant computational efficiency advantages over traditional DFT methods, yet the diversity...
arXiv:2509.21493v2 Announce Type: replace Abstract: We propose Sci2Pol-Bench and Sci2Pol-Corpus, the first benchmark and training dataset for evaluating and fine-tuning large language models (LLMs) on...
arXiv:2509.22075v4 Announce Type: replace Abstract: Post-training compression of large language models (LLMs) often relies on low-rank weight approximations that represent each column of the weight...
arXiv:2509.22138v2 Announce Type: replace Abstract: Wasserstein distances define a metric between probability measures on arbitrary metric spaces, including meta-measures (measures over measures). The resulting Wasserstein...
arXiv:2509.24368v2 Announce Type: replace Abstract: We introduce the first watermark tailored for diffusion language models (DLMs), an emergent LLM paradigm able to generate tokens in...