Stay updated with the latest research and technology news
arXiv:2512.09374v3 Announce Type: replace Abstract: A language is said to be in catalytic logspace if we can test membership using a deterministic logspace machine that...
arXiv:2512.10524v2 Announce Type: replace Abstract: A pre-trained unconditional diffusion model, combined with posterior sampling or maximum a posteriori (MAP) estimation techniques, can solve arbitrary inverse...
arXiv:2512.11585v2 Announce Type: replace Abstract: Traditional measures of closeness and betweenness centrality in networks rely on the shortest paths between nodes. Many standard metrics fail...
arXiv:2512.12307v3 Announce Type: replace Abstract: While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the...
arXiv:2512.12783v3 Announce Type: replace Abstract: Financial exclusion constrains entrepreneurship, increases income volatility, and widens wealth gaps. Underbanked consumers in Istanbul often have no bureau file...
arXiv:2512.14253v2 Announce Type: replace Abstract: In this work, we introduce FLAME, a family of extremely lightweight and capable Time Series Foundation Models, which support both...
arXiv:2512.15922v2 Announce Type: replace Abstract: Despite initial successes and a variety of architectures, retrieval-augmented generation systems still struggle to reliably retrieve and connect the multi-step...
arXiv:2512.16956v2 Announce Type: replace Abstract: Retrieving code functions, classes or files that are relevant in order to solve a given user query, bug report or...
arXiv:2512.17043v2 Announce Type: replace Abstract: Knowledge Graph Question Answering (KGQA) has largely focused on entity-centric queries that return a single answer entity. However, many real-world...
arXiv:2512.17058v2 Announce Type: replace Abstract: We establish the last missing link allowing to describe those complete separable metric spaces $X$ in which the $k$ nearest...
arXiv:2512.17873v2 Announce Type: replace Abstract: Standard diffusion models (DMs) rely on the total destruction of data into non-informative white noise, forcing the backward process to...
arXiv:2512.20113v3 Announce Type: replace Abstract: Subsurface delaminations in concrete bridge decks remain undetectable through conventional visual inspection, necessitating automated non-destructive evaluation methods. This work introduces...
arXiv:2512.21446v2 Announce Type: replace Abstract: Masked diffusion language models (MDLMs) offer the potential for parallel token generation, but most open-source MDLMs decode fewer than 5...
arXiv:2512.21736v3 Announce Type: replace Abstract: High-quality AI-powered video dubbing demands precise audio-lip synchronization, high-fidelity visual generation, and faithful preservation of identity and background. Most existing...
arXiv:2512.22170v2 Announce Type: replace Abstract: Post-training alignment of video generation models with human preferences is a critical goal. Developing effective Reward Models (RMs) for this...
arXiv:2512.22283v3 Announce Type: replace Abstract: PINNs enhance scientific computing by incorporating physical laws into neural network structures, leading to significant advancements in scientific computing. However,...
arXiv:2512.22894v2 Announce Type: replace Abstract: Deceptive UI designs, widely instantiated across the web and commonly known as dark patterns, manipulate users into performing actions misaligned...
arXiv:2512.23075v2 Announce Type: replace Abstract: Policy gradient methods for Large Language Models optimize a policy $\pi_\theta$ via a surrogate objective computed from samples of a...
arXiv:2512.23087v2 Announce Type: replace Abstract: Reinforcement Learning (RL) for Large Language Models (LLMs) faces a fundamental tension: the numerical divergence between high-throughput inference engines and...
arXiv:2512.23213v2 Announce Type: replace Abstract: We propose LLM-PeerReview, an unsupervised LLM Ensemble method that selects the most ideal response from multiple LLM-generated candidates for each...
arXiv:2512.23829v2 Announce Type: replace Abstract: Inverse problems are important mathematical problems that seek to recover model parameters from noisy data. Since inverse problems are often...
arXiv:2512.24985v3 Announce Type: replace Abstract: Vision Language Models (VLMs) are increasingly adopted as central reasoning modules for embodied agents. Existing benchmarks evaluate their capabilities under...
arXiv:2601.01754v2 Announce Type: replace Abstract: Transformers excel empirically on tasks that process well-formed inputs according to some grammar, such as natural language and code. However,...
arXiv:2601.02075v4 Announce Type: replace Abstract: Molecular dynamics (MD) simulations are essential for understanding atomic-scale behaviors in materials science, yet writing LAMMPS scripts remains highly specialized...