Stay updated with the latest research and technology news
arXiv:2601.18012v2 Announce Type: replace Abstract: Large language models are now used daily for writing, search, and analysis, and their natural language understanding continues to improve....
arXiv:2601.18231v2 Announce Type: replace Abstract: Adapting pre-trained models to unseen feature modalities has become increasingly important due to the growing need for cross-disciplinary knowledge integration....
arXiv:2601.18374v2 Announce Type: replace Abstract: City council minutes are typically lengthy and formal documents with a bureaucratic writing style. Although publicly available, their structure often...
arXiv:2601.18435v2 Announce Type: replace Abstract: Predicting clinical severity from genotype remains a fundamental challenge in molecular medicine, particularly for enzymes whose function depends on sub-atomic-scale...
arXiv:2601.18588v2 Announce Type: replace Abstract: Training stability is typically regarded as a prerequisite for reliable optimization in large language models. In this work, we analyze...
arXiv:2601.18626v2 Announce Type: replace Abstract: Natural gradients have long been studied in deep reinforcement learning due to their fast convergence properties and covariant weight updates....
arXiv:2601.18702v3 Announce Type: replace Abstract: The pursuit of scale in deep learning has entrenched a trade-off: computational throughput is prioritized at the expense of numerical...
arXiv:2601.19171v2 Announce Type: replace Abstract: While generative AI enables high-fidelity UI generation from text prompts, users struggle to articulate design intent and evaluate or refine...
arXiv:2601.19245v3 Announce Type: replace Abstract: Hallucination detection is critical for deploying large language models (LLMs) in real-world applications. Existing hallucination detection methods achieve strong performance...
arXiv:2601.19261v2 Announce Type: replace Abstract: Split learning is a distributed training paradigm where a neural network is partitioned between clients and a server, which allows...
arXiv:2601.19490v2 Announce Type: replace Abstract: Fact-checking remains a demanding and time-consuming task, still largely dependent on manual verification and unable to match the rapid spread...
arXiv:2601.19500v2 Announce Type: replace Abstract: It is well known that reusing cryptocurrency addresses undermines privacy. This also applies if the same addresses are used in...
arXiv:2601.19612v2 Announce Type: replace Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.g. simulated)...
arXiv:2601.19933v3 Announce Type: replace Abstract: Large language models exhibit a systematic tendency toward early semantic commitment: given ambiguous input, they collapse multiple valid interpretations into...
arXiv:2601.20125v3 Announce Type: replace Abstract: Diffusion Language Models (DLMs) represent a promising alternative to autoregressive language models, using bidirectional masked token prediction. Yet their susceptibility...
arXiv:2601.20232v2 Announce Type: replace Abstract: Visual Prompt Tuning (VPT) adapts a frozen Vision Transformer (ViT) to downstream tasks by inserting a small number of learnable...
arXiv:2601.20800v2 Announce Type: replace Abstract: We propose conditional PED-ANOVA (condPED-ANOVA), a principled framework for estimating hyperparameter importance (HPI) in conditional search spaces, where the presence...
arXiv:2601.20917v2 Announce Type: replace Abstract: We present masked Lagrange reconstruction, a technique that enables threshold ML-DSA (FIPS 204) with arbitrary thresholds $T$ while producing standard...
arXiv:2601.21008v2 Announce Type: replace Abstract: Operations Research practitioners routinely debug infeasible models through an iterative process: analyzing Irreducible Infeasible Subsystems (\IIS{}), identifying constraint conflicts, and...
arXiv:2601.21083v3 Announce Type: replace Abstract: As large language models (LLMs) improve, so do their offensive applications: frontier agents now generate working exploits for under $50...
arXiv:2601.21183v2 Announce Type: replace Abstract: Reasoning models frequently agree with incorrect user suggestions -- a behavior known as sycophancy. However, it is unclear where in...
arXiv:2601.21239v2 Announce Type: replace Abstract: Although Large Language Models have advanced Automated Heuristic Design, treating algorithm evolution as a monolithic text generation task overlooks the...
arXiv:2601.21449v2 Announce Type: replace Abstract: Scaling data volume and diversity is critical for generalizing embodied intelligence. While synthetic data generation offers a scalable alternative to...
arXiv:2601.21452v2 Announce Type: replace Abstract: While works such as OneRec have validated the scaling laws of Large Language Models (LLMs) in recommender systems, they rely...