Explore tools, prompts, skills, news and resources related to arXiv 第2页.
Latest articles, prompts, use cases and editorial content about arXiv 第2页
Researchers introduce neural triage decoding, a framework that uses syndrome consistency to adaptively allocate neural computation for high-rate quantum low-density parity-check codes. A local neural message-passing netw...
Researchers introduce MetaRefine, a lightweight architecture that refines existing image assessment scores using original-image geometry, multi-level visual features, and the frozen model's score. Across 100 configu...
FIRME is a registry-anchored memory graph designed to reconcile recurring investor observations into persistent canonical relationships while retaining source, time, and context. It uses rule-based within-period fusion t...
An arXiv preprint reports that multi-turn reinforcement learning in simulation improved a language model’s structured psychiatric intake performance compared with its identically prompted base model. In 120 encounters wi...
This arXiv paper proposes prefix executability, a trajectory-level evaluation protocol that checks whether every prefix of a predicted tool-call sequence stays executable under tool schemas, state preconditions, and data...
The paper proposes Neighbor Event-Curve Augmentation (NECA), a model-agnostic method that retrieves training-set patients with similar early-window ICU profiles and converts their subsequent organ dysfunction onset times...
The paper presents IMPACT, a physics-informed multimodal deep learning framework for 10- to 110-minute-ahead probabilistic photovoltaic power forecasting. Its four-branch architecture combines plant-level temporal histor...
Researchers present a model-agnostic neurosymbolic framework for interpreting the final hidden layer of audio classifiers through symbolic concept induction. The method is evaluated on music genre classification with GTZ...
A new paper proposes training chain embedding retrievers on their own retrieval histories, including mistakes, rather than only on gold-standard histories. The method mixes these on-policy states with teacher-forced exam...
The paper identifies a sequence-confidence misalignment in reinforcement learning with verifiable rewards: because the advantage is blind to a policy's confidence, a response the policy barely found and one it produ...
This arXiv paper examines role spoofing, an attack in which malicious text—such as content from a tool output or webpage—exploits LLM role confusion to impersonate the user. The authors show that models track speakers us...
Researchers introduce TOME-Math, a large-scale corpus that turns 2,118 university-level mathematics textbooks into roughly 380K structured proof-supervision records while preserving chapter order, proposition-proof links...
Researchers introduce OpenConjecture, a dataset of conjectures drawn from arXiv mathematics papers published since February 2026, and use a random sample of 200 as open problems. Frontier GPT models were run over three p...
EpiCoach is an LLM-agent system that treats a single cross-country mountain biker as the subject of auditable N-of-1 science, keeping claims in an evidence-gated hypothesis registry that requires a probabilistic predicti...
The paper proposes a unified post-training quantization framework for large language models that jointly optimizes quantization ranges, linear transformations, and weight rounding. It derives a Hessian-guided approximati...
Researchers present Guideline-derived Decision Graph (GDGraph), a framework that decouples guideline compilation from case evaluation for radiological risk stratification and management planning. During compilation, a la...
This arXiv study examines looping in dense decoder-only transformers, where weights are reused to make models deeper without increasing parameter count. It finds that looping the full transformer gives the strongest qual...
The paper measures the energy cost of speculative decoding under production serving conditions on H100 and H200 GPUs using SGLang with CUDA graphs, at batch sizes up to 64 across five corpora. It finds that on dense mode...
Researchers adapt a joint embedding predictive architecture (JEPA) to train participant-specific encoders on fMRI data alone, without ever exposing the encoders to stimulus images or image-derived representations. On the...
The paper recasts perturbation-based uncertainty quantification for question answering as a quality-diversity search problem. Its proposed Neighborhood Elites (NE) constructor spreads answer-preserving rewrites across tw...
