c

cs.CL updates on arXiv.org热榜

更新于刚刚 · 50 条热点

10月10日 11:25 更新，当前榜单前三是「Diffu-LoRA: A Novel…」。「Wieszcz-XIX: A 3.1-…」。「Large Language Mode…」。这是一个人工智能方向的信息源，内容以模型进展、研究与工具发布为主。本页当前收录 50 条，保留cs.CL updates on arXiv.org的原始排序和指标，不把不同平台的数据直接相加，每条标题尽量直达原始页面。本站只做聚合与排序，内容版权归cs.CL updates on arXiv.org及原作者所有。

也常被搜索为：cs.CL updates on arXiv.org热点

Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion Models

cs.CL updates on arXiv.org 2729.9 万热度发布于 23小时前抓取于刚刚

Wieszcz-XIX: A 3.1-Billion-Word Corpus of Pre-1918 Polish and Temporally Bounded Language Models Trained From Scratch

cs.CL updates on arXiv.org 2608.8 万热度发布于 23小时前抓取于刚刚

Large Language Model-Assisted Preparation of Transportation Management Plans: A Case Study with WisDOT WisTMP System

cs.CL updates on arXiv.org 2490.7 万热度发布于 23小时前抓取于刚刚

Cognitive Thermometers: Machine Learning and Logical Complexity

cs.CL updates on arXiv.org 2375.6 万热度发布于 23小时前抓取于刚刚

Lossy Compressive Text Autoencoders

cs.CL updates on arXiv.org 2263.5 万热度发布于 23小时前抓取于刚刚

Clarify, Then Focus: Statement Normalization for Conversation Analytics at Scale

cs.CL updates on arXiv.org 2154.3 万热度发布于 23小时前抓取于刚刚

Grammar Concept Annotation at Scale: Deployed Fine-Tuned Small Language Models Outperform Prompted Frontier Models

cs.CL updates on arXiv.org 2048.1 万热度发布于 23小时前抓取于刚刚

Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute

cs.CL updates on arXiv.org 1944.7 万热度发布于 23小时前抓取于刚刚

Disentangling Linguistic and Paralinguistic Information with Routed Sparse Autoencoders

cs.CL updates on arXiv.org 1844.3 万热度发布于 23小时前抓取于刚刚

Sparse Attention Is Matrix Approximation, Not Choosing from a Bag of Values

cs.CL updates on arXiv.org 1746.8 万热度发布于 23小时前抓取于刚刚

Stochastic Teacher Intervention for Agentic On-Policy Distillation

cs.CL updates on arXiv.org 1652.2 万热度发布于 23小时前抓取于刚刚

Large Language Models for Machine Translation Quality Annotation: Humans and Models Are Both Challenged

cs.CL updates on arXiv.org 1560.4 万热度发布于 23小时前抓取于刚刚

AI4Fire: Evaluating Large Language Models on Wildfire Tasks

cs.CL updates on arXiv.org 1471.5 万热度发布于 23小时前抓取于刚刚

When Citations Mislead? A Claim-Level Benchmark for Legal Hallucination Detection

cs.CL updates on arXiv.org 1385.4 万热度发布于 23小时前抓取于刚刚

Back in Style: A Sociolinguistic Approach to Authoring and Measuring Persona Fidelity in User Simulation

cs.CL updates on arXiv.org 1302.2 万热度发布于 23小时前抓取于刚刚

Prompts versus Rules: Auditing and Controlling Speech Naturalness Behaviors in Voice User Simulators

cs.CL updates on arXiv.org 1221.7 万热度发布于 23小时前抓取于刚刚

FedAlphaEdit: Null-Space-Aligned Merging for Collaborative Knowledge Editing

cs.CL updates on arXiv.org 1144.1 万热度发布于 23小时前抓取于刚刚

Clinician use of language models diverges from how the models are evaluated

cs.CL updates on arXiv.org 1069.2 万热度发布于 23小时前抓取于刚刚

Lapras: Latent Reasoning for Time Series Language Models

cs.CL updates on arXiv.org 997.1 万热度发布于 23小时前抓取于刚刚

SFT-as-Context Mitigates Forgetting in Supervised Fine-Tuning

cs.CL updates on arXiv.org 927.7 万热度发布于 23小时前抓取于刚刚