1
小鹏智驾出海欧洲：两周微调适配一个国家，计划 2027 年落地 NGP
IT之家 10 月 12 日消息，据彭博社报道，在巴黎车展前夕，小鹏汽车通用智能中心负责人刘先明接受采访时透露，该公司成功在约两周时间内，将智驾系统从一个欧洲国家微调适配到另一个欧洲国家。 刘先明指出，这一适配过程所需的数据量，仅为训练底层人工智能基础模型所需数据的万分之一。 我们只需利用非常少量的…
2
An AI pentest agent that structurally can't hallucinate a vulnerability — and runs offline
用证据门控从结构上杜绝漏洞幻觉的AI渗透测试智能体，全离线运行，安全报告终于不是AI编的故事了
If you point any LLM at a target and ask it to "write a security report," it will confidently invent findings that aren't there: an imagined TLS weakn…
3
Performance of a domain-specific large language model in answering patient questions in psychiatry
精神病学专用模型对战通用聊天机器人，评测医疗问答的临床准确性，AI落地医疗的新探索。
arXiv:2608.22797v1 Announce Type: new Abstract: Background This study was designed to evaluate whether a domain-specific large language model (LLM) tr…
4
Unveiling the Depth-Performance Dilemma in Split-Federated Fine-tuning of LLMs
揭秘LLM拆分联邦微调中的深度-性能权衡，为分布式训练优化提供新视角。
arXiv:2608.22188v1 Announce Type: new Abstract: Split Federated Fine-tuning (SFF) is a promising paradigm for scaling Large Language Models (LLMs) by …
5
6
RAG vs. Fine-Tuning: The AI Engineer's Decision Framework
RAG与微调如何选？一文给出AI工程师的决策框架，帮你告别盲目调参，精准落地生成式AI应用。
The Senior Engineer’s Decision Framework: RAG vs. Fine-Tuning For many engineering teams, the journey into Large Language Models (LLMs) often begins w…
7
Knowing but Not Saying: Preventing Factual Access Failures in LLM SFT via Recall-Anchored Distillation
大模型微调后“知道却说不出口”的难题，用召回锚定蒸馏可精准破解。
arXiv:2608.20794v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) can degrade factual behavior outside the target domain. This degradation …
8
When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems
零样本大模型能否替代精调NLU？这项研究用ATIS和CLINC150实测，给出基于意图空间的决策框架，生产环境选型必看。
arXiv:2608.20371v1 Announce Type: cross Abstract: A common claim is that zero-shot large language models (LLMs) can replace fine-tuned NLU classifiers…
9
Fine-tuning LLMs for Tourist Trajectory Prediction using Field Experiment Data
用田野实验数据微调大模型，精准预测游客轨迹，为智慧城市出行规划提供新思路
arXiv:2608.20830v1 Announce Type: cross Abstract: Evaluating mobility interventions at tourist destinations requires predicting visitor behavior under…
10
RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
微调会破坏大模型拒答防线？这项几何保持微调技术让安全对齐不缩水。
arXiv:2605.01913v2 Announce Type: replace-cross Abstract: Fine-tuning safety-aligned language models for downstream tasks often leads to substantial d…
11
Projector Is All You Train
投影器成训练核心？这篇论文挑战传统微调范式，或为高效训练提供新思路。
arXiv:2608.19726v1 Announce Type: cross Abstract: The typical training process of a multimodal large language model (MLLM) involves adapting both the …
12
Figurative and Cultural Knowledge in LLMs: Investigating Cross-Domain Transfer through Fine-Tuning
微调能否让大模型“懂比喻、懂文化”？跨领域迁移研究揭示语言模型深层认知边界
arXiv:2608.18361v1 Announce Type: new Abstract: Figurative language is deeply culturally embedded; fluent use requires not just linguistic competence …
13
Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements
只用极少GPU就能微调长时程LLM智能体，破解长程推理训练算力困局的新方案。
arXiv:2608.17310v1 Announce Type: new Abstract: Reinforcement Learning (RL) has been promising in single-turn LLM fine-tuning. However, long-horizon a…
14
Pedagogical AI in Mental Health: A Tri-Stream Fine-Tuned LLM Framework for Automated Clinical Supervision and Risk Triage
用微调LLM填补心理督导缺口，自动完成临床监督与风险分流。
arXiv:2608.18438v1 Announce Type: cross Abstract: Modern mental healthcare faces a critical shortage of senior supervisory oversight, leading to a "su…
15
KA2L: A Knowledge-Aware Active Learning Framework for LLMs
提出知识感知主动学习框架，精准提升大模型领域知识的掌握深度，为微调注入新思路。
arXiv:2603.17566v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) with high-quality knowledge has been shown to enhance the…
16
Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization
元学习+LoRA让大模型快速适应跨域偏好，个性化调校从此更聪明高效。
arXiv:2608.12389v1 Announce Type: new Abstract: Cross-domain zero- or few-shot personalization aims to generate user-preferred responses in unseen con…
17
Weightless Fine-Tuning: Personalizing LLMs via Logit-Space Transport
不用改权重，在输出空间“调参”就能个性化LLM，轻量又省资源。
arXiv:2608.11342v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is a standard approach for adapting LLMs to a target distribution, but in…
18
Unsloth Desktop
本地跑AI模型还支持微调，隐私安全且零门槛，桌面端神器。
Run and train AI models locally on your desktop Discussion | Link
19
From Manuals to Maintenance: Fine-Tuning MedGemma for Multi-Modal Imaging System Support in Low-Resource Settings
用微调MedGemma助力低资源地区成像系统维护，医疗AI落地新思路。
arXiv:2608.08896v1 Announce Type: new Abstract: Imaging device downtime is a major barrier to healthcare delivery in low- and middle-income countries …
20
Dual-Node NVIDIA DGX Spark over Tailscale: A Remote-Access Testbed for Distributed LLM Training and Cyber-Threat-Intelligence Fine-Tuning
用两台 NVIDIA DGX Spark 组远程集群，通过 Tailscale 打通分布式 LLM 训练与网络威胁情报微调，实操部署手册齐全。
arXiv:2608.07226v1 Announce Type: cross Abstract: Compact AI systems make local language-model experimentation increasingly accessible, yet practical …