标签 - 392
NLPNERBERT论文英文写作技巧投稿技巧AgentSubGraphLagnGraphSparse AutoencoderFeature Activation CoverageData SynthesisPost-trainingInterpretabilityLLaMAMistralQwenCross-model TransferPAC-Bayesian TheoryMidtraining分布式桥接灾难性遗忘持续预训练课程学习代码领域数学领域中间训练Neo4jCypher预训练大型语言模型深度学习Zero-ShotHuggingFaceLLM量化8-bitTransformer训练网络CVVLPALBEF多模态对比学习EMAALBERT预训练模型PDFPromptKaggle对抗数据增强知识图谱AttentionBLIPBLIP2BootstrappingQ-Former关系分类LSTMMemory-Network机器学习调参性能测试BLOOM评估基准大模型SpanAAAI2020NestedCRFBiLSTMCoT语言模型Few-Shot思维链ChatMLCMLDataChatGPT数据处理Instruction-Tuning调研报告LLaMA2训练经验句子表示ACL2021词向量交叉熵损失LossThroughputLatency推理加速Continuous-BatchingBatch计算机视觉KerasCyclical学习率特征分析Rank-N微调TensorFlow模型调参参数优化CNNDenseNetCVPR2017Grokking电商应用开发架构设计聚类Fine-TuningEDARLHFPeftTRLLoRAQLoRAPyTorchFLANICLR2022Self-TrainingNeurIPS2020Semi-SupervisedFixMatchGPTRole产品Git主题模型BoostingGBMCredit-ScoreIVWOE强化学习PPOInstructBLIPInverse-ScalingFMGPT-EngineerBabyAGIAutoGPTAIReAct智能体GPT4VLLMMLCCTranslateTensor-ParallelismTokenizerMOSSChatGLMSoft-PromptCLIPSequence-LabelingEmbeddingRAGMASSSeq2SeqMQAGQAMHA部署多并发uWSGIFlask负载测试PythonRPS多线程多进程DropoutMultimodal-LeanringBLIP-2MM-CoTNEZHALayer-NormalizationICML2020Pre-LNPost-LNWarm-up词表TextPrunerXGBoost特征重要性Pointerint4QuantizationBlock-wise-QuantizationNormalFloatFinetuning知识库Agentic RLGradient DisentanglementTool-useReasoningMulti-LoRALEASGRPO梯度冲突RLDLRDropoutKL优化损失函数LangChainRGF预训练语言模型SFLMHard-PromptEMNLP2021robertaData-ScalingSFTSRFTSFT-RL融合熵感知权重数学推理策略优化RFT强化微调搜索智能问答行业分享半监督学习EnsembleSnapshot-Ensembles团队管理工作ChatBIText2SQLStructBERTICLR2020经验总结信息提取大语言模型IEDB数据库Text2DB实操经验上下文Deep-Thinking RatioJensen-Shannon DivergenceTest-Time ScalingChain-of-ThoughtLayer-wise AnalysisEarly StoppingSelf-ConsistencyInference EfficiencyGPT-OSSDeepSeek-R1Qwen3PagedAttentionRNNYunque DeepResearchMulti-AgentDynamic MemorySub-goal DrivenSupervisor ModuleGAIABrowseCompPOMDP层次化架构原子能力池腾讯开源SkillLatexHTMLArxivVicunaBaiChuanYi加速ONNX后训练SWE软件智能体CodeLightGBMCatBoost特征选择ChatIE信息抽取Claude CodeAI 编程助手Agent 架构Prompt Engineering上下文管理SkillsMCP工程化ClaudeLLM产品CondaAnacondacw2vecngramembeddingTransformersTop-KSamplingTop-PBeam-SearcheinsumAIGCStacking评估指标F1KSAUCAccuracy中训练MoERoPEDeepSeekKimiVLMFuyu地理高德Gaiic命名实体提取竞赛自然语言处理Ddrop对抗训练Hexo医疗GPT-4模型调优prompt技巧语义网络图像分类流量预测Spatial-Dropoutskillkimikimi cli实体抽取关系抽取RDFOWLRDFS正则化标签平滑QASimilarityLookaheadOptimizerAdaptationTransfer-learningICL美团技术MobileBERT模型压缩移动端学术会议pipAdamWSGDDatasetTFRecordArchitecture应用架构时间序列交叉验证SSRVPNLinuxUbuntuTransformer-XL长文本可分类卷积分组卷积扩张卷积转置卷积基础知识ZwiftpythonMacosWinEmergentGPT-3