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对抗知识图谱数据增强BLIPBootstrappingBLIP2Q-Former关系分类AttentionLSTMMemory-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ChatMLCMLDataInstruction-TuningChatGPT调研报告LLaMA2训练经验数据处理词向量ThroughputLatency推理加速Continuous-BatchingBatch交叉熵损失Loss句子表示ACL2021Cyclical学习率计算机视觉特征分析KerasRank-N微调TensorFlow模型调参参数优化CNNDenseNetCVPR2017电商应用开发架构设计Grokking聚类EDARLHFFine-TuningPeftTRLLoRAFLANICLR2022Self-TrainingNeurIPS2020Semi-SupervisedFixMatchGPTRole产品GitQLoRAPyTorchBoostingGBM主题模型Credit-ScoreIVWOE强化学习PPOInstructBLIPInverse-ScalingFMGPT-EngineerBabyAGIAutoGPTAIReAct智能体GPT4VLLMMLCCTranslateTensor-ParallelismTokenizerMOSSChatGLMSequence-LabelingMASSSeq2SeqSoft-PromptCLIPEmbeddingRAGMQAGQAMHA部署多并发uWSGIFlask负载测试PythonRPS多线程多进程NEZHADropoutMultimodal-LeanringBLIP-2MM-CoTLayer-NormalizationICML2020Pre-LNPost-LNWarm-up词表TextPrunerXGBoost特征重要性PointerDLRDropoutKL优化损失函数int4QuantizationBlock-wise-QuantizationNormalFloatFinetuning知识库LangChainRGF预训练语言模型SFLMHard-PromptEMNLP2021Agentic RLGradient DisentanglementTool-useReasoningMulti-LoRALEASGRPO梯度冲突RLData-ScalingSFTrobertaSRFTSFT-RL融合熵感知权重数学推理策略优化RFT强化微调半监督学习搜索智能问答行业分享EnsembleSnapshot-EnsemblesChatBIText2SQLStructBERTICLR2020团队管理工作经验总结信息提取大语言模型IEDB数据库Text2DB上下文实操经验PagedAttentionDeep-Thinking RatioJensen-Shannon DivergenceTest-Time ScalingChain-of-ThoughtLayer-wise AnalysisEarly StoppingSelf-ConsistencyInference EfficiencyGPT-OSSDeepSeek-R1Qwen3Yunque DeepResearchMulti-AgentDynamic MemorySub-goal DrivenSupervisor ModuleGAIABrowseCompPOMDP层次化架构原子能力池腾讯开源RNNSkillLatexHTMLArxivVicunaBaiChuanYi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cw2vecngramembeddingCondaAnacondaTransformersTop-KSamplingTop-PBeam-SearcheinsumAIGCStacking评估指标F1KSAUCAccuracyVLMFuyuGaiic命名实体提取竞赛自然语言处理Ddrop对抗训练地理高德Hexo医疗GPT-4prompt模型调优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中训练MoERoPEDeepSeekKimi