Training (학습/파인튜닝)

Training (학습/파인튜닝) 관련 AI 뉴스를 한국어로 요약해 드립니다.

이 카테고리에서 얻을 수 있는 정보

Training (학습/파인튜닝) 카테고리는 글로벌 AI/ML 뉴스에서 해당 주제와 직접 연결된 핵심 기사만 모아 빠르게 탐색할 수 있는 허브입니다. 태그별 빈도와 최신성을 함께 확인해 흐름을 파악하고, 관심 주제의 상세 기사로 바로 이동할 수 있습니다.

관심 태그 추가

LoRA228 GRPO160 RL110 RLHF99 PPO90 RLVR33 DPO32 XGBoost30 SFT27 AdamW18 DINO17 QLoRA14 PEFT12 SAC12 Behavior Cloning11 DQN11 Active Learning9 Continual Learning9 Random Forest9 Deep Learning8 Physical AI8 Backpropagation7 Gradient Descent7 On-policy distillation7 Bayesian Inference6 Multimodal RL6 OPSD6 Variational Inference6 Contrastive learning5 cross entropy5 Distributed Training5 Federated Learning5 Fine-tuning5 Graph Neural Network5 Imitation Learning5 OPD5 Rectified Flow5 Self-play5 Sim-to-Real5 Test-Time Training5 DAPO4 DMD4 Predictive Coding4 Self-Supervised Learning4 DAgger3 Ensemble Methods3 Group Relative Policy Optimization (GRPO)3 HACPO3 HG-DAgger3 Pre-training3 REINFORCE3 RLAIF3 SDPO3 Self Forcing3 STDP3 TD33 Transfer Learning3 UMAP3 ALS2 Barlow Twins2 BetaZero2 Causal RL2 Compositional Learning2 Curriculum Learning2 Data Augmentation2 DDP2 DIAYN2 Domain Adaptation2 double descent2 Dropout2 EMA2 ERD2 Franca2 GAIL2 GiGPO2 GloVe2 Go-Explore2 Gradient Boosting2 GRAM2 GSPO2 gVisor2 Hamiltonian-SMT2 Hebbian Learning2 IMG Sign2 InfoNCE2 Instruction Tuning2 Inverse Dynamics2 MAP-Elites2 Maximum Likelihood Estimation2 MEMIT2 Neuro-Symbolic2 Online Learning2 Optogenetics2 ORB2 Physics-Informed ML2 POMCP2 PRM2 Prompt Tuning2 Pseudo-Labeling2 QAT2 REPO2 reward hacking2 Reward Hypothesis2 Reward Model2 RFT2 Ridge regression2 RLMF2 Self-Distillation2 Self-Refine2 3DreamBooth1 8-fold data augmentation1 A2C1 A3C1 ABC1 Ability-aware Environment Selection (AES)1 ACC1 Adaptive Gradient Clipping1 ADMIRE1 Adversarial Evolution1 AdvFD1 AES-SIV1 AGE1 Agentic Data Flow1 Agentic RL1 Agentic Training1 AgentOPSD1 AGI safety course1 ALTER1 AMVL1 Anchor-Align1 Answer-Backtracked Credit Assignment (ABC)1 ARC-Forcing1 Arithmetic Repetition Complexity1 Astrolabe1 AtomiMed1 Attention Z-Reg1 autoresearch@home1 AWR1 Back-translation1 BEACON1 BERTMap1 Bilinear Game1 Behavioral Multi-Token Prediction (BMTP)1 Boosted Control Function1 Boosting1 BRAID1 C3-GP1 CAA1 CAPI1 CAST1 Catastrophic Forgetting1 Causal Analysis1 Causal-rCM1 CCPL1 CE1 Centroid1 CLaaS1 CLeaD1 CLIP-style objective1 Coconut-style1 Complete(d)P1 Concept Data Attribution1 Consistency Distillation1 ConstrainedZero1 Continual RL1 Continuous Learning1 Continuous Online Learning1 Contrastive Decoding Diffing1 ControlG1 convolve1 Coreset Selection1 CoRT1 Counterfactual Perturbation Consistency1 CoVe1 CPDN1 CPR1 Cross-Layer Value Routing (CLVR)1 Cross-modal Distillation1 Cycle-Consistency1 DanceOPD1 DAPD1 DAPR1 DART-SD1 Data-Conditioned Method Planning1 Data-Construction-Skill1 Data Labeling1 Dataset Enrichment1 ddiff1 Deep Delta Learning1 Deep Clustering1 DeepSearch-Evolve1 DenoiseRL1 Dense Panoramic Ray-Conditioning (DPRC)1 DICE-RL1 Diffusion-based Semantic Compression (DiSCo)1 DiffusionNFT1 DiffusionOPSD1 diffusion teacher1 Digital Red Queen1 Direct-OPD1 Disentanglement1 Distribution Matching1 DO-ALL1 DOPD1 dOPSD1 DPE1 DP-FedGD1 DPPR1 DP-SGD1 DreamBooth1 Dream Rehearsal1 Dr. GRPO1 Drop-Then-Recovery (DTR)1 DRQ1 DSDR1 Dueling DDQN1 dynamic_select1 Elastic-net1 EML1 Empirical Likelihood1 Empirical Risk Minimization1 End-to-End Learning1 Epsilon-greedy1 Equivariant Optimal-Transport Flow Matching1 ERM1 ESPO1 Evidential Learning1 Evolutionary Strategies1 EWC1 Exact-match Caching1 Expectation Maximization1 Faithful-RFT1 FastOPD1 FastSVERL1 f-divergence1 FD-Loss1 FedAvg1 FedNova1 FedProx1 FedUMM1 FIM1 FlashSAC1 FlowMirror1 Flux-GS1 Focal Loss1 FOCUS1 From Scratch1 FullFT1 Fused Lasso1 GBNF1 GDPO1 Generative Causal Testing (GCT)1 Genetic Programming1 GenFirst1 GenomeDiff1 Geometry-Aware Memory Augmentation (GMA)1 GeoPT1 GFPO1 GIFT1 GP-C-LUCB1 Gradient Accumulation1 Gradient-Based Connections1 Group Based RL1 Grouped Cross-Entropy (GCE)1 He Initialization1 HeRA1 Hierarchical Difficulty Curriculum (HDC)1 HIL1 Holistic Data Scheduler1 Homoscedastic Uncertainty Weighting1 IC-LoRA1 ICRL1 ID Representation Forcing1 Implicit Differentiation1 Implicit Error Counting (IEC)1 InfoPO1 InnerZoom1 INSIGHT1 Instruction Selection1 Interdisciplinary Doctoral Program in Statistics (IDPS)1 J-Zero1 Keyframe Evidence Memory1 KNN1 Laplacian Visual Prompting1 Latent Lookahead1 LESS1 LIMEN1 LIPPAX1 LK Loss1 LLM-teacher Distillation1 LMO1 Local Extra SGD1 Local Learning Rule1 LOEO1 Logit Mixing1 LoKR1 LongForcing1 LoopRPT1 LOPE1 LoRS1 Louvain1 LSVI-UCB1 MALA1 Manana1 MANCE1 Manifold Bandits1 MAPD1 Masked Boundary Modeling1 Masked Depth Modeling1 Matryoshka Learning1 MAXIS Loss1 MaxSim1 MeanFlowNFT1 Medprompt1 MegaTrain1 MemLearner1 Memory-R11 Meta-Learning1 MET-D1 Midtraining1 MIM1 MindForge1 MIPI1 MIPU1 Mixture-of-Kittens1 MixUp1 ML Modelling1 MMProLong1 Momentum1 Monte Carlo Dropout1 MOPD1 MRPO1 MSE1 MSFT1 MultAttnAttrib1 Multi4D1 Multiprobe Grid1 Multi-Task Learning1 MultiTF1 MV-Forcing1 Native Factorized Weights (NFW)1 NCE1 NEAT1 Nested Learning1 Next-Token Prediction1 NOCs1 Noise Contrastive Estimation1 Nonlinear Regression1 NoRA1 Numeric Gradient1 OAR-Flow1 OGAR1 OmniBoost1 OmniDPO1 Open-Reasoner-Zero1 OPID1 OPSA1 Optimization1 OraRL1 OrthoReg1 OSCAR1 OSFB1 Oversampling1 PAC Learning1 Parallel-RL1 Parameter-Efficient Fine-Tuning1 Pass-Conditioned Reading1 PatternRL1 PDM1 PEPO1 Perceptual Hashing1 Perceptual Flow Matching1 PGD1 Stability Metric Φ1 PICA1 PipeDream-2BW1 PIPO1 PIRL1 PivotRL1 POET-X1 Policy Conditioning1 Policy Gradient1 Policy Iteration1 Policy Optimization1 PopuLoRA1 Post-training1 PowerCool1 PRA1 PRA-GRPO1 Prior Selection1 Progress Advantage1 Progressive Training1 Protein Language Model1 Prototypical Contrastive Learning1 Proxy Prompt Reinforcement Learning1 PTR1 Pulsed Learning1 PuzzleMix1 Q-Synth Module1 Quantization-Aware Healing1 Quantization-Aware Training1 Quantum Machine Learning1 RAD-GRPO1 RAHA1 RayPE1 RCORE1 rDPO1 ReGFT1 Relay-OPD1 Remember‑R11 Requential Coding1 Resource2Skill1 Reverse KL1 Reverse-KL Divergence1 reward shaping1 RFE1 Riemannian Flow Matching1 RLHEV1 RL-Index1 RLinf1 RLOO1 RLSD1 RLSVR1 RLVF1 R-MFT1 RoboTTT1 RoCEv21 rollback reward1 ROPD1 RP-SFT1 SA-DMD1 SAGE-GRPO1 SaMer1 Sample Weight Decay1 SAMPO1 SA-MRPO1 SAO1 SAR1 SEED1 Selective Learning1 Self-Distilled Reasoning (SDR)1 Self-Evolution1 Self-Flow1 Self Gradient Forcing1 SELFCI1 Self-OPD1 Self-Patching1 SetFit1 SGBM1 SHA-2561 Shapley values1 ShortOPD1 Signed MaxSim1 SimpleOPD1 SimPO1 Simulated Environment1 SKILL01 Skill Self-Play1 SMOTE1 Soft Actor-Critic1 SoftDTW1 Soufflé Datalog1 SPA1 SPAM1 Sparse Upcycling1 SPIFFE1 SRA1 SRL1 SRM-LoRA1 SSKD1 SSync1 Stable LatentMoE1 Stochastic Gradient Descent1 StudentSim1 Subliminal Learning1 Super Sensing1 SVERL1 SVRL1 SWE-RL1 SWIM1 synthetic dynamics1 TACO1 TacSL1 Task-Aware Knowledge Compression (TAKC)1 TASKER1 TBPTT1 TD3-BC1 TDM-R11 Teacher Forcing1 Test-Time Learning1 Tinylora1 TN-GSPO1 Token-Superposition Training1 TOP-D1 TORC1 Training Dynamics1 Training-Free1 Transductive Learning1 Transliteration1 TREK1 T-Rex1 TRIAGE1 TTPO1 TTRL1 TurboDiffusion1 TurnOPD1 UniMatch V21 u-OPSD1 URLVR1 USAF1 VAD1 Value Iteration1 Verbalizable Representations1 VESPO1 VibeWorlding-Gym1 Visual Pretraining1 VR-GRPO1 V-Zero1 WarpSAC1 WavFlow1 Weight Space Learning1 Working Memory Depth Recurrence1 world rehearsal1 XKD-Dial1 zElo1

Training (학습/파인튜닝) 관련 모든 뉴스 보기 →

자주 묻는 질문

Training (학습/파인튜닝) 카테고리에는 어떤 기준으로 기사가 포함되나요?

기사의 핵심 주제와 엔티티 태그를 기준으로 자동 분류되며, 관련성이 낮거나 중복된 항목은 우선순위가 낮게 조정됩니다.

태그 옆 숫자는 무엇을 의미하나요?

각 태그가 연결된 누적 기사 수를 의미합니다. 숫자가 클수록 해당 주제의 노출 빈도가 높은 편입니다.

최신 기사만 빠르게 보려면 어떻게 해야 하나요?

하단의 모든 뉴스 보기 링크를 통해 필터된 피드로 이동하면 최신순으로 관련 기사를 연속 탐색할 수 있습니다.