#Fine-tuning

57개의 포스트

[axolotl] Gemma 3 QLoRA 설정 개선: Vision Tower 동결과 model_type 제거

Gemma 3 모델의 QLoRA 학습 설정에서 불필요한 model_type 명시를 제거하고, unfrozen_parameters로 Vision Tower를 동결하는 패턴을 분석합니다.

#Axolotl #Gemma3 #QLoRA #Fine-tuning #Configuration

2026년 3월 20일

[논문리뷰] Learn Hard Problems During RL with Reference Guided Fine-tuning

arXiv에 게시된 'Learn Hard Problems During RL with Reference Guided Fine-tuning' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Mathematical Reasoning #Reward Sparsity #Fine-tuning #Large Language Models #Reference-Guided Learning #DAPO

2026년 3월 2일

[논문리뷰] Half-Truths Break Similarity-Based Retrieval

Seong Joon Oh이 arXiv에 게시한 'Half-Truths Break Similarity-Based Retrieval' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Models #CLIP #Compositional Reasoning #Image-Text Retrieval #Fine-tuning #Hard Negatives #Unit-level Supervision #Half-Truths

2026년 3월 2일

[논문리뷰] FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment

Shuai Chen이 arXiv에 게시한 'FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment' 논문에 대한 자세한 리뷰입니다.

#Review #World Modeling #Generalist Policies #Representation Alignment #Diffusion Models #Robotics #Fine-tuning #Egocentric Data #VLA

2026년 2월 19일

[논문리뷰] Adapting Vision-Language Models for E-commerce Understanding at Scale

arXiv에 게시된 'Adapting Vision-Language Models for E-commerce Understanding at Scale' 논문에 대한 자세한 리뷰입니다.

#Review #E-commerce #Vision-Language Models #Multimodal Understanding #Instruction Tuning #Attribute Extraction #Fine-tuning #Benchmarking #LLMs

2026년 2월 12일

[논문리뷰] Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models

Maria Liakata이 arXiv에 게시한 'Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Reasoning #Deduction #Induction #Abduction #Out-of-Domain Generalization #Symbolic Reasoning #Fine-tuning #Upcycling

2026년 2월 9일

[논문리뷰] MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods

arXiv에 게시된 'MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Reasoning #Data-centric AI #Chain-of-Thought #Large Language Models #Visual Question Answering #STEM Reasoning #Dataset #Fine-tuning

2026년 1월 29일

[논문리뷰] Exploring Reasoning Reward Model for Agents

Zhixun Li이 arXiv에 게시한 'Exploring Reasoning Reward Model for Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Reinforcement Learning #Reward Modeling #Reasoning-aware Feedback #Large Language Models (LLMs)#Multi-modal Agents #Fine-tuning #Critique Generation

2026년 1월 29일

[논문리뷰] Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models

arXiv에 게시된 'Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Models #Spatial Intelligence #Benchmark #Evaluation #Prompt Engineering #Multimodal LLMs #Fine-tuning #Spatial Reasoning

2026년 1월 29일

[논문리뷰] Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

arXiv에 게시된 'Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning' 논문에 대한 자세한 리뷰입니다.

#Review #Video Models #Visuomotor Control #Robot Policy #Fine-tuning #Diffusion Models #World Models #Model-based Planning #Imitation Learning

2026년 1월 22일

[논문리뷰] Typhoon OCR: Open Vision-Language Model For Thai Document Extraction

arXiv에 게시된 'Typhoon OCR: Open Vision-Language Model For Thai Document Extraction' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Model #OCR #Thai Language Processing #Document Understanding #Low-Resource Language #Data Synthesis #Fine-tuning #Layout Analysis

2026년 1월 21일

[논문리뷰] Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation

Ziyang Yan이 arXiv에 게시한 'Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation' 논문에 대한 자세한 리뷰입니다.

#Review #Medical Image Segmentation #Foundation Models #SAM3 #Fine-tuning #Prompt-driven #Domain Adaptation #Text-guided Segmentation

2026년 1월 19일

[논문리뷰] More Images, More Problems? A Controlled Analysis of VLM Failure Modes

arXiv에 게시된 'More Images, More Problems? A Controlled Analysis of VLM Failure Modes' 논문에 대한 자세한 리뷰입니다.

#Review #Vision Language Models #Multi-Image Understanding #Failure Analysis #Evaluation Benchmark #Attention Mechanism #Fine-tuning #MIMIC

2026년 1월 18일

[논문리뷰] Motion Attribution for Video Generation

arXiv에 게시된 'Motion Attribution for Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Motion Attribution #Video Generation #Diffusion Models #Gradient-based Attribution #Temporal Dynamics #Motion Masking #Fine-tuning #Data Curation

2026년 1월 13일

[논문리뷰] COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs

arXiv에 게시된 'COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Evaluation #Policy Alignment #Organizational Policies #AI Safety #Adversarial Robustness #Refusal Behavior #Prompt Engineering #Fine-tuning

2026년 1월 5일

[논문리뷰] When Reasoning Meets Its Laws

Liu Ziyin이 arXiv에 게시한 'When Reasoning Meets Its Laws' 논문에 대한 자세한 리뷰입니다.

#Review #Large Reasoning Models #Reasoning Behaviors #Compute Law #Accuracy Law #Monotonicity #Compositionality #Fine-tuning #LORE-BENCH

2025년 12월 21일

[논문리뷰] SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories

arXiv에 게시된 'SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories' 논문에 대한 자세한 리뷰입니다.

#Review #Software Engineering Benchmarks #Large Language Models (LLMs)#Code Generation #Automated Benchmark Generation #Multilingual #GitHub Pull Requests #Test Oracle #Fine-tuning

2025년 12월 21일

[논문리뷰] Adaptation of Agentic AI

Zhiyi Shi이 arXiv에 게시한 'Adaptation of Agentic AI' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic AI #Adaptation #Agent Adaptation #Tool Adaptation #Reinforcement Learning #Fine-tuning #Modular AI

2025년 12월 18일

[논문리뷰] Sliding Window Attention Adaptation

arXiv에 게시된 'Sliding Window Attention Adaptation' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Sliding Window Attention #Model Adaptation #Long Context #Inference Optimization #Fine-tuning #Chain-of-Thought #Sparse Attention

2025년 12월 14일

[논문리뷰] Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models

arXiv에 게시된 'Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Language Models #Masked Diffusion Language Models #Context Comprehension #Locality Bias #Mask Tokens #Fine-tuning #Mask-agnostic Loss #Long-context Processing

2025년 12월 2일

[논문리뷰] World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models

Na Min An이 arXiv에 게시한 'World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Models #Culture Mixing #VQA #Synthetic Data Generation #Multicultural Understanding #Model Robustness #Fine-tuning #Cultural Bias

2025년 11월 30일

[논문리뷰] TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval

arXiv에 게시된 'TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval' 논문에 대한 자세한 리뷰입니다.

#Review #Information Retrieval #Turkish Language #Late-Interaction Models #ColBERT #Dense Retrieval #MUVERA #Benchmarking #Low-Resource NLP #Fine-tuning

2025년 11월 20일

[논문리뷰] Do LLMs Feel? Teaching Emotion Recognition with Prompts, Retrieval, and Curriculum Learning

arXiv에 게시된 'Do LLMs Feel? Teaching Emotion Recognition with Prompts, Retrieval, and Curriculum Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Emotion Recognition in Conversation #Large Language Models #Prompt Engineering #Demonstration Retrieval #Curriculum Learning #Fine-tuning #Affective Computing #SOTA

2025년 11월 10일

[논문리뷰] VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks

arXiv에 게시된 'VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks' 논문에 대한 자세한 리뷰입니다.

#Review #Neuro-symbolic AI #Chain-of-Thought #Large Language Models #Logical Consistency #Automated Verification #Fine-tuning #SMT Solvers #Self-Reflection

2025년 11월 9일

[논문리뷰] Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization

Aleksandr I. Panov이 arXiv에 게시한 'Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #OOD Generalization #Representation Alignment #Fine-tuning #Robotics #Visual Representations #Attention Maps #t-SNE

2025년 11월 9일

[논문리뷰] TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning

Shaoheng Lin이 arXiv에 게시한 'TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #Agentic Reasoning #Thinking-with-Images #Visual Reasoning Benchmark #Tool Use #Image Manipulation #Fine-tuning

2025년 11월 9일

[논문리뷰] Performance Trade-offs of Optimizing Small Language Models for E-Commerce

Nikola Tankovic이 arXiv에 게시한 'Performance Trade-offs of Optimizing Small Language Models for E-Commerce' 논문에 대한 자세한 리뷰입니다.

#Review #Small Language Models #E-commerce #Intent Recognition #Fine-tuning #QLoRA #Quantization #GPTQ #GGUF #Hardware-aware Optimization

2025년 10월 31일

[논문리뷰] VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations

Jiayi Zhang이 arXiv에 게시한 'VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations' 논문에 대한 자세한 리뷰입니다.

#Review #Visualization Quality Assessment #MLLMs #Benchmark #Aesthetics #Fidelity #Expressiveness #Fine-tuning #Reinforcement Learning

2025년 10월 29일

[논문리뷰] Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMS

arXiv에 게시된 'Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMS' 논문에 대한 자세한 리뷰입니다.

#Review #Audio-Visual Speech Recognition #Large Language Models #Attention Sinks #Massive Activations #Decorrelation Loss #Fine-tuning #Multimodal AI

2025년 10월 28일

[논문리뷰] Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost

Min Yang이 arXiv에 게시한 'Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost' 논문에 대한 자세한 리뷰입니다.

#Review #Machine Translation Evaluation #Large Reasoning Models #LLM-as-a-judge #MQM #Fine-tuning #Thinking Calibration #Computational Efficiency #Meta-evaluation

2025년 10월 27일

[논문리뷰] DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents

arXiv에 게시된 'DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #Fine-tuning #Data Mixing Optimization #Mobile Phone Agents #Downstream Task Prediction #Benchmark #Neural Networks

2025년 10월 23일

[논문리뷰] IF-VidCap: Can Video Caption Models Follow Instructions?

arXiv에 게시된 'IF-VidCap: Can Video Caption Models Follow Instructions?' 논문에 대한 자세한 리뷰입니다.

#Review #Video Captioning #Instruction Following #MLLMs #Benchmark #Controllable Generation #Multimodal Evaluation #Fine-tuning

2025년 10월 22일

[논문리뷰] VLA-0: Building State-of-the-Art VLAs with Zero Modification

arXiv에 게시된 'VLA-0: Building State-of-the-Art VLAs with Zero Modification' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #VLA-0 #Zero Modification #Text-based Action Prediction #Robot Manipulation #Large Language Models #Fine-tuning #State-of-the-Art

2025년 10월 17일

[논문리뷰] Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs

arXiv에 게시된 'Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs' 논문에 대한 자세한 리뷰입니다.

#Review #LLM #NPC #Game Dialogue #Persona-Grounded Dialogue #Task Execution #Prompt Engineering #Fine-tuning #Deflanderization

2025년 10월 16일

[논문리뷰] LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens

arXiv에 게시된 'LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models (LLMs)#Machine Translation (MT)#Chain-of-Thought (CoT)#Knowledge Distillation #Fine-tuning #Prompt Engineering #Synthetic Data

2025년 10월 15일

[논문리뷰] Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation

Han Shi이 arXiv에 게시한 'Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Autoregressive Models #Text-to-Image Generation #Inference Acceleration #Jacobi Decoding #Denoising Diffusion Models #Speculative Decoding #Multi-token Prediction #Fine-tuning

2025년 10월 13일

[논문리뷰] Fast-dLLM v2: Efficient Block-Diffusion LLM

arXiv에 게시된 'Fast-dLLM v2: Efficient Block-Diffusion LLM' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion LLMs #Inference Acceleration #Parallel Decoding #Autoregressive Models #Caching #Fine-tuning #Block-wise Attention

2025년 10월 8일

[논문리뷰] Thai Semantic End-of-Turn Detection for Real-Time Voice Agents

Monthol Charattrakool이 arXiv에 게시한 'Thai Semantic End-of-Turn Detection for Real-Time Voice Agents' 논문에 대한 자세한 리뷰입니다.

#Review #End-of-Turn Detection #Thai NLP #Voice Agents #Real-time Inference #Transformer Models #Few-shot Learning #Fine-tuning #Latency Optimization

2025년 10월 7일

[논문리뷰] HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition

arXiv에 게시된 'HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition' 논문에 대한 자세한 리뷰입니다.

#Review #Code-Switching #Speech Recognition #Korean-English ASR #Evaluation Framework #Multilingual ASR #Loanword Processing #Fine-tuning #Hierarchical Labeling

2025년 10월 7일

[논문리뷰] NuRisk: A Visual Question Answering Dataset for Agent-Level Risk Assessment in Autonomous Driving

arXiv에 게시된 'NuRisk: A Visual Question Answering Dataset for Agent-Level Risk Assessment in Autonomous Driving' 논문에 대한 자세한 리뷰입니다.

#Review #Visual Question Answering (VQA)#Autonomous Driving #Risk Assessment #Spatio-Temporal Reasoning #Large Vision Models (VLMs)#Dataset #Bird-Eye-View (BEV)#Fine-tuning

2025년 10월 6일

[논문리뷰] VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators

Zirui Ge이 arXiv에 게시한 'VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #Reinforcement Learning #World Models #Fine-tuning #Embodied AI #Robotics #Reward Design #Distribution Shift

2025년 10월 2일

[논문리뷰] BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses

Julian McAuley이 arXiv에 게시한 'BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Bias Mitigation #Benchmark #Evaluation Metrics #Prompt Engineering #Fine-tuning #Bias-Free Score #Fairness

2025년 10월 2일

[논문리뷰] Knowledge Homophily in Large Language Models

Nedim Lipka이 arXiv에 게시한 'Knowledge Homophily in Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #LLM #Knowledge Homophily #Graph Neural Networks #Knowledge Graph #Knowledge Injection #Question Answering #Fine-tuning #Knowledge Retrieval

2025년 10월 1일

[논문리뷰] DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder

arXiv에 게시된 'DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Models #Video Autoencoder #Deep Compression #Model Acceleration #Fine-tuning #Latent Space #Temporal Modeling

2025년 10월 1일

[논문리뷰] SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention

arXiv에 게시된 'SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformers #Sparse Attention #Linear Attention #Model Acceleration #Video Generation #Attention Mechanisms #Fine-tuning

2025년 9월 30일

[논문리뷰] Fine-tuning Done Right in Model Editing

Du Su이 arXiv에 게시한 'Fine-tuning Done Right in Model Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Model Editing #Fine-tuning #Large Language Models #Catastrophic Forgetting #Breadth-First Pipeline #Depth-First Pipeline #Localized Tuning #Lifelong Learning

2025년 9월 29일

[논문리뷰] CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition

arXiv에 게시된 'CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition' 논문에 대한 자세한 리뷰입니다.

#Review #Historical Text Recognition #Vision-Language Model #Open-Weight Model #OCR #Cultural Heritage #Low-Cost AI #Dataset Curation #Fine-tuning

2025년 9월 29일

[논문리뷰] Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR

Zeina Aldallal이 arXiv에 게시한 'Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR' 논문에 대한 자세한 리뷰입니다.

#Review #Arabic OCR #Vision-Language Model #Fine-tuning #Document Understanding #Markdown Conversion #Benchmark

2025년 9월 24일

[논문리뷰] Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents

Chao Zhang이 arXiv에 게시한 'Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Role-playing Agents (RPAs)#Multimodal AI #Video Understanding #Large Language Models (LLMs)#Dataset Creation #Dynamic Role Profiles #Adaptive Temporal Sampling #Fine-tuning

2025년 9월 22일

[논문리뷰] MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

Xijun Gu이 arXiv에 게시한 'MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks' 논문에 대한 자세한 리뷰입니다.

#Review #Instruction-based Image Editing #Dataset #Multi-modal LLM #Image Generation #Style Transfer #Multi-task Learning #Fine-tuning

2025년 9월 19일

[논문리뷰] TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning

Simin Ma이 arXiv에 게시한 'TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning' 논문에 대한 자세한 리뷰입니다.

#Review #Instruction Augmentation #Fine-tuning #Large Language Models #Task-Centric #Data Diversity #Task Alignment #Breadth-First Search #Constraint Generation

2025년 8월 29일

[논문리뷰] Unraveling the cognitive patterns of Large Language Models through module communities

Jianxi Gao이 arXiv에 게시한 'Unraveling the cognitive patterns of Large Language Models through module communities' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Network Community Structure #Cognitive Skills #AI Interpretability #Module Communities #Fine-tuning #Neural Plasticity

2025년 8월 27일

[논문리뷰] Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning

Arman Cohan이 arXiv에 게시한 'Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Scientific Reasoning #Knowledge Retrieval #Reasoning Probing #Benchmarks #Chain-of-Thought #Fine-tuning

2025년 8월 27일

[논문리뷰] CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning

Yulun Zhang이 arXiv에 게시한 'CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Reasoning #Contrastive Learning #Reinforcement Learning #Fine-tuning #Chain-of-Thought (CoT)#Annotated Data #Model Stability

2025년 8월 25일

[논문리뷰] AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

Yong Li이 arXiv에 게시한 'AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Fine-tuning #Reinforcement Learning #Meta-learning #Adaptive Control #Imitation Learning #Exploration #Reasoning

2025년 8월 14일

[논문리뷰] BiasGym: Fantastic Biases and How to Find (and Remove) Them

Arnav Arora이 arXiv에 게시한 'BiasGym: Fantastic Biases and How to Find (and Remove) Them' 논문에 대한 자세한 리뷰입니다.

#Review #Bias Mitigation #LLMs #Mechanistic Interpretability #Fine-tuning #Attention Steering #Stereotype Analysis #Safety Alignment

2025년 8월 13일

[논문리뷰] Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal

Chengcheng Wan이 arXiv에 게시한 'Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal' 논문에 대한 자세한 리뷰입니다.

#Review #Code Reasoning #CoT Compression #LLMs #Efficiency #Surprisal #Pruning #Fine-tuning #Large Reasoning Models

2025년 8월 11일