Research Wiki

Obsidian 노트 1,375장을 LLM이 색인하고 점검합니다. 노트 본문은 그대로 두고, 아래 숫자는 전부 노트에서 다시 계산됩니다.

lint가 자동으로 만든 리포트
노트보기
1,375+0이번 달
논문
757
개념
415
강의
60
읽은 깊이보기
229/ 754 논문에 손을 댐
Full paper
29
Summary
154
Abstract
46
점검 대기큐 보기
948노트, 69%
미연결
499
끊김
143
오래됨
465
리뷰 활동보기
726올해, 월 평균 66
1월11월

관심 지도

논문 노트의 Topic 키워드를 같은 논문에 함께 쓰인 횟수로 이었습니다. 원이 클수록 그 키워드가 붙은 논문이 많고, 원을 누르면 아래 표가 그 키워드로 걸러집니다.

논문 25편 이상그 외 키워드
AI SafetyAI Safety, 논문 59편BenchmarkBenchmark, 논문 47편Theory of MindTheory of Mind, 논문 43편LLM agentsLLM agents, 논문 42편LLM evaluationLLM evaluation, 논문 36편InterpretabilityInterpretability, 논문 34편Self-knowledgeSelf-knowledge, 논문 29편LLMLLM, 논문 27편ARC-AGIARC-AGI, 논문 26편Looped transformerLooped transformer, 논문 20편MetacognitionMetacognition, 논문 19편Reinforcement LearningReinforcement Learning, 논문 19편Self-preservationSelf-preservation, 논문 19편ReasoningReasoning, 논문 18편Self-awarenessSelf-awareness, 논문 16편HallucinationHallucination, 논문 13편Instrumental ConvergenceInstrumental Convergence, 논문 13편Latent reasoningLatent reasoning, 논문 13편SurveySurvey, 논문 13편AlignmentAlignment, 논문 12편CalibrationCalibration, 논문 11편Question answeringQuestion answering, 논문 11편Fine-tuningFine-tuning, 논문 10편Self-improvementSelf-improvement, 논문 10편UncertaintyUncertainty, 논문 10편World modelWorld model, 논문 10편AgencyAgency, 논문 9편Self-supervised learningSelf-supervised learning, 논문 8편Chain-of-ThoughtChain-of-Thought, 논문 7편Game TheoryGame Theory, 논문 7편Instruction FollowingInstruction Following, 논문 7편LLM-as-a-JudgeLLM-as-a-Judge, 논문 7편OuroOuro, 논문 7편RLHFRLHF, 논문 7편
월별 리뷰 수2026년, Review-Date 기준
분야16개 중 상위 7
AI
953
Books
110
Psychology
67
Study
60
Mathematics
41
Statistics
33
DS Lab
31
그 외 9개 분야
80

논문 노트 탐색

위 지도에서 키워드를 고르거나 칩을 눌러 거르고, 열 머리글을 눌러 정렬합니다. 처음에는 최근 리뷰한 50편만 보여 줍니다.

754 / 754편
카테고리
상태
깊이
제목저자연도카테고리깊이상태리뷰
AI Arms and Influence - Frontier Models Exhibit Sophisticated Reasoning in Simulated Nuclear CrisesarXiv preprintKenneth Payne2026BenchmarkUnread시작 전10-10
Building Machines That Learn and Think Like PeopleBehavioral and Brain Sciences, 40, e253Brenden M. Lake et al.2017AGIUnread시작 전10-08
How to Grow a Mind - Statistics, Structure, and AbstractionScienceJoshua B. Tenenbaum et al.2011SurveyUnread시작 전10-08
Learning to Forget - Continual Prediction with LSTMNeural ComputationFelix A. Gers et al.2000ArchitectureUnread시작 전10-08
Neural Turing MachinesarXiv preprint (cs.NE)Alex Graves et al.2014ArchitectureUnread시작 전10-08
A Mechanistic Analysis of Looped Reasoning Language ModelsarXiv preprintHugh Blayney et al.2026ArchitectureUnread시작 전10-07
A Survey on Latent ReasoningarXiv preprintRui-Jie Zhu et al.2025SurveySummary읽는 중10-07
Adaptive Computation Time for Recurrent Neural NetworksarXiv preprint (cs.NE)Alex Graves2016ArchitectureSummary완료10-07
Adaptive Depth in Looped Transformers - Diagnosing Learned Halting Gates and Trajectory ReadoutsarXiv preprint (cs.LG)Andrei Cristian Popescu et al.2026ArchitectureUnread시작 전10-07
ALBERT - A Lite BERT for Self-supervised Learning of Language RepresentationsICLR 2020Zhenzhong Lan et al.2020ArchitectureUnread시작 전10-07
Bridging the Gap Between Latent and Explicit Reasoning with Looped TransformersarXiv preprintYing Fan et al.2026ReasoningUnread시작 전10-07
Chain of Thought Monitorability - A New and Fragile Opportunity for AI SafetyarXiv preprint (position paper)Tomek Korbak, Mikita Balesni et al.2025AGIUnread시작 전10-07
Decoding Looped Transformers Better for (Almost) FreearXiv preprintWeihao Liu et al.2026ReasoningUnread시작 전10-07
Deep Equilibrium ModelsNeurIPS 2019Shaojie Bai et al.2019ArchitectureUnread시작 전10-07
Dissecting Hierarchical Reasoning Models - A Mechanistic StudyarXiv preprintLeo Raphael Rodrigues, Jian Kang2026ReasoningUnread시작 전10-07
End-to-end Algorithm Synthesis with Recurrent Networks - Logical Extrapolation Without OverthinkingNeurIPS 2022Arpit Bansal et al.2022ReasoningUnread시작 전10-07
Hierarchical Reasoning ModelarXiv preprintGuan Wang et al.2025ReasoningUnread시작 전10-07
Hierarchical Reasoning Models - Perspectives and MisconceptionsarXiv preprint (Working Paper)Renee Ge et al.2025ReasoningUnread시작 전10-07
Latent Chain-of-Thought Decoding the Depth-Recurrent TransformerCOLM 2025 Workshop on the Application of LLM Explainability to Reasoning and PlanningWenquan Lu et al.2025ReasoningUnread시작 전10-07
Looped Transformers are Better at Learning Learning AlgorithmsICLR 2024Liu Yang et al.2024ArchitectureUnread시작 전10-07
Looped Transformers for Length GeneralizationICLR 2025Ying Fan et al.2025ArchitectureUnread시작 전10-07
Looped Transformers under the Jacobian Lens - Does the Global Workspace Survive Recurrence?arXiv preprintWenlong Wang, Fergal Reid2026ArchitectureUnread시작 전10-07
LoopViT - Scaling Visual ARC with Looped TransformersarXiv preprintWen-Jie Shu et al.2026ArchitectureUnread시작 전10-07
Mixture-of-Recursions - Learning Dynamic Recursive Depths for Adaptive Token-Level ComputationarXiv preprintSangmin Bae et al.2025ArchitectureUnread시작 전10-07
On the Chain-of-Thought Monitorability of Looped Language ModelsarXiv preprintHan Wang et al.2026BenchmarkUnread시작 전10-07
Relaxed Recursive Transformers - Effective Parameter Sharing with Layer-wise LoRAarXiv preprintSangmin Bae et al.2024ArchitectureUnread시작 전10-07
Retrofitting Recurrent Depth into a Pretrained Language Model - Installation, Extrapolation, Transfer, and Retention at Two Parameter BudgetsarXiv preprintMark Shapiro2026ArchitectureUnread시작 전10-07
Scaling Latent Reasoning via Looped Language ModelsarXiv preprintRui-Jie Zhu et al.2025ArchitectureUnread시작 전10-07
Scaling Laws for Looped Mixture of ExpertsarXiv preprintYanbei Chen et al.2026ArchitectureUnread시작 전10-07
Scaling up Test-Time Compute with Latent Reasoning - A Recurrent Depth ApproacharXiv preprintJonas Geiping et al.2025ArchitectureUnread시작 전10-07
Shared Weights, Selected Computations - How Looped Transformers Route What Each Loop DoesarXiv preprintJiaju Wu et al.2026ArchitectureUnread시작 전10-07
Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language ModelsICML 2026Xiao-Wen Yang et al.2026TrainingUnread시작 전10-07
SuperPos-Prompt - Enhancing Soft Prompt Tuning of Language Models with Superposition of Multi Token EmbeddingsarXiv preprintMohammadAli SadraeiJavaeri et al.2024OptimizationUnread시작 전10-07
Teaching Pretrained Language Models to Think Deeper with Retrofitted RecurrencearXiv preprintSean McLeish et al.2025TrainingUnread시작 전10-07
TextGrad - Automatic Differentiation via TextarXiv preprintMert Yuksekgonul et al.2024OptimizationUnread시작 전10-07
The Surprising Effectiveness of Shared Memory in Looped TransformersarXiv preprintGiovanni Monea et al.2026ArchitectureUnread시작 전10-07
Towards Looped Models Done Right, Part II - Rethinking at Fixed PointsarXiv preprintBenhao Huang et al.2026ArchitectureUnread시작 전10-07
Understanding Dynamic Compute Allocation in Recurrent TransformersarXiv preprint (cs.CL)Ibraheem Muhammad Moosa et al.2026BenchmarkUnread시작 전10-07
Universal TransformersICLR 2019Mostafa Dehghani et al.2019ArchitectureFull읽는 중10-07
What Limits Recursive Reasoning Models - Optimization, Architecture and Test-Time ScalingarXiv preprint (under review at ICLR 2027)Yuliana Shakhvalieva et al.2026OptimizationUnread시작 전10-07
A multi-agent reinforcement learning model of common-pool resource appropriationNIPS 2017Julien Perolat et al.2017ApplicationUnread시작 전10-06
Beyond the high score - Prosocial ability profiles of multi-agent populationsarXiv preprintMarko Tešić et al.2025BenchmarkUnread시작 전10-06
Cooperate or Collapse - Emergence of Sustainable Cooperation in a Society of LLM AgentsNeurIPS 2024Giorgio Piatti et al.2024BenchmarkUnread시작 전10-06
CoopEval - Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social DilemmasICML 2026 (PMLR 306)Emanuel Tewolde et al.2026BenchmarkUnread시작 전10-06
Deviation Ratings - A General Clone-Invariant Rating MethodarXiv preprintLuke Marris et al.2025BenchmarkUnread시작 전10-06
Evaluating Agents using Social Choice TheoryarXiv preprintMarc Lanctot et al.2023BenchmarkUnread시작 전10-06
More Capable, Less Cooperative - When LLMs Fail At Zero-Cost CollaborationICML 2026 (PMLR 306)Advait Yadav et al.2026BenchmarkUnread시작 전10-06
Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting PotICML 2021Joel Z. Leibo et al.2021BenchmarkUnread시작 전10-06
Shapley-Coop - Credit Assignment for Emergent Cooperation in Self-Interested LLM AgentsarXiv preprintYun Hua et al.2025ReasoningUnread시작 전10-06
SODE - Analyzing Social Dynamics in LLM AgentsarXiv preprint (cs.MA)Inseo Jung et al.2026BenchmarkUnread시작 전10-06

논문 형식 대기목록

전환 대기 393편 · 현행 v3 보호 52편

구형 상세 요약 구조 330편 · 구형 v2 구조 63편 · 기타 형식 · 수동/미확인 포함 309편 · v3 본문 구조 확인 52편

대기 상태만 표시하며 본문을 자동 수정하지 않습니다.

품질 큐

948/ 1,375 노트

lint가 찾아낸 문제입니다. 읽기만 하고 고치지 않으며, 사람이 승인한 것만 수정됩니다.

143끊김issue 737LINK-BROKEN 638
ASSET-MISSING 99
133메타데이터issue 142META-DATE 114
META-TYPE-ENUM 11
META-PAPER-SOURCE 9
499미연결issue 500WIKI-ORPHAN 495
LINK-AMBIGUOUS 5
105내용 검토issue 105CONTENT-THIN 104
CONTENT-STATUS 1
465오래됨issue 465REVIEW-STALE 465
집계 기준 2026-11-01. 큐 항목의 경로와 상세는 공개 페이지로 나오지 않습니다. 신규 논문 preread는 0 / 757편이 새 양식입니다.