SOTAVerified

ARC

Papers

Showing 150 of 554 papers

TitleStatusHype
Fast Text-to-Audio Generation with Adversarial Post-TrainingCode7
DataDecide: How to Predict Best Pretraining Data with Small ExperimentsCode3
ARC Prize 2024: Technical ReportCode3
The Surprising Effectiveness of Test-Time Training for Few-Shot LearningCode3
Digitizing Touch with an Artificial Multimodal FingertipCode3
CAX: Cellular Automata Accelerated in JAXCode3
Monte Carlo Tree Search Boosts Reasoning via Iterative Preference LearningCode3
Addressing the Abstraction and Reasoning Corpus via Procedural Example GenerationCode3
Neural networks for abstraction and reasoning: Towards broad generalization in machinesCode3
ST-MoE: Designing Stable and Transferable Sparse Expert ModelsCode3
Finetuned Language Models Are Zero-Shot LearnersCode3
A Parallelizable Lattice Rescoring Strategy with Neural Language ModelsCode3
The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal PuzzlesCode2
Searching Latent Program SpacesCode2
Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-RewardingCode2
Combining Induction and Transduction for Abstract ReasoningCode2
ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement LearningCode2
Scaling Laws with Vocabulary: Larger Models Deserve Larger VocabulariesCode2
Flow of Reasoning:Training LLMs for Divergent Problem Solving with Minimal ExamplesCode2
Yuan 2.0-M32: Mixture of Experts with Attention RouterCode2
Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual ModalitiesCode1
HELM: Hyperbolic Large Language Models via Mixture-of-Curvature ExpertsCode1
PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical TuningCode1
DRACO: Differentiable Reconstruction for Arbitrary CBCT OrbitsCode1
IterGen: Iterative Semantic-aware Structured LLM Generation with BacktrackingCode1
MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual AlignmentCode1
Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and ObjectsCode1
Matérn Kernels for Tunable Implicit Surface ReconstructionCode1
DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual TasksCode1
Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning TasksCode1
H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus BenchmarkCode1
Dependency Transformer Grammars: Integrating Dependency Structures into Transformer Language ModelsCode1
The FineWeb Datasets: Decanting the Web for the Finest Text Data at ScaleCode1
AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language ModelsCode1
Cross-Modal Learning for Anomaly Detection in Complex Industrial Process: Methodology and BenchmarkCode1
ARC: A Generalist Graph Anomaly Detector with In-Context LearningCode1
Frenet-Serret Frame-based Decomposition for Part Segmentation of 3D Curvilinear StructuresCode1
Is The Watermarking Of LLM-Generated Code Robust?Code1
CodeIt: Self-Improving Language Models with Prioritized Hindsight ReplayCode1
Generalized Planning for the Abstraction and Reasoning CorpusCode1
Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image SegmentationCode1
Token-Level Adaptation of LoRA Adapters for Downstream Task GeneralizationCode1
Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL PrincipleCode1
Efficient Adaptation of Large Vision Transformer via Adapter Re-ComposingCode1
Large Language Model (LLM) as a System of Multiple Expert Agents: An Approach to solve the Abstraction and Reasoning Corpus (ARC) ChallengeCode1
Hypothesis Search: Inductive Reasoning with Language ModelsCode1
An Approach to Solving the Abstraction and Reasoning Corpus (ARC) ChallengeCode1
Evaluating Emotion Arcs Across Languages: Bridging the Global Divide in Sentiment AnalysisCode1
ANPL: Towards Natural Programming with Interactive DecompositionCode1
LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based RepresentationsCode1
Show:102550
← PrevPage 1 of 12Next →

No leaderboard results yet.