| A | B | C | D | E | F | |
|---|---|---|---|---|---|---|
1 | Title | Average Score | Standard Deviation | Individual Scores | Author-defined Area | |
2 | Git Re-Basin: Merging Models modulo Permutation Symmetries | 8.67 | 0.94 | 10;8;8 | Deep Learning and representational learning | |
3 | Rethinking the Expressive Power of GNNs via Graph Biconnectivity | 8.67 | 0.94 | 10;8;8 | Deep Learning and representational learning | |
4 | Emergence of Maps in the Memories of Blind Navigation Agents | 8.50 | 0.87 | 8;8;8;10 | Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics) | |
5 | DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems | 8.50 | 0.87 | 10;8;8;8 | Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics) | |
6 | Graph Neural Networks for Link Prediction with Subgraph Sketching | 8.50 | 0.87 | 8;8;8;10 | Deep Learning and representational learning | |
7 | Revisiting the Entropy Semiring for Neural Speech Recognition | 8.50 | 1.66 | 10;8;6;10 | Applications (eg, speech processing, computer vision, NLP) | |
8 | Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning | 8.25 | 2.05 | 8;10;10;5 | Theory (eg, control theory, learning theory, algorithmic game theory) | |
9 | Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering | 8.00 | 0.00 | 8;8;8 | General Machine Learning (ie none of the above) | |
10 | Fast Nonlinear Vector Quantile Regression | 8.00 | 0.00 | 8;8;8 | Probabilistic Methods (eg, variational inference, causal inference, Gaussian processes) | |
11 | Scaling Up Probabilistic Circuits by Latent Variable Distillation | 8.00 | 0.00 | 8;8;8 | Probabilistic Methods (eg, variational inference, causal inference, Gaussian processes) | |
12 | ‚Äã‚ÄãWhat learning algorithm is in-context learning? Investigations with linear models | 8.00 | 0.00 | 8;8;8 | Deep Learning and representational learning | |
13 | FedExP: Speeding up Federated Averaging via Extrapolation | 8.00 | 0.00 | 8;8;8 | Optimization (eg, convex and non-convex optimization) | |
14 | DreamFusion: Text-to-3D using 2D Diffusion | 8.00 | 0.00 | 8;8;8;8 | Generative models | |
15 | ReAct: Synergizing Reasoning and Acting in Language Models | 8.00 | 0.00 | 8;8;8 | Applications (eg, speech processing, computer vision, NLP) | |
16 | The Lie Derivative for Measuring Learned Equivariance | 8.00 | 0.00 | 8;8;8 | Deep Learning and representational learning | |
17 | Agree to Disagree: Diversity through Disagreement for Better Transferability | 8.00 | 0.00 | 8;8;8;8 | Deep Learning and representational learning | |
18 | Can We Find Nash Equilibria at a Linear Rate in Markov Games? | 8.00 | 0.00 | 8;8;8;8 | Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics) | |
19 | Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness | 8.00 | 0.00 | 8;8;8 | Deep Learning and representational learning | |
20 | Robust Scheduling with GFlowNets | 8.00 | 0.00 | 8;8;8;8 | Applications (eg, speech processing, computer vision, NLP) | |
21 | Strong inductive biases provably prevent harmless interpolation | 8.00 | 0.00 | 8;8;8 | Theory (eg, control theory, learning theory, algorithmic game theory) | |
22 | Confidential-PROFITT: Confidential PROof of FaIr Training of Trees | 8.00 | 0.00 | 8;8;8 | Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics) | |
23 | Minimum Variance Unbiased N:M Sparsity for the Neural Gradients | 8.00 | 0.00 | 8;8;8 | Deep Learning and representational learning | |
24 | Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives | 8.00 | 0.00 | 8;8;8 | General Machine Learning (ie none of the above) | |
25 | Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning | 8.00 | 0.00 | 8;8;8 | Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics) | |
26 | Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability | 8.00 | 0.00 | 8;8;8 | Deep Learning and representational learning | |
27 | Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness | 8.00 | 0.00 | 8;8;8;8 | Applications (eg, speech processing, computer vision, NLP) | |
28 | AudioGen: Textually Guided Audio Generation | 8.00 | 0.00 | 8;8;8;8 | Applications (eg, speech processing, computer vision, NLP) | |
29 | Martingale Posterior Neural Processes | 8.00 | 0.00 | 8;8;8 | Probabilistic Methods (eg, variational inference, causal inference, Gaussian processes) | |
30 | Sign and Basis Invariant Networks for Spectral Graph Representation Learning | 8.00 | 0.00 | 8;8;8;8 | Deep Learning and representational learning | |
31 | Conditional Antibody Design as 3D Equivariant Graph Translation | 8.00 | 0.00 | 8;8;8;8 | Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability ) | |
32 | Evaluating Long-Term Memory in 3D Mazes | 8.00 | 0.00 | 8;8;8 | Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics) | |
33 | Benchmarking Deformable Object Manipulation with Differentiable Physics | 8.00 | 0.00 | 8;8;8 | Infrastructure (eg, datasets, competitions, implementations, libraries) | |
34 | Generating Diverse Cooperative Agents by Learning Incompatible Policies | 8.00 | 0.00 | 8;8;8;8 | Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics) | |
35 | Asymptotic Instance-Optimal Algorithms for Interactive Decision Making | 8.00 | 1.26 | 8;8;10;8;6 | Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics) | |
36 | Geometric Networks Induced by Energy Constrained Diffusion | 8.00 | 1.41 | 8;6;8;10 | Deep Learning and representational learning | |
37 | Generate rather than Retrieve: Large Language Models are Strong Context Generators | 8.00 | 1.41 | 8;10;8;6 | Applications (eg, speech processing, computer vision, NLP) | |
38 | Betty: An Automatic Differentiation Library for Multilevel Optimization | 8.00 | 1.41 | 8;6;10;8 | Infrastructure (eg, datasets, competitions, implementations, libraries) | |
39 | Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching | 8.00 | 1.63 | 10;8;6 | Deep Learning and representational learning | |
40 | Transformers Learn Shortcuts to Automata | 8.00 | 1.63 | 8;10;6 | Theory (eg, control theory, learning theory, algorithmic game theory) | |
41 | A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification | 8.00 | 1.63 | 8;10;6 | Applications (eg, speech processing, computer vision, NLP) | |
42 | Relative representations enable zero-shot latent space communication | 8.00 | 1.63 | 10;6;8 | Deep Learning and representational learning | |
43 | On the duality between contrastive and non-contrastive self-supervised learning | 7.75 | 1.79 | 8;5;8;10 | Unsupervised and Self-supervised learning | |
44 | Flow Matching for Generative Modeling | 7.75 | 1.79 | 10;8;8;5 | Generative models | |
45 | DiffEdit: Diffusion-based semantic image editing with mask guidance | 7.75 | 1.79 | 8;5;8;10 | Generative models | |
46 | GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation | 7.67 | 2.05 | 8;5;10 | Applications (eg, speech processing, computer vision, NLP) | |
47 | Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning | 7.60 | 0.80 | 8;8;8;6;8 | Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics) | |
48 | BigVGAN: A Universal Neural Vocoder with Large-Scale Training | 7.60 | 0.80 | 8;8;8;8;6 | Applications (eg, speech processing, computer vision, NLP) | |
49 | Exponential Generalization Bounds with Near-Optimal Rates for $L_q$-Stable Algorithms | 7.60 | 0.80 | 8;6;8;8;8 | Theory (eg, control theory, learning theory, algorithmic game theory) | |
50 | CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representations | 7.60 | 0.80 | 8;6;8;8;8 | Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability ) | |
51 | Concept-level Debugging of Part-Prototype Networks | 7.50 | 0.87 | 6;8;8;8 | Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics) | |
52 | WikiWhy: Answering and Explaining Cause-and-Effect Questions | 7.50 | 0.87 | 8;6;8;8 | Infrastructure (eg, datasets, competitions, implementations, libraries) | |
53 | GEASS: Neural causal feature selection for high-dimensional biological data | 7.50 | 0.87 | 8;8;6;8 | Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability ) | |
54 | Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions | 7.50 | 0.87 | 6;8;8;8 | Generative models | |
55 | SMART: Self-supervised Multi-task pretrAining with contRol Transformers | 7.50 | 0.87 | 8;8;8;6 | Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics) | |
56 | The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry | 7.50 | 0.87 | 8;8;8;6 | Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics) | |
57 | Provably Efficient Neural Offline Reinforcement Learning via Perturbed Rewards | 7.50 | 0.87 | 8;8;8;6 | Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics) | |
58 | Near-optimal Coresets for Robust Clustering | 7.50 | 0.87 | 8;8;8;6 | Theory (eg, control theory, learning theory, algorithmic game theory) | |
59 | PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification | 7.50 | 0.87 | 6;8;8;8 | Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability ) | |
60 | GLM-130B: An Open Bilingual Pre-trained Model | 7.50 | 0.87 | 8;8;8;6 | Applications (eg, speech processing, computer vision, NLP) | |
61 | Provably Auditing Ordinary Least Squares in Low Dimensions | 7.50 | 0.87 | 8;8;6;8 | Theory (eg, control theory, learning theory, algorithmic game theory) | |
62 | Effects of Graph Convolutions in Multi-layer Networks | 7.50 | 0.87 | 8;8;8;6 | Theory (eg, control theory, learning theory, algorithmic game theory) | |
63 | Few-shot Cross-domain Image Generation via Inference-time Latent-code Learning | 7.50 | 0.87 | 8;8;6;8 | Generative models | |
64 | Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs | 7.50 | 0.87 | 8;8;8;6 | Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability ) | |
65 | Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree search | 7.50 | 0.87 | 8;8;8;6 | Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability ) | |
66 | Prompt-to-Prompt Image Editing with Cross-Attention Control | 7.50 | 0.87 | 8;8;6;8 | Generative models | |
67 | UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks | 7.50 | 0.87 | 8;6;8;8 | Applications (eg, speech processing, computer vision, NLP) | |
68 | Omnigrok: Grokking Beyond Algorithmic Data | 7.50 | 0.87 | 6;8;8;8 | Deep Learning and representational learning | |
69 | A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics | 7.50 | 0.87 | 8;8;8;6 | Infrastructure (eg, datasets, competitions, implementations, libraries) | |
70 | Accurate Image Restoration with Attention Retractable Transformer | 7.50 | 0.87 | 8;8;8;6 | Applications (eg, speech processing, computer vision, NLP) | |
71 | Generalized structure-aware missing view completion network for incomplete multi-view clustering | 7.50 | 0.87 | 8;8;6;8 | Deep Learning and representational learning | |
72 | PEER: A Collaborative Language Model | 7.50 | 0.87 | 6;8;8;8 | Applications (eg, speech processing, computer vision, NLP) | |
73 | Empowering Networks With Scale and Rotation Equivariance Using A Similarity Convolution | 7.50 | 0.87 | 8;8;6;8 | Deep Learning and representational learning | |
74 | Token Merging: Your ViT But Faster | 7.50 | 0.87 | 6;8;8;8 | Deep Learning and representational learning | |
75 | Image as Set of Points | 7.50 | 0.87 | 8;8;6;8 | Deep Learning and representational learning | |
76 | Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore | 7.50 | 0.87 | 8;8;8;6 | Applications (eg, speech processing, computer vision, NLP) | |
77 | Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask? | 7.50 | 1.66 | 8;6;10;6 | Deep Learning and representational learning | |
78 | PV3D: A 3D Generative Model for Portrait Video Generation | 7.50 | 1.66 | 6;8;10;6 | Generative models | |
79 | H2RBox: Horizonal Box Annotation is All You Need for Oriented Object Detection | 7.50 | 1.66 | 8;6;6;10 | Applications (eg, speech processing, computer vision, NLP) | |
80 | Minimax Optimal Kernel Operator Learning via Multilevel Training | 7.40 | 1.74 | 10;5;8;8;6 | Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability ) | |
81 | Few-Shot Domain Adaptation For End-to-End Communication | 7.33 | 0.94 | 8;6;8 | Applications (eg, speech processing, computer vision, NLP) | |
82 | Combinatorial Pure Exploration of Causal Bandits | 7.33 | 0.94 | 8;8;6 | Theory (eg, control theory, learning theory, algorithmic game theory) | |
83 | The In-Sample Softmax for Offline Reinforcement Learning | 7.33 | 0.94 | 8;6;8 | Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics) | |
84 | Discrete Predictor-Corrector Diffusion Models for Image Synthesis | 7.33 | 0.94 | 8;6;8 | Generative models | |
85 | Binding Language Models in Symbolic Languages | 7.33 | 0.94 | 8;8;6 | Applications (eg, speech processing, computer vision, NLP) | |
86 | Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems | 7.33 | 0.94 | 8;8;6 | Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability ) | |
87 | Learning Language Representations with Logical Inductive Bias | 7.33 | 0.94 | 6;8;8 | Deep Learning and representational learning | |
88 | Contrastive Corpus Attribution for Explaining Representations | 7.33 | 0.94 | 8;8;6 | Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics) | |
89 | SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments | 7.33 | 0.94 | 8;6;8 | Infrastructure (eg, datasets, competitions, implementations, libraries) | |
90 | Disentanglement of Correlated Factors via Hausdorff Factorized Support | 7.33 | 0.94 | 8;6;8 | Deep Learning and representational learning | |
91 | Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping | 7.33 | 0.94 | 6;8;8 | Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics) | |
92 | DiffusER: Diffusion via Edit-based Reconstruction | 7.33 | 0.94 | 6;8;8 | Applications (eg, speech processing, computer vision, NLP) | |
93 | Efficient recurrent architectures through activity sparsity and sparse back-propagation through time | 7.33 | 0.94 | 6;8;8 | Deep Learning and representational learning | |
94 | Symmetric Pruning in Quantum Neural Networks | 7.33 | 0.94 | 8;8;6 | General Machine Learning (ie none of the above) | |
95 | Incremental Learning of Structured Memory via Closed-Loop Transcription | 7.33 | 0.94 | 8;6;8 | Neuroscience and Cognitive Science (e.g., neural coding, brain-computer interfaces) | |
96 | Scaling Forward Gradient With Local Losses | 7.33 | 0.94 | 8;6;8 | Deep Learning and representational learning | |
97 | Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning | 7.33 | 0.94 | 8;6;8 | Deep Learning and representational learning | |
98 | Progress measures for grokking via mechanistic interpretability | 7.33 | 0.94 | 6;8;8 | Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics) | |
99 | Simplified State Space Layers for Sequence Modeling | 7.33 | 0.94 | 8;6;8 | Deep Learning and representational learning | |
100 | Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms | 7.33 | 0.94 | 6;8;8 | Theory (eg, control theory, learning theory, algorithmic game theory) |