arXivSub Start free trial

ICML 2023 Papers with Code

International Conference on Machine Learning Β· 421 papers with a public code repository

"Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts

Haoran Zhang (Massachusetts Institute of Technology), Shalmali Joshi (Columbia University)

CodeDomain AdaptationExplainability and InterpretabilityBiomedical Data

🎯 What it does: This paper models the problem of attributing model performance degradation as a cooperative game, using causal graphs to decompose distribution shifts into actionable mechanisms, and allocates overall performance changes to each mechanism through Shapley values.

2D-Shapley: A Framework for Fragmented Data Valuation

Liu Zhihong, Ruoxi Jia (Virginia Tech)

CodeAnomaly DetectionData-Centric LearningTabular

🎯 What it does: A 2D-Shapley framework is proposed to quantify the contributions of fragmented data (neither sharing features nor samples), along with corresponding fairness axioms and analytical expressions.

A Closer Look at Self-Supervised Lightweight Vision Transformers

Shaoru Wang (Chinese Academy of Sciences), Weiming Hu (Chinese Academy of Sciences)

CodeClassificationObject DetectionSegmentationKnowledge DistillationRepresentation LearningTransformerContrastive LearningImage

🎯 What it does: This paper studies the use of self-supervised pre-training methods on lightweight Vision Transformers and evaluates their impact on downstream tasks.

A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests

Bohang Zhang (Peking University), Liwei Wang (Peking University)

CodeGraph Neural NetworkGraph

🎯 What it does: This paper systematically studies the expressiveness of subgraph Graph Neural Networks (subgraph GNNs), proposes and fully constructs the Subgraph Weisfeiler–Lehman (SWL) hierarchy, reveals the expressive power of different aggregation and pooling designs, and proves that the strongest form is SSWL.

A Connection between One-Step RL and Critic Regularization in Reinforcement Learning

Benjamin Eysenbach (Carnegie Mellon University), Ruslan Salakhutdinov (Carnegie Mellon University)

CodeReinforcement Learning

🎯 What it does: This paper proves through theoretical derivation and experimental validation that when the regularization strength λ=1, first-order RL and Critic regularization yield the same policy, and explores their performance in offline RL.

A Deep Conjugate Direction Method for Iteratively Solving Linear Systems

Ayano Kaneda (Waseda University), Joseph Teran (University of California)

CodeOptimizationConvolutional Neural NetworkTabular

🎯 What it does: A deep learning-based conjugate direction method (DCDM) is proposed to iteratively solve large-scale sparse symmetric positive definite linear systems, focusing on the solution of the discrete Poisson equation.

A Hybrid Quantum-Classical Approach based on the Hadamard Transform for the Convolutional Layer

Hongyi Pan (University of Illinois Chicago), Ahmet Cetin

CodeClassificationRecognitionComputational EfficiencyConvolutional Neural NetworkImage

🎯 What it does: A hybrid quantum-classical convolution layer based on Hadamard transform (HT-Perceptron) is proposed, which can replace traditional Conv2D to achieve frequency domain convolution.

A Kernel-Based View of Language Model Fine-Tuning

Sadhika Malladi (Princeton University), Sanjeev Arora (Princeton University)

CodeOptimizationTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringText

🎯 What it does: This paper addresses the fine-tuning of pre-trained language models for downstream tasks from the perspective of the Neural Tangent Kernel (NTK). It derives the early training kernel (SignGD kernel) suitable for the Adam optimizer and demonstrates that during the fine-tuning process using natural language prompts, model updates often follow kernel behavior. Additionally, it explains the effectiveness of low-rank subspace fine-tuning methods (such as LoRA) from a kernel perspective.

A Neural PDE Solver with Temporal Stencil Modeling

Zhiqing Sun (Carnegie Mellon University), Shinjae Yoo (Brookhaven National Laboratory)

CodeSuper ResolutionOptimizationConvolutional Neural NetworkTime SeriesPhysics Related

🎯 What it does: A Temporal Stencil Modeling (TSM) method has been developed to achieve learnable flux approximation in time-varying partial differential equations in conservation form through a convolution volume method.

A Picture of the Space of Typical Learnable Tasks

Rahul Ramesh (University of Pennsylvania), Pratik Chaudhari (University of Pennsylvania)

CodeClassificationMeta LearningContrastive LearningImage

🎯 What it does: The paper uses information geometry methods to unify the modeling, distance measurement, trajectory re-indexing, and visualization of deep network prediction models trained on different tasks and learning algorithms (supervised, meta-learning, semi-supervised, self-supervised, contrastive learning, etc.), thereby revealing the structure and commonalities of the learnable task space.

A Reinforcement Learning Framework for Dynamic Mediation Analysis

Lin Ge (North Carolina State University), Rui Song (North Carolina State University)

CodeOptimizationReinforcement LearningTime SeriesBiomedical Data

🎯 What it does: A dynamic mediation analysis framework based on reinforcement learning is proposed, constructing a Mediated Markov Decision Process (MMDP), and decomposing the Average Treatment Effect (ATE) into Immediate Direct Effect (IDE), Immediate Mediation Effect (IME), Delayed Direct Effect (DDE), and Delayed Mediation Effect (DME).

A Robust Test for the Stationarity Assumption in Sequential Decision Making

Jitao Wang (University of Michigan), Zhenke Wu (University of Michigan)

CodeReinforcement LearningTabularTime SeriesSequentialBiomedical DataElectronic Health Records

🎯 What it does: A dual robust testing method in offline reinforcement learning is proposed to detect whether the stationarity assumption of the Markov Decision Process (MDP) holds.

A Three-regime Model of Network Pruning

Yefan Zhou (University of California), Michael W. Mahoney (University of California)

CodeCompressionOptimizationHyperparameter SearchConvolutional Neural NetworkImage

🎯 What it does: This paper proposes a three-stage model based on two parameters: 'temperature' and 'load', to predict how hyperparameters during the training phase (such as the number of training epochs and batch size) affect the subsequent network pruning results. The model categorizes the gradient landscapes of the network before and after pruning into three regimes (Regime I, II-A, II-B).

A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations

Bilal Chughtai, Neel Nanda

CodeTransformerGraph

🎯 What it does: This study investigates the internal mechanisms of small neural networks when performing finite group composition tasks, discovering that the network implements a general algorithm based on representation theory (GCR), which is validated through reverse engineering and ablation studies.

A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition

Shentong Mo (Carnegie Mellon University), Pedro Morgado (University of Wisconsin Madison)

CodeRecognitionRetrievalConvolutional Neural NetworkContrastive LearningMultimodalityAudio

🎯 What it does: A unified audio-visual learning framework, OneAVM, is proposed, achieving single-model inference for audio source localization, separation, and recognition tasks.

Accelerated Stochastic Optimization Methods under Quasar-convexity

Qiang Fu (Sun Yat-sen University), Ashia Camage Wilson

CodeOptimizationTabularTime Series

🎯 What it does: Two accelerated stochastic optimization methods for star-convex functions are proposedβ€”QASGD and QASVRG, which can achieve fast convergence under L-smooth and (strong) star-convex conditions;

Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time

Toon Vanderschueren (KU Leuven), Mihaela van der Schaar (University of Cambridge)

CodeDrug DiscoveryReinforcement LearningTime SeriesSequentialBiomedical Data

🎯 What it does: The study investigates how to learn to predict treatment outcomes over time in the presence of informative sampling in observational data.

Actor-Critic Alignment for Offline-to-Online Reinforcement Learning

Zishun Yu (University of Illinois Chicago), Xinhua Zhang (University of Illinois Chicago)

CodeReinforcement LearningTabular

🎯 What it does: A new offline-to-online reinforcement learning framework is proposed, which aligns the policy and value function obtained from offline learning through an 'actor-critic alignment' step, followed by online fine-tuning.

AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation

YiFan Zhang, Tieniu Tan (Nanjing University)

CodeDomain AdaptationImage

🎯 What it does: Proposes AdaNPC, a framework that utilizes a KNN non-parametric classifier for online adaptation during testing, storing and gradually updating source domain features and labels in memory.

Adaptive Annealed Importance Sampling with Constant Rate Progress

Shirin Goshtasbpour (ETH Zurich), Fernando Perez-Cruz (ETH Zurich)

CodeTabularOrdinary Differential Equation

🎯 What it does: Research and improve the intermediate distribution path and scheduling strategy of Annealed Importance Sampling (AIS), proposing a constant rate scheduling and implementing the Constant Rate AIS (CR-AIS) algorithm.

Adaptive Compositional Continual Meta-Learning

Bin Wu (Zhejiang University), Qiang Zhang (Zhejiang University)

CodeMeta LearningImage

🎯 What it does: An adaptive combinatorial continuous meta-learning algorithm ACML is proposed for learning shareable meta-knowledge in non-stationary task sequences.

Adaptive Computation with Elastic Input Sequence

Fuzhao Xue (Google), Yang You (National University of Singapore)

CodeClassificationRecognitionComputational EfficiencyTransformerImage

🎯 What it does: Proposes AdaTape, which achieves adaptive computation on input sequences through variable-length tape tokens;

Adaptive Estimation of Graphical Models under Total Positivity

Jiaxi Ying (Hong Kong University of Science and Technology), Daniel P. Palomar (Hong Kong University of Science and Technology)

CodeOptimizationGraph Neural NetworkGraphTime SeriesFinance Related

🎯 What it does: An adaptive multi-stage estimation method is proposed for estimating the precision matrix of M-matrices or diagonally dominant M-matrices under the MTP2 Gaussian graphical model.

Adaptive Smoothing Gradient Learning for Spiking Neural Networks

Ziming Wang (Zhejiang University), Huajin Tang (Zhejiang University)

CodeClassificationOptimizationSpiking Neural NetworkImageTime SeriesSequentialAudio

🎯 What it does: An Adaptive Smoothing Gradient Learning (ASGL) method is proposed for directly training deep Spiking Neural Networks (SNNs), enabling the network to gradually converge to a true spiking network by mixing simulated activations and random spike noise during training.

Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift

Yijun Dong (University of Texas at Austin), Rachel Ward (University of Texas at Austin)

CodeSegmentationOptimizationConvolutional Neural NetworkTransformerImageBiomedical DataMagnetic Resonance ImagingComputed Tomography

🎯 What it does: Proposes the Adaptive Weighted Data Augmentation Consistency Regularization (AdaWAC) algorithm to address the issues of concept drift and the imbalance of sparse/dense label information in medical image segmentation.

Adversarial Policies Beat Superhuman Go AIs

Tony Tong Wang, Stuart Russell (University of California Berkeley)

CodeAdversarial AttackReinforcement Learning

🎯 What it does: Trained adversarial strategies against the top Go AI KataGo, achieving win rates of 99.9% and over 97% with minimal computational resources (only 0.13% of KataGo's training) without using search or using 10^7 search nodes, respectively.

All in a Row: Compressed Convolution Networks for Graphs

Junshu Sun (Chinese Academy of Sciences), Qingming Huang (Chinese Academy of Sciences)

CodeClassificationRepresentation LearningGraph Neural NetworkGraph

🎯 What it does: This paper proposes a differentiable graph regularization method and a hierarchical graph convolutional network CoCN based on diagonal convolution, aimed at achieving Euclidean convolution transfer on graph data, capable of simultaneously learning node features and structural features.

Alternately Optimized Graph Neural Networks

Haoyu Han (Michigan State University), Jiliang Tang (Michigan State University)

CodeOptimizationComputational EfficiencyGraph Neural NetworkGraph

🎯 What it does: A training framework for graph neural networks based on single-layer optimization (ALT-OPT) has been designed and implemented, replacing the traditional end-to-end two-layer optimization with alternating optimization of pseudo-labels and MLP parameters.

An Effective Meaningful Way to Evaluate Survival Models

Shi-ang Qi (University of Alberta), Russell Greiner (University of Alberta)

CodeBiomedical DataElectronic Health Records

🎯 What it does: A MAE-PO metric based on pseudo-observation is proposed to evaluate survival prediction models with right censoring, and the effectiveness of this metric is assessed through the generation of realistic semi-synthetic datasets.

An Instrumental Variable Approach to Confounded Off-Policy Evaluation

Yang Xu (North Carolina State University), Rui Song (North Carolina State University)

CodeReinforcement LearningVideo

🎯 What it does: This paper proposes a framework for offline policy evaluation (OPE) using instrumental variables (IV) in the presence of unmeasured confounding in MDP (and POMDP) environments.

Anchor Sampling for Federated Learning with Partial Client Participation

Feijie Wu (Purdue University), Jing Gao (Purdue University)

CodeFederated LearningComputational EfficiencyConvolutional Neural NetworkImage

🎯 What it does: A federated learning framework named FedAMD is proposed, which divides some participating clients into anchor point groups and miner groups through anchor point sampling, using large-batch gradients and multi-step small-batch updates to accelerate training and improve model performance.

Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization

Yushi Bai (Tsinghua University), Lei Hou (Tsinghua University)

CodeOptimizationExplainability and InterpretabilityGraph Neural NetworkGraph

🎯 What it does: The QTO (Query Computation Tree Optimization) method is proposed, which utilizes pre-trained knowledge graph embeddings (KGE) to score first-order subqueries and accurately solves the optimal entity allocation on the query computation tree through forward-backward recursive propagation, ensuring both the optimality of the answers and the interpretability of intermediate variables.

Anti-Exploration by Random Network Distillation

Alexander Nikulin (Tinkoff), Sergey Kolesnikov (Tinkoff)

CodeKnowledge DistillationReinforcement LearningTabularBenchmark

🎯 What it does: A new offline RL method called SAC-RND is developed, which utilizes random network distillation for uncertainty estimation and suppresses exploration in offline RL.

Applied Online Algorithms with Heterogeneous Predictors

Jessica Maghakian (Stony Brook University), Zhenhua Liu

CodeOptimizationReinforcement LearningTime Series

🎯 What it does: This paper studies the combination of online algorithms and diverse predictors, proposing an algorithm for the rental/purchase problem using parameter prediction and input prediction, and validating it on the task of minimizing bandwidth costs in distributed systems.

Are labels informative in semi-supervised learning? Estimating and leveraging the missing-data mechanism.

Aude Sportisse (Cote d'Azur University), Pierre-Alexandre Mattei (Cote d'Azur University)

CodeClassificationData-Centric LearningSupervised Fine-TuningImage

🎯 What it does: This study addresses the problem of non-random missing labels (MNAR) in semi-supervised learning, proposing to estimate the missing mechanism and debias any SSL algorithm through inverse propensity weighting.

Are Random Decompositions all we need in High Dimensional Bayesian Optimisation?

Juliusz Krzysztof Ziomek (Huawei Noah's Ark Lab), Haitham Bou Ammar (Huawei Noah's Ark Lab)

CodeOptimizationTabular

🎯 What it does: This paper proposes the use of random tree decomposition in high-dimensional Bayesian optimization as a replacement for traditional data-based decomposition learning, constructing the Random Decomposition Upper Confidence Bound (RDUCB) algorithm, and proving its theoretical guarantee of optimal error and information gain balance in expectation.

Atari-5: Distilling the Arcade Learning Environment down to Five Games

Matthew Aitchison (Australian National University), Marcus Hutter (DeepMind)

CodeKnowledge DistillationReinforcement LearningVideoBenchmark

🎯 What it does: This paper proposes a systematic method based on linear regression to select a representative subset from a large number of Atari games and approximate the median score of the complete ALE benchmark using this subset.

AudioLDM: Text-to-Audio Generation with Latent Diffusion Models

Haohe Liu (University of Surrey), Mark D Plumbley

CodeGenerationData SynthesisSuper ResolutionDiffusion modelMultimodalityAudio

🎯 What it does: This study proposes a continuous latent diffusion model based on CLAP embeddings for text-to-audio (TTA) generation.

Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning

Mingqi Yuan (Hong Kong Polytechnic University), Wenjun Zeng (Eastern Institute for Advanced Study)

CodeReinforcement Learning

🎯 What it does: Enhancing exploration capabilities in reinforcement learning by automatically selecting and using different intrinsic reward functions.

Automatically marginalized MCMC in probabilistic programming

Jinlin Lai (University of Massachusetts Amherst), Daniel Sheldon (University of Massachusetts Amherst)

CodeOptimizationComputational EfficiencyTabular

🎯 What it does: This paper proposes an automated method for edge reversal and variable marginalization of directed graphical models generated by probabilistic programming languages, significantly reducing the variable dimension of HMC sampling and improving sampling efficiency.

Auxiliary Modality Learning with Generalized Curriculum Distillation

Yu Shen (University of Maryland), Ming Lin

CodeAutonomous DrivingKnowledge DistillationMultimodalityPoint Cloud

🎯 What it does: This paper proposes the Auxiliary Modality Learning (AML) framework, systematically defines and classifies auxiliary modalities and network architectures, and introduces the Smart Auxiliary Modality Distillation (SAMD) method to automatically select the optimal auxiliary modality and enhance the performance of the main modality through curriculum distillation under the 'super model' condition.

B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding

Miruna Oprescu (Cornell University), Uri Shalit (Technion Israel Institute of Technology)

CodeTabularFinance Related

🎯 What it does: Proposes the B-Learner method for estimating the upper and lower bounds of conditional average treatment effects (CATE) in the presence of hidden confounding.

Bag of Tricks for Training Data Extraction from Language Models

Weichen Yu (Institute of Automation, Chinese Academy of Sciences), Shuicheng YAN

CodeHyperparameter SearchTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: In response to the issue of training data leakage in language models, this paper systematically evaluates and improves various techniques in the two main stages of training data extraction: generation and ranking, proposing a complete extraction process based on GPT-Neo.

Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process

Zhibin Duan (Xidian University), Mingyuan Zhou (University of Texas at Austin)

CodeGraph Neural NetworkText

🎯 What it does: A knowledge-driven text data coarsening process and the corresponding advanced generative model ProGBN are proposed, which enhance the deep representation and quality of topics in topic models through a coarse-to-fine generation process.

Behavior Contrastive Learning for Unsupervised Skill Discovery

Rushuai Yang (Shanghai Artificial Intelligence Laboratory), Xuelong Li (Northwestern Polytechnical University)

CodeRobotic IntelligenceReinforcement LearningContrastive LearningSequential

🎯 What it does: This paper proposes an unsupervised skill discovery method based on behavior contrastive learning (BeCL), which maximizes the mutual information between different trajectory states under the same skill, achieving both diverse skill learning and improved state coverage.

Benign Overfitting in Two-layer ReLU Convolutional Neural Networks

Yiwen Kou (University of California), Quanquan Gu (University of California)

CodeConvolutional Neural Network

🎯 What it does: This study investigates the benign overfitting phenomenon of two-layer ReLU convolutional neural networks in the presence of label-flipping noise, providing convergence bounds for training error and risk limits for testing error.

Better Diffusion Models Further Improve Adversarial Training

Zekai Wang (Wuhan University), Shuicheng YAN

CodeGenerationAdversarial AttackConvolutional Neural NetworkDiffusion modelGenerative Adversarial NetworkImage

🎯 What it does: By using more advanced diffusion models (EDM) to generate high-quality conditional images, combined with adversarial training (TRADES) to enhance the model's robustness against adversarial attacks.

Better Training of GFlowNets with Local Credit and Incomplete Trajectories

Ling Pan (Mila Quebec AI Institute), Yoshua Bengio (Mila Quebec AI Institute)

CodeGenerationData SynthesisGraph Neural NetworkReinforcement LearningGraph

🎯 What it does: This paper proposes the Forward-Looking GFlowNet (FL-GFN) method, which utilizes energy/reward information from intermediate states to achieve more efficient credit assignment and supports training using only incomplete trajectories.

BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Junnan Li (Salesforce Research), Steven Hoi (Salesforce Research)

CodeGenerationRetrievalTransformerLarge Language ModelVision Language ModelImageTextMultimodality

🎯 What it does: BLIP-2 pretrains a vision-language model by inserting a lightweight query Transformer (Q-Former) between a frozen image encoder and a large language model, completing zero-shot generation and retrieval tasks from images to text.

Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach

Xuan Son Nguyen (CY Cergy Paris UniversitΓ©), Shuo Yang (CY Cergy Paris UniversitΓ©)

CodeClassificationRecognitionVideoGraph

🎯 What it does: This paper studies how to construct neural networks on Symmetric Positive Definite (SPD) and Grassmann manifolds, proposing to extend gyrovector space theory to these two types of matrix manifolds, and based on this, defines basic operations and layers such as inner product, gyro angle, gyro isometries, and polynomial logistic regression (MLR) on SPD.

CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling

Jun Zhang (Shanghai AI Laboratory), Lingpeng Kong (The University of Hong Kong)

CodeTransformerTextPoint CloudTime SeriesBenchmark

🎯 What it does: This paper proposes a comprehensive attention benchmark (CAB) for long sequence modeling and evaluates nine mainstream efficient attention architectures under four fine-grained attention modes (non-causal self-attention, causal self-attention, non-causal cross-attention, causal cross-attention).

Can Neural Network Memorization Be Localized?

Pratyush Maini (Carnegie Mellon University), Chiyuan Zhang (Google Research)

CodeClassificationOptimizationConvolutional Neural NetworkTransformerSupervised Fine-TuningImage

🎯 What it does: This paper studies the spatial localization of the 'memorization' phenomenon in neural networks, proving that memorization is not concentrated in the last few layers of the model, but rather dispersed across a few neurons in different layers. It proposes an 'Example-Tied Dropout' method that directs memorization towards a pre-specified set of neurons.

Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?

Boris Knyazev (Samsung), Simon Lacoste-Julien (Mila)

CodeOptimizationRepresentation LearningTransformerImage

🎯 What it does: Designed and trained a large-scale Graph Hyper-Network (GHN-3) that can quickly predict ImageNet pre-trained parameters and use these parameters to initialize models of various architectures, thereby reducing pre-training costs.

CataBEEM: Integrating Latent Interaction Categories in Node-wise Community Detection Models for Network Data

Yuhua Zhang (University of Michigan), Walter H. Dempsey (University of Michigan)

CodeGraph Neural NetworkGraph

🎯 What it does: A CataBEEM model under an edge-exchangeable framework is proposed to simultaneously learn latent categories at the interaction level and community structures at the node level, achieving scalable variational EM inference on large-scale interaction networks.

Causal Strategic Classification: A Tale of Two Shifts

Guy Horowitz (Technion Israel Institute of Technology), Nir Rosenfeld (Technion Israel Institute of Technology)

CodeClassificationOptimizationTabularFinance Related

🎯 What it does: This paper studies the strategic classification problem where users can change features and these changes affect the true labels, and proposes a learning framework and algorithm that incorporates causal relationships.

Chemically Transferable Generative Backmapping of Coarse-Grained Proteins

Soojung Yang (Massachusetts Institute of Technology), Rafael Gomez-Bombarelli

CodeGenerationProtein Structure PredictionAuto EncoderBiomedical Data

🎯 What it does: A generative post-mapping method has been developed that can quickly recover all atomic-level details from coarse-grained (only containing α carbon) structures;

CLIPood: Generalizing CLIP to Out-of-Distributions

Yang Shu (Tsinghua University), Mingsheng Long (Tsinghua University)

CodeDomain AdaptationTransformerSupervised Fine-TuningPrompt EngineeringContrastive LearningImageTextMultimodality

🎯 What it does: Fine-tune the CLIP model with a focus on achieving better generalization capabilities under the OOD setting where domain shift and new classes (open class) coexist in downstream tasks.

CLUSTSEG: Clustering for Universal Segmentation

James Chenhao Liang, Wenguan Wang (Zhejiang University)

CodeSegmentationTransformerImage

🎯 What it does: This paper proposes CLUSTSEG, a unified framework based on transformers that can simultaneously perform superpixel, semantic, instance, and panoptic segmentation tasks.

CLUTR: Curriculum Learning via Unsupervised Task Representation Learning

Abdus Salam Azad (University of California), Ion Stoica (University of California)

CodeRepresentation LearningRecurrent Neural NetworkReinforcement LearningAuto EncoderSequential

🎯 What it does: Developed a curriculum learning algorithm CLUTR based on unsupervised task representation learning for unsupervised environment design in reinforcement learning.

CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design

Desi R. Ivanova (University of Oxford), Adam Foster (Microsoft Research)

CodeOptimizationReinforcement LearningTabular

🎯 What it does: A general context optimization framework CO-BED is proposed, which utilizes the expected information gain from Bayesian experimental design (CMV-EIG) to guide experimental design, thereby achieving better contextual decisions during the deployment phase.

Competing for Shareable Arms in Multi-Player Multi-Armed Bandits

Renzhe Xu (Tsinghua University), Peng Cui (Tsinghua University)

CodeOptimizationReinforcement Learning

🎯 What it does: A shared reward model for multi-player multi-armed bandits is designed, and the SMAA algorithm is proposed to implement the learning and competition of self-interested players.

Complementary Attention for Multi-Agent Reinforcement Learning

Jianzhun Shao (Tsinghua University), Xiangyang Ji (Tsinghua University)

CodeRecurrent Neural NetworkReinforcement LearningSequential

🎯 What it does: In multi-agent reinforcement learning, this paper proposes a new framework called CAMA to simultaneously address the issues of attention dispersion and information insufficiency caused by dynamic team sizes and partial observability. The framework divides environmental entities into high-attention and low-attention parts through an entity partitioning module, enhancing attention on high-attention entities using inverse models, and using a global coach to generate compressed information for low-attention entities to achieve attention compensation, thereby enabling more robust and efficient collaborative decision-making.

Composer: Creative and Controllable Image Synthesis with Composable Conditions

Lianghua Huang (Alibaba Group), Jingren Zhou (Alibaba Group)

CodeGenerationData SynthesisDiffusion modelImage

🎯 What it does: Composer is constructed, a multi-conditional diffusion model that enables controllable and creative image synthesis by combining the decomposed representations of images.

Compositional Exemplars for In-context Learning

Jiacheng Ye (University of Hong Kong), Lingpeng Kong (University of Hong Kong)

CodeGenerationRetrievalTransformerLarge Language ModelContrastive LearningText

🎯 What it does: This paper proposes a global example subset selection method called CEIL based on Conditional DPP, which utilizes the output probabilities of large language models for contrastive learning to automatically select the most helpful demonstration example set in In-Context Learning.

Computational Asymmetries in Robust Classification

Samuele Marro (University of Bologna), Michele Lombardi (University of Bologna)

CodeClassificationAdversarial AttackConvolutional Neural NetworkImageBenchmark

🎯 What it does: The paper explores the computational asymmetry of robust classification from both theoretical and experimental perspectives, proving that attacking ReLU classifiers is NP-hard, while finding robust parameters during the training phase is Ξ£Pβ‚‚-hard; it proposes a defense method based on attacks called Counter-Attack and provides its complexity; further experiments demonstrate that heuristic attacks can reliably approach the decision boundary distance, and the UG100 dataset is released.

Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models

Harshit Varma (Indian Institute of Technology Bombay), Sunita Sarawagi (Indian Institute of Technology Bombay)

CodeTransformerText

🎯 What it does: CTREEOT is proposed, a differentiable and convergent conditional tree matching algorithm that adapts tree prediction models using a small number of cases during inference.

Conditionally Strongly Log-Concave Generative Models

Florentin Guth (Ecole Normale Superieure), Stéphane Mallat (Collège de France)

CodeGenerationScore-based ModelImageMultimodalityPhysics Related

🎯 What it does: This paper proposes a Conditional Strong Log-Convex (CSLC) generative model that decomposes high-dimensional data into several conditional log-convex sub-distributions through adaptive orthogonal projection, achieving theoretically guaranteed learning and sampling.

Constrained Causal Bayesian Optimization

Virginia Aglietti (DeepMind), Silvia Chiappa (DeepMind)

CodeOptimizationGraphTabularElectronic Health Records

🎯 What it does: This paper proposes a constrained causal Bayesian optimization (cCBO) method under a known causal graph, aimed at finding the optimal intervention set that satisfies multiple constraints to optimize the expected value of the target variable.

Constrained Efficient Global Optimization of Expensive Black-box Functions

Wenjie Xu (Automatic Control Laboratory EPFL), Colin Jones

CodeOptimizationTabular

🎯 What it does: The CONFIG algorithm is proposed to solve the efficient global optimization problem of constrained expensive black-box functions.

Continual Task Allocation in Meta-Policy Network via Sparse Prompting

Yijun Yang (Southern University of Science and Technology), Yuhui Shi (Southern University of Science and Technology)

CodeMeta LearningReinforcement LearningPrompt EngineeringSequential

🎯 What it does: This paper proposes the CoTASP method, which dynamically extracts sub-networks from a meta-policy network using sparse prompts to achieve continual task learning, addressing the plasticity-stability trade-off problem.

Continuous Spatiotemporal Transformer

Antonio Henrique de Oliveira Fonseca (Yale University), David van Dijk (Yale University)

CodeRestorationAutonomous DrivingOptimizationTransformerVideoTime SeriesBiomedical DataOrdinary Differential Equation

🎯 What it does: A Transformer architecture named Continuous Spatiotemporal Transformer (CST) is proposed, specifically designed for learning continuous spatiotemporal dynamical systems, ensuring the model outputs are continuous and smooth, achieving high-quality interpolation and prediction across various tasks.

Continuously Parameterized Mixture Models

Christopher M Bender, Junier Oliva

CodeAnomaly DetectionImageOrdinary Differential Equation

🎯 What it does: A continuous parameterized mixed model (CPMM) utilizing neural ODEs is proposed, achieving density estimation and clustering of high-dimensional complex data through a hierarchical structure and curriculum learning.

Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining

Zekun Qi (Xi'an Jiaotong University), Li Yi (Tsinghua University)

CodeRepresentation LearningTransformerContrastive LearningPoint Cloud

🎯 What it does: A 3D representation learning framework called RECON is proposed, which integrates contrastive learning and generative reconstruction.

Controlled Differential Equations on Long Sequences via Non-standard Wavelets

Sourav Pal (University of Wisconsin Madison), Vikas Singh (University of Wisconsin Madison)

CodeClassificationOptimizationComputational EfficiencyRecurrent Neural NetworkAuto EncoderTime SeriesSequentialBiomedical DataElectrocardiogramOrdinary Differential Equation

🎯 What it does: A non-standard wavelet decomposition (BCR-DE) framework based on the Beylkin–Coifman–Rokhlin (BCR) algorithm is proposed, simplifying long-time series neural controlled differential equations (NCDE) into a single integral transform and constraining the operator to Calderon-Zygmund (CZ) class, achieving efficient training and inference.

Convex Geometry of ReLU-layers, Injectivity on the Ball and Local Reconstruction

Daniel Haider (Austrian Academy of Sciences), Peter Balazs (University of Vienna)

CodeOptimizationConvolutional Neural NetworkTabular

🎯 What it does: This paper studies the injectivity of ReLU layers on a finite radius sphere (and its non-negative part) within the framework of frame theory, and provides a computable upper bound bias estimation method (PBE) along with the corresponding reconstruction formula.

Covariate balancing using the integral probability metric for causal inference

Insung Kong (Seoul National University), Yongdai Kim (Seoul National University)

CodeAdversarial AttackTabular

🎯 What it does: Two weighting methods (parametric and non-parametric CBIPM) were designed using Integral Probability Metrics (IPM) to achieve covariate balance and estimate average treatment effects.

Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss

Pierre BrΓ©chet (Max Planck Institute for Mathematics in the Sciences), Guido Montufar

CodeGenerationOptimizationTabular

🎯 What it does: Analyzed and proved the critical point structure and convergence of deep linear networks when trained with the Bures-Wasserstein loss.

CrossSplit: Mitigating Label Noise Memorization through Data Splitting

Jihye Kim (Samsung Advanced Institute of Technology), Simon Lacoste-Julien (Mila)

CodeClassificationConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: A robust training framework named CrossSplit is proposed, which randomly divides the training set with noisy labels into two parts, trains two networks on the two parts of the data respectively, and uses each other's predictions to soften the labels, combined with semi-supervised learning to reduce the model's memory of incorrect labels.

DADAO: Decoupled Accelerated Decentralized Asynchronous Optimization

Adel Nabli (Sorbonne UniversitΓ©), Edouard Oyallon (Sorbonne UniversitΓ©)

CodeOptimizationTabular

🎯 What it does: A DADAO algorithm is proposed for asynchronously, decoupled, and accelerated minimization of the sum of strongly convex smooth functions in distributed networks.

Data Feedback Loops: Model-driven Amplification of Dataset Biases

Rohan Taori (Stanford University), Tatsunori Hashimoto

CodeGenerationData-Centric LearningImageText

🎯 What it does: Discusses the feedback loop generated when model outputs are used as future training data and studies its impact on bias amplification.

Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least

Siddharth Joshi (University of California Los Angeles), Baharan Mirzasoleiman (University of California Los Angeles)

CodeClassificationData-Centric LearningContrastive LearningImage

🎯 What it does: This paper studies which training samples in contrastive self-supervised learning can most enhance model performance and proposes a subset selection method called SAS based on maximizing expected augmented similarity.

Dataset Distillation with Convexified Implicit Gradients

Noel Loo (Massachusetts Institute of Technology), Daniela Rus (Massachusetts Institute of Technology)

CodeOptimizationKnowledge DistillationConvolutional Neural NetworkImage

🎯 What it does: A composite reparameterization and convex data distillation algorithm based on implicit gradients (RCIG) is proposed, which can compress the original dataset into a minimal number of synthetic samples through a single gradient update and train high-quality models on various tasks.

Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time

Zichang Liu (Rice University), Beidi Chen (Carnegie Mellon University)

CodeComputational EfficiencyTransformerLarge Language ModelText

🎯 What it does: A dynamic sparse structure is proposed for the inference process of large-scale language models (LLMs), which retains only a portion of attention heads and MLP neurons for each input. The DEJAVU system is constructed to achieve real-time sparse prediction and hardware-friendly execution, significantly reducing inference latency.

Delayed Feedback in Kernel Bandits

Sattar Vakili (MediaTek Research), Ciara Pike-Burke (Imperial College London)

CodeOptimizationReinforcement LearningTabular

🎯 What it does: This paper studies the kernel bandwidth problem with stochastic delayed feedback and proposes an algorithm called BPE-Delay, aimed at optimizing the learning process of kernel functions.

Delving into Noisy Label Detection with Clean Data

Chenglin Yu (Wuhan University), Weiwei Liu (Wuhan University)

CodeClassificationData-Centric LearningConvolutional Neural NetworkImage

🎯 What it does: A Benjamini–Hochberg (BH) multiple hypothesis testing framework (BHN) is proposed, which utilizes a small amount of clean data to identify and eliminate noisy labels in neural networks by treating noisy label detection as a multiple hypothesis testing problem and calibrating empirical p-values.

Denoising MCMC for Accelerating Diffusion-Based Generative Models

Beomsu Kim (KAIST), Jong Chul Ye (KAIST)

CodeGenerationData SynthesisComputational EfficiencyDiffusion modelScore-based ModelImageStochastic Differential EquationOrdinary Differential Equation

🎯 What it does: The Denoising MCMC (DMCMC) framework is proposed, which combines MCMC with reverse SDE/ODE solvers to accelerate sampling of score models.

DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature

Eric Mitchell (Stanford University), Chelsea Finn (Stanford University)

CodeGenerationAnomaly DetectionTransformerLarge Language ModelText

🎯 What it does: A zero-shot machine-generated text detection method based on probabilistic curvature, called DetectGPT, is proposed.

Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score

Shuhai Zhang (South China University of Technology), Mingkui Tan (South China University of Technology)

CodeAnomaly DetectionAdversarial AttackConvolutional Neural NetworkTransformerDiffusion modelImageStochastic Differential Equation

🎯 What it does: Proposes and uses the Expected Perturbation Score (EPS) as a statistic for detecting adversarial samples, and constructs an EPS-based Maximum Mean Discrepancy (MMD) detection method called EPS-AD;

DevFormer: A Symmetric Transformer for Context-Aware Device Placement

Haeyeon Kim (Korea Advanced Institute of Science and Technology), Jinkyoo Park (Korea Advanced Institute of Science and Technology)

CodeOptimizationTransformerTabular

🎯 What it does: A Transformer model named DevFormer is proposed for offline context hardware design optimization, particularly for the decap placement problem.

Difference-in-Differences Meets Tree-based Methods: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding

Caizhi Tang (Ant Group), JUN ZHOU

CodeData SynthesisRecommendation SystemOptimizationTabularTime SeriesFinance Related

🎯 What it does: This paper proposes a framework that combines difference-in-differences and tree models to estimate the conditional average treatment effect (CATT) in the presence of unmeasured confounding in balanced panel data.

Differentiable Multi-Target Causal Bayesian Experimental Design

Panagiotis Tigas (University of Oxford), Stefan Bauer (Helmholtz AI)

CodeOptimizationGraph Neural NetworkGraph

🎯 What it does: A gradient-based differentiable Bayesian experimental design method is proposed for batch multi-objective causal model learning.

Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models

Phillip Rust (University of Copenhagen), Anders SΓΈgaard (University of Copenhagen)

CodeSafty and PrivacyExplainability and InterpretabilityTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: The study investigates the compatibility and conflicts between multilingual language models in differential privacy, language fairness, and the impact of training data sparsity.

Differentially Private Optimization on Large Model at Small Cost

Zhiqi Bu (Amazon Web Services), George Karypis (University of Minnesota)

CodeOptimizationSafty and PrivacyComputational EfficiencyTransformerLarge Language ModelImageText

🎯 What it does: The Book-Keeping (BK) algorithm is proposed, achieving nearly the same time and memory overhead as non-private training through a single round of backpropagation in differential privacy training.

Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?

Victor Boutin (Toulouse Institute), Thomas Serre (Brown University)

CodeGenerationDiffusion modelContrastive LearningImage

🎯 What it does: This study investigates a one-shot drawing task, comparing the performance of humans and various generative models (VAE, GAN, diffusion models) in terms of drawing diversity and recognizability, and proposes originality metrics and generalization curves for more granular evaluation.

Dink-Net: Neural Clustering on Large Graphs

Yue Liu (National University of Defense Technology), Stan Z. Li (Westlake University)

CodeGraph Neural NetworkContrastive LearningGraph

🎯 What it does: A scalable deep graph clustering method Dink-Net is proposed, achieving a unified framework for self-supervised node discrimination and neural clustering modules.

Direct Parameterization of Lipschitz-Bounded Deep Networks

Ruigang Wang (University of Sydney), Ian Manchester

CodeOptimizationConvolutional Neural NetworkImage

🎯 What it does: A new direct parameterization method is proposed, allowing deep neural networks to automatically satisfy the β„“2 Lipschitz upper bound during training, and enabling learning through standard gradient optimization.

Dirichlet Diffusion Score Model for Biological Sequence Generation

Pavel Avdeyev (University of Texas Southwestern Medical Center), Jian Zhou (University of Texas Southwestern Medical Center)

CodeGenerationData SynthesisTransformerDiffusion modelScore-based ModelSequentialBiomedical DataStochastic Differential Equation

🎯 What it does: A continuous-time fractional model for diffusion on probability simplices is proposedβ€”the Dirichlet Diffusion Fractional Model (DDSM), which is applied to discrete data generation, especially for biological sequences (such as human promoters) and constrained data (Sudoku) generation and solving.

Discover and Cure: Concept-aware Mitigation of Spurious Correlation

Shirley Wu (Stanford University), James Zou (Stanford University)

CodeClassificationExplainability and InterpretabilityContrastive LearningImage

🎯 What it does: Proposes the DISC method, which uses interpretable concepts to identify and eliminate spurious correlations in image classification.

Discovering Object-Centric Generalized Value Functions From Pixels

Somjit Nath (Ecole de technologie superieure), Samira Ebrahimi Kahou (Mila-Quebec AI Institute)

CodeRobotic IntelligenceReinforcement LearningImage

🎯 What it does: This paper proposes an end-to-end OC-GVFs method that automatically discovers object features from pixels using Slot Attention, and then maps these features to cumulants to learn a Generalized Value Function (GVF), thereby providing a rich and interpretable representation for control policies.

Disentangled Generative Models for Robust Prediction of System Dynamics

Stathi Fotiadis (Imperial College London), Anil Anthony Bharath (Imperial College London)

CodeGenerationData SynthesisRecurrent Neural NetworkAuto EncoderImageTime SeriesOrdinary Differential Equation

🎯 What it does: Constructed a decoupled variational autoencoder under the supervision of dynamical system parameters, achieving long-term and robust predictions of system states.