arXivSub Start free trial

NeurIPS 2023 Papers with Code β€” Page 12

Conference on Neural Information Processing Systems Β· 1376 papers

Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning

Yihua Zhang (Michigan State University), Sijia Liu (Michigan State University)

CodeComputational EfficiencyData-Centric LearningConvolutional Neural NetworkImage

🎯 What it does: This study investigates strategies for pruning the source dataset in transfer learning to enhance pre-training efficiency and downstream performance.

Self-Adaptive Motion Tracking against On-body Displacement of Flexible Sensors

Chengxu Zuo (Xiamen University), Yipeng Qin (Cardiff University)

CodeObject TrackingDomain AdaptationRecurrent Neural NetworkSupervised Fine-TuningTime Series

🎯 What it does: This study investigates the data distribution drift caused by displacement of wearable flexible sensors at different wearing positions and proposes an unsupervised adaptive motion tracking network.

Self-Chained Image-Language Model for Video Localization and Question Answering

Shoubin Yu (University of North Carolina Chapel Hill), Mohit Bansal (University of North Carolina Chapel Hill)

CodeRecognitionRetrievalTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringVision Language ModelVideoText

🎯 What it does: This paper proposes a Self-Chained Video Localization and Answering (SeViLA) framework based on a single image-language model BLIP-2, which first uses a Localizer to locate key frames with language perception, and then employs an Answerer to perform video question answering or event prediction on these frames, refining the Localizer through pseudo-labels generated from the answers.

Self-Supervised Visual Acoustic Matching

Arjun Somayazulu (University of Texas at Austin), Kristen Grauman (Meta Platforms)

CodeGenerative Adversarial NetworkMultimodalityAudio

🎯 What it does: Proposes a self-supervised visual-acoustic matching method

Self-Weighted Contrastive Learning among Multiple Views for Mitigating Representation Degeneration

Jie Xu (University of Electronic Science and Technology of China), Xiaofeng Zhu (University of Electronic Science and Technology of China)

CodeRepresentation LearningAuto EncoderContrastive LearningImageVideo

🎯 What it does: This paper proposes a self-weighted multi-view contrastive learning framework SEM, which utilizes reconstruction regularization to alleviate the representation degradation problem in multi-view contrastive learning.

Semantic segmentation of sparse irregular point clouds for leaf/wood discrimination

Yuchen BAI, Florence Forbes (University of Grenoble Alpes)

CodeClassificationSegmentationPoint Cloud

🎯 What it does: A SOUL network based on PointNet++ is proposed for semantic segmentation of leaf and wood materials from sparse and heterogeneous point clouds generated by drone LiDAR.

Semi-Implicit Denoising Diffusion Models (SIDDMs)

yanwu xu, Tingbo Hou (Boston University)

CodeGenerationData SynthesisDiffusion modelGenerative Adversarial NetworkImage

🎯 What it does: This paper proposes a Semi-Implicit Denoising Diffusion Model (SIDDM), which decomposes the denoising distribution into implicit edge matching and explicit conditional matching (AFD), achieving large step sampling while maintaining high-quality samples.

Semi-Supervised Contrastive Learning for Deep Regression with Ordinal Rankings from Spectral Seriation

Weihang Dai (Hong Kong University of Science and Technology), Xiaomeng Li (Hong Kong University of Science and Technology)

CodeContrastive LearningBiomedical DataMagnetic Resonance Imaging

🎯 What it does: A new semi-supervised contrastive learning framework CLSS is proposed, which utilizes the feature similarity matrix of unlabeled samples to recover ordinal relationships through spectral sequence algorithms, and applies it to contrastive learning and predictive supervision.

Sequential Subset Matching for Dataset Distillation

Jiawei Du (Agency for Science Technology and Research), Joey Tianyi Zhou (Agency for Science Technology and Research)

CodeData SynthesisOptimizationKnowledge DistillationMeta LearningImage

🎯 What it does: The SeqMatch method is proposed, which divides synthetic data into multiple subsets and optimizes them sequentially to address the issue of insufficient high-order feature distillation caused by excessive compression of low-level features.

Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots

Ruixiang Tang (Rice University), Xia Hu (Rice University)

CodeClassificationAdversarial AttackTransformerSupervised Fine-TuningText

🎯 What it does: A honeypot module is proposed, which inserts a small classifier at the lower layers of a pre-trained language model (PLM) to specifically absorb and cover backdoor information during the fine-tuning process, allowing the main network to only learn the original task.

SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations

Qitian Wu (Shanghai Jiao Tong University), Junchi Yan (Shanghai Jiao Tong University)

CodeRepresentation LearningGraph Neural NetworkTransformerGraph

🎯 What it does: This paper proposes SGFormer, a simplified Transformer model that utilizes a single-layer global linear attention combined with GCN to achieve efficient learning of large-scale graph node representations.

Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstruction

Souhaib Attaiki (Γ‰cole Polytechnique), Maks Ovsjanikov (Γ‰cole Polytechnique)

CodeObject DetectionSegmentationGraph Neural NetworkDiffusion modelPoint CloudMesh

🎯 What it does: A zero-shot non-rigid shape matching method SNK is proposed, achieving shape matching through unsupervised feature mapping and decoder reconstruction directly on a single pair of shapes.

Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples

Shaokui Wei (Chinese University of Hong Kong), Baoyuan Wu (Chinese University of Hong Kong)

CodeOptimizationAdversarial AttackConvolutional Neural NetworkGenerative Adversarial NetworkImage

🎯 What it does: A Shared Adversarial Unlearning (SAU) method is proposed to eliminate backdoor attacks on deep neural networks by generating and removing shared adversarial samples.

Sharp Bounds for Generalized Causal Sensitivity Analysis

Dennis Frauen (LMU Munich), Stefan Feuerriegel (LMU Munich)

CodeFlow-based ModelTabularTime Series

🎯 What it does: This paper proposes a generalized marginal sensitivity model (GMSM) and derives sharp boundaries under various causal effects (average treatment effect, mediation effect, path effect, and distribution effect), providing scalable algorithms to estimate these boundaries from observational data.

Sharpness-Aware Minimization Leads to Low-Rank Features

Maksym Andriushchenko (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne), Nicolas Flammarion (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne)

CodeClassificationOptimizationRepresentation LearningConvolutional Neural NetworkTransformerContrastive LearningImage

🎯 What it does: This paper studies the impact of Sharpness-Aware Minimization (SAM) on the feature rank of deep networks, finding that SAM can significantly reduce the feature rank across different models (ResNet, ViT, MLP-Mixer, etc.) and different tasks (classification, contrastive learning);

ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer

Haoran You (Georgia Institute of Technology), Yingyan Celine Lin (Georgia Institute of Technology)

CodeClassificationComputational EfficiencyTransformerMixture of ExpertsImage

🎯 What it does: Reparameterize the pre-trained Vision Transformer by replacing multiplication operations with shifts and additions to construct the ShiftAddViT model.

SHOT: Suppressing the Hessian along the Optimization Trajectory for Gradient-Based Meta-Learning

JunHoo Lee (Seoul National University), Nojun Kwak (Seoul National University)

CodeOptimizationMeta LearningImage

🎯 What it does: This paper proposes an explicit suppression of the Hessian matrix on the optimization trajectory in gradient-based meta-learning, achieved by minimizing the distance between the target model and the reference model.

SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization

Hao Dong (ETH Zurich), Olga Fink (EPFL)

CodeDomain AdaptationContrastive LearningMultimodality

🎯 What it does: A framework for multimodal domain generalization, SimMMDG, is proposed by splitting each modality feature into shared and exclusive parts, and enhancing the model's generalization ability to unknown domains through supervised contrastive learning, distance constraints, and cross-modal translation.

SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling

Jiaxiang Dong (Tsinghua University), Mingsheng Long (Tsinghua University)

CodeClassificationTransformerContrastive LearningTime SeriesSequential

🎯 What it does: This paper proposes SimMTM, a self-supervised pre-training framework for time series based on multiple masked sequence aggregation, aimed at improving the performance of prediction and classification tasks.

Simple and Asymmetric Graph Contrastive Learning without Augmentations

Teng Xiao (Pennsylvania State University), Suhang Wang (Zhejiang University)

CodeClassificationRepresentation LearningGraph Neural NetworkContrastive LearningGraph

🎯 What it does: This paper proposes GraphACL, a framework for asymmetric contrastive learning that does not rely on graph data augmentation. It learns node representations by utilizing the one-hop neighbor context and two-hop homophily, making it applicable to both homophilic and heterophilic graphs.

Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions

Sayantan Choudhury (Johns Hopkins University), Nicolas Loizou (Johns Hopkins University)

CodeOptimization

🎯 What it does: This paper proposes a new convergence analysis framework for the Single-Call Stochastic Extragradient methods (such as SPEG and SOG), providing convergence proofs for two types of structured non-monotone variational inequalities (quasi-strongly monotone and weak Minty) under weak assumptions (without the need for bounded variance or growth conditions), and unifying the consideration of arbitrary sampling (including uniform, importance sampling, and arbitrary mini-batch).

Slimmed Asymmetrical Contrastive Learning and Cross Distillation for Lightweight Model Training

Jian Meng (Cornell Tech), Jae-sun Seo (Cornell Tech)

CodeComputational EfficiencyKnowledge DistillationRepresentation LearningConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: This paper designs a lightweight contrastive learning framework SACL-XD, which can train small networks from scratch and achieve high accuracy.

SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation

Mengcheng Lan (Nanyang Technological University), Wayne Zhang (SenseTime Research)

CodeSegmentationRepresentation LearningTransformerContrastive LearningImage

🎯 What it does: Designed the SmooSeg method, which utilizes smoothness priors and energy minimization to achieve unsupervised semantic segmentation.

SmoothHess: ReLU Network Feature Interactions via Stein's Lemma

Max Torop (Northeastern University), Jennifer Dy (Northeastern University)

CodeOptimizationAdversarial AttackConvolutional Neural NetworkGaussian SplattingImageTime SeriesBiomedical Data

🎯 What it does: Using Gaussian convolution on the output of ReLU networks to obtain a smooth function, we estimate its Hessian to capture the second-order interactions of features.

SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

Yanyu Li (Snap Inc.), Jian Ren (Snap Inc.)

CodeGenerationData SynthesisComputational EfficiencyKnowledge DistillationDiffusion modelImage

🎯 What it does: A text-to-image diffusion model has been implemented on mobile devices, completing in under 2 seconds using 8 denoising steps, with image quality comparable to Stable Diffusion v1.5.

SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities

Hugues Van Assel (Γ‰cole normale supΓ©rieure de Lyon), Nicolas Courty (UniversitΓ© Bretagne Sud)

CodeOptimizationImageBiomedical Data

🎯 What it does: This paper proposes Symmetric Entropic Affinities and a dimensionality reduction algorithm based on this matrix called SNEkhorn.

SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation

Zhuoyan Luo (Tsinghua University), Yujiu Yang (Tsinghua University)

CodeObject DetectionSegmentationTransformerContrastive LearningVideoTextMultimodality

🎯 What it does: Proposes the SOC framework to achieve video-level multimodal understanding, enhancing RVOS through semantic-assisted object clustering.

SODA: Robust Training of Test-Time Data Adaptors

Zige Wang (Peking University), Bo Han (Hong Kong Baptist University)

CodeDomain AdaptationOptimizationConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: In scenarios where model parameters are inaccessible, a test-time data adaptation method called SODA based on zero-order optimization is proposed.

Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks

Changhyeon Lee (Ulsan National Institute of Science and Technology), Seulki Lee (Ulsan National Institute of Science and Technology)

CodeTransformerText

🎯 What it does: This paper proposes a method to approximate the softmax output during the training process of attention networks such as Transformer, reducing the activation memory usage.

Solving a Class of Non-Convex Minimax Optimization in Federated Learning

Xidong Wu (University of Pittsburgh), Heng Huang (University of Maryland)

CodeOptimizationFederated LearningImage

🎯 What it does: This paper studies non-convex-convex, non-convex-strongly convex, and non-convex-PL (Polyak-Lojasiewicz) minimax optimization problems in a federated learning environment, and proposes two improved algorithms, FedSGDA+ and FedSGDA-M.

Solving Inverse Physics Problems with Score Matching

Benjamin Holzschuh (Technical University of Munich), Nils Thuerey (Technical University of Munich)

CodeScore-based ModelContrastive LearningTime SeriesPhysics RelatedStochastic Differential EquationOrdinary Differential Equation

🎯 What it does: This paper proposes a method for inverse physical solving that combines score matching with differentiable physical simulation, capable of inferring the initial state from the final state of the system and sampling the posterior distribution.

Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models

Litu Rout (University of Texas at Austin), Sanjay Shakkottai (University of Texas at Austin)

CodeRestorationSuper ResolutionDiffusion modelImageStochastic Differential Equation

🎯 What it does: Using pre-trained Latent Diffusion Models to solve linear inverse problems (such as image inpainting, denoising, super-resolution, etc.)

SoTTA: Robust Test-Time Adaptation on Noisy Data Streams

Taesik Gong (Nokia Bell Labs), Sung-Ju Lee (KAIST)

CodeDomain AdaptationImage

🎯 What it does: This paper proposes a testing-time adaptive method for noisy samples (SoTTA), aimed at enhancing the model's robustness to noisy samples in real-world testing streams.

Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio

Xudong XU, Alexander Richard (Meta Reality Labs Research)

CodeGenerationData SynthesisPose EstimationMultimodalityAudio

🎯 What it does: Using audio captured by a head-mounted microphone and human joint posture information, a multimodal network was constructed that can generate a three-dimensional sound field covering the human body, enabling spatial audio rendering at any spatial location.

SPA: A Graph Spectral Alignment Perspective for Domain Adaptation

Zhiqing Xiao (Zhejiang University), Junbo Zhao (Zhejiang University)

CodeDomain AdaptationGraph Neural NetworkImage

🎯 What it does: This paper addresses the problem of unsupervised domain adaptation and proposes a framework based on spectral alignment, which captures cross-domain transferability while enhancing intra-domain discriminability.

SPACE: Single-round Participant Amalgamation for Contribution Evaluation in Federated Learning

Yi-Chung Chen (National Taiwan University), Ming-Syan Chen (National Taiwan University)

CodeFederated LearningImage

🎯 What it does: A single-round participant fusion evaluation method called SPACE is proposed for efficiently assessing the contributions of each client in federated learning.

Sparse Modular Activation for Efficient Sequence Modeling

Liliang Ren (University of Illinois at Urbana-Champaign), ChengXiang Zhai

CodeOptimizationComputational EfficiencyTransformerTextSequentialAudio

🎯 What it does: Designed and implemented a differentiable Sparse Modular Activation (SMA) mechanism, constructing the SeqBoat network, which utilizes SMA for dynamic sparse activation state space models (SSM) and gated attention units (GAU) to achieve efficient sequence modeling;

Sparse Parameterization for Epitomic Dataset Distillation

Xing Wei (Xi'an Jiaotong University), Zhiheng Ma (Shenzhen Institute of Advanced Technology)

CodeData SynthesisKnowledge DistillationRecurrent Neural NetworkTransformerImage

🎯 What it does: A sparse parameterization-based Epitomic dataset distillation framework SPEED is proposed, capable of synthesizing information-rich synthetic data in extremely low storage space.

Spatial-frequency channels, shape bias, and adversarial robustness

Ajay Subramanian (New York University), Denis G. Pelli (New York University)

CodeClassificationRecognitionAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: This paper proposes and utilizes critical band masking experiments to compare the object recognition performance of humans and various deep networks under the influence of frequency domain noise, assessing their spatial frequency channel characteristics.

Spatially Resolved Gene Expression Prediction from Histology Images via Bi-modal Contrastive Learning

Ronald Xie (University of Toronto), Gary Bader

CodeRepresentation LearningData-Centric LearningConvolutional Neural NetworkContrastive LearningImageBiomedical Data

🎯 What it does: A dual-modal contrastive learning-based embedding framework called BLEEP is proposed, which can predict the spatial resolution of gene expression from H&E tissue slice images.

Speculative Decoding with Big Little Decoder

Sehoon Kim (University of California), Kurt Keutzer (University of California)

CodeGenerationComputational EfficiencyTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: The Big Little Decoder (BiLD) framework is proposed, which generates text collaboratively using a small model (autoregressive) and a large model (non-autoregressive), significantly reducing inference latency through fallback and rollback strategies without altering the training process.

Spike-driven Transformer

Man Yao (Institute of Automation Chinese Academy of Sciences), Guoqi Li (Institute of Automation Chinese Academy of Sciences)

CodeClassificationRecognitionSpiking Neural NetworkTransformerImage

🎯 What it does: Proposes Spike-Driven Transformer, which integrates the spike-driven principle of SNN with Transformer, allowing the network to achieve attention and MLP computation solely through sparse addition.

Spontaneous symmetry breaking in generative diffusion models

Gabriel Raya (Jheronimus Academy of Data Science), Luca Ambrogioni (Radboud University)

CodeGenerationData SynthesisDiffusion modelImageStochastic Differential Equation

🎯 What it does: This paper studies the phenomenon of spontaneous symmetry breaking in the generation process of diffusion models and utilizes this phenomenon to improve fast samplers.

SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning

Dohyeok Lee (Seoul National University), Jungwoo Lee (Seoul National University)

CodeReinforcement LearningSequential

🎯 What it does: A Q-ensemble independence regularization method SPQR based on random matrix theory is proposed, which uses the KL divergence between the eigenvalue distribution and the Wigner semicircle distribution to reduce the correlation of the Q-ensemble and suppress estimation bias.

Spuriosity Didn’t Kill the Classifier: Using Invariant Predictions to Harness Spurious Features

Cian Eastwood (University of Edinburgh), Bernhard SchΓΆlkopf (Max Planck Institute for Intelligent Systems)

CodeDomain AdaptationImage

🎯 What it does: The Stable Feature Boosting (SFB) algorithm is proposed, which utilizes stable feature predictions to adjust and leverage unstable (artifact) features in an unsupervised manner to enhance domain generalization performance.

Squared Neural Families: A New Class of Tractable Density Models

Russell Tsuchida (Data61 CSIRO), Dino Sejdinovic (University of Adelaide)

CodeGenerationOptimizationFlow-based ModelTabular

🎯 What it does: A class of interpretable probability density models called Squared Neural Family (SNEFY) is proposed, which constructs distributions by normalizing the squared 2-norm of a single hidden layer neural network with respect to a base measure.

Stabilized Neural Differential Equations for Learning Dynamics with Explicit Constraints

Alistair White (Technical University of Munich), Niklas Boers (University of Exeter)

CodeTime SeriesSequentialPhysics RelatedStochastic Differential EquationOrdinary Differential Equation

🎯 What it does: A Stabilized Neural Differential Equation (SNDE) is proposed, which enforces the solution trajectory to remain on any explicit constraint manifold by adding a penalty term based on the constrained Jacobian to the neural ODE.

Stable Diffusion is Unstable

Chengbin Du (University of Sydney), Chang Xu (University of Sydney)

CodeGenerationAdversarial AttackTransformerPrompt EngineeringDiffusion modelImageText

🎯 What it does: This paper studies the instability of Stable Diffusion under slight perturbations of text prompts and proposes an automatic attack method called ATM based on Gumbel-Softmax, which can generate perturbations similar to the original prompts but lead to generation failures.

Stable Vectorization of Multiparameter Persistent Homology using Signed Barcodes as Measures

David Loiseaux (Inria d'UniversitΓ© CΓ΄te d'Azur), Steve Oudot (Inria d'UniversitΓ© CΓ΄te d'Azur)

CodeClassificationDrug DiscoveryGraphTime Series

🎯 What it does: This paper presents a complete feature generation pipeline that treats the signature barcode of multiparameter persistent homology as a signature measure, and provides two stable vectorization methods (convolutional images and sliced Wasserstein kernels) to achieve efficient vectorization of multiparameter persistent homology.

StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners

Yonglong Tian (Google Research), Dilip Krishnan (Google Research)

CodeClassificationSegmentationGenerationRepresentation LearningTransformerDiffusion modelContrastive LearningImageText

🎯 What it does: Using synthetic images generated by the text-to-image model Stable Diffusion for visual representation learning.

Star-Shaped Denoising Diffusion Probabilistic Models

Andrey Okhotin (Higher School of Economics University), Dmitry P. Vetrov

CodeRestorationGenerationData SynthesisDiffusion modelImageText

🎯 What it does: A star-shaped denoising diffusion probabilistic model (SS-DDPM) is proposed, which can implement diffusion models on any exponential family distribution through a non-Markovian forward process that relies only on the marginal distribution.

State Sequences Prediction via Fourier Transform for Representation Learning

Mingxuan Ye (University of Science and Technology of China), Feng Wu (University of Science and Technology of China)

CodeRepresentation LearningReinforcement LearningTime SeriesSequential

🎯 What it does: An auxiliary self-supervised task is proposed that uses Fourier transform prediction in the frequency domain for infinite step state sequences to learn high-quality representations.

State-Action Similarity-Based Representations for Off-Policy Evaluation

Brahma S Pavse, Josiah P. Hanna (University of Wisconsin - Madison)

CodeReinforcement LearningTabular

🎯 What it does: A state-action similarity metric ROPE based on OPE is proposed, which learns an encoder from offline data and improves data efficiency in FQE.

StateMask: Explaining Deep Reinforcement Learning through State Mask

Zelei Cheng (Northwestern University), Xinyu Xing (Northwestern University)

CodeExplainability and InterpretabilityReinforcement LearningSequential

🎯 What it does: The StateMask explanation method is proposed, which learns a state masking network to randomize actions at non-critical moments without significantly affecting the final reward of the target DRL agent, thereby identifying and quantifying which states are most important for the final reward.

Statistical Knowledge Assessment for Large Language Models

Qingxiu Dong (Peking University), Lei Li (Carnegie Mellon University)

CodeLarge Language ModelPrompt EngineeringText

🎯 What it does: A statistical method called KaRR is proposed to evaluate the reliability of factual answers generated by large language models under different prompts;

Statistically Valid Variable Importance Assessment through Conditional Permutations

Ahmad Chamma (Inria), Bertrand Thirion (Inria)

CodeBiomedical DataMagnetic Resonance Imaging

🎯 What it does: A conditional permutation importance method (CPI) is proposed and implemented to provide statistically valid variable importance assessments in the presence of correlated features.

StEik: Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation

Huizong Yang (Georgia Institute of Technology), Anthony Yezzi (Georgia Institute of Technology)

CodeOptimizationPoint CloudMeshBenchmark

🎯 What it does: This study investigates the instability caused by the eikonal loss in neural SDF learning and proposes a new regularization method and a network structure using quadratic layers to stabilize optimization and improve detail reconstruction quality.

Stein $\Pi$-Importance Sampling

Congye Wang (Newcastle University), Chris J. Oates (Newcastle University)

CodeTabularBenchmark

🎯 What it does: The Stein Π-Importance Sampling method is proposed, which approximates the target distribution P by sampling from a Π-invariant Markov chain and post-processing through Stein discrepancy.

STEVE-1: A Generative Model for Text-to-Behavior in Minecraft

Shalev Lifshitz (University of Toronto), Sheila A. McIlraith

CodeGenerationRobotic IntelligenceTransformerPrompt EngineeringVision Language ModelVideoTextMultimodality

🎯 What it does: In the Minecraft game, STEVE-1 is constructed using a pre-trained VPT behavior model and the MineCLIP visual-text alignment model, enabling the generation of low-level control behaviors based on text or visual instructions.

Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths

Lars Holdijk (University of Oxford), Max Welling (University of Amsterdam)

CodeOptimizationReinforcement LearningSequentialPhysics RelatedStochastic Differential Equation

🎯 What it does: A path integral stochastic optimal control method (PIPS) is proposed, which does not require prior specification of collective variables (CVs), for efficiently sampling the transition paths of molecular systems between two steady states.

STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning

Weipu Zhang (Beijing Institute of Technology), Gao Huang (Tsinghua University)

CodeTransformerReinforcement LearningAuto EncoderWorld ModelSequential

🎯 What it does: A Transformer-based random world model STORM is proposed for sample-efficient reinforcement learning.

Strategic Behavior in Two-sided Matching Markets with Prediction-enhanced Preference-formation

Stefania Ionescu (University of ZΓΌrich), Aniko Hannak

CodeTabularSequential

🎯 What it does: This paper proposes a framework for embedding predictive models into two-sided matching markets and defines the concept of 'adversarial interaction attack' for the first time, which refers to the returning party interacting with the matching object in a non-optimal way in the current round to disrupt future predictions and matching results. Through economic models and simplified analysis, it is demonstrated that such attacks can yield benefits for the returning party in certain situations, and it further illustrates the inequality and overall welfare decline caused by these attacks.

Structural Pruning for Diffusion Models

Gongfan Fang (National University of Singapore), Xinchao Wang (National University of Singapore)

CodeGenerationCompressionComputational EfficiencyDiffusion modelImage

🎯 What it does: This paper proposes a structural pruning method for diffusion models called Diff-Pruning, which achieves the generation of lightweight models without retraining by retaining the core parameters of the pre-trained model and removing redundant weights.

Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects

Tianhang Cheng (University of Illinois Urbana-Champaign), Shenlong Wang (University of Illinois Urbana-Champaign)

CodePose EstimationOptimizationSimultaneous Localization and MappingImage

🎯 What it does: This paper proposes inverse rendering in a single image containing repeated objects, utilizing multi-view information of the repeated objects to recover the geometry, material, and environmental lighting of the same object.

Structure Learning with Adaptive Random Neighborhood Informed MCMC

Xitong Liang (University College London), Jim Griffin (University College London)

CodeReinforcement LearningGraphBiomedical Data

🎯 What it does: A new MCMC sampler PARNI-DAG has been developed for complete Bayesian structure learning under observed data, sampling directly in the DAG space and achieving efficient mixing.

Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data

Xin Zheng (Monash University), Shirui Pan (Griffith University)

CodeCompressionKnowledge DistillationGraph Neural NetworkGraph

🎯 What it does: This paper proposes a Structure-Free Graph Compression (SFGC) method that compresses large-scale graph data into an unstructured set of nodes while implicitly encoding the graph structure information into node attributes.

Structured Neural Networks for Density Estimation and Causal Inference

Asic Q Chen (University of Toronto), Rahul G Krishnan (University of Toronto)

CodeFlow-based ModelTabular

🎯 What it does: A structured neural network (StrNN) is proposed, which implements explicit constraints on conditional independence through weight masking and integrates it into autoregressive flows (StrAF) and continuous flows (StrCNF) for density estimation and causal inference.

Structured State Space Models for In-Context Reinforcement Learning

Chris Lu (University of Oxford), Feryal Behbahani (DeepMind)

CodeMeta LearningRecurrent Neural NetworkReinforcement LearningSequential

🎯 What it does: This paper designs and evaluates an S5 structured state space model that can reset hidden states through parallel scanning during training, aimed at addressing the intrinsic learning problem of long sequences in reinforcement learning.

Structured Voronoi Sampling

Afra Amini (ETH Zurich), Ryan Cotterell (Johns Hopkins University)

CodeGenerationOptimizationTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: This paper studies a gradient-based sampling method called Structural Voronoi Sampling (SVS) for sampling from discrete language models and achieving controlled text generation.

Subclass-Dominant Label Noise: A Counterexample for the Success of Early Stopping

Yingbin Bai (University of Sydney), Tongliang Liu (University of Sydney)

CodeClassificationConvolutional Neural NetworkImage

🎯 What it does: This paper studies a new type of label noise called Subclass Dominant Noise (SDN) and proposes a correction method called NoiseCluster for this noise.

SUBP: Soft Uniform Block Pruning for 1$\times$N Sparse CNNs Multithreading Acceleration

Jingyang Xiang (Zhejiang University), Yong Liu (Zhejiang University)

CodeObject DetectionSegmentationComputational EfficiencyConvolutional Neural NetworkImage

🎯 What it does: A zero-training soft unified block pruning (SUBP) method is proposed for constructing 1Γ—N sparse convolutional neural networks and achieving inference acceleration in a multi-threaded CPU environment.

Suggesting Variable Order for Cylindrical Algebraic Decomposition via Reinforcement Learning

Fuqi Jia (Chinese Academy of Sciences), Jian Zhang (Chinese Academy of Sciences)

CodeOptimizationGraph Neural NetworkReinforcement LearningTabular

🎯 What it does: Two variants based on reinforcement learning and graph neural networks (GRL-SVO(UP) and GRL-SVO(NUP)) have been designed and implemented to automatically suggest variable ordering in Cylindrical Algebraic Decomposition (CAD).

Supervised Pretraining Can Learn In-Context Reinforcement Learning

Jonathan Lee, Emma Brunskill (Stanford University)

CodeTransformerSupervised Fine-TuningReinforcement LearningSequential

🎯 What it does: Designed and trained a Decision-Pretrained Transformer (DPT), which achieves reinforcement learning by allowing the Transformer to predict the optimal action during multi-task pre-training given a contextual dataset.

Supply-Side Equilibria in Recommender Systems

Meena Jagadeesan (University of California Berkeley), Jacob Steinhardt (University of California Berkeley)

CodeRecommendation SystemTabular

🎯 What it does: Construct and analyze a supply-side equilibrium model in recommendation systems, exploring the impact of multi-dimensional content vectors and production costs on content specialization and market competition.

Supported Value Regularization for Offline Reinforcement Learning

Yixiu Mao (Tsinghua University), Xiangyang Ji (Tsinghua University)

CodeReinforcement Learning

🎯 What it does: A Support Value Regularization (SVR) method is proposed, which penalizes the Q-values of out-of-distribution (OOD) actions that exceed the support of the behavior dataset in offline reinforcement learning, while retaining the standard Bellman update in the in-distribution (ID) region, thus addressing the issues of overestimation and extrapolation error.

Survival Permanental Processes for Survival Analysis with Time-Varying Covariates

Hideaki Kim (NTT Corporation)

CodeOptimizationTime SeriesBiomedical Data

🎯 What it does: This paper proposes a non-parametric Bayesian survival model based on permanent processesβ€”SurvPPβ€”to analyze survival data with time-varying covariates. It transforms infinite-dimensional optimization into finite-dimensional parameterization through a representation theorem, achieving MAP inference with linear time complexity.

SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting

Shane Bergsma (Huawei Cloud), Lei Guo (Huawei Cloud)

CodeRecurrent Neural NetworkTransformerTime SeriesSequential

🎯 What it does: The SutraNets method is proposed, which splits long sequences into low-frequency subsequences and uses subsequence autoregressive generation to address the issues of error accumulation and signal path in long sequence prediction.

Swarm Reinforcement Learning for Adaptive Mesh Refinement

Niklas Freymuth (Karlsruhe Institute of Technology), Gerhard Neumann (Karlsruhe Institute of Technology)

CodeGraph Neural NetworkReinforcement LearningMesh

🎯 What it does: An adaptive grid refinement method based on adaptive swarm reinforcement learning (ASMR) is proposed, treating each grid cell as an agent and utilizing graph neural networks to learn refinement strategies without the need for error estimation during inference.

SwiFT: Swin 4D fMRI Transformer

Peter Yongho Kim (Seoul National University), Taesup Moon (Seoul National University)

CodeClassificationRepresentation LearningTransformerContrastive LearningBiomedical DataMagnetic Resonance Imaging

🎯 What it does: A novel 4D Swin Transformer model, SwiFT, has been developed for end-to-end learning of brain spatiotemporal dynamics directly from high-dimensional fMRI volumes, as well as for biological and cognitive predictions.

Switching Autoregressive Low-rank Tensor Models

Hyun Dong Lee (Stanford University), Scott Linderman

CodeVideoTime Series

🎯 What it does: The Switching Autoregressive Low-rank Tensor (SALT) model is proposed, which constrains the autoregressive tensor of ARHMM with low-rank tensor decomposition, combining the interpretability of ARHMM with the parameter efficiency of SLDS.

Switching Temporary Teachers for Semi-Supervised Semantic Segmentation

Jaemin Na (Ajou University), Wonjun Hwang (Ajou University)

CodeSegmentationDomain AdaptationImage

🎯 What it does: Proposes a Dual Teacher framework that uses dual temporary teachers to alternately train a single student model, alleviating the teacher-student coupling problem.

SyncTREE: Fast Timing Analysis for Integrated Circuit Design through a Physics-informed Tree-based Graph Neural Network

Yuting Hu (University at Buffalo), Jinjun Xiong (University at Buffalo)

CodeGraph Neural NetworkContrastive LearningGraph

🎯 What it does: A tree-structured graph neural network called SyncTREE is proposed for fast and accurate prediction of the timing (delay and slope) of integrated circuit interconnect RC trees.

Synthetic Experience Replay

Cong Lu (University of Oxford), Jack Parker-Holder (University of Oxford)

CodeData SynthesisReinforcement LearningDiffusion modelScore-based ModelImageTabular

🎯 What it does: This paper proposes a Synthetic Experience Replay (SYNTHER) method based on diffusion models for synthesizing and upsampling experience data in both offline and online reinforcement learning, aimed at enhancing sample efficiency and learning effectiveness.

Systematic Visual Reasoning through Object-Centric Relational Abstraction

Taylor Whittington Webb, Jonathan Cohen

CodeRecognitionObject DetectionTransformerImage

🎯 What it does: Combining object-centered representation with relational abstraction, the OCRA model is proposed for visual reasoning.

T2T: From Distribution Learning in Training to Gradient Search in Testing for Combinatorial Optimization

Yang Li (Shanghai Jiao Tong University), Junchi Yan (Shanghai Jiao Tong University)

CodeOptimizationGraph Neural NetworkDiffusion modelGraph

🎯 What it does: Proposed the T2T framework: during the training phase, a discrete diffusion model is used to learn the high-quality solution distribution for each instance, while in the testing phase, instance-level gradient search is performed by incorporating the target gradient into the diffusion denoising process to improve the initial solution.

Tailoring Self-Attention for Graph via Rooted Subtrees

Siyuan Huang (Shanghai Jiaotong University), Zhouhan Lin (Shanghai Jiaotong University)

CodeClassificationGraph Neural NetworkTransformerGraph

🎯 What it does: Proposes a Subtree Attention Mechanism (STA) and designs STAGNN based on it for node classification tasks.

Tanh Works Better with Asymmetry

Dongjin Kim (Korea University), Suhyun Kim (Korea Institute of Science and Technology)

CodeClassificationConvolutional Neural NetworkImage

🎯 What it does: This study explores whether placing Batch Normalization after the activation function (Swap) when using bounded activation functions can improve model performance. It finds that this approach produces asymmetric saturation and high sparsity, allowing bounded activation functions to approximate ReLU, significantly increasing accuracy.

Tanimoto Random Features for Scalable Molecular Machine Learning

Austin Tripp (University of Cambridge), JosΓ© Miguel HernΓ‘ndez-Lobato (University of Cambridge)

CodeDrug DiscoveryGraphBenchmark

🎯 What it does: Two random feature methods are proposed to approximate the Tanimoto kernel (TMM) in molecular fingerprints and its new extended kernel TDP. Theoretical upper bounds on the error are provided and evaluated on real molecular data.

TART: A plug-and-play Transformer module for task-agnostic reasoning

Kush Bhatia (Stanford University), Christopher Re

CodeClassificationTransformerLarge Language ModelSupervised Fine-TuningImageTextAudio

🎯 What it does: This study investigates the performance gap between large language models (LLMs) in context learning and task-specific fine-tuning, and proposes a general reasoning module named TART, which enhances the model's reasoning ability by combining a Transformer trained on synthetic logistic regression tasks with the embeddings of any pre-trained model.

Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models

Guillermo Ortiz-Jimenez (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne), Pascal Frossard (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne)

CodeClassificationRecognitionTransformerVision Language ModelImageMultimodality

🎯 What it does: The research improved the task arithmetic editing method of pre-trained models, enabling the model to achieve multi-task learning and task forgetting through addition and subtraction of task vectors.

Task-aware Distributed Source Coding under Dynamic Bandwidth

Po-han Li (University of Texas at Austin), Hyeji Kim (University of Texas at Austin)

CodeObject DetectionCompressionRobotic IntelligenceAuto EncoderImage

🎯 What it does: This paper proposes a task-aware distributed source coding framework called NDPCA, which can dynamically adapt to any available bandwidth with a single model in multi-sensor networks, while maintaining high performance for downstream tasks such as denoising, robotic arm grasping, and satellite target detection after compression.

Task-aware world model learning with meta weighting via bi-level optimization

Huining Yuan (Beihang University), Yue Deng (Beihang University)

CodeOptimizationMeta LearningReinforcement LearningWorld ModelSequential

🎯 What it does: A task-aware world model learning framework TEMPO based on dual-layer optimization is proposed, which uses a meta-weight network to perform task-aware weighting of training samples;

Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training

Yefan Zhou (Dartmouth), Yaoqing Yang (Nanjing University)

CodeOptimizationConvolutional Neural NetworkImage

🎯 What it does: This paper proposes and implements TempBalance, a hierarchical learning rate scheduling method based on the Heavy-Tail Self-Regularization theory, which enhances training effectiveness by dynamically adjusting the 'temperature' of each layer.

TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery

Jialin Chen (Yale University), Zhitao Ying

CodeExplainability and InterpretabilityGraph Neural NetworkGraphTime Series

🎯 What it does: This paper proposes TempME, an interpretable framework for temporal graph neural networks based on the information bottleneck, which utilizes temporal motifs to generate compact and consistent explanation subgraphs.

Temporal Causal Mediation through a Point Process: Direct and Indirect Effects of Healthcare Interventions

Γ‡ağlar HΔ±zlΔ± (Aalto University), Pekka Marttinen (Aalto University)

CodeTime SeriesBiomedical DataElectronic Health Records

🎯 What it does: A dynamic causal mediation analysis framework based on point process is proposed to separate the direct and indirect effects of medical interventions on continuous time outcomes.

Temporal Continual Learning with Prior Compensation for Human Motion Prediction

Jianwei Tang (Sun Yat-sen University), Jian-Fang Hu (Sun Yat-sen University)

CodePose EstimationRecurrent Neural NetworkGraph Neural NetworkTransformerTime SeriesSequential

🎯 What it does: A multi-stage continual learning framework called Temporal Continual Learning (TCL) has been designed and implemented, introducing a Prior Compensation Factor (PCF) to alleviate knowledge forgetting, aimed at human motion prediction.

TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials

Guillem Simeon (Universitat Pompeu Fabra), Gianni De Fabritiis (Universitat Pompeu Fabra)

CodeDrug DiscoveryGraph Neural NetworkTabularPhysics Related

🎯 What it does: A Cartesian second-order tensor-based O(3)-equivariant message passing network, TensorNet, is proposed for learning molecular potential energy, forces, and other vector/tensor properties.

Test-Time Amendment with a Coarse Classifier for Fine-Grained Classification

Kanishk Jain (International Institute of Information Technology Hyderabad), Vineet Gandhi (University of TΓΌbingen)

CodeClassificationImage

🎯 What it does: A Hierarchical Ensembles (HiE) post-correction method is proposed: fine-grained and coarse-grained classifiers are trained separately, and during inference, the fine-grained predictions are multiplied by the corresponding parent class probabilities and normalized, thereby reducing error severity and improving Top-1 accuracy.

Test-Time Distribution Normalization for Contrastively Learned Visual-language Models

Yifei Zhou (University of California), Ser-Nam Lim (University of Central Florida)

CodeClassificationRetrievalVision Language ModelContrastive LearningImageText

🎯 What it does: A technique using Distribution Mean Normalization (DN) during the inference phase is proposed and evaluated to align with the InfoNCE objective of contrastive learning models (such as CLIP) during training, improving the performance of traditional dot product similarity.

Test-time Training for Matching-based Video Object Segmentation

Juliette Bertrand (Czech Technical University in Prague), Giorgos Tolias (Czech Technical University in Prague)

CodeObject DetectionSegmentationSupervised Fine-TuningVideoBenchmark

🎯 What it does: For the task of video object segmentation (VOS) based on matching, a scheme for adaptive fine-tuning of the model during inference is proposed and validated, known as Test-time Training (TTT).