Skip to content

Latest commit

 

History

History
2614 lines (1958 loc) · 163 KB

ICLR2023-Papers-with-Code.md

File metadata and controls

2614 lines (1958 loc) · 163 KB

ICLR 2023 论文和开源项目合集

本仓库旨在收集ICLR最新研究进展，尤其是LLM方面，涉及NLP领域的各个方向，此项目长期不定时更新。

欢迎watch和fork！不过给个star⭐就更好了❤️。

知乎地址：ShuYini

微信公众号: AINLPer（每日更新，欢迎关注）

ICLR2023 Accept Paper With Code

1、DFPC: Data flow driven pruning of coupled channels without data.

2、TVSPrune - Pruning Non-discriminative filters via Total Variation separability of intermediate representations without fine tuning

3、EquiMod: An Equivariance Module to Improve Visual Instance Discrimination

4、Solving stochastic weak Minty variational inequalities without increasing batch size

5、LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning

6、Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learning

7、Task-Aware Information Routing from Common Representation Space in Lifelong Learning

8、FairGBM: Gradient Boosting with Fairness Constraints

9、Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples

10、Don’t fear the unlabelled: safe semi-supervised learning via debiasing

11、Boosting Causal Discovery via Adaptive Sample Reweighting

12、Unveiling the sampling density in non-uniform geometric graphs

13、Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study

14、Behavior Proximal Policy Optimization

15、Mole-BERT: Rethinking Pre-training Graph Neural Networks for Molecules

16、A Message Passing Perspective on Learning Dynamics of Contrastive Learning

17、Confidence-Based Feature Imputation for Graphs with Partially Known Features

18、Evolving Populations of Diverse RL Agents with MAP-Elites

19、Selective Frequency Network for Image Restoration

20、MA-BERT: Towards Matrix Arithmetic-only BERT Inference by Eliminating Complex Non-Linear Functions

21、CASR: Generating Complex Sequences with Autoregressive Self-Boost Refinement

22、UL2: Unifying Language Learning Paradigms

23、Arbitrary Virtual Try-on Network: Characteristics Representation and Trade-off between Body and Clothing

24、Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts

25、Backpropagation through Combinatorial Algorithms: Identity with Projection Works

26、Feature selection and low test error in shallow low-rotation ReLU networks

27、Mid-Vision Feedback

28、TrojText: Test-time Invisible Textual Trojan Insertion

29、Improved Training of Physics-Informed Neural Networks Using Energy-Based Priors: a Study on Electrical Impedance Tomography

30、Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing

31、FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning

32、Imitating Graph-Based Planning with Goal-Conditioned Policies

33、Computational Language Acquisition with Theory of Mind

34、What Makes Convolutional Models Great on Long Sequence Modeling?

35、Neural Systematic Binder

36、CktGNN: Circuit Graph Neural Network for Electronic Design Automation

37、Specformer: Spectral Graph Neural Networks Meet Transformers

38、Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization

39、Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought

40、Masked Distillation with Receptive Tokens

41、Understanding the Covariance Structure of Convolutional Filters

42、HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention

43、Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning

44、PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales

45、Linearly Mapping from Image to Text Space

46、Augmentation Component Analysis: Modeling Similarity via the Augmentation Overlaps

47、UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph

48、Simple Emergent Action Representations from Multi-Task Policy Training

49、Compositional Task Representations for Large Language Models

50、REPAIR: REnormalizing Permuted Activations for Interpolation Repair

51、Unsupervised Learning for Combinatorial Optimization Needs Meta Learning

52、Broken Neural Scaling Laws

53、Adaptive Optimization in the $\infty$-Width Limit

54、Avoiding spurious correlations via logit correction

55、Implicit Regularization for Group Sparsity

56、Pruning Deep Neural Networks from a Sparsity Perspective

57、Large Language Models are Human-Level Prompt Engineers

58、OPTQ: Accurate Quantization for Generative Pre-trained Transformers

59、Continual Pre-training of Language Models

60、Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions

61、Min-Max Multi-objective Bilevel Optimization with Applications in Robust Machine Learning

62、A Control-Centric Benchmark for Video Prediction

63、Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors

64、Equal Improvability: A New Fairness Notion Considering the Long-term Impact

65、Decomposed Prompting: A Modular Approach for Solving Complex Tasks

66、Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems

67、Transferable Unlearnable Examples

68、Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport

69、Information Plane Analysis for Dropout Neural Networks

70、Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement

71、Fast Sampling of Diffusion Models with Exponential Integrator

72、Empowering Graph Representation Learning with Test-Time Graph Transformation

73、Interpretable Geometric Deep Learning via Learnable Randomness Injection

74、Compositionality with Variation Reliably Emerges in Neural Networks

75、f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation

76、Progressive Mix-Up for Few-Shot Supervised Multi-Source Domain Transfer

77、FunkNN: Neural Interpolation for Functional Generation

78、Transformer-based World Models Are Happy With 100k Interactions

79、Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks

80、A VAE for Transformers with Nonparametric Variational Information Bottleneck

81、Recitation-Augmented Language Models

82、Language models are multilingual chain-of-thought reasoners

83、Reward Design with Language Models

84、Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation

85、Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules

86、Integrating Symmetry into Differentiable Planning with Steerable Convolutions

87、Hyper-Decision Transformer for Efficient Online Policy Adaptation

88、Solving Continuous Control via Q-learning

89、DensePure: Understanding Diffusion Models for Adversarial Robustness

90、Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences

91、Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealing

92、Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation

93、How gradient estimator variance and bias impact learning in neural networks

94、Planning with Sequence Models through Iterative Energy Minimization

95、Verifying the Union of Manifolds Hypothesis for Image Data

96、Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning

97、ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond

98、Composing Task Knowledge With Modular Successor Feature Approximators

99、Distributed Extra-gradient with Optimal Complexity and Communication Guarantees

100、DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics

101、Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning

102、Taking a Step Back with KCal: Multi-Class Kernel-Based Calibration for Deep Neural Networks

103、SemPPL: Predicting Pseudo-Labels for Better Contrastive Representations

104、CrAM: A Compression-Aware Minimizer

105、Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints

106、Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation

107、Logical Message Passing Networks with One-hop Inference on Atomic Formulas

108、Revisiting Robustness in Graph Machine Learning

109、Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees

110、Planning with Large Language Models for Code Generation

111、Making Better Decision by Directly Planning in Continuous Control

112、(Certified!!) Adversarial Robustness for Free!

113、SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments

114、Revisiting Populations in multi-agent Communication

115、Disentanglement of Correlated Factors via Hausdorff Factorized Support

116、$\mathcal{O}$-GNN: incorporating ring priors into molecular modeling

117、MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection

118、Latent Neural ODEs with Sparse Bayesian Multiple Shooting

119、$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference

120、Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism

121、Online Boundary-Free Continual Learning by Scheduled Data Prior

122、EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data

123、Learning What and Where: Disentangling Location and Identity Tracking Without Supervision

124、On the Trade-Off between Actionable Explanations and the Right to be Forgotten

125、Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse

126、A View From Somewhere: Human-Centric Face Representations

127、Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach

128、Imitating Human Behaviour with Diffusion Models

129、Contrastive Meta-Learning for Partially Observable Few-Shot Learning

130、Efficient Planning in a Compact Latent Action Space

131、Copy is All You Need

132、Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection

133、Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners

134、Learning Fast and Slow for Online Time Series Forecasting

135、DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training

136、Holistic Adversarially Robust Pruning

137、Defending against Adversarial Audio via Diffusion Model

138、Sampling-based inference for large linear models, with application to linearised Laplace

139、Revisit Finetuning strategy for Few-Shot Learning to Transfer the Emdeddings

140、Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling

141、CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers

142、Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning

143、Sampling-free Inference for Ab-Initio Potential Energy Surface Networks

144、Consolidator: Mergable Adapter with Group Connections for Visual Adaptation

145、FastFill: Efficient Compatible Model Update

146、Learnable Graph Convolutional Attention Networks

147、SLTUNET: A Simple Unified Model for Sign Language Translation

148、Graph-based Deterministic Policy Gradient for Repetitive Combinatorial Optimization Problems

149、Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield Energy

150、MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning

151、$\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells

152、Learning Vortex Dynamics for Fluid Inference and Prediction

153、Quality-Similar Diversity via Population Based Reinforcement Learning

154、Language Models are Realistic Tabular Data Generators

155、Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation

156、Data augmentation alone can improve adversarial training

157、Complexity-Based Prompting for Multi-step Reasoning

158、Quantized Compressed Sensing with Score-Based Generative Models

159、Visually-Augmented Language Modeling

160、When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning

161、Mind's Eye: Grounded Language Model Reasoning through Simulation

162、DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing

163、Squeeze Training for Adversarial Robustness

164、An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation

165、Long-Tailed Partial Label Learning via Dynamic Rebalancing

166、Task Ambiguity in Humans and Language Models

167、Preference Transformer: Modeling Human Preferences using Transformers for RL

168、Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks

169、More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization

170、On Compositional Uncertainty Quantification for Seq2seq Graph Parsing

171、Understanding Embodied Reference with Touch-Line Transformer

172、Scaling Forward Gradient With Local Losses

173、Label-free Concept Bottleneck Models

174、Causal Estimation for Text Data with (Apparent) Overlap Violations

175、MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations

176、GLM-130B: An Open Bilingual Pre-trained Model

177、M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation

178、3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation

179、Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small

180、Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning

181、Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning

182、Offline RL for Natural Language Generation with Implicit Language Q Learning

183、CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos

184、On the Soft-Subnetwork for Few-Shot Class Incremental Learning

185、Fairness and Accuracy under Domain Generalization

186、Graph Signal Sampling for Inductive One-Bit Matrix Completion: a Closed-form Solution

187、Automatic Chain of Thought Prompting in Large Language Models

188、Moderate Coreset: A Universal Method of Data Selection for Real-world Data-efficient Deep Learning

189、Machine Unlearning of Federated Clusters

190、Latent Variable Representation for Reinforcement Learning

191、ROCO: A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs

192、FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning

193、Diffusion Models for Causal Discovery via Topological Ordering

194、Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic

195、Guiding Safe Exploration with Weakest Preconditions

196、Parameter-Efficient Fine-Tuning Design Spaces

197、Open-Vocabulary Object Detection upon Frozen Vision and Language Models

198、Koopman Neural Operator Forecaster for Time-series with Temporal Distributional Shifts

199、Revisiting the Assumption of Latent Separability for Backdoor Defenses

200、PerFedMask: Personalized Federated Learning with Optimized Masking Vectors

201、Variational Latent Branching Model for Off-Policy Evaluation

202、BigVGAN: A Universal Neural Vocoder with Large-Scale Training

203、FedFA: Federated Feature Augmentation

204、Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?

205、Learning Hyper Label Model for Programmatic Weak Supervision

206、Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness

207、Anamnesic Neural Differential Equations with Orthogonal Polynomial Projections

208、A critical look at the evaluation of GNNs under heterophily: Are we really making progress?

209、Learning to Segment from Noisy Annotations: A Spatial Correction Approach

210、Text Summarization with Oracle Expectation

211、Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations

212、Red PANDA: Disambiguating Image Anomaly Detection by Removing Nuisance Factors

213、Is Attention All That NeRF Needs?

214、The Dark Side of AutoML: Towards Architectural Backdoor Search

215、ChordMixer: A Scalable Neural Attention Model for Sequences with Different Length

216、Boosting Adversarial Transferability using Dynamic Cues

217、MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models

218、Part-Based Models Improve Adversarial Robustness

219、Extremely Simple Activation Shaping for Out-of-Distribution Detection

220、Learning Simultaneous Navigation and Construction in Grid Worlds

221、PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs

222、Efficient Model Updates for Approximate Unlearning of Graph-Structured Data

223、LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification

224、AudioGen: Textually Guided Audio Generation

225、On the Data-Efficiency with Contrastive Image Transformation in Reinforcement Learning

226、Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs

227、Energy-based Out-of-Distribution Detection for Graph Neural Networks

228、More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity

229、Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting

230、Liquid Structural State-Space Models

231、Equivariant Hypergraph Diffusion Neural Operators

232、Prompting GPT-3 To Be Reliable

233、Mitigating Memorization of Noisy Labels via Regularization between Representations

234、Policy Expansion for Bridging Offline-to-Online Reinforcement Learning

235、DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models

236、Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs

237、Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model

238、MEDICAL IMAGE UNDERSTANDING WITH PRETRAINED VISION LANGUAGE MODELS: A COMPREHENSIVE STUDY

239、Non-parametric Outlier Synthesis

240、A Learning Based Hypothesis Test for Harmful Covariate Shift

241、Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild

242、Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection

243、TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation

244、Jointly Learning Visual and Auditory Speech Representations from Raw Data

245、CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Alignment

246、A Simple Yet Powerful Deep Active Learning With Snapshots Ensembles

247、On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning

248、ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency

249、Benchmarking Constraint Inference in Inverse Reinforcement Learning

250、Memory Gym: Partially Observable Challenges to Memory-Based Agents

251、Neural Architecture Design and Robustness: A Dataset

252、Context-enriched molecule representations improve few-shot drug discovery

253、Test-Time Adaptation via Self-Training with Nearest Neighbor Information

254、Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats

255、Unsupervised Manifold Alignment with Joint Multidimensional Scaling

256、On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning.

257、Uni-Mol: A Universal 3D Molecular Representation Learning Framework

258、KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP

259、MultiViz: Towards Visualizing and Understanding Multimodal Models

260、Hyperbolic Self-paced Learning for Self-supervised Skeleton-based Action Representations

261、New Insights for the Stability-Plasticity Dilemma in Online Continual Learning

262、StyleMorph: Disentangled 3D-Aware Image Synthesis with a 3D Morphable StyleGAN

263、Efficient Offline Policy Optimization with a Learned Model

264、Video Scene Graph Generation from Single-Frame Weak Supervision

265、Versatile Neural Processes for Learning Implicit Neural Representations

266、Better Generative Replay for Continual Federated Learning

267、Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning

268、Transformer-Patcher: One Mistake Worth One Neuron

269、Predictive Inference with Feature Conformal Prediction

270、Recon: Reducing Conflicting Gradients From the Root For Multi-Task Learning

271、CircNet: Meshing 3D Point Clouds with Circumcenter Detection

272、RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data

273、Toward Adversarial Training on Contextualized Language Representation

274、Optimal Activation Functions for the Random Features Regression Model

275、EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model

276、Improving Object-centric Learning with Query Optimization

277、Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition

278、Latent State Marginalization as a Low-cost Approach for Improving Exploration

279、PV3D: A 3D Generative Model for Portrait Video Generation

280、SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication

281、Prototypical Calibration for Few-shot Learning of Language Models

282、Hierarchical Sliced Wasserstein Distance

283、Learning Hierarchical Protein Representations via Complete 3D Graph Networks

284、ILA-DA: Improving Transferability of Intermediate Level Attack with Data Augmentation

285、Coverage-centric Coreset Selection for High Pruning Rates

286、Contrastive Alignment of Vision to Language Through Parameter-Efficient Transfer Learning

287、Out-of-distribution Representation Learning for Time Series Classification

288、 BEEF: Bi-Compatible Class-Incremental Learning via Energy-Based Expansion and Fusion

289、Schema Inference for Interpretable Image Classification

290、Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting

291、Write and Paint: Generative Vision-Language Models are Unified Modal Learners

292、Data Valuation Without Training of a Model

293、HotProtein: A Novel Framework for Protein Thermostability Prediction and Editing

294、Behavior Prior Representation learning for Offline Reinforcement Learning

295、On the Perils of Cascading Robust Classifiers

296、Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions

297、SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency

298、Stable Target Field for Reduced Variance Score Estimation in Diffusion Models

299、Sparse tree-based Initialization for Neural Networks

300、VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesis

301、How Much Space Has Been Explored? Measuring the Chemical Space Covered by Databases and Machine-Generated Molecules

302、Understanding new tasks through the lens of training data via exponential tilting

303、FedDAR: Federated Domain-Aware Representation Learning

304、SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models

305、Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective

306、Deep Generative Symbolic Regression

307、Predictor-corrector algorithms for stochastic optimization under gradual distribution shift

308、AIM: Adapting Image Models for Efficient Video Action Recognition

309、Distributionally Robust Post-hoc Classifiers under Prior Shifts

310、Unicom: Universal and Compact Representation Learning for Image Retrieval

311、GAIN: On the Generalization of Instructional Action Understanding

312、DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases

313、ManyDG: Many-domain Generalization for Healthcare Applications

314、NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis

315、AnyDA: Anytime Domain Adaptation

316、How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?

317、Improving Deep Regression with Ordinal Entropy

318、3D Segmenter: 3D Transformer based Semantic Segmentation via 2D Panoramic Distillation

319、GOOD: Exploring geometric cues for detecting objects in an open world

320、TabCaps: A Capsule Neural Network for Tabular Data Classification with BoW Routing

321、Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning

322、Clifford Neural Layers for PDE Modeling

323、SYNC: SAFETY-AWARE NEURAL CONTROL FOR STABILIZING STOCHASTIC DELAY-DIFFERENTIAL EQUATIONS

324、ImaginaryNet: Learning Object Detectors without Real Images and Annotations

325、Temperature Schedules for self-supervised contrastive methods on long-tail data

326、Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN

327、Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training

328、Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding

329、DENSE RGB SLAM WITH NEURAL IMPLICIT MAPS

330、Monocular Scene Reconstruction with 3D SDF Transformers

331、D4AM: A General Denoising Framework for Downstream Acoustic Models

332、Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning

333、CO3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving

334、Advancing Radiograph Representation Learning with Masked Record Modeling

335、Re-parameterizing Your Optimizers rather than Architectures

336、Protein Representation Learning via Knowledge Enhanced Primary Structure Reasoning

337、Masked Image Modeling with Denoising Contrast

338、GoBigger: A Scalable Platform for Cooperative-Competitive Multi-Agent Interactive Simulation

339、Masked Unsupervised Self-training for Label-free Image Classification

340、GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis

341、Molecule Generation For Target Protein Binding with Structural Motifs

342、Towards Robustness Certification Against Universal Perturbations

343、Basic Binary Convolution Unit for Binarized Image Restoration Network

344、Deep Generative Modeling on Limited Data with Regularization by Nontransferable Pre-trained Models

345、Can CNNs Be More Robust Than Transformers?

346、Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions

347、Protein Representation Learning by Geometric Structure Pretraining

348、Guiding continuous operator learning through Physics-based boundary constraints

349、NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes

350、Diffusion Probabilistic Modeling of Protein Backbones in 3D for the motif-scaffolding problem

351、Reversible Column Networks

352、Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Experts

353、On the Robustness of Safe Reinforcement Learning under Observational Perturbations

354、Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization

355、Behind the Scenes of Gradient Descent: A Trajectory Analysis via Basis Function Decomposition

356、Evaluating Long-Term Memory in 3D Mazes

357、Become a Proficient Player with Limited Data through Watching Pure Videos

358、Proactive Multi-Camera Collaboration for 3D Human Pose Estimation

359、Human MotionFormer: Transferring Human Motions with Vision Transformers

360、Understanding Zero-shot Adversarial Robustness for Large-Scale Models

361、Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval

362、Dataless Knowledge Fusion by Merging Weights of Language Models

363、Spatial Attention Kinetic Networks with E(n)-Equivariance

364、Robust Fair Clustering: A Novel Fairness Attack and Defense Framework

365、CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning

366、Graph Domain Adaptation via Theory-Grounded Spectral Regularization

367、Deep Reinforcement Learning for Cost-Effective Medical Diagnosis

368、Everybody Needs Good Neighbours: An Unsupervised Locality-based Method for Bias Mitigation

369、POPGym: Benchmarking Partially Observable Reinforcement Learning

370、Learning Locality and Isotropy in Dialogue Modeling

371、Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling

372、Combating Exacerbated Heterogeneity for Robust Models in Federated Learning

373、Approximate Vanishing Ideal Computations at Scale

374、TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis

375、NORM: Knowledge Distillation via N-to-One Representation Matching

376、Switch-NeRF: Learning Scene Decomposition with Mixture of Experts for Large-scale Neural Radiance Fields

377、Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?

378、SeaFormer: Squeeze-enhanced Axial Transformer for Mobile Semantic Segmentation

379、Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization

380、Continual Transformers: Redundancy-Free Attention for Online Inference

381、CodeT: Code Generation with Generated Tests

382、Visual Imitation Learning with Patch Rewards

383、EVC: Towards Real-Time Neural Image Compression with Mask Decay

384、StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training

385、The KFIoU Loss for Rotated Object Detection

386、BrainBERT: Self-supervised representation learning for intracranial recordings

387、Generate rather than Retrieve: Large Language Models are Strong Context Generators

388、Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models

389、Reliability of CKA as a Similarity Measure in Deep Learning

390、Deep Ranking Ensembles for Hyperparameter Optimization

391、Fair Attribute Completion on Graph with Missing Attributes

392、Robustness to corruption in pre-trained Bayesian neural networks

393、Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning

394、ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation

395、Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance

396、Denoising Masked Autoencoders Help Robust Classification

397、SCoMoE: Efficient Mixtures of Experts with Structured Communication

398、LDMIC: Learning-based Distributed Multi-view Image Coding

399、Masked Frequency Modeling for Self-Supervised Visual Pre-Training

400、Test-Time Robust Personalization for Federated Learning

401、Learning Object-Language Alignments for Open-Vocabulary Object Detection

402、Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning

403、TempCLR: Temporal Alignment Representation with Contrastive Learning

404、Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint

405、Progressively Compressed Auto-Encoder for Self-supervised Representation Learning

406、S-NeRF: Neural Radiance Fields for Street Views

407、MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization

408、Exploring Low-Rank Property in Multiple Instance Learning for Whole Slide Image Classification

409、Towards Addressing Label Skews in One-Shot Federated Learning

410、Causal Balancing for Domain Generalization

411、Towards One-shot Neural Combinatorial Solvers: Theoretical and Empirical Notes on the Cardinality-Constrained Case

412、Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning

413、DDM$^2$: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models

414、NTK-SAP: Improving neural network pruning by aligning training dynamics

415、Effective Self-supervised Pre-training on Low-compute Networks without Distillation

416、CoRTX: Contrastive Framework for Real-time Explanation

417、OTOv2: Automatic, Generic, User-Friendly

418、Can discrete information extraction prompts generalize across language models?

419、ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure

420、Interactive Portrait Harmonization

421、Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikes

422、Contextual Convolutional Networks

423、Scenario-based Question Answering with Interacting Contextual Properties

424、DamoFD: Digging into Backbone Design on Face Detection

425、Towards Smooth Video Composition

426、LPT: Long-tailed Prompt Tuning for Image Classification

427、DiffMimic: Efficient Motion Mimicking with Differentiable Physics

428、Knowledge Distillation based Degradation Estimation for Blind Super-Resolution

429、Graph Contrastive Learning for Skeleton-based Action Recognition

430、Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation

431、Spikformer: When Spiking Neural Network Meets Transformer

432、Multimodal Analogical Reasoning over Knowledge Graphs

433、MECTA: Memory-Economic Continual Test-Time Model Adaptation

434、Conditional Positional Encodings for Vision Transformers

435、ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills

436、A Graph Neural Network Approach to Automated Model Building in Cryo-EM Maps

437、One Transformer Can Understand Both 2D & 3D Molecular Data

438、Distilling Cognitive Backdoor Patterns within an Image

439、Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching

440、Mind the Gap: Offline Policy Optimization for Imperfect Rewards

441、SQA3D: Situated Question Answering in 3D Scenes

442、Learning to Compose Soft Prompts for Compositional Zero-Shot Learning

443、Topology-aware Robust Optimization for Out-of-Distribution Generalization

444、Out-of-distribution Detection with Implicit Outlier Transformation

445、Extracting Robust Models with Uncertain Examples

446、Neural Groundplans: Persistent Neural Scene Representations from a Single Image

447、On The Inadequacy of Optimizing Alignment and Uniformity in Contrastive Learning of Sentence Representations

448、GFlowNets and variational inference

449、Hierarchical Relational Learning for Few-Shot Knowledge Graph Completion

450、Function-Consistent Feature Distillation

451、The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition

452、MCAL: Minimum Cost Human-Machine Active Labeling

453、PatchDCT: Patch Refinement for High Quality Instance Segmentation

454、Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification

455、Real-Time Image Demoir$\acute{e}$ing on Mobile Devices

456、Bit-Pruning: A Sparse Multiplication-Less Dot-Product

457、DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training

458、Trainability Preserving Neural Pruning

459、TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding

460、A Unified Framework for Soft Threshold Pruning

461、Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning

462、A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification

463、BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection

464、H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection

465、Diversify and Disambiguate: Out-of-Distribution Robustness via Disagreement

466、Surgical Fine-Tuning Improves Adaptation to Distribution Shifts

467、On amortizing convex conjugates for optimal transport

468、DualAfford: Learning Collaborative Visual Affordance for Dual-gripper Manipulation

469、The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image

470、Contextual Image Masking Modeling via Synergized Contrasting without View Augmentation for Faster and Better Visual Pretraining

471、Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning

Accept notable+top+25%25

1、Few-Shot Domain Adaptation For End-to-End Communication

2、Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering

3、Guarded Policy Optimization with Imperfect Online Demonstrations

4、STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables

5、Ask Me Anything: A simple strategy for prompting language models

6、The In-Sample Softmax for Offline Reinforcement Learning

7、Guiding Energy-based Models via Contrastive Latent Variables

8、Binding Language Models in Symbolic Languages

9、gDDIM: Generalized denoising diffusion implicit models

10、Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and Efficiency

11、Contrastive Audio-Visual Masked Autoencoder

12、Optimal Transport for Offline Imitation Learning

13、Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization

14、TEMPERA: Test-Time Prompt Editing via Reinforcement Learning

15、SMART: Self-supervised Multi-task pretrAining with contRol Transformers

16、Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations

17、Using Language to Extend to Unseen Domains

18、Hebbian Deep Learning Without Feedback

19、ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations

20、Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries

21、Choreographer: Learning and Adapting Skills in Imagination

22、Learning About Progress From Experts

23、Learning Fair Graph Representations via Automated Data Augmentations

24、Self-supervised learning with rotation-invariant kernels

25、VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training

26、UNICORN: A Unified Backdoor Trigger Inversion Framework

27、Training language models to summarize narratives improves brain alignment

28、Efficient recurrent architectures through activity sparsity and sparse back-propagation through time

29、Capturing the Motion of Every Joint: 3D Human Pose and Shape Estimation with Independent Tokens

30、Learning Diffusion Bridges on Constrained Domains

31、Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

32、Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning

33、Decompositional Generation Process for Instance-Dependent Partial Label Learning

34、Building a Subspace of Policies for Scalable Continual Learning

35、Not All Tasks Are Born Equal: Understanding Zero-Shot Generalization

36、Minimum Variance Unbiased N:M Sparsity for the Neural Gradients

37、Mosaic Representation Learning for Self-supervised Visual Pre-training

38、FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation

39、PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification

40、Solving Constrained Variational Inequalities via a First-order Interior Point-based Method

41、CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks

42、Data Continuity Matters: Improving Sequence Modeling with Lipschitz Regularizer

43、CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis

44、Re-calibrating Feature Attributions for Model Interpretation

45、Adversarial Diversity in Hanabi

46、ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning

47、DocPrompting: Generating Code by Retrieving the Docs

48、A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation

49、Progress measures for grokking via mechanistic interpretability

50、PiFold: Toward effective and efficient protein inverse folding

51、Planning Goals for Exploration

52、MeshDiffusion: Score-based Generative 3D Mesh Modeling

53、Post-hoc Concept Bottleneck Models

54、Learning Controllable Adaptive Simulation for Multi-resolution Physics

55、Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?

56、MEDFAIR: Benchmarking Fairness for Medical Imaging

57、Learning with Stochastic Orders

58、Powderworld: A Platform for Understanding Generalization via Rich Task Distributions

59、NTFields: Neural Time Fields for Physics-Informed Robot Motion Planning

60、A Unified Algebraic Perspective on Lipschitz Neural Networks

61、ZiCo: Zero-shot NAS via inverse Coefficient of Variation on Gradients

62、Few-shot Cross-domain Image Generation via Inference-time Latent-code Learning

63、Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!

64、Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers

65、Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent

66、Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection

67、DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion

68、D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory

69、Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning

70、On the Usefulness of Embeddings, Clusters and Strings for Text Generation Evaluation

71、VA-DepthNet: A Variational Approach to Single Image Depth Prediction

72、DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems

73、Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images

74、LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation

75、ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks

76、Learning to Grow Pretrained Models for Efficient Transformer Training

77、InCoder: A Generative Model for Code Infilling and Synthesis

78、UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks

79、Benchmarking Offline Reinforcement Learning on Real-Robot Hardware

80、CUDA: Curriculum of Data Augmentation for Long-tailed Recognition

81、A framework for benchmarking Class-out-of-distribution detection and its application to ImageNet

82、Stochastic Multi-Person 3D Motion Forecasting

83、Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting

84、Code Translation with Compiler Representations

85、Sign and Basis Invariant Networks for Spectral Graph Representation Learning

86、Omnigrok: Grokking Beyond Algorithmic Data

87、SketchKnitter: Vectorized Sketch Generation with Diffusion Models

88、Programmatically Grounded, Compositionally Generalizable Robotic Manipulation

89、Toeplitz Neural Network for Sequence Modeling

90、QuAnt: Quantum Annealing with Learnt Couplings

91、Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective

92、Diffusion Posterior Sampling for General Noisy Inverse Problems

93、A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning

94、Mass-Editing Memory in a Transformer

95、Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation

96、A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation

97、HiViT: A Simpler and More Efficient Design of Hierarchical Vision Transformer

98、A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics

99、NeRN: Learning Neural Representations for Neural Networks

100、AANG : Automating Auxiliary Learning

101、Multifactor Sequential Disentanglement via Structured Koopman Autoencoders

102、Packed Ensembles for efficient uncertainty estimation

103、Multi-domain image generation and translation with identifiability guarantees

104、Hidden Markov Transformer for Simultaneous Machine Translation

105、Continual evaluation for lifelong learning: Identifying the stability gap

106、One-Pixel Shortcut: On the Learning Preference of Deep Neural Networks

107、A Holistic View of Label Noise Transition Matrix in Deep Learning and Beyond

108、Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle

109、GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation

110、Accurate Image Restoration with Attention Retractable Transformer

111、Neural Episodic Control with State Abstraction

112、Diffusion Models Already Have A Semantic Latent Space

113、Learning Label Encodings for Deep Regression

114、Multi-skill Mobile Manipulation for Object Rearrangement

115、Simplicial Embeddings in Self-Supervised Learning and Downstream Classification

116、Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors

117、Vision Transformer Adapter for Dense Predictions

118、PLOT: Prompt Learning with Optimal Transport for Vision-Language Models

119、LAVA: Data Valuation without Pre-Specified Learning Algorithms

120、Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets

121、Exploring Active 3D Object Detection from a Generalization Perspective

122、Neuro-Symbolic Procedural Planning with Commonsense Prompting

123、CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representations

124、MPCFORMER: FAST, PERFORMANT AND PRIVATE TRANSFORMER INFERENCE WITH MPC

125、Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs

126、TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second

127、Human Motion Diffusion Model

128、Multi-lingual Evaluation of Code Generation Models

129、Visual Recognition with Deep Nearest Centroids

130、EVA3D: Compositional 3D Human Generation from 2D Image Collections

131、Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction

132、No Reason for No Supervision: Improved Generalization in Supervised Models

133、ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation

134、Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning

135、An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

136、IS SYNTHETIC DATA FROM GENERATIVE MODELS READY FOR IMAGE RECOGNITION?

137、MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

138、Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling

Accept notable+top+5%25

1、Encoding Recurrence into Transformers

2、Scaling Up Probabilistic Circuits by Latent Variable Distillation

3、WikiWhy: Answering and Explaining Cause-and-Effect Questions

4、The Role of Coverage in Online Reinforcement Learning

5、​​What learning algorithm is in-context learning? Investigations with linear models

6、Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning

7、Dichotomy of Control: Separating What You Can Control from What You Cannot

8、Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection

9、DreamFusion: Text-to-3D using 2D Diffusion

10、Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching

11、Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach

12、ReAct: Synergizing Reasoning and Acting in Language Models

13、Do We Really Need Complicated Model Architectures For Temporal Networks?

14、Efficient Conditionally Invariant Representation Learning

15、Learning on Large-scale Text-attributed Graphs via Variational Inference

16、Extreme Q-Learning: MaxEnt RL without Entropy

17、Efficient Attention via Control Variates

18、Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics

19、SimPer: Simple Self-Supervised Learning of Periodic Targets

20、Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness

21、REVISITING PRUNING AT INITIALIZATION THROUGH THE LENS OF RAMANUJAN GRAPH

22、Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement

23、A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification

24、Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction

25、Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation

26、MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting

27、From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data

28、The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation

29、Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

30、Transformers are Sample-Efficient World Models

31、Tailoring Language Generation Models under Total Variation Distance

32、View Synthesis with Sculpted Neural Points

33、Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting

34、Betty: An Automatic Differentiation Library for Multilevel Optimization

35、Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization

36、Win: Weight-Decay-Integrated Nesterov Acceleration for Adaptive Gradient Algorithms

37、Towards Stable Test-time Adaptation in Dynamic Wild World

38、MocoSFL: enabling cross-client collaborative self-supervised learning

39、3D generation on ImageNet

40、Token Merging: Your ViT But Faster

41、Image as Set of Points