Skip to content

Latest commit

 

History

History
1388 lines (1034 loc) · 86.5 KB

ICLR2022-Papers-with-Code.md

File metadata and controls

1388 lines (1034 loc) · 86.5 KB
Raw

ICLR 2022 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）

ICLR2022 Accept Paper With Code

1、Learning to Downsample for Segmentation of Ultra-High Resolution Images

2、Sample and Computation Redistribution for Efficient Face Detection

3、Sound Adversarial Audio-Visual Navigation

4、Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations

5、Improving Mutual Information Estimation with Annealed and Energy-Based Bounds

6、CrossBeam: Learning to Search in Bottom-Up Program Synthesis

7、Top-label calibration and multiclass-to-binary reductions

8、MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining

9、It Takes Four to Tango: Multiagent Self Play for Automatic Curriculum Generation

10、CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing

11、Can an Image Classifier Suffice For Action Recognition?

12、NeuPL: Neural Population Learning

13、AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation

14、Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable

15、Graph Condensation for Graph Neural Networks

16、On Evaluation Metrics for Graph Generative Models

17、ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods

18、Contextualized Scene Imagination for Generative Commonsense Reasoning

19、Optimal Representations for Covariate Shift

20、Gradient Importance Learning for Incomplete Observations

21、Improving Non-Autoregressive Translation Models Without Distillation

22、Efficient Token Mixing for Transformers via Adaptive Fourier Neural Operators

23、COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

24、Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields

25、Modeling Label Space Interactions in Multi-label Classification using Box Embeddings

26、Data Efficient Language-Supervised Zero-Shot Recognition with Optimal Transport Distillation

27、FedBABU: Toward Enhanced Representation for Federated Image Classification

28、Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off

29、Fast AdvProp

30、Pix2seq: A Language Modeling Framework for Object Detection

31、NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs

32、NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training

33、Network Augmentation for Tiny Deep Learning

34、Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions

35、How Attentive are Graph Attention Networks?

36、Towards Empirical Sandwich Bounds on the Rate-Distortion Function

37、Learning to Generalize across Domains on Single Test Samples

38、Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory

39、The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks

40、HTLM: Hyper-Text Pre-Training and Prompting of Language Models

41、Discovering Latent Concepts Learned in BERT

42、Learning Transferable Reward for Query Object Localization with Policy Adaptation

43、Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap

44、Collapse by Conditioning: Training Class-conditional GANs with Limited Data

45、Graph-less Neural Networks: Teaching Old MLPs New Tricks Via Distillation

46、Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?

47、Illiterate DALL-E Learns to Compose

48、Cross-Domain Imitation Learning via Optimal Transport

49、Geometric Transformers for Protein Interface Contact Prediction

50、StyleNeRF: A Style-based 3D Aware Generator for High-resolution Image Synthesis

51、Adversarial Retriever-Ranker for Dense Text Retrieval

52、Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations

53、Boosting the Certified Robustness of L-infinity Distance Nets

54、Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients

55、Overcoming The Spectral Bias of Neural Value Approximation

56、Towards Evaluating the Robustness of Neural Networks Learned by Transduction

57、A Zest of LIME: Towards Architecture-Independent Model Distances

58、Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization

59、OBJECT DYNAMICS DISTILLATION FOR SCENE DECOMPOSITION AND REPRESENTATION

60、Relational Surrogate Loss Learning

61、Knowledge Infused Decoding

62、Continual Normalization: Rethinking Batch Normalization for Online Continual Learning

63、Towards Continual Knowledge Learning of Language Models

64、Convergent Graph Solvers

65、Defending Against Image Corruptions Through Adversarial Augmentations

66、Attacking deep networks with surrogate-based adversarial black-box methods is easy

67、Auto-scaling Vision Transformers without Training

68、Fine-grained Differentiable Physics: A Yarn-level Model for Fabrics

69、Missingness Bias in Model Debugging

70、Conditional Object-Centric Learning from Video

71、Evaluating Model-Based Planning and Planner Amortization for Continuous Control

72、Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks

73、Knowledge Removal in Sampling-based Bayesian Inference

74、Bag of Instances Aggregation Boosts Self-supervised Distillation

75、Regularized Autoencoders for Isometric Representation Learning

76、On the Pitfalls of Analyzing Individual Neurons in Language Models

77、Fast Generic Interaction Detection for Model Interpretability and Compression

78、Query Embedding on Hyper-Relational Knowledge Graphs

79、TAda! Temporally-Adaptive Convolutions for Video Understanding

80、Learning a subspace of policies for online adaptation in Reinforcement Learning

81、Attention-based Interpretability with Concept Transformers

82、Target-Side Input Augmentation for Sequence to Sequence Generation

83、Gradient Matching for Domain Generalization

84、UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning

85、Label-Efficient Semantic Segmentation with Diffusion Models

86、Enhancing Cross-lingual Transfer by Manifold Mixup

87、Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization

88、Exploring extreme parameter compression for pre-trained language models

89、Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks

90、Offline Reinforcement Learning with Value-based Episodic Memory

91、MonoDistill: Learning Spatial Features for Monocular 3D Object Detection

92、Open-vocabulary Object Detection via Vision and Language Knowledge Distillation

93、Graph-Relational Domain Adaptation

94、Revisit Kernel Pruning with Lottery Regulated Grouped Convolutions

95、AdaAug: Learning Class- and Instance-adaptive Data Augmentation Policies

96、PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication

97、Graph Neural Networks with Learnable Structural and Positional Representations

98、Cross-Lingual Transfer with Class-Weighted Language-Invariant Representations

99、Graph Auto-Encoder via Neighborhood Wasserstein Reconstruction

100、ComPhy: Compositional Physical Reasoning of Objects and Events from Videos

101、On Redundancy and Diversity in Cell-based Neural Architecture Search

102、No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models

103、Generalizing Few-Shot NAS with Gradient Matching

104、The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training

105、Learning Weakly-supervised Contrastive Representations

106、Conditional Contrastive Learning with Kernel

107、Granger causal inference on DAGs identifies genomic loci regulating transcription

108、GDA-AM: ON THE EFFECTIVENESS OF SOLVING MIN-IMAX OPTIMIZATION VIA ANDERSON MIXING

109、Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations

110、An Agnostic Approach to Federated Learning with Class Imbalance

111、Optimizer Amalgamation

112、LoRA: Low-Rank Adaptation of Large Language Models

113、Efficient Computation of Deep Nonlinear Infinite-Width Neural Networks that Learn Features

114、Hindsight Foresight Relabeling for Meta-Reinforcement Learning

115、Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop

116、Neural Methods for Logical Reasoning over Knowledge Graphs

117、Consistent Counterfactuals for Deep Models

118、Unified Visual Transformer Compression

119、One After Another: Learning Incremental Skills for a Changing World

120、Mention Memory: incorporating textual knowledge into Transformers through entity mention attention

121、FILM: Following Instructions in Language with Modular Methods

122、CrowdPlay: Crowdsourcing Human Demonstrations for Offline Learning

123、Model Agnostic Interpretability for Multiple Instance Learning

124、Federated Learning from Only Unlabeled Data with Class-conditional-sharing Clients

125、Object Pursuit: Building a Space of Objects via Discriminative Weight Generation

126、Fast Model Editing at Scale

127、An Autoregressive Flow Model for 3D Molecular Geometry Generation from Scratch

128、Pre-training Molecular Graph Representation with 3D Geometry

129、Taming Sparsely Activated Transformer with Stochastic Experts

130、DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools

131、An Explanation of In-context Learning as Implicit Bayesian Inference

132、Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System

133、Differentiable Scaffolding Tree for Molecule Optimization

134、Fast topological clustering with Wasserstein distance

135、Label Leakage and Protection in Two-party Split Learning

136、Autonomous Reinforcement Learning: Formalism and Benchmarking

137、Bridging Recommendation and Marketing via Recurrent Intensity Modeling

138、Controlling the Complexity and Lipschitz Constant improves Polynomial Nets

139、BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis

140、Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction

141、CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting

142、Plant 'n' Seek: Can You Find the Winning Ticket?

143、FastSHAP: Real-Time Shapley Value Estimation

144、Efficient Sharpness-aware Minimization for Improved Training of Neural Networks

145、Effective Model Sparsification by Scheduled Grow-and-Prune Methods

146、Distributionally Robust Models with Parametric Likelihood Ratios

147、Training Structured Neural Networks Through Manifold Identification and Variance Reduction

148、Gradient Information Matters in Policy Optimization by Back-propagating through Model

149、Subspace Regularizers for Few-Shot Class Incremental Learning

150、Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting

151、TAPEX: Table Pre-training via Learning a Neural SQL Executor

152、Lipschitz-constrained Unsupervised Skill Discovery

153、cosFormer: Rethinking Softmax In Attention

154、The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models

155、Learning Value Functions from Undirected State-only Experience

156、WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection

157、GradSign: Model Performance Inference with Theoretical Insights

158、Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods

159、Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning

160、Differentiable Gradient Sampling for Learning Implicit 3D Scene Reconstructions from a Single Image

161、On Robust Prefix-Tuning for Text Classification

162、Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation

163、Crystal Diffusion Variational Autoencoder for Periodic Material Generation

164、MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer

165、Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction

166、Spherical Message Passing for 3D Molecular Graphs

167、On the Learning and Learnability of Quasimetrics

168、A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning

169、Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning

170、Latent Image Animator: Learning to Animate Images via Latent Space Navigation

171、Know Thyself: Transferable Visual Control Policies Through Robot-Awareness

172、Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How

173、Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity

174、Unsupervised Disentanglement with Tensor Product Representations on the Torus

175、VOS: Learning What You Don't Know by Virtual Outlier Synthesis

176、PoNet: Pooling Network for Efficient Token Mixing in Long Sequences

177、Huber Additive Models for Non-stationary Time Series Analysis

178、Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios

179、Dynamic Token Normalization improves Vision Transformers

180、Symbolic Learning to Optimize: Towards Interpretability and Scalability

181、Multi-Task Processes

182、Environment Predictive Coding for Visual Navigation

183、Sparsity Winning Twice: Better Robust Generalization from More Efficient Training

184、Pseudo Numerical Methods for Diffusion Models on Manifolds

185、Deep AutoAugment

186、Robust Unlearnable Examples: Protecting Data Privacy Against Adversarial Learning

187、Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

188、Self-ensemble Adversarial Training for Improved Robustness

189、Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice

190、RvS: What is Essential for Offline RL via Supervised Learning?

191、A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion

192、Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL

193、Learning Versatile Neural Architectures by Propagating Network Codes

194、Do deep networks transfer invariances across classes?

195、Task-Induced Representation Learning

196、Generative Models as a Data Source for Multiview Representation Learning

197、GiraffeDet: A Heavy-Neck Paradigm for Object Detection

198、Auto-Transfer: Learning to Route Transferable Representations

199、Focus on the Common Good: Group Distributional Robustness Follows

200、Acceleration of Federated Learning with Alleviated Forgetting in Local Training

201、Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification

202、New Insights on Reducing Abrupt Representation Change in Online Continual Learning

203、Discovering Invariant Rationales for Graph Neural Networks

204、Associated Learning: an Alternative to End-to-End Backpropagation that Works on CNN, RNN, and Transformer

205、Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework

206、FP-DETR: Detection Transformer Advanced by Fully Pre-training

207、Efficient and Differentiable Conformal Prediction with General Function Classes

208、Safe Neurosymbolic Learning with Differentiable Symbolic Execution

209、Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space

210、MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts

211、Do We Need Anisotropic Graph Neural Networks?

212、Language-driven Semantic Segmentation

213、Learning Super-Features for Image Retrieval

214、Backdoor Defense via Decoupling the Training Process

215、Learning to Complete Code with Sketches

216、Accelerated Policy Learning with Parallel Differentiable Simulation

217、Image BERT Pre-training with Online Tokenizer

218、Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception

219、Reverse Engineering of Imperceptible Adversarial Image Perturbations

220、Signing the Supermask: Keep, Hide, Invert

221、DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

222、Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity

223、Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference

224、Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations

225、AS-MLP: An Axial Shifted MLP Architecture for Vision

226、Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

227、Learning Temporally Causal Latent Processes from General Temporal Data

228、QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization

229、Uncertainty Modeling for Out-of-Distribution Generalization

230、Surrogate Gap Minimization Improves Sharpness-Aware Training

231、Anytime Dense Prediction with Confidence Adaptivity

232、FedPara: Low-rank Hadamard Product for Communication-Efficient Federated Learning

233、RegionViT: Regional-to-Local Attention for Vision Transformers

234、R4D: Utilizing Reference Objects for Long-Range Distance Estimation

235、Quadtree Attention for Vision Transformers

236、Deep Attentive Variational Inference

237、ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity

238、Unsupervised Discovery of Object Radiance Fields

239、Towards Better Understanding and Better Generalization of Low-shot Classification in Histology Images with Contrastive Learning

240、Handling Distribution Shifts on Graphs: An Invariance Perspective

241、Generalized Demographic Parity for Group Fairness

242、Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data

243、OntoProtein: Protein Pretraining With Gene Ontology Embedding

244、Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

245、Fast Differentiable Matrix Square Root

246、Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph

247、CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention

248、Hot-Refresh Model Upgrades with Regression-Free Compatible Training in Image Retrieval

249、Chemical-Reaction-Aware Molecule Representation Learning

250、Entroformer: A Transformer-based Entropy Model for Learned Image Compression

251、Dual Lottery Ticket Hypothesis

252、Skill-based Meta-Reinforcement Learning

253、InfinityGAN: Towards Infinite-Pixel Image Synthesis

254、NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy

255、CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

256、Fixed Neural Network Steganography: Train the images, not the network

257、Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains

258、Learning to Schedule Learning rate with Graph Neural Networks

259、Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing

260、Transformers Can Do Bayesian Inference

261、MAML is a Noisy Contrastive Learner in Classification

262、ViDT: An Efficient and Effective Fully Transformer-based Object Detector

263、Representation-Agnostic Shape Fields

264、Learning Features with Parameter-Free Layers

265、Incremental False Negative Detection for Contrastive Learning

266、GradMax: Growing Neural Networks using Gradient Information

267、Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View

ICLR2022 Accept Spotlight With Code

1、Dynamics-Aware Comparison of Learned Reward Functions

2、RotoGrad: Gradient Homogenization in Multitask Learning

3、On Improving Adversarial Transferability of Vision Transformers

4、On the Connection between Local Attention and Dynamic Depth-wise Convolution

5、GreaseLM: Graph REASoning Enhanced Language Models

6、Adversarial Support Alignment

7、Learning meta-features for AutoML

8、MT3: Multi-Task Multitrack Music Transcription

9、SphereFace2: Binary Classification is All You Need for Deep Face Recognition

10、Boosting Randomized Smoothing with Variance Reduced Classifiers

11、Linking Emergent and Natural Languages via Corpus Transfer

12、Fairness in Representation for Multilingual NLP: Insights from Controlled Experiments on Conditional Language Modeling

13、Multi-Stage Episodic Control for Strategic Exploration in Text Games

14、Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking

15、Towards a Unified View of Parameter-Efficient Transfer Learning

16、GNN-LM: Language Modeling based on Global Contexts via GNN

17、AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning

18、Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100

19、Looking Back on Learned Experiences For Class/task Incremental Learning

20、Contrastive Fine-grained Class Clustering via Generative Adversarial Networks

21、Learning Multimodal VAEs through Mutual Supervision

22、Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers

23、ViTGAN: Training GANs with Vision Transformers

24、Revisiting Design Choices in Offline Model Based Reinforcement Learning

25、On the Importance of Firth Bias Reduction in Few-Shot Classification

26、Controlling Directions Orthogonal to a Classifier

27、Score-Based Generative Modeling with Critically-Damped Langevin Diffusion

28、Responsible Disclosure of Generative Models Using Scalable Fingerprinting

29、Possibility Before Utility: Learning And Using Hierarchical Affordances

30、How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective

31、Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics

32、RelaxLoss: Defending Membership Inference Attacks without Losing Utility

33、Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design

34、Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No Retraining

35、Compositional Training for End-to-End Deep AUC Maximization

36、DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting

37、Context-Aware Sparse Deep Coordination Graphs

38、Omni-Dimensional Dynamic Convolution

39、Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks

40、EViT: Expediting Vision Transformers via Token Reorganizations

41、Multitask Prompted Training Enables Zero-Shot Task Generalization

42、When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

43、A General Analysis of Example-Selection for Stochastic Gradient Descent

44、Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning

45、Tackling the Generative Learning Trilemma with Denoising Diffusion GANs

46、Imbedding Deep Neural Networks

47、Emergent Communication at Scale

48、Label Encoding for Regression Networks

49、Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks

ICLR2022 Accept Oral With Code

1、Neural Structured Prediction for Inductive Node Classification

2、Natural Language Descriptions of Deep Visual Features

3、Data-Efficient Graph Grammar Learning for Molecular Generation

4、Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path

5、Weighted Training for Cross-Task Learning

6、MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling

7、Extending the WILDS Benchmark for Unsupervised Adaptation

8、Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling

9、Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting

10、PiCO: Contrastive Label Disambiguation for Partial Label Learning

11、BEiT: BERT Pre-Training of Image Transformers

12、Efficiently Modeling Long Sequences with Structured State Spaces

13、GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation

14、Large Language Models Can Be Strong Differentially Private Learners

15、Open-Set Recognition: A Good Closed-Set Classifier is All You Need

16、A Fine-Grained Analysis on Distribution Shift

17、Representational Continuity for Unsupervised Continual Learning

18、F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization

19、DISCOVERING AND EXPLAINING THE REPRESENTATION BOTTLENECK OF DNNS

20、Vision-Based Manipulators Need to Also See from Their Hands

21、Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design

22、Sparse Communication via Mixed Distributions

23、Real-Time Neural Voice Camouflage

24、RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation

25、CycleMLP: A MLP-like Architecture for Dense Prediction

26、Language modeling via stochastic processes