ICLR - arXivDaily 期刊&会议

2402.03445 2024-02-22 cs.CV cs.GR cs.LG

Denoising Diffusion via Image-Based Rendering

Titas Anciukevičius, Fabian Manhardt, Federico Tombari, Paul Henderson

Comments Accepted at ICLR 2024. Project page: https://anciukevicius.github.io/generative-image-based-rendering

2308.06912 2024-02-22 cs.LG cs.CL

CausalLM is not optimal for in-context learning

Nan Ding, Tomer Levinboim, Jialin Wu, Sebastian Goodman, Radu Soricut

Comments ICLR 2024 conference paper. Code available at: https://github.com/google-research/causallm_icl

2305.15399 2024-02-22 cs.CV cs.AI cs.GR

Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape

Rundi Wu, Ruoshi Liu, Carl Vondrick, Changxi Zheng

Comments Accepted to ICLR 2024. Project page: https://Sin3DM.github.io, Code: https://github.com/Sin3DM/Sin3DM

2211.07245 2024-02-22 cs.CV cs.AI cs.LG stat.ML

Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition

Jean-Rémy Conti, Stéphan Clémençon

Comments Accepted to ICLR 2024

2402.12874 2024-02-21 cs.LG

Skill or Luck? Return Decomposition via Advantage Functions

Hsiao-Ru Pan, Bernhard Schölkopf

Comments ICLR 2024

2402.12745 2024-02-21 quant-ph cs.DS math.OC

Near-Optimal Quantum Algorithm for Minimizing the Maximal Loss

Hao Wang, Chenyi Zhang, Tongyang Li

Comments 22 pages, 1 figure, To appear in The Twelfth International Conference on Learning Representations (ICLR 2024)

2402.12673 2024-02-21 cs.LG

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies

Xiangyu Liu, Chenghao Deng, Yanchao Sun, Yongyuan Liang, Furong Huang

Comments International Conference on Learning Representations (ICLR) 2024, spotlight

2402.12598 2024-02-21 cs.LG cs.AI

Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations

Giovanni De Felice, Andrea Cini, Daniele Zambon, Vladimir V. Gusev, Cesare Alippi

Comments Accepted at ICLR 2024

2402.12418 2024-02-21 cs.LG cs.AI cs.NE

Beyond Uniform Scaling: Exploring Depth Heterogeneity in Neural Architectures

Akash Guna R. T, Arnav Chavan, Deepak Gupta

Comments Accepted At ICLR 2024 (Tiny Paper Track)

2310.08587 2024-02-21 cs.CV

Pseudo-Generalized Dynamic View Synthesis from a Video

Xiaoming Zhao, Alex Colburn, Fangchang Ma, Miguel Angel Bautista, Joshua M. Susskind, Alexander G. Schwing

Comments ICLR 2024; Originally titled as "Is Generalized Dynamic Novel View Synthesis from Monocular Videos Possible Today?"; Project page: https://xiaoming-zhao.github.io/projects/pgdvs

2310.08513 2024-02-21 cs.NE cs.AI q-bio.NC

How connectivity structure shapes rich and lazy learning in neural circuits

Yuhan Helena Liu, Aristide Baratin, Jonathan Cornford, Stefan Mihalas, Eric Shea-Brown, Guillaume Lajoie

Comments Published at ICLR 2024

2310.04918 2024-02-21 cs.AI

SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning

Lei You, Hei Victor Cheng

Comments Published as a conference paper at ICLR 2024

2310.03013 2024-02-21 cs.LG cs.AI

SemiReward: A General Reward Model for Semi-supervised Learning

Siyuan Li, Weiyang Jin, Zedong Wang, Fang Wu, Zicheng Liu, Cheng Tan, Stan Z. Li

Comments ICLR 2024 Camera Ready. Preprint V2 (25 pages) with the source code at https://github.com/Westlake-AI/SemiReward

2305.17342 2024-02-21 cs.LG cs.AI

Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL

Xiangyu Liu, Souradip Chakraborty, Yanchao Sun, Furong Huang

Comments International Conference on Learning Representations (ICLR) 2024

2305.11463 2024-02-21 cs.LG math.PR stat.ML

Generative Sliced MMD Flows with Riesz Kernels

Johannes Hertrich, Christian Wald, Fabian Altekrüger, Paul Hagemann

Comments Published as a conference paper at ICLR 2024

2305.10790 2024-02-21 eess.AS cs.SD

Listen, Think, and Understand

Yuan Gong, Hongyin Luo, Alexander H. Liu, Leonid Karlinsky, James Glass

Comments Accepted at ICLR 2024. Code, dataset, and models are available at https://github.com/YuanGongND/ltu. The interactive demo is at https://huggingface.co/spaces/yuangongfdu/ltu

2402.12233 2024-02-20 cs.CL

Empirical Study on Updating Key-Value Memories in Transformer Feed-forward Layers

Zihan Qiu, Zeyu Huang, Youcheng Huang, Jie Fu

Comments Accepted to Tiny Paper @ ICLR 2024. Codes available at this $\href{https://github.com/qiuzh20/Tuning-keys-v.s.-values}{this\,repo}$

2402.12181 2024-02-20 cs.LG cs.AI cs.CV

Revisiting Data Augmentation in Deep Reinforcement Learning

Jianshu Hu, Yunpeng Jiang, Paul Weng

Comments Accepted in ICLR 2024

2311.07568 2024-02-20 cs.LG

Feature emergence via margin maximization: case studies in algebraic tasks

Depen Morwani, Benjamin L. Edelman, Costin-Andrei Oncescu, Rosie Zhao, Sham Kakade

Comments Accepted as Spotlight at ICLR 2024

2309.13598 2024-02-20 cs.CV cs.LG stat.ML

On the Posterior Distribution in Denoising: Application to Uncertainty Quantification

Hila Manor, Tomer Michaeli

Comments Accepted for ICLR 2024. Code and examples are available on the project webpage in https://hilamanor.github.io/GaussianDenoisingPosterior/

2305.19306 2024-02-20 cs.NE cs.AI cs.LG

A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks

Jintang Li, Huizhe Zhang, Ruofan Wu, Zulun Zhu, Baokun Wang, Changhua Meng, Zibin Zheng, Liang Chen

Comments Accepted to ICLR 2024; Code is available at https://github.com/EdisonLeeeee/SpikeGCL

2303.05754 2024-02-20 cs.LG cs.AI cs.CV stat.ML

Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems

Hyungjin Chung, Suhyeon Lee, Jong Chul Ye

Comments ICLR 2024; 28 pages, 9 figures

2402.11984 2024-02-20 cs.NE cs.AI cs.LG

Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks

Mingqing Xiao, Qingyan Meng, Zongpeng Zhang, Di He, Zhouchen Lin

Comments Accepted by ICLR 2024

2402.11928 2024-02-20 cs.CV

Separating common from salient patterns with Contrastive Representation Learning

Robin Louiset, Edouard Duchesnay, Antoine Grigis, Pietro Gori

Comments Published at ICLR 2024

2402.11733 2024-02-20 cs.LG cs.AI cs.CV

The Effectiveness of Random Forgetting for Robust Generalization

Vijaya Raghavan T Ramkumar, Bahram Zonooz, Elahe Arani

Comments Published as a conference paper at ICLR 2024

2402.11682 2024-02-20 cs.LG cs.CV

Learning Conditional Invariances through Non-Commutativity

Abhra Chaudhuri, Serban Georgescu, Anjan Dutta

Comments International Conference on Learning Representations (ICLR) 2024

2402.11473 2024-02-20 cs.CV

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection

Jiawei Liang, Siyuan Liang, Aishan Liu, Xiaojun Jia, Junhao Kuang, Xiaochun Cao

Comments ICLR 2024 Spotlight

2402.11458 2024-02-20 cs.CV

Key Patch Proposer: Key Patches Contain Rich Information

Jing Xu, Beiwen Tian, Hao Zhao

Comments Accepted by ICLR 2024 Tiny Papers (notable)

2402.11095 2024-02-20 cs.CV

GIM: Learning Generalizable Image Matcher From Internet Videos

Xuelun Shen, Zhipeng Cai, Wei Yin, Matthias Müller, Zijun Li, Kaixuan Wang, Xiaozhi Chen, Cheng Wang

Comments Accepted to ICLR 2024 for spotlight presentation

2402.11025 2024-02-20 cs.LG stat.ML

Training Bayesian Neural Networks with Sparse Subspace Variational Inference

Junbo Li, Zichen Miao, Qiang Qiu, Ruqi Zhang

Journal ref Published at International Conference on Learning Representations (ICLR) 2024