SPI-GAN: Denoising Diffusion GANs with Straight-Path Interpolations
Comments Accepted at ICLR 2024 Practical ML for Developing Countries Workshop (PML4DC)
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
An Analysis of Human Alignment of Latent Diffusion Models
Comments Accepted at the ICLR 2024 Workshop on Representational Alignment
Causal Graph Neural Networks for Wildfire Danger Prediction
Comments Accepted by ICLR 2024 Machine Learning for Remote Sensing (ML4RS) Workshop
Online Continual Learning For Interactive Instruction Following Agents
Comments ICLR 2024 (Project page: https://bhkim94.github.io/projects/CL-ALFRED)
LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses
Comments accepted to ICLR 2024
Making RL with Preference-based Feedback Efficient via Randomization
Comments Accepted at ICLR 2024
PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction
Comments Accepted to ICLR 2024. Find the project page at https://porf.active.vision/
Scaling Laws of RoPE-based Extrapolation
Comments 26 pages, 12 figures, Accepted by ICLR 2024
Demystifying Embedding Spaces using Large Language Models
Comments Accepted to ICLR 2024
Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic
Comments ICLR 2024. Datasets and the online server details are available at https://sites.google.com/view/alice-benchmarks
CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis
Comments ICLR 2024. https://sites.google.com/view/CIFAR-10-warehouse/
Quantifying the Plausibility of Context Reliance in Neural Machine Translation
Comments ICLR 2024 Camera Ready. Code: https://github.com/gsarti/pecore. Artifacts: https://huggingface.co/collections/gsarti/pecore-iclr-2024-65edab42e28439e21b612c2e
Linear attention is (maybe) all you need (to understand transformer optimization)
Comments Published at ICLR 2024
DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models
Comments ICLR 2024
CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
Comments Accepted to ICLR 2024. Code is available at https://github.com/lifan-yuan/CRAFT
Class Incremental Learning via Likelihood Ratio Based Task Prediction
Journal ref ICLR 2024
In-Context Learning Learns Label Relationships but Is Not Conventional Learning
Comments Accepted for publication at ICLR 2024
UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science
Comments ICLR 2024, 9 pages
Threshold-Consistent Margin Loss for Open-World Deep Metric Learning
Comments Accepted to ICLR'24
VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks
Journal ref The Twelfth International Conference on Learning Representations (ICLR 2024)
Reverse Diffusion Monte Carlo
Comments 44 pages, 16 figures, ICLR 2024
Two-stage LLM Fine-tuning with Less Specialization and More Generalization
Comments ICLR 2024
Robustifying and Boosting Training-Free Neural Architecture Search
Comments Accepted by ICLR 2024. Code available at https://github.com/hzf1174/RoBoT
Imbalance-aware Presence-only Loss Function for Species Distribution Modeling
Comments Tackling Climate Change with Machine Learning at ICLR 2024
Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
Comments ICLR 2024 Spotlight; 26 pages, 9 figures, 20 tables;
Unknown Domain Inconsistency Minimization for Domain Generalization
Comments 25 pages, 7 figures, Accepted to the twelfth International Conference on Learninig Representations (ICLR 24)
Enhancing Transfer Learning with Flexible Nonparametric Posterior Sampling
Comments ICLR 2024
MEND: Meta dEmonstratioN Distillation for Efficient and Effective In-Context Learning
Comments ICLR 2024
Enhancing Joint Motion Prediction for Individuals with Limb Loss Through Model Reprogramming
Journal ref ICLR 2024 Workshop: Learning from Time Series for Health
Making Pre-trained Language Models Great on Tabular Prediction
Comments Accepted to ICLR 2024 as spotlight presentation (Notable Top 5%). OpenReview link is https://openreview.net/forum?id=anzIzGZuLi, codes will be available at https://github.com/jyansir/tp-berta
