Cognitive resilience: Unraveling the proficiency of image-captioning models to interpret masked visual content
Comments Accepted as tiny paper in ICLR 2024
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
LAMPER: LanguAge Model and Prompt EngineeRing for zero-shot time series classification
Comments Accepted as tiny paper in ICLR 2024
Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View
Comments Appears at ICLR 2024 (oral)
When Semantic Segmentation Meets Frequency Aliasing
Comments Accepted by ICLR 2024
Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback
Comments Published as a conference paper at ICLR 2024. The website is available at https://uni-rlhf.github.io/
Self-Supervised Contrastive Learning for Long-term Forecasting
Comments Accepted at International Conference on Learning Representations (ICLR) 2024
Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
Comments ICLR 2024 (Spotlight). Project page: https://real3dportrait.github.io
Discovering modular solutions that generalize compositionally
Comments Published as a conference paper at ICLR 2024; Code available at https://github.com/smonsays/modular-hyperteacher
I-PHYRE: Interactive Physical Reasoning
Comments 21 pages, ICLR 2024
Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
Comments ICLR 2024
CLEX: Continuous Length Extrapolation for Large Language Models
Comments ICLR 2024
MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
Journal ref ICLR 2024 (Spotlight)
Ghost on the Shell: An Expressive Representation of General 3D Shapes
Comments ICLR 2024 Oral (v3: 30 pages, 19 figures, Project Page: https://gshell3d.github.io/)
Towards Robust Multi-Modal Reasoning via Model Selection
Comments Accepted by ICLR 2024
Local Search GFlowNets
Comments ICLR 2024 (Spotlight paper), 18 pages, 17 figures
TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series
Comments 28 pages, 15 figures, The Twelfth International Conference on Learning Representations (ICLR 2024)
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
Comments ICLR 2024
InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
Comments This work was accepted at ICLR 2024
Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
Comments iclr 2024 camera-ready
Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
Comments Accepted by ICLR 2024
DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
Comments Accepted to ICLR 2024
Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting
Comments ICLR 2024
CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity
Comments Published at ICLR 2024. Project page at http://aditya.bhatts.org/CrossQ and code release at https://github.com/adityab/CrossQ
DreamFlow: High-Quality Text-to-3D Generation by Approximating Probability Flow
Comments ICLR 2024
ClimateQ&A: Bridging the gap between climate scientists and the general public
Comments Accepted as a workshop paper at "Tackling Climate Change with Machine Learning", ICLR 2024
Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
Comments Accepted by ICLR 2024
Win-Win: Training High-Resolution Vision Transformers from Two Windows
Comments ICLR 2024
Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Comments ICLR 2024
A Benchmark Study on Calibration
Comments ICLR 2024 poster
Noisy Interpolation Learning with Shallow Univariate ReLU Networks
Comments To appear at ICLR 2024. Updated version with minor changes in the presentation
