TMLR 2024
1,177 papers
Top Research Directions
Research directions most represented by TMLR 2024 papers.
Top Authors
Impactful Papers
Papers from TMLR 2024 that shaped research clusters.
Foundational
Robust Distortion-free Watermarks for Language Models
foundational
Distribution Preserving Watermarking for
Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models
foundational
Logit-Free Confidence Scoring Under Inte
AGG: Amortized Generative 3D Gaussians for Single Image to 3D
foundational
Isotropic Regularization for 3D Gaussian
Unsupervised 3D Scene Representation Learning via Movable Object Inference
foundational
Cross-Dimensional Error Propagation in 3
Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models
foundational
Semantic Entropy for Language Model Unce
Making Translators Privacy-aware on the User's Side
foundational
Feedback-Guided Adversarial Anonymizatio
On the Inherent Privacy Properties of Discrete Denoising Diffusion Models
foundational
Temporal Privacy Dynamics in Diffusion M
C3DM: Constrained-Context Conditional Diffusion Models for Imitation Learning
foundational
Iterative Visual Refinement via Dynamic
Influential
λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space
influential
Tuning Free Identity Preservation in Gen
LEA: Learning Latent Embedding Alignment Model for fMRI Decoding and Encoding
influential
Safeguarding Cognitive Liberty in Neural
Mechanistic Interpretability for AI Safety - A Review
influential
Resolving Superposition with Sparse Auto
ProFeAT: Projected Feature Adversarial Training for Self-Supervised Learning of Robust Representatio
influential
Self-Supervised Adversarial Training for
SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks
influential
Scaling Spiking Neural Networks to Large
Unified Convergence Theory of Stochastic and Variance-Reduced Cubic Newton Methods
influential
Amortized Optimization via Lazy Curvatur
λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space
influential
Tuning-Free Personalization of Text-to-I