Long-form factuality in large language models
Comments NeurIPS 2024; 72 pages, 18 figures, 30 tables. Code at https://github.com/google-deepmind/long-form-factuality
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
Comments NeurIPS 2024 (Oral). The first two authors contributed equally
Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent
Comments NeurIPS camera ready
Estimating Epistemic and Aleatoric Uncertainty with a Single Model
Comments 19 pages, 11 figures. To be published in Conference on Neural Information Processing Systems (NeurIPS) 2024
CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions
Comments NeurIPS 2024
Towards Calibrated Robust Fine-Tuning of Vision-Language Models
Comments NeurIPS 2024 (a short version was presented at the NeurIPS 2023 Workshop on Distribution Shifts); Major modification of (v7): Fixing the x-axis of Figure 3 and Pearson correlation, accordingly
RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models
Comments NeurIPS 2024
Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits
Comments To appear in Proceedings of NeurIPS 24
Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning
Comments Accepted by NeurIPS 2024
Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts
Comments Published in NeurIPS 2024
Harmformer: Harmonic Networks Meet Transformers for Continuous Roto-Translation Equivariance
Comments Appears in NeurIPS 2024 Workshop on Symmetry and Geometry in Neural Representations
The N-Grammys: Accelerating Autoregressive Inference with Learning-Free Batched Speculation
Journal ref ENLSP-IV 2024 - 4th NeurIPS Efficient Natural Language and Speech Processing Workshop, Dec 2024, Vancouver, Canada
Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach
Comments In NeurIPS'24
Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis
Comments NeurIPS 2024 Accepted
Temporal-Difference Learning Using Distributed Error Signals
Comments 10 pages, to be published at NeurIPS 2024
Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data
Comments Accepted at NeurIPS 2024
Long Context RAG Performance of Large Language Models
Comments 2024 NeurIPS workshop on Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning
PACE: Pacing Operator Learning to Accurate Optical Field Simulation for Complicated Photonic Devices
Comments Accepeted by Neurips 2024, 21 pages
Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology
Comments Accepted at NeurIPS 2024 Workshop on Large Foundation Models for Educational Assessment (FM-Assess)
Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
Comments accepted by NeurIPS 2024
Enhancing Table Representations with LLM-powered Synthetic Data Generation
Comments the Thirty-Eighth Annual Conference on Neural Information Processing Systems Table Representation Workshop
Classification Done Right for Vision-Language Pre-Training
Comments NeurIPS 2024
Confidence Calibration of Classifiers with Many Classes
Comments NeurIPS 2024; code available at https://github.com/allglc/tva-calibration
Diversity Progress for Goal Selection in Discriminability-Motivated RL
Comments 11 pages including appendices, full-track paper at the Intrinsically Motivated Open-ended Learning workshop at NeurIPS 2024
DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Rendering
Comments Accepted by NeurIPS 2024
Why Go Full? Elevating Federated Learning Through Partial Network Updates
Comments 27 pages, 8 figures, accepted by NeurIPS 2024
TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Models
Comments Accepted by the Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
Comments NeurIPS 2024
Improving Context-Aware Preference Modeling for Language Models
Comments NeurIPS 2024. 10 pages (29 with references and appendix)
No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations
Comments NeurIPS 2024. Code available at https://github.com/WalterSimoncini/fungivision
