NeuralFluid: Neural Fluidic System Design and Control with Differentiable Simulation
Comments Accepted to NeurIPS 2024; Project webpage: https://people.csail.mit.edu/liyifei/publication/neuralfluid/
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization
Comments 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
Comments Accepted by NeurIPS 2024
GRANOLA: Adaptive Normalization for Graph Neural Networks
Comments NeurIPS 2024
Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks
Comments Accepted to NeurIPS 2024
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Comments The camera-ready version of JailbreakBench v1.0 (accepted at NeurIPS 2024 Datasets and Benchmarks Track): more attack artifacts, more test-time defenses, a more accurate jailbreak judge (Llama-3-70B with a custom prompt), a larger dataset of human preferences for selecting a jailbreak judge (300 examples), an over-refusal evaluation dataset, a semantic refusal judge based on Llama-3-8B
Deep Submodular Peripteral Networks
Comments Accepted at NeurIPS 2024 as spotlight presentation
Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
Comments Accepted at NeurIPS 2024
Unveiling the Potential of Robustness in Selecting Conditional Average Treatment Effect Estimators
Comments This paper was accepted by NeurIPS-2024
SparseLLM: Towards Global Pruning for Pre-trained Language Models
Comments NeurIPS 2024
InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
Comments The paper has been accepted by NeurIPS 2024
Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
Comments 35 pages, 14 figures. NeurIPS 2024
QGFN: Controllable Greediness with Action Values
Comments Accepted by 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field
Comments 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
Graph Convolutions Enrich the Self-Attention in Transformers!
Comments Accepted to NeurIPS 2024. Jeongwhan Choi and Hyowon Wi are co-first authors with equal contributions
Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse
Comments Accepted to NeurIPS 2024
Nesterov acceleration despite very noisy gradients
Comments Accepted to NeurIPS 2024
Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
Comments Accepted to NeurIPS 2024
Bridging Geometric States via Geometric Diffusion Bridge
Comments 33 pages, 5 tables; NeurIPS 2024 Camera Ready version
Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning
Comments Accepted at NeurIPS 2024, code available at https://github.com/PR-Ryan/DEMO
Federated Black-Box Adaptation for Semantic Segmentation
Comments Accepted at NEURIPS 2024
The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domains
Comments Accepted to NeurIPS 2024
Dense Associative Memory Through the Lens of Random Features
Comments Accepted to NeurIPS 2024
Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers
Comments Accepted as NeurIPS 2024 spotlight. 33 pages, 26 figures
On Sampling Strategies for Spectral Model Sharding
Comments Accepted to NeurIPS 2024
Matchmaker: Self-Improving Large Language Model Programs for Schema Matching
Comments Accepted to NeurIPS 2024, GenAI for Health Workshop and Table Representation Learning Workshop
Benchmark Data Repositories for Better Benchmarking
Comments Accepted to NeurIPS Datasets and Benchmarks 2024
Identifying Spatio-Temporal Drivers of Extreme Events
Comments Accepted at the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
EigenVI: score-based variational inference with orthogonal function expansions
Comments 25 pages, 9 figures. Advances in Neural Information Processing Systems (NeurIPS), 2024
Unveiling Synthetic Faces: How Synthetic Datasets Can Expose Real Identities
Comments Accepted in NeurIPS 2024 Workshop on New Frontiers in Adversarial Machine Learning
