LLM2Swarm: Robot Swarms that Responsively Reason, Plan, and Collaborate through LLMs
Comments Accepted at NeurIPS 2024 Workshop on Open-World Agents. Code: https://github.com/Pold87/LLM2Swarm/
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
DreamSteerer: Enhancing Source Image Conditioned Editability using Personalized Diffusion Models
Comments Published as a conference paper at NeurIPS 2024
System 2 Reasoning Capabilities Are Nigh
Journal ref The First Workshop on System-2 Reasoning at Scale, NeurIPS 2024
A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning
Comments Accepted at NeurIPS'2024 (D&B)
Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs
Comments NeurIPS '24 Workshop on Fine-Tuning in Modern Machine Learning: Principles and Scalability
From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection
Comments This paper has been accepted for NeurIPS 2024. Code and data are available at https://github.com/ameliawong1996/From_News_to_Forecast
Real-Time Recurrent Learning using Trace Units in Reinforcement Learning
Comments Neurips 2024
The Sample-Communication Complexity Trade-off in Federated Q-Learning
Comments Accepted to NeurIPS 2024
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
Comments Accepted as an oral paper (top 5%) at the ICML 2024 Mechanistic Interpretability Workshop and to the NeurIPS 2024 Main Conference
Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control
Comments Accepted by NeurIPS 2024
DiffPhyCon: A Generative Approach to Control Complex Physical Systems
Comments NeurIPS 2024 poster. 51 pages, 19 figures
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
Comments Accepted at NeurIPS 2024 (Spotlight)
CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics
Comments Project website: https://gao-jiawei.com/Research/CooHOI/. NeurIPS 2024 Spotlight
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
Comments Accepted in NeurIPS 2024 Datasets and Benchmarks Track
Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation
Comments NeurIPS 2024. Project page: https://albert100121.github.io/Depth-Anywhere/
Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models
Comments 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
Scale Equivariant Graph Metanetworks
Comments Accepted at NeurIPS 2024. 34 pages
On the Worst Prompt Performance of Large Language Models
Comments Accepted at NeurIPS 2024
Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation
Comments Accepted at 38th Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks
Structured Learning of Compositional Sequential Interventions
Comments Camera ready version (NeurIPS 2024)
Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections
Comments Accepted by NeurIPS 2024
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
Comments NeurIPS 2024
einspace: Searching for Neural Architectures from Fundamental Operations
Comments NeurIPS 2024. Project page at https://linusericsson.github.io/einspace/
Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure
Comments Accepted to NeurIPS 2024. 76 pages. 23 figures. 90 tables
Slight Corruption in Pre-training Data Makes Better Diffusion Models
Comments NeurIPS 2024 Spotlight
Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations
Comments Accepted to NeurIPS 2024
Neural Isometries: Taming Transformations for Equivariant ML
Comments NeurIPS 2024
Adam with model exponential moving average is effective for nonconvex optimization
Comments NeurIPS 2024
$C^2M^3$: Cycle-Consistent Multi-Model Merging
Comments In Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
Accelerating Transformers with Spectrum-Preserving Token Merging
Comments Accepted at NeurIPS 2024
