computational resources
The hardware and software resources required for running AI models, including CPU/GPU power, memory, storage, and network capabilities. Efficient utilization of these resources is critical for scaling AI applications and training large models.
- Atom of Thoughts for Markov LLM Test-Time Scaling
- DEFT: Decompositional Efficient Fine-Tuning for Text-to-Image Models
- Democratizing Clinical Risk Prediction with Cross-Cohort Cross-Modal Knowledge Transfer
- Dynamic Semantic-Aware Correlation Modeling for UAV Tracking
- Fast Data Attribution for Text-to-Image Models
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning
- HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models
- Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive Decoding
- Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
- Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving
- Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression
- Multi-Objective One-Shot Pruning for Large Language Models
- Results of the Big ANN: NeurIPS’23 competition
- SignFlow Bipartite Subgraph Network For Large-Scale Graph Link Sign Prediction
- Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families
- Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning
- Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control
- System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
- TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting
- Truthful Aggregation of LLMs with an Application to Online Advertising