unified framework
A comprehensive structure that integrates various concepts, methodologies, or models into a single cohesive system. In AI, a unified framework can help resolve issues of interoperability among different approaches.
- A Principled Path to Fitted Distributional Evaluation
- A Unified Analysis of Stochastic Gradient Descent with Arbitrary Data Permutations and Beyond
- A Unified Framework for Variable Selection in Model-Based Clustering with Missing Not at Random
- BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model
- Fairness-aware Bayes Optimal Functional Classification
- Fast attention mechanisms: a tale of parallelism
- From Softmax to Score: Transformers Can Effectively Implement In-Context Denoising Steps
- GoRA: Gradient-driven Adaptive Low Rank Adaptation
- Gymnasium: A Standard Interface for Reinforcement Learning Environments
- HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation
- IA-GGAD: Zero-shot Generalist Graph Anomaly Detection via Invariant and Affinity Learning
- On the Sample Complexity of Differentially Private Policy Optimization
- ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
- Spatial Understanding from Videos: Structured Prompts Meet Simulation Data
- TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting
- Uni-LoRA: One Vector is All You Need
- Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning