model architecture
The structured design of a machine learning model, specifying the arrangement and types of layers, the connections between them, and the overall flow of data. The architecture significantly influences a model's performance and capabilities.
- BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models
- Exploring Diffusion Transformer Designs via Grafting
- Exploring Diffusion Transformer Designs via Grafting
- From Black-box to Causal-box: Towards Building More Interpretable Models
- K-DeCore: Facilitating Knowledge Transfer in Continual Structured Knowledge Reasoning via Knowledge Decoupling
- LawShift: Benchmarking Legal Judgment Prediction Under Statute Shifts
- LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
- Learning to Insert for Constructive Neural Vehicle Routing Solver
- Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
- MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness
- Many Minds, One Goal: Time Series Forecasting via Sub-task Specialization and Inter-agent Cooperation
- MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
- NormFit: A Lightweight Solution for Few-Shot Federated Learning with Non-IID Data
- PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis
- Progressive Data Dropout: An Embarrassingly Simple Approach to Train Faster
- SEMPO: Lightweight Foundation Models for Time Series Forecasting
- Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments
- Towards Generalizable 3D Human Pose Estimation via Ensembles on Flat Loss Landscapes
- Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
- UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces
- UniZyme: A Unified Protein Cleavage Site Predictor Enhanced with Enzyme Active-Site Knowledge
- When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoning