competitive performance
The capability of an AI model to achieve results that are on par with or better than existing models on benchmark tasks, reflecting its effectiveness.
- Accelerating 3D Molecule Generative Models with Trajectory Diagnosis
- CHPO: Constrained Hybrid-action Policy Optimization for Reinforcement Learning
- Continuous Simplicial Neural Networks
- Differentiable Hierarchical Visual Tokenization
- Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition
- Fair Continuous Resource Allocation with Equality of Impact
- Fast Data Attribution for Text-to-Image Models
- Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
- Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators
- Fully Dynamic Algorithms for Chamfer Distance
- How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?
- How Particle System Theory Enhances Hypergraph Message Passing
- Learning conformational ensembles of proteins based on backbone geometry
- NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
- Optimal Online Change Detection via Random Fourier Features
- Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
- Pre-trained Large Language Models Learn to Predict Hidden Markov Models In-context
- Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization
- Sparse Gaussian Processes: Structured Approximations and Power-EP Revisited
- Storyboard-guided Alignment for Fine-grained Video Action Recognition
- Synthetic Series-Symbol Data Generation for Time Series Foundation Models
- Tensor Decomposition Networks for Accelerating Machine Learning Force Field Computations
- The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
- The Promise of RL for Autoregressive Image Editing
- Universal Few-shot Spatial Control for Diffusion Models