scalability
Scalability in AI refers to the capability of a model or system to efficiently handle increasing amounts of data or a growing number of tasks without significant drops in performance. This is crucial for deploying AI solutions in real-world scenarios where data volume and complexity can grow rapidly.
- 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
- 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
- A Unified Framework for Provably Efficient Algorithms to Estimate Shapley Values
- ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
- Accelerating data-driven algorithm selection for combinatorial partitioning problems
- Angular Constraint Embedding via SpherePair Loss for Constrained Clustering
- Bidirectional Representations Augmented Autoregressive Biological Sequence Generation: Application in De Novo Peptide Sequencing
- Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification
- Causal Discovery over Clusters of Variables in Markovian Systems
- Conditional Panoramic Image Generation via Masked Autoregressive Modeling
- Constrained Posterior Sampling: Time Series Generation with Hard Constraints
- DGCBench: A Deep Graph Clustering Benchmark
- DINO-Foresight: Looking into the Future with DINO
- DSCS: Fast CPDAG-Based Verification of Collapsible Submodels in High-Dimensional Bayesian Networks
- Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models
- Deep Learning with Plausible Deniability
- Deep learning for continuous-time stochastic control with jumps
- Differentiable Decision Tree via "ReLU+Argmin" Reformulation
- DuoGPT: Training-free Dual Sparsity through Activation-aware Pruning in LLMs
- EUGens: Efficient, Unified and General Dense Layers
- EconGym: A Scalable AI Testbed with Diverse Economic Tasks
- Efficient Adaptive Federated Optimization
- Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games
- Estimating Hitting Times Locally at Scale
- Estimating cognitive biases with attention-aware inverse planning
- Exploring Tradeoffs through Mode Connectivity for Multi-Task Learning
- Fast attention mechanisms: a tale of parallelism
- Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos
- Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods
- FlashMo: Geometric Interpolants and Frequency-Aware Sparsity for Scalable Efficient Motion Generation
- GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling
- GRIP: A Graph-Based Reasoning Instruction Producer
- Generalized Top-k Mallows Model for Ranked Choices
- Generative Graph Pattern Machine
- Geometry Aware Operator Transformer as an efficient and accurate neural surrogate for PDEs on arbitrary domains
- Heterogeneous Graph Transformers for Simultaneous Mobile Multi-Robot Task Allocation and Scheduling under Temporal Constraints
- High-Performance Arithmetic Circuit Optimization via Differentiable Architecture Search
- Horizon Reduction Makes RL Scalable
- HubGT: Fast Graph Transformer with Decoupled Hierarchy Labeling
- Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning
- KAIROS: Scalable Model-Agnostic Data Valuation
- Large Language Diffusion Models
- Large Language Diffusion Models
- LayerNavigator: Finding Promising Intervention Layers for Efficient Activation Steering in Large Language Models
- Learning long range dependencies through time reversal symmetry breaking
- Learning long range dependencies through time reversal symmetry breaking
- MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures
- MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering
- MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants
- Memory Mosaics at scale
- Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression
- MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition
- Model Reconciliation via Cost-Optimal Explanations in Probabilistic Logic Programming
- Momentum Multi-Marginal Schrödinger Bridge Matching
- Multi-Agent Reinforcement Learning with Communication-Constrained Priors
- Neither Valid nor Reliable? Investigating the Use of LLMs as Judges
- NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval
- Nyström-Accelerated Primal LS-SVMs: Breaking the $O(an^3)$ Complexity Bottleneck for Scalable ODEs Learning
- Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency
- Oracle-Efficient Combinatorial Semi-Bandits
- Parameter-Free Hypergraph Neural Network for Few-Shot Node Classification
- Physics-informed machine learning with domain decomposition and global dynamics for three-dimensional intersecting flows
- Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
- Position: Biology is the Challenge Physics-Informed ML Needs to Evolve
- Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism
- Random Forest Autoencoders for Guided Representation Learning
- Reparameterized LLM Training via Orthogonal Equivalence Transformation
- Repo2Run: Automated Building Executable Environment for Code Repository at Scale
- SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning
- SORTeD Rashomon Sets of Sparse Decision Trees: Anytime Enumeration
- SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes
- SWE-bench Goes Live!
- SWE-smith: Scaling Data for Software Engineering Agents
- Scalable Evaluation and Neural Models for Compositional Generalization
- Scalable Fingerprinting of Large Language Models
- Scalable In-context Ranking with Generative Models
- Scalable Neural Network Geometric Robustness Validation via Hölder Optimisation
- Scaling Image Geo-Localization to Continent Level
- Searching Latent Program Spaces
- ShortListing Model: A Streamlined Simplex Diffusion for Discrete Variable Generation
- Show-o2: Improved Native Unified Multimodal Models
- SimSort: A Data-Driven Framework for Spike Sorting by Large-Scale Electrophysiology Simulation
- Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics
- Strassen Attention, Split VC Dimension and Compositionality in Transformers
- Subgraph Federated Learning via Spectral Methods
- Towards Automated Petrography
- Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach
- Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models
- Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties
- Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning
- Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project
- UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces
- Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time
- Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs
- VCM: Vision Concept Modeling with Adaptive Vision Token Compression via Instruction Fine-Tuning
- Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision
- Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
- What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions
- ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding
- scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration