No article text was recorded for this version.
dynamic inference-time scaling
Version 1 of 164 papers74 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Dynamic Path-Controllable Deep Unfolding Network for Compressive Sensing
- Blog: One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers
- Blog: Dynamic Capacity Networks
- Blog: Core Context Aware Attention for Long Context Language Modeling
- Blog: SkipW: Resource Adaptable RNN with Strict Upper Computational Limit
- Blog: PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression
- Blog: Green Edge AI: A Contemporary Survey
- Blog: PointBeV: A Sparse Approach to BeV Predictions
- Blog: EBJR: Energy-Based Joint Reasoning for Adaptive Inference
- Blog: Changing Model Behavior at Test-time Using Reinforcement Learning
- Blog: I3D: Transformer architectures with input-dependent dynamic depth for speech recognition
- Blog: AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications
- Blog: CLiFT: Compressive Light-Field Tokens for Compute Efficient and Adaptive Neural Rendering
- Blog: The Right Tool for the Job: Matching Model and Instance Complexities
- Blog: DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
- Blog: Multi-Shot Pedestrian Re-Identification via Sequential Decision Making
- Blog: Glance and Focus Networks for Dynamic Visual Recognition
- Blog: Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning
- Blog: Accelerating Transducers through Adjacent Token Merging
- Blog: Scalable Video Object Segmentation With Identification Mechanism
- Blog: System-status-aware Adaptive Network for Online Streaming Video Understanding
- Blog: Efficient Reasoning with Balanced Thinking
- Blog: Dynamic Layer Gating for Speech Enhancement
- Blog: Dynamic neural networks: advantages and challenges
- Blog: Adaptivity and Modularity for Efficient Generalization Over Task Complexity
- Blog: Universally Slimmable Networks and Improved Training Techniques
- Blog: Sparse Universal Transformer
- Blog: Compute Where it Counts: Self Optimizing Language Models
- Blog: Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
- Blog: Deep Adaptive Inference Networks for Single Image Super-Resolution
- Blog: S2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search
- Blog: Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts
- Blog: LookupViT: Compressing Visual Information to a Limited Number of Tokens
- Blog: Long-Distance Gesture Recognition Using Dynamic Neural Networks
- Blog: Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding
- Blog: Whittle Index with Multiple Actions and State Constraint for Inventory Management
- Blog: Channel Gating Neural Networks
- Blog: Exploring Dynamic Transformer for Efficient Object Tracking
- Blog: COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models
- Blog: Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
- Blog: Model Slicing for Supporting Complex Analytics with Elastic Inference Cost and Resource Constraints
- Blog: Core Context Aware Transformers for Long Context Language Modeling
- Blog: Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer
- Blog: Speed up Object Detection on Gigapixel-level Images with Patch Arrangement
- Blog: FastBERT: a Self-distilling BERT with Adaptive Inference Time
- Blog: WildCat: Near-Linear Attention in Theory and Practice
- Blog: Bringing AI to edge: From deep learning's perspective
- Blog: Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules
- Blog: Robust Text Classifier on Test-Time Budgets
- Blog: Mixture of Nested Experts: Adaptive Processing of Visual Tokens
- Blog: Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition
- Blog: FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting
- Blog: Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs
- Blog: Dynamic Neural Networks: A Survey
- Blog: DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
- Blog: Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
- Blog: Fully Dynamic Inference With Deep Neural Networks
- Blog: Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
- Blog: Multi-Mode Transformer Transducer with Stochastic Future Context
- Blog: Anytime Representation Learning
Showing 60 of 64 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_dynamic_inference_time_scaling_f14fafb9,
title = {dynamic inference-time scaling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/dynamic-inference-time-scaling/rdr_f14fafb911e94caea81285f01a683936},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_dynamic_inference_time_scaling_f14fafb9_v1,
title = {dynamic inference-time scaling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/dynamic-inference-time-scaling/rdr_f14fafb911e94caea81285f01a683936/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}