No article text was recorded for this version.
inference latency bottleneck (VLM inference latency)
Version 1 of 162 papers64 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Space-Aware Instruction Tuning: Dataset and Benchmark for Guide Dog Robots Assisting the Visually Impaired
- Blog: VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions
- Blog: Spatially Guided Training for Vision-Language-Action Model
- Blog: Socially Aware Robot Navigation through Scoring Using Vision-Language Models
- Blog: EfficientEQA: An Efficient Approach for Open Vocabulary Embodied Question Answering
- Blog: GazeXplain: Learning to Predict Natural Language Explanations of Visual Scanpaths
- Blog: VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models
- Blog: Vision Language Model for Interpretable and Fine-grained Detection of Safety Compliance in Diverse Workplaces
- Blog: Expand Your SCOPE: Semantic Cognition over Potential-Based Exploration for Embodied Visual Navigation
- Blog: Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World
- Blog: LERa: Replanning with Visual Feedback in Instruction Following
- Blog: Leveraging Vision-Language Models for Open-Vocabulary Instance Segmentation and Tracking
- Blog: Combo-Action: Training Agent For FPS Game with Auxiliary Tasks
- Blog: MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting
- Blog: TextInPlace: Indoor Visual Place Recognition in Repetitive Structures with Scene Text Spotting and Verification
- Blog: DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
- Blog: VL-TGS: Trajectory Generation and Selection Using Vision Language Models in Mapless Outdoor Environments
- Blog: SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding
- Blog: HiTeA: Hierarchical Temporal Alignment for Training-Free Long-Video Temporal Grounding
- Blog: CABTO: Context-Aware Behavior Tree Grounding for Robot Manipulation
- Blog: HAMLET: Switch Your Vision-Language-Action Model into a History-Aware Policy
- Blog: Cultivating Gaming Sense for Yourself: Making VLMs Gaming Experts
- Blog: A Hierarchical Test Platform for Vision Language Model (VLM)-Integrated Real-World Autonomous Driving
- Blog: Sketchtopia: A Dataset and Foundational Agents for Benchmarking Asynchronous Multimodal Communication with Iconic Feedback
- Blog: ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectors
- Blog: Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
- Blog: Vision-Language Models as Success Detectors
- Blog: VLM-SFD: VLM-Assisted Siamese Flow Diffusion Framework for Dual-Arm Cooperative Manipulation
- Blog: MOKA: Open-Vocabulary Robotic Manipulation through Mark-Based Visual Prompting
- Blog: VLM-Social-Nav: Socially Aware Robot Navigation Through Scoring Using Vision-Language Models
- Blog: Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits
- Blog: Navi2Gaze: Leveraging Foundation Models for Navigation and Target Gazing
- Blog: Latent Action Pretraining from Videos
- Blog: ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
- Blog: Imagine, Verify, Execute: Memory-Guided Agentic Exploration with Vision-Language Models
- Blog: Joint Navigation and Manipulation Planning with 3D Interaction Chains
- Blog: InSituTale: Enhancing Augmented Data Storytelling with Physical Objects
- Blog: AffordGrasp: In-Context Affordance Reasoning for Open-Vocabulary Task-Oriented Grasping in Clutter
- Blog: Exploring the Reliability of Foundation Model-Based Frontier Selection in Zero-Shot Object Goal Navigation
- Blog: Bird's-eye-view Informed Reasoning Driver
- Blog: 3D Visual Illusion Depth Estimation
- Blog: InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation
- Blog: Object Captioning and Retrieval with Natural Language
- Blog: Natural Language-based State Representation in Deep Reinforcement Learning
- Blog: SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
- Blog: JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse
- Blog: HSGG: Training-Free Hierarchical Scene Graph Generation with Geometry-Guided Relation Reasoning
- Blog: VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility
- Blog: SimCache: Similarity Caching for Efficient VLM-based Scene Understanding
- Blog: LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction
- Blog: ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context
- Blog: TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP
- Blog: Empowering World Models with Reflection for Embodied Video Prediction
- Blog: CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
- Blog: RoboGround: Robotic Manipulation with Grounded Vision-Language Priors
- Blog: Leveraging Vision-Language Models for Open-Vocabulary Instance Segmentation and Tracking
- Blog: NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
- Blog: Zero-shot Active Mapping via Fused 360-BEV Representations and Vision–Language Models
- Blog: WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation
- Blog: Think, Remember, Navigate: Zero-Shot Object-Goal Navigation with VLM-Powered Reasoning
Showing 60 of 62 papers.
History & citation
Current · Permanent link
- This direction split from Dual System Architectures for Real Time Robotic Control (52% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_inference_latency_bottleneck_vlm_inferen_6bbd5973,
title = {inference latency bottleneck (VLM inference latency)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/inference-latency-bottleneck-vlm-inference-latency/rdr_6bbd597327124ad391809647c8bd4519},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_inference_latency_bottleneck_vlm_inferen_6bbd5973_v1,
title = {inference latency bottleneck (VLM inference latency)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/inference-latency-bottleneck-vlm-inference-latency/rdr_6bbd597327124ad391809647c8bd4519/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}