Flamingo models reach new state-of-the-art few-shot results on image and video tasks by bridging frozen vision and language models with cross-attention layers trained on interleaved web-scale data.
Vlm: Task-agnostic video-language model pre-training for video understanding
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
T-MOR is a multi-modal contrastive framework that pre-trains transferable skeleton motion representations using a new 1M video-skeleton-text dataset and shows gains on action classification and temporal detection benchmarks plus few/zero-shot settings.
Privatar partitions VR avatar reconstruction via frequency-domain decomposition, keeping sensitive components local and offloading the rest with distribution-aware minimal perturbation noise, achieving 2.37x throughput with provable privacy.
Systematic tests of VLM backbones, policy architectures, and cross-embodiment data yield RoboVLMs that set new SOTA on robot manipulation benchmarks while requiring few manual designs.
Describes a modular VLA framework with semantic voxel mapping via OwlViT and VLM-based command classification and grounding for the CMU VLA Challenge.
citing papers explorer
-
Flamingo: a Visual Language Model for Few-Shot Learning
Flamingo models reach new state-of-the-art few-shot results on image and video tasks by bridging frozen vision and language models with cross-attention layers trained on interleaved web-scale data.
-
T-MOR: Learning Motion-Aware Skeleton Representations for Human Action Recognition
T-MOR is a multi-modal contrastive framework that pre-trains transferable skeleton motion representations using a new 1M video-skeleton-text dataset and shows gains on action classification and temporal detection benchmarks plus few/zero-shot settings.
-
Dual-Anchoring: Addressing State Drift in Vision-Language Navigation
Privatar partitions VR avatar reconstruction via frequency-domain decomposition, keeping sensitive components local and offloading the rest with distribution-aware minimal perturbation noise, achieving 2.37x throughput with provable privacy.
-
What Matters in Building Vision-Language-Action Models for Generalist Robots
Systematic tests of VLM backbones, policy architectures, and cross-embodiment data yield RoboVLMs that set new SOTA on robot manipulation benchmarks while requiring few manual designs.
-
A Modular Vision-Language-Action Robotics Framework for Indoor Environments
Describes a modular VLA framework with semantic voxel mapping via OwlViT and VLM-based command classification and grounding for the CMU VLA Challenge.