DeepGaze3.5-VL treats visual scanpaths as discrete token sequences predicted autoregressively by vision-language models, achieving 2.18 bits IG on MIT1003 and outperforming prior specialized models even with matched encoders.
hub
Pix2seq: A language modeling framework for object detection
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
TAIHRI is the first task-aware VLM for close-range HRI that localizes metric-scale 3D coordinates of critical keypoints by quantizing space and performing 2D keypoint reasoning via next-token prediction.
SAM 2++ unifies video tracking across mask, box, and point granularities via task-specific prompts, a unified decoder, task-adaptive memory, and a new multi-granularity dataset, reporting state-of-the-art results.
PaLI jointly scales a 4B-parameter vision transformer with language models on a new 10B multilingual image-text dataset to reach state-of-the-art results on vision-language tasks while keeping a simple modular design.
PARCEL is a new visual tokenization architecture combining pool-anchored resampling with conditioned elastic queries to enhance performance-efficiency tradeoffs in LVLMs over prior matryoshka methods.
Training VLMs to point via text induces serial processing that eliminates binding errors and enables compositional generalization on multi-object tasks.
SceneParser introduces hierarchical scene parsing as object-part-affordance chains, a VLM trained with pseudo labels and curriculum learning, and SceneParser-Bench with 1.74M affordance annotations, showing better structure-aware results than existing MLLMs.
Moondream Segmentation achieves 80.2% cIoU on RefCOCO by autoregressively decoding paths from referring expressions and using RL to refine masks, plus releases a cleaned RefCOCO-M dataset.
Raster2Seq generates labeled polygon sequences autoregressively from floorplan images via an anchor-guided decoder, claiming state-of-the-art results on Structure3D, CubiCasa5K, Raster2Graph and generalization to WAFFLE.
Grounded SAM integrates Grounding DINO and SAM to support text-prompted open-world detection and segmentation, achieving 48.7 mean AP on SegInW zero-shot with the base detector and huge segmenter.
SeeClick improves visual GUI agents via GUI grounding pre-training on automatically curated data and introduces the ScreenSpot benchmark, with results indicating that stronger grounding boosts downstream task performance.
GPT-3.5 is turned into an autonomous-vehicle motion planner by representing driving scenes and trajectories as language tokens and applying a prompting-reasoning-finetuning pipeline, with results shown on nuScenes.
Kosmos-2 grounds text to image regions by encoding refer expressions as Markdown links to sequences of location tokens and trains on a new GrIT dataset of grounded image-text pairs.
CheXanatomy trains VLMs to generate 2D anatomical masks via next-token prediction on synthetic CXRs from CT, matching U-Net performance with better domain-shift robustness and sample efficiency.
TinyVLA achieves faster inference and higher data efficiency than OpenVLA on robotic manipulation tasks by initializing from high-speed multimodal models and adding a diffusion policy decoder, without any pre-training phase.
citing papers explorer
No citing papers match the current filters.