30 citations · 72 across the 17 of their papers we have counts for
20 papers
Bottlenecked semantic compression by representation reconstruction
Xiaoya Tang, Shilong Liu, Daniel Smolyak +3
Vision Transformers incur high computational costs when processing long visual token sequences. Existing reduction methods typically rank tokens independently and discard those dee…
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed
Qize Yu, Lianrui Fan, Bowen Ping +19
Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output tokens. We view grounding as visual evidenc…
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
Shihao Wang, Shilong Liu, Yuanguo Kuang +10
Vision-language models (VLMs) commonly formulate visual grounding and detection as a coordinate-token generation problem, serializing each 2D box into multiple 1D tokens that are l…
Chain-of-Ground: Improving GUI Grounding via Iterative Reasoning and Reference Feedback
Aiden Yiliu Li, Bizhi Yu, Daoan Lei +2
GUI grounding aims to align natural language instructions with precise regions in complex user interfaces. Advanced multimodal large language models show strong ability in visual G…
SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features
Jinyuan Qu, Hongyang Li, Xingyu Chen +5
In this paper, we present SegDINO3D, a novel Transformer encoder-decoder framework for 3D instance segmentation. As 3D training data is generally not as sufficient as 2D training i…
Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models
Zhiqi Li, Guo Chen, Shilong Liu +24
Recently, promising progress has been made by open-source vision-language models (VLMs) in bringing their capabilities closer to those of proprietary frontier models. However, most…
TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video
Jinyuan Qu, Hongyang Li, Shilong Liu +3
In this paper, built upon TAPTRv2, we present TAPTRv3. TAPTRv2 is a simple yet effective DETR-like point tracking framework that works fine in regular videos but tends to fail in l…
DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
Tianhe Ren, Yihao Chen, Qing Jiang +17
In this paper, we introduce DINO-X, which is a unified object-centric vision model developed by IDEA Research with the best open-world object detection performance to date. DINO-X…
TAPTRv2: Attention-based Position Update Improves Tracking Any Point
Hongyang Li, Hao Zhang, Shilong Liu +5
In this paper, we present TAPTRv2, a Transformer-based approach built upon TAPTR for solving the Tracking Any Point (TAP) task. TAPTR borrows designs from DEtection TRansformer (DE…
Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection
Tianhe Ren, Qing Jiang, Shilong Liu +13
This paper introduces Grounding DINO 1.5, a suite of advanced open-set object detection models developed by IDEA Research, which aims to advance the "Edge" of open-set object detec…
T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy
Qing Jiang, Feng Li, Zhaoyang Zeng +3
We present T-Rex2, a highly practical model for open-set object detection. Previous open-set object detection methods relying on text prompts effectively encapsulate the abstract c…
TAPTR: Tracking Any Point with Transformers as Detection
Hongyang Li, Hao Zhang, Shilong Liu +4
In this paper, we propose a simple and strong framework for Tracking Any Point with TRansformers (TAPTR). Based on the observation that point tracking bears a great resemblance to…
LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models
Hao Zhang, Hongyang Li, Feng Li +8
With the recent significant advancements in large multi-modal models (LMMs), the importance of their grounding capability in visual chat is increasingly recognized. Despite recent…
Interfacing Foundation Models' Embeddings
Xueyan Zou, Linjie Li, Jianfeng Wang +10
Foundation models possess strong capabilities in reasoning and memorizing across modalities. To further unleash the power of foundation models, we present FIND, a generalized inter…
Visual In-Context Prompting
Feng Li, Qing Jiang, Hao Zhang +9
In-context prompting in large language models (LLMs) has become a prevalent approach to improve zero-shot capabilities, but this idea is less explored in the vision domain. Existin…
T-Rex: Counting by Visual Prompting
Qing Jiang, Feng Li, Tianhe Ren +4
We introduce T-Rex, an interactive object counting model designed to first detect and then count any objects. We formulate object counting as an open-set object detection task with…
LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents
Shilong Liu, Hao Cheng, Haotian Liu +10
LLaVA-Plus is a general-purpose multimodal assistant that expands the capabilities of large multimodal models. It maintains a skill repository of pre-trained vision and vision-lang…
InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image
Jianhui Li, Shilong Liu, Zidong Liu +5
With the success of Neural Radiance Field (NeRF) in 3D-aware portrait editing, a variety of works have achieved promising results regarding both quality and 3D consistency. However…
TOSS:High-quality Text-guided Novel View Synthesis from a Single Image
Yukai Shi, Jianan Wang, He Cao +7
In this paper, we present TOSS, which introduces text to the task of novel view synthesis (NVS) from just a single RGB image. While Zero-1-to-3 has demonstrated impressive zero-sho…
Vision-Language Intelligence: Tasks, Representation Learning, and Large Models
Feng Li, Hao Zhang, Yi-Fan Zhang +5
This paper presents a comprehensive survey of vision-language (VL) intelligence from the perspective of time. This survey is inspired by the remarkable progress in both computer vi…