Visual Grounding

We introduce BrainSAIL (Semantic Attribution and Image Localization), a method for linking neural selectivity with spatially distributed semantic visual concepts in natural scenes. BrainSAIL leverages recent advances in large-scale artificial neural networks, using them to provide insights into the functional topology of the brain. To overcome the challenge presented by the co-occurrence of multiple categories in natural images, BrainSAIL exploits semantically consistent, dense spatial features from pre-trained vision models, building upon their demonstrated ability to robustly predict neural activity. This method derives clean, spatially dense embeddings without requiring any additional training, and employs a novel denoising process that leverages the semantic consistency of images under random augmentations. By unifying the space of whole-image embeddings and dense visual features and then applying voxel-wise encoding models to these features, we enable the identification of specific subregions of each image which drive selectivity patterns in different areas of the higher visual cortex. This provides a powerful tool for dissecting the neural mechanisms that underlie semantic visual processing for natural images. We validate BrainSAIL on cortical regions with known category selectivity, demonstrating its ability to accurately localize and disentangle selectivity to diverse visual concepts. Next, we demonstrate BrainSAIL's ability to characterize high-level visual selectivity to scene properties and low-level visual features such as depth, luminance, and saturation, providing insights into the encoding of complex visual information. Finally, we use BrainSAIL to directly compare the feature selectivity of different brain encoding models across different regions of interest in visual cortex. Our innovative method paves the way for significant advances in mapping and decomposing high-level visual representations in the human brain.

Multimodal large language models (MLLMs) are transforming the capabilities of graphical user interface (GUI) agents, facilitating their transition from controlled simulations to complex, real-world applications across various platforms. However, the effectiveness of these agents hinges on the robustness of their grounding capability. Current GUI agents predominantly utilize text-based representations such as HTML or accessibility trees, which, despite their utility, often introduce noise, incompleteness, and increased computational overhead. In this paper, we advocate a human-like embodiment for GUI agents that perceive the environment entirely visually and directly perform pixel-level operations on the GUI. The key is visual grounding models that can accurately map diverse referring expressions of GUI elements to their coordinates on the GUI across different platforms. We show that a simple recipe, which includes web-based synthetic data and slight adaptation of the LLaVA architecture, is surprisingly effective for training such visual grounding models. We collect the largest dataset for GUI visual grounding so far, containing 10M GUI elements and their referring expressions over 1.3M screenshots, and use it to train UGround, a strong universal visual grounding model for GUI agents. Empirical results on six benchmarks spanning three categories (grounding, offline agent, and online agent) show that 1) UGround substantially outperforms existing visual grounding models for GUI agents, by up to 20\% absolute, and 2) agents with UGround outperform state-of-the-art agents, despite the fact that existing agents use additional text-based input while ours only uses visual perception. These results provide strong support for the feasibility and promises of GUI agents that navigate the digital world as humans do.

Enabling intelligent agents to comprehend and interact with 3D environments through natural language is crucial for advancing robotics and human-computer interaction. A fundamental task in this field is ego-centric 3D visual grounding, where agents locate target objects in real-world 3D spaces based on verbal descriptions. However, this task faces two significant challenges: (1) loss of fine-grained visual semantics due to sparse fusion of point clouds with ego-centric multi-view images, (2) limited textual semantic context due to arbitrary language descriptions. We propose DenseGrounding, a novel approach designed to address these issues by enhancing both visual and textual semantics. For visual features, we introduce the Hierarchical Scene Semantic Enhancer, which retains dense semantics by capturing fine-grained global scene features and facilitating cross-modal alignment. For text descriptions, we propose a Language Semantic Enhancer that leverage large language models to provide rich context and diverse language descriptions with additional context during model training. Extensive experiments show that DenseGrounding significantly outperforms existing methods in overall accuracy, achieving improvements of **5.81%** and **7.56%** when trained on the comprehensive full training dataset and smaller mini subset, respectively, further advancing the SOTA in ego-centric 3D visual grounding. Our method also achieves **1st place** and receives **Innovation Award** in the 2024 Autonomous Grand Challenge Multi-view 3D Visual Grounding Track, validating its effectiveness and robustness.

Language models (LMs) have become a staple of the code-writing toolbox. Their pre-training recipe has, however, remained stagnant over recent years, barring the occasional changes in data sourcing and filtering strategies. In particular, research exploring modifications to Code-LMs' pre-training objectives, geared towards improving data efficiency and better disentangling between syntax and semantics, has been noticeably sparse, especially compared with corresponding efforts in natural language LMs. In this work, we examine grounding on obfuscated code as a means of helping Code-LMs look beyond the surface-form syntax and enhance their pre-training sample efficiency. To this end, we compile ObscuraX, a dataset of approximately 55M source and obfuscated code pairs in seven languages. Subsequently, we pre-train ObscuraCoder models, ranging in size from 255M to 2.8B parameters, on a 272B-token corpus that includes ObscuraX and demonstrate that our obfuscation-based pre-training recipe leads to consistent improvements in Code-LMs' abilities compared to both vanilla autoregressive pre-training as well as existing de-obfuscation (DOBF) objectives. ObscuraCoder demonstrates sizeable gains across multiple tests of syntactic and semantic code understanding, along with improved capabilities in multilingual code completion, multilingual code commit summarization, and multi-purpose library-oriented code generation.

Large video models, pretrained on massive quantities of amount of Internet video, provide a rich source of physical knowledge about the dynamics and motions of objects and tasks. However, video models are not grounded in the embodiment of an agent, and do not describe how to actuate the world to reach the visual states depicted in a video. To tackle this problem, current methods use a separate vision-based inverse dynamic model trained on embodiment-specific data to map image states to actions. Gathering data to train such a model is often expensive and challenging, and this model is limited to visual settings similar to the ones in which data is available. In this paper, we investigate how to directly ground video models to continuous actions through self-exploration in the embodied environment -- using generated video states as visual goals for exploration. We propose a framework that uses trajectory level action generation in combination with video guidance to enable an agent to solve complex tasks without any external supervision, e.g., rewards, action labels, or segmentation masks. We validate the proposed approach on 8 tasks in Libero, 6 tasks in MetaWorld, 4 tasks in Calvin, and 12 tasks in iThor Visual Navigation. We show how our approach is on par with or even surpasses multiple behavior cloning baselines trained on expert demonstrations while without requiring any action annotations.

Conditional Neural Fields (CNFs) are increasingly being leveraged as continuous signal representations, by associating each data-sample with a latent variable that conditions a shared backbone Neural Field (NeF) to reconstruct the sample. However, existing CNF architectures face limitations when using this latent downstream in tasks requiring fine-grained geometric reasoning, such as classification and segmentation. We posit that this results from lack of explicit modelling of geometric information (e.g. locality in the signal or the orientation of a feature) in the latent space of CNFs. As such, we propose Equivariant Neural Fields (ENFs), a novel CNF architecture which uses a geometry-informed cross-attention to condition the NeF on a geometric variable—a latent point cloud of features—that enables an equivariant decoding from latent to field. We show that this approach induces a steerability property by which both field and latent are grounded in geometry and amenable to transformation laws: if the field transforms, the latent representation transforms accordingly—and vice versa. Crucially, this equivariance relation ensures that the latent is capable of (1) representing geometric patterns faitfhully, allowing for geometric reasoning in latent space, (2) weight-sharing over similar local patterns, allowing for efficient learning of datasets of fields. We validate these main properties in a range of tasks including classification, segmentation, forecasting, reconstruction and generative modelling, showing clear improvement over baselines with a geometry-free latent space.

In this paper, we present a 3D visual grounding method called CityAnchor for localizing an urban object in a city-scale point cloud. Recent developments in multiview reconstruction enable us to reconstruct city-scale point clouds but how to conduct visual grounding on such a large-scale urban point cloud remains an open problem. Previous 3D visual grounding system mainly concentrates on localizing an object in an image or a small-scale point cloud, which is not accurate and efficient enough to scale up to a city-scale point cloud. We address this problem with a multi-modality LLM which consists of two stages, a coarse localization and a fine-grained matching. Given the text descriptions, the coarse localization stage locates possible regions on a projected 2D map of the point cloud while the fine-grained matching stage accurately determines the most matched object in these possible regions. We conduct experiments on the CityRefer dataset and a new synthetic dataset annotated by us, both of which demonstrate our method can produce accurate 3D visual grounding on a city-scale 3D point cloud.

Hierarchical classification predicts labels across multiple levels of a taxonomy, e.g., from coarse-level \textit{Bird} to mid-level \textit{Hummingbird} to fine-level \textit{Green hermit}, allowing flexible recognition under varying visual conditions. It is commonly framed as multiple single-level tasks, but each level may rely on different visual cues. Distinguishing \textit{Bird} from \textit{Plant} relies on {\it global features} like {\it feathers} or {\it leaves}, while separating \textit{Anna's hummingbird} from \textit{Green hermit} requires {\it local details} such as {\it head coloration}. Prior methods improve accuracy using external semantic supervision, but such statistical learning criteria fail to ensure consistent visual grounding at test time, resulting in incorrect hierarchical classification. We propose, for the first time, to enforce \textit{internal visual consistency} by aligning fine-to-coarse predictions through intra-image segmentation. Our method outperforms zero-shot CLIP and state-of-the-art baselines on hierarchical classification benchmarks, achieving both higher accuracy and more consistent predictions. It also improves internal image segmentation without requiring pixel-level annotations.

Large Vision-Language Models (LVLMs) often produce responses that misalign with factual information, a phenomenon known as hallucinations. While hallucinations are well-studied, the exact causes behind them remain underexplored. In this paper, we first investigate the root causes of hallucinations in LVLMs. Our findings reveal that existing mitigation techniques primarily reduce hallucinations for visual recognition prompts—those that require simple descriptions of visual elements—but fail for cognitive prompts that demand deliberate reasoning. We identify the core issue as a lack of true visual perception in LVLMs: although they can accurately recognize visual elements, they struggle to fully interpret these elements in the context of the input prompt and effectively link this recognition to their internal knowledge, which is critical for reasoning. To address this gap, we introduce Visual Description Grounded Decoding (VDGD), a simple, robust, and training-free method designed to enhance visual perception and improve reasoning capabilities in LVLMs. VDGD works by first generating a detailed description of the image and appending it as a prefix to the instruction. During response generation, tokens are sampled based on their KL divergence to the description, favoring candidates with lower divergence. Experimental results on multiple visual reasoning benchmarks and LVLMs demonstrate that VDGD consistently outperforms existing baselines 2% - 33%. Finally, we introduce VaLLu, a benchmark designed for comprehensive evaluation of the cognitive capabilities of LVLMs.