While 3D MLLMs have achieved significant progress, they are restricted to object and scene understanding and struggle to understand 3D spatial structures at the part level. In this paper, we introduce Kestrel, representing a novel approach that empowers 3D MLLMs with part-aware understanding, enabling better interpretation and segmentation grounding of 3D objects at the part level. Despite its significance, the current landscape lacks tasks and datasets that endow and assess this capability. Therefore, we propose two novel tasks: (1) Part-Aware Point Grounding, the model is tasked with directly predicting a part-level segmentation mask based on user instructions, and (2) Part-Aware Point Grounded Captioning, the model provides a detailed caption that includes part-level descriptions and their corresponding masks. To support learning and evaluating for these tasks, we introduce 3DCoMPaT Grounded Instructions Dataset (3DCoMPaT-GRIN). 3DCoMPaT-GRIN Vanilla, comprising 789k part-aware point cloud-instruction-segmentation mask triplets, is used to evaluate MLLMs' ability of part-aware segmentation grounding. 3DCoMPaT-GRIN Grounded Caption, containing 107k part-aware point cloud-instruction-grounded caption triplets, assesses both MLLMs' part-aware language comprehension and segmentation grounding capabilities. Our introduced tasks, dataset, and Kestrel represent a preliminary effort to bridge the gap between human cognition and 3D MLLMs, i.e., the ability to perceive and engage with the environment at both global and part levels. Extensive experiments on the 3DCoMPaT-GRIN show that Kestrel can generate user-specified segmentation masks, a capability not present in any existing 3D MLLM. Kestrel thus established a benchmark for evaluating the part-aware language comprehension and segmentation grounding of 3D objects. Project page at https://feielysia.github.io/Kestrel.github.io/

Integrating multimodal knowledge into large language models (LLMs) represents a significant advancement in dialogue generation capabilities. However, the effective incorporation of such knowledge in zero-resource scenarios remains a substantial challenge due to the scarcity of diverse, high-quality dialogue datasets. To address this, we propose the Visual Implicit Knowledge Distillation Framework (VIKDF), an innovative approach aimed at enhancing LLMs for enriched dialogue generation in zero-resource contexts by leveraging implicit multimodal knowledge. VIKDF comprises two main stages: knowledge distillation, using an Implicit Query Transformer to extract and encode visual implicit knowledge from image-text pairs into knowledge vectors; and knowledge integration, employing a novel Bidirectional Variational Information Fusion technique to seamlessly integrate these distilled vectors into LLMs. This enables the LLMs to generate dialogues that are not only coherent and engaging but also exhibit a deep understanding of the context through implicit multimodal cues, effectively overcoming the limitations of zero-resource scenarios. Our extensive experimentation across two dialogue datasets shows that VIKDF outperforms existing state-of-the-art models in generating high-quality dialogues. The code will be publicly available following acceptance.

As large language models (LLMs) evolve, their integration with 3D spatial data (3D-LLMs) has seen rapid progress, offering unprecedented capabilities for understanding and interacting with physical spaces. This survey provides a comprehensive overview of the methodologies enabling LLMs to process, understand, and generate 3D data. Highlighting the unique advantages of LLMs, such as in-context learning, step-by-step reasoning, open-vocabulary capabilities, and extensive world knowledge, we underscore their potential to significantly advance spatial comprehension and interaction within embodied Artificial Intelligence (AI) systems. Our investigation spans various 3D data representations, from point clouds to Neural Radiance Fields (NeRFs). It examines their integration with LLMs for tasks such as 3D scene understanding, captioning, question-answering, and dialogue, as well as LLM-based agents for spatial reasoning, planning, and navigation. The paper also includes a brief review of other methods that integrate 3D and language. The meta-analysis presented in this paper reveals significant progress yet underscores the necessity for novel approaches to harness the full potential of 3D-LLMs. Hence, with this paper, we aim to chart a course for future research that explores and expands the capabilities of 3D-LLMs in understanding and interacting with the complex 3D world. To support this survey, we have established a project page where papers related to our topic are organized and listed: https://github.com/ActiveVisionLab/Awesome-LLM-3D.

Never having seen an object and heard its sound simultaneously, can the model still accurately localize its visual position from the input audio? In this work, we concentrate on the Audio-Visual Localization and Segmentation tasks but under the demanding zero-shot and few-shot scenarios. To achieve this goal, different from existing approaches that mostly employ the encoder-fusion-decoder paradigm to decode localization information from the fused audio-visual feature, we introduce the encoder-prompt-decoder paradigm, aiming to better fit the data scarcity and varying data distribution dilemmas with the help of abundant knowledge from pre-trained models. Specifically, we first propose to construct Semantic-aware Audio Prompt (SAP) to help the visual foundation model focus on sounding objects, meanwhile, the semantic gap between the visual and audio modalities is also encouraged to shrink. Then, we develop a Correlation Adapter (ColA) to keep minimal training efforts as well as maintain adequate knowledge of the visual foundation model. By equipping with these means, extensive experiments demonstrate that this new paradigm outperforms other fusion-based methods in both the unseen class and cross-dataset settings. We hope that our work can further promote the generalization study of Audio-Visual Localization and Segmentation in practical application scenarios.

In this paper, we study the problem of recovering the latent vertex correspondence between two correlated random graphs with vastly inhomogeneous and unknown edge probabilities between different pairs of vertices. Inspired by and extending the matching algorithm via degree profiles by Ding, Ma, Wu and Xu (2021), we obtain an efficient matching algorithm as long as the minimal average degree is at least $\Omega(\log^{2} n)$ and the minimal correlation is at least $1 - O(\log^{-2} n)$.

Existing adversarial attacks against Object Detectors (ODs) suffer from two inherent limitations. Firstly, ODs have complicated meta-structure designs, hence most advanced attacks for ODs concentrate on attacking specific detector-intrinsic structures, which makes it hard for them to work on other detectors and motivates us to design a generic attack against ODs. Secondly, most works against ODs make Adversarial Examples (AEs) by generalizing image-level attacks from classification to detection, which brings redundant computations and perturbations in semantically meaningless areas (e.g., backgrounds) and leads to an emergency for seeking controllable attacks for ODs. To this end, we propose a generic white-box attack, LGP (local perturbations with adaptively global attacks), to blind mainstream object detectors with controllable perturbations. For a detector-agnostic attack, LGP tracks high-quality proposals and optimizes three heterogeneous losses simultaneously. In this way, we can fool the crucial components of ODs with a part of their outputs without the limitations of specific structures. Regarding controllability, we establish an object-wise constraint that exploits foreground-background separation adaptively to induce the attachment of perturbations to foregrounds. Experimentally, the proposed LGP successfully attacked sixteen state-of-the-art object detectors on MS-COCO and DOTA datasets, with promising imperceptibility and transferability obtained. Codes are publicly released in https://github.com/liguopeng0923/LGP.git

We propose an efficient algorithm for matching two correlated Erd\H{o}s--R\'enyi graphs with $n$ vertices whose edges are correlated through a latent vertex correspondence. When the edge density $q= n^{- \alpha+o(1)}$ for a constant $\alpha \in [0,1)$, we show that our algorithm has polynomial running time and succeeds to recover the latent matching as long as the edge correlation is non-vanishing. This is closely related to our previous work on a polynomial-time algorithm that matches two Gaussian Wigner matrices with non-vanishing correlation, and provides the first polynomial-time random graph matching algorithm (regardless of the regime of $q$) when the edge correlation is below the square root of the Otter's constant (which is $\approx 0.338$).

Motivated by the problem of matching vertices in two correlated Erd\H{o}s-R\'enyi graphs, we study the problem of matching two correlated Gaussian Wigner matrices. We propose an iterative matching algorithm, which succeeds in polynomial time as long as the correlation between the two Gaussian matrices does not vanish. Our result is the first polynomial time algorithm that solves a graph matching type of problem when the correlation is an arbitrarily small constant.

For two correlated graphs which are independently sub-sampled from a common Erd\H{o}s-R\'enyi graph $\mathbf{G}(n, p)$, we wish to recover their \emph{latent} vertex matching from the observation of these two graphs \emph{without labels}. When $p = n^{-\alpha+o(1)}$ for $\alpha\in (0, 1]$, we establish a sharp information-theoretic threshold for whether it is possible to correctly match a positive fraction of vertices. Our result sharpens a constant factor in a recent work by Wu, Xu and Yu.

We study the problem of reconstructing a perfect matching $M^*$ hidden in a randomly weighted $n\times n$ bipartite graph. The edge set includes every node pair in $M^*$ and each of the $n(n-1)$ node pairs not in $M^*$ independently with probability $d/n$. The weight of each edge $e$ is independently drawn from the distribution $\mathcal{P}$ if $e \in M^*$ and from $\mathcal{Q}$ if $e \notin M^*$. We show that if $\sqrt{d} B(\mathcal{P},\mathcal{Q}) \le 1$, where $B(\mathcal{P},\mathcal{Q})$ stands for the Bhattacharyya coefficient, the reconstruction error (average fraction of misclassified edges) of the maximum likelihood estimator of $M^*$ converges to $0$ as $n\to \infty$. Conversely, if $\sqrt{d} B(\mathcal{P},\mathcal{Q}) \ge 1+\epsilon$ for an arbitrarily small constant $\epsilon>0$, the reconstruction error for any estimator is shown to be bounded away from $0$ under both the sparse and dense model, resolving the conjecture in [Moharrami et al. 2019, Semerjian et al. 2020]. Furthermore, in the special case of complete exponentially weighted graph with $d=n$, $\mathcal{P}=\exp(\lambda)$, and $\mathcal{Q}=\exp(1/n)$, for which the sharp threshold simplifies to $\lambda=4$, we prove that when $\lambda \le 4-\epsilon$, the optimal reconstruction error is $\exp\left( - \Theta(1/\sqrt{\epsilon}) \right)$, confirming the conjectured infinite-order phase transition in [Semerjian et al. 2020].