Neural Information Processing Systems http://nips.cc/

However, prior attempts to include equivariances in CNPs do not scale effectively beyond two input dimensions.

However, experiments in this paper show that QE systems may disagree with deductivereasoning on answers that do not require generalization or relaxation.

AI is no longer just a translator or image recognizer. Today, we engage with systems that remember our preferences, proactively manage our calendars, and even provide emotional support. They build ongoing bonds with users. They change their behavior based on our habits. They don't just wait for commands; they suggest next steps.

A critical aspect of human visual perception is the ability to parse visual scenes into individual objects and further into object parts, forming part-whole hierarchies. Such composite structures could induce a rich set of semantic concepts and relations, thus playing an important role in the interpretation and organization of visual signals as well as for the generalization of visual perception and reasoning. However, existing visual reasoning benchmarks mostly focus on objects rather than parts. Visual reasoning based on the full part-whole hierarchy is much more challenging than object-centric reasoning due to finer-grained concepts, richer geometry relations, and more complex physics. Therefore, to better serve for part-based conceptual, relational and physical reasoning, we introduce a new large-scale diagnostic visual reasoning dataset named PTR.

Objects and their relationships are critical contents for image understanding. A scene graph provides a structured description that captures these properties of an image.

However, prior attempts to include equivariances in CNPs do not scale effectively beyond two input dimensions.

Standard attention mechanisms in transformers employ static token representations that remain unchanged across all pair-wise computations in each layer. This limits their representational alignment with the potentially diverse relational dynamics of each token-pair interaction. While they excel in domains with relatively homogeneous relationships, standard attention's static relational learning struggles to capture the diverse, heterogeneous inter-channel dependencies of multivariate time series (MTS) data--where different channel-pair interactions within a single system may be governed by entirely different physical laws or temporal dynamics. To better align the attention mechanism for such domain phenomena, we propose attention with dynamic relational priming (prime attention). Unlike standard attention where each token presents an identical representation across all of its pair-wise interactions, prime attention tailors each token dynamically (or per interaction) through learnable modulations to best capture the unique relational dynamics of each token pair, optimizing each pair-wise interaction for that specific relationship. This representational plasticity of prime attention enables effective extraction of relationship-specific information in MTS while maintaining the same asymptotic computational complexity as standard attention. Our results demonstrate that prime attention consistently outperforms standard attention across benchmarks, achieving up to 6.5% improvement in forecasting accuracy. In addition, we find that prime attention achieves comparable or superior performance using up to 40% less sequence length compared to standard attention, further demonstrating its superior relational modeling capabilities. An important challenge in applying transformers to multivariate time series (MTS) stems from domain mismatch. In language modeling, token relationships are predominantly semantic in nature, enabling most critical patterns to be captured by simple weighted sums of token representations. Similarly, in computer vision, spatial relationships dominate, enabling attention mechanisms to focus on regions of interest through uniform spatial reasoning. Learning on graphs exhibits comparable homogeneity, where node relationships are fundamentally structural and connectivity-based, allowing standard attention to model interactions through meaningful topological patterns (that are sometimes separated by relationship type (Schlichtkrull et al., 2018; Hu et al., 2020; Wang et al., 2019)). By static, we mean that token representations in each layer are fixed relative to all other tokens throughout pair-wise modeling. We classify this property of standard attention mechanisms as static relational learning.

3D Visual Grounding (3DVG) involves localizing target objects in 3D point clouds based on natural language. While prior work has made strides using textual descriptions, leveraging spoken language-known as Audio-based 3D Visual Grounding-remains underexplored and challenging. Motivated by advances in automatic speech recognition (ASR) and speech representation learning, we propose Audio-3DVG, a simple yet effective framework that integrates audio and spatial information for enhanced grounding. Rather than treating speech as a monolithic input, we decompose the task into two complementary components. First, we introduce (i) Object Mention Detection, a multi-label classification task that explicitly identifies which objects are referred to in the audio, enabling more structured audio-scene reasoning. Second, we propose an (ii) Audio-Guided Attention module that models the interactions between target candidates and mentioned objects, enhancing discrimination in cluttered 3D environments. To support benchmarking, we (iii) synthesize audio descriptions for standard 3DVG datasets, including ScanRefer, Sr3D, and Nr3D. Experimental results demonstrate that Audio-3DVG not only achieves new state-of-the-art performance in audio-based grounding, but also competes with text-based methods, highlight the promise of integrating spoken language into 3D vision tasks.