Related papers: LASAR: Towards Spatio-temporal Reasoning with Late…

Sequential decision-making in high-dimensional continuous action spaces, particularly in stochastic environments, faces significant computational challenges. We explore this challenge in the traditional offline RL setting, where an agent…

Spatio-temporal reasoning in time series involves the explicit synthesis of temporal dynamics, spatial dependencies, and textual context. This capability is vital for high-stakes decision-making in systems such as traffic networks, power…

Reinforcement Learning (RL) faces significant challenges in adaptive healthcare interventions, such as dementia care, where data is scarce, decisions require interpretability, and underlying patient-state dynamic are complex and causal in…

Spatial sound reasoning is a fundamental human skill, enabling us to navigate and interpret our surroundings based on sound. In this paper we present BAT, which combines the spatial sound perception ability of a binaural acoustic scene…

Recent advancements in robot navigation, particularly with end-to-end learning approaches such as reinforcement learning (RL), have demonstrated strong performance. However, successful navigation still depends on two key capabilities:…

Contrastive language--audio pretraining (CLAP) has achieved remarkable success as an audio--text embedding framework, but existing approaches are limited to monaural or single-source conditions and cannot fully capture spatial information.…

Spatial reasoning is an essential problem in embodied AI research. Efforts to enhance spatial reasoning abilities through supplementary spatial data and fine-tuning have proven limited and ineffective when addressing complex embodied tasks,…

Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either…

Large Language Models (LLMs) achieve superior performance through Chain-of-Thought (CoT) reasoning, but these token-level reasoning chains are computationally expensive and inefficient. In this paper, we introduce Compressed Latent…

EEG-based emotion recognition plays an important role in developing adaptive brain-computer communication systems, yet faces two fundamental challenges in practical implementations: (1) effective integration of non-stationary…

Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While…

Large reasoning models (LRMs) generate extended solutions, yet it remains unclear whether these traces reflect substantive internal computation or merely verbosity and overthinking. Although recent hidden-state analyses suggest that…

Vision-Language-Action (VLA) models benefit from chain-of-thought (CoT) reasoning, but existing approaches incur high inference overhead and rely on discrete reasoning representations that mismatch continuous perception and control. We…

We present MetaSpatial, the first reinforcement learning (RL)-based framework designed to enhance 3D spatial reasoning in vision-language models (VLMs), enabling real-time 3D scene generation without the need for hard-coded optimizations.…

While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, most LMMs default to verbalizing perceptual content into text, a strong limitation for tasks…

Skeleton-based action recognition has made great progress recently, but many problems still remain unsolved. For example, most of the previous methods model the representations of skeleton sequences without abundant spatial structure…

Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. However, existing approaches largely rely on visual supervision and produce latent…

Chain-of-thought (CoT) prompting is a popular in-context learning (ICL) approach for large language models (LLMs), especially when tackling complex reasoning tasks. Traditional ICL approaches construct prompts using examples that contain…

Executing complex manipulation in cluttered environments requires satisfying coupled geometric and temporal constraints. Although Spatio-Temporal Logic (SpaTiaL) offers a principled specification framework, its use in gradient-based…

Mobile robots are often deployed over long durations in diverse open, dynamic scenes, including indoor setting such as warehouses and manufacturing facilities, and outdoor settings such as agricultural and roadway operations. A core…