18 accepted papers
Effectively integrating diverse sensory modalities is crucial for robotic manipulation. However, the typical approach of feature concatenation is often suboptimal: dominant modalities such as vision can overwhelm sparse but critical signals like touch in contact-rich tasks, and monolithic architectu…
A common belief in multimodal research is that the perceptual weaknesses of vision--language models can be compensated by stronger language reasoning (e.g., chain-of-thought, in-context learning, or external tools). We challenge this assumption. We argue that for a broad class of visual tasks hard t…
Large Language Model (LLM)-based scientific agents have accelerated scientific discovery, yet they often suffer from significant inefficiencies due to adherence to fixed initial priors. Existing approaches predominantly operate within a static hypothesis space, which restricts the discovery of novel…
Snapshot compressive imaging (SCI) captures multispectral images (MSIs) using a single coded two-dimensional (2-D) measurement, but reconstructing high-fidelity MSIs from these compressed inputs remains a fundamentally ill-posed challenge. Recent diffusion-based methods improve quality but are limit
Automatic audio captioning is essential for audio understanding, enabling applications such as accessibility and content indexing. However, evaluating the quality of audio captions remains a major challenge, especially in reference-free settings where high-quality ground-truth captions are unavailab…
As large language models (LLMs) become integral to code-related tasks, a central question emerges: Do LLMs truly understand program semantics? We introduce EquiBench, a new benchmark for evaluating LLMs through equivalence checking, i.e., determining whether two programs produce identical outputs fo
Few-shot learning (FSL) has been employed in hyperspectral image (HSI) classification, achieving excellent performance with limited training data. However, existing HSI few-shot classification methods often encounter the problem of insufficient domain-transferable knowledge learning that is either f…
Large Language Models (LLMs) are increasingly employed as automated evaluators to assess the safety of generated content, yet their reliability in this role remains uncertain. This study evaluates a diverse set of 11 LLM judge models across critical safety domains, examining three key aspects: self-…
In NLP, language–gender associations are commonly grounded in the author’s gender identity, inferred from their language use. However, this identity-based framing risks reinforcing stereotypes and marginalizing individuals who do not conform to normative language–gender associations. To address this
Quantization techniques are widely used to improve inference speed and deployment of large language models. While a wide body of work examines the impact of quantization on LLMs in English, none have evaluated across languages. We conduct a thorough analysis of quantized multilingual LLMs, focusing…
Sampling-based planning algorithms like Rapidly-exploring Random Tree (RRT) are versatile in solving path planning problems. RRT* offers asymptotic optimality but requires growing the tree uniformly over the free space, which leaves room for efficiency improvement. To accelerate convergence, rule-ba…
Accurate and robust localization is essential for mobile robots. Recently, millimeter wave (mmWave) radars have been widely used for odometry, owing to their robustness to all-weather conditions, lightweight and low cost. However, existing radar-based odometry methods degrade severely in high-dynami
Emergent properties have been widely adopted as a term to describe behavior not present in smaller models but observed in larger models (Wei et al., 2022a). Recent work suggests that the trade-off incurred by quantization is also an emergent property, with sharp drops in performance in models over…
Definitions of the distance between two machine learning models either characterize the similarity of the models' predictions or of their weights. While similarity of weights is attractive because it implies similarity of predictions in the limit, it suffers from being inapplicable to comparing mode…
The millimeter-wave radar, as an important sensor, is widely used in autonomous driving. In recent years, to meet the requirement of high level autonomous driving applications, attentions have been paid to generate high-quality radar point clouds. However, in the complex roadway environment, the wea…
Visual Question Answering (VQA) is a challenging task which requires a fine-grained semantic understanding of visual and textual contents. Existing works focus on better modality representations. However, these methods give little consideration to the long-tailed data distribution in common VQA data…
The barcode navigation based on QR (quick response) codes is widely employed in industrial logistics due to its accurate localization and flexible movement paths. However, the regular repair of damaged barcodes and robot speed control when approaching the barcodes are required. In this study, we pre…
In this paper, we consider stochastic second-order methods for minimizing a finite summation of nonconvex functions. One important key is to find an ingenious but cheap scheme to incorporate local curvature information. Since the true Hessian matrix is often a combination of a cheap part and an expe…