Related papers: RF-Analyzer: Can Vision-Language Models Learn RF U…
The advent of next-generation radio telescopes is set to transform radio astronomy by producing massive data volumes that challenge traditional processing methods. Deep learning techniques have shown strong potential in automating radio…
Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM. Our approach focuses on analyzing the…
Recent advances in Multimodal Large Language Models (MLLMs) have shown remarkable capabilities in understanding both images and 3D data, yet these modalities face inherent limitations in comprehensively representing object geometry and…
Vision-Language models (VLMs) achieve strong performance on multimodal tasks but often fail at systematic visual reasoning tasks, leading to inconsistent or illogical outputs. Neuro-symbolic methods promise to address this by inducing…
The development of Large Vision-Language Models (LVLMs) is striving to catch up with the success of Large Language Models (LLMs), yet it faces more challenges to be resolved. Very recent works enable LVLMs to localize object-level visual…
Radar sensors provide reliable perception across adverse weather, lighting, and long-range conditions, yet existing machine learning approaches remain fragmented and task-specific, with each downstream task employing distinct architectures…
Chart summarization, which focuses on extracting key information from charts and interpreting it in natural language, is crucial for generating and delivering insights through effective and accessible data analysis. Traditional methods for…
The adaptation of large-scale Vision-Language Models (VLMs) through post-training reveals a pronounced generalization gap: models fine-tuned with Reinforcement Learning (RL) consistently achieve superior out-of-distribution (OOD)…
In cognitive science and AI, a longstanding question is whether machines learn representations that align with those of the human mind. While current models show promise, it remains an open question whether this alignment is superficial or…
The recent advancements in Vision Language Models (VLMs) have demonstrated progress toward true intelligence requiring robust reasoning capabilities. Beyond pattern recognition, linguistic reasoning must integrate with visual comprehension,…
Spatial understanding remains a weakness of Large Vision-Language Models (LVLMs). Existing supervised fine-tuning (SFT) and recent reinforcement learning with verifiable rewards (RLVR) pipelines depend on costly supervision, specialized…
Reinforcement Learning (RL) has been shown to significantly boost reasoning capabilities of large language models (LLMs) in math, coding, and multi-hop reasoning tasks. However, RL fine-tuning requires abundant high-quality verifiable data,…
In recent years, the emergence of models capable of generating images from text has attracted considerable interest, offering the possibility of creating realistic images from text descriptions. Yet these advances have also raised concerns…
Accurately identifying the material composition of objects is a critical capability for AI robots powered by large language models (LLMs) to perform context-aware manipulation. Radar technologies offer a promising sensing modality for…
The prevalence and low cost of LLMs have led to a rise of synthetic content. From review sites to court documents, "natural" content has been contaminated by data points that appear similar to natural data, but are in fact LLM-generated. In…
Recent advances in LVLMs have improved vision-language understanding, but they still struggle with spatial perception, limiting their ability to reason about complex 3D scenes. Unlike previous approaches that incorporate 3D representations…
Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs. The SR methods learned on synthetic data do not perform well in…
Deep learning (DL) finds rich applications in the wireless domain to improve spectrum awareness. Typically, DL models are either randomly initialized following a statistical distribution or pretrained on tasks from other domains in the form…
Visual-language models (VLMs) have recently been introduced in robotic mapping using the latent representations, i.e., embeddings, of the VLMs to represent semantics in the map. They allow moving from a limited set of human-created labels…
While recent advancements in large language models (LLMs) bring us closer to achieving artificial general intelligence, the question persists: Do LLMs truly understand language, or do they merely mimic comprehension through pattern…