Related papers: Vision-Language Reasoning for Geolocalization: A R…
Geographic reasoning is a fundamental cognitive capability that requires models to infer plausible locations by synthesizing visual evidence with spatial world knowledge. Despite recent advances in large vision-language models (LVLMs),…
Recent advances in multimodal large language models(MLLMs) have led to remarkable progress in visual grounding, enabling fine-grained cross-modal alignment between textual queries and image regions. However, transferring such capabilities…
Recent advances in MLLMs are reframing segmentation from fixed-category prediction to instruction-grounded localization. While reasoning based segmentation has progressed rapidly in natural scenes, remote sensing lacks a generalizable…
Recent studies have demonstrated the efficacy of using Reinforcement Learning (RL) in building reasoning models that articulate chains of thoughts prior to producing final answers. However, despite ongoing advances that aim at enabling…
This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions. Previous RL-based methods have achieved breakthroughs in performance and interpretability but still remain…
This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…
Remote Sensing Visual Grounding (RSVG) aims to localize target objects in large-scale aerial imagery based on natural language descriptions. Owing to the vast spatial scale and high semantic ambiguity of remote sensing scenes, these…
Geo-localization from a single image at planet scale (essentially an advanced or extreme version of the kidnapped robot problem) is a fundamental and challenging task in applications such as navigation, autonomous driving and disaster…
Humans perceive and reason about their surroundings in four dimensions by building persistent, structured internal representations that encode semantic meaning, spatial layout, and temporal dynamics. These multimodal memories enable them to…
Image geolocation aims to infer capture locations based on visual content. Fundamentally, this constitutes a reasoning process composed of \textit{hypothesis-verification cycles}, requiring models to possess both geospatial reasoning…
Recently DeepSeek R1 has shown that reinforcement learning (RL) can substantially improve the reasoning capabilities of Large Language Models (LLMs) through a simple yet effective design. The core of R1 lies in its rule-based reward…
Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they remain limited in long-horizon multimodal scenarios, often suffering from visual…
This paper proposes ReaGeo, an end-to-end geocoding framework based on large language models, designed to overcome the limitations of traditional multi-stage approaches that rely on text or vector similarity retrieval over geographic…
Humans can robustly localize visual evidence and provide grounded answers even in noisy environments by identifying critical cues and then relating them to the full context in a bottom-up manner. Inspired by this, we propose DeepScan, a…
Training robust and generalizable reward models for human visual preferences is essential for aligning text-to-image and text-to-video generative models with human intent. However, current reward models often fail to generalize, and…
Image geo-localization aims to determine where a photograph was taken, a task that often requires more than recognizing visible landmarks. Human experts typically solve it through an iterative workflow: they inspect informative regions,…
Empowered by large-scale training, vision-language models (VLMs) achieve strong image and video understanding, yet their ability to perform spatial reasoning in both static scenes and dynamic videos remains limited. Recent advances try to…
Harnessing publicly available, large-scale web data, such as street view and satellite imagery, urban socio-economic sensing is of paramount importance for achieving global sustainable development goals. With the emergence of Large…
In this paper, we are tackling the proposal-free referring expression grounding task, aiming at localizing the target object according to a query sentence, without relying on off-the-shelf object proposals. Existing proposal-free methods…
While traditional methods for instruction-following typically assume prior linguistic and perceptual knowledge, many recent works in reinforcement learning (RL) have proposed learning policies end-to-end, typically by training neural…