Related papers: Think and Answer ME: Benchmarking and Exploring Mu…
Recent advances in vision-language models (VLMs) have achieved remarkable performance on standard medical benchmarks, yet their true clinical reasoning ability remains unclear. Existing datasets predominantly emphasize classification…
Remote Sensing (RS) is a crucial technology for observing, monitoring, and interpreting our planet, with broad applications across geoscience, economics, humanitarian fields, etc. While artificial intelligence (AI), particularly deep…
Referring expression counting (REC) is an intention-driven task that requires context-aware visual reasoning. While recent vision-language models incorporate language for visual understanding, most existing REC methods rely on rulebased…
Current visual grounding models are either based on a Multimodal Large Language Model (MLLM) that performs auto-regressive decoding, which is slow and risks hallucinations, or on re-aligning an LLM with vision features to learn new special…
Recognition and reasoning are two pillars of visual understanding. However, these tasks have an imbalance in focus; whereas recent advances in neural networks have shown strong empirical performance in visual recognition, there has been…
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…
The reasoning-based pose estimation (RPE) benchmark has emerged as a widely adopted evaluation standard for pose-aware multimodal large language models (MLLMs). Despite its significance, we identified critical reproducibility and…
Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning…
Egocentric interaction perception is one of the essential branches in investigating human-environment interaction, which lays the basis for developing next-generation intelligent systems. However, existing egocentric interaction…
Reasoning segmentation requires models to ground complex, implicit textual queries into precise pixel-level masks. Existing approaches rely on a single segmentation token $\texttt{<SEG>}$, whose hidden state implicitly encodes both semantic…
Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing imagery according to natural language expressions. Previous methods typically rely on sentence-level vision-language alignment, which struggles to exploit…
Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that…
Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches…
Visual generation models have made remarkable progress in creating realistic images from text prompts, yet struggle with complex prompts that specify multiple objects with precise spatial relationships and attributes. Effective handling of…
Grounded Multimodal Named Entity Recognition (GMNER) is a nascent multimodal task that aims to identify named entities, entity types and their corresponding visual regions. GMNER task exhibits two challenging properties: 1) The weak…
The ability to perform Chain-of-Thought (CoT) reasoning marks a major milestone for multimodal models (MMs), enabling them to solve complex visual reasoning problems. Yet a critical question remains: is such reasoning genuinely grounded in…
Elucidating the reasoning process with structured explanations from question to answer is crucial, as it significantly enhances the interpretability, traceability, and trustworthiness of question-answering (QA) systems. However, structured…
Foundation models constitute a significant advancement in computer vision: after a single, albeit costly, training phase, they can address a wide array of tasks. In the field of Earth observation, over 75 remote sensing vision foundation…
Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often generate a single query for retrieval at each reasoning step, limiting information…
In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or science domains. This…