相关论文: HYDRA: A Hyper Agent for Dynamic Compositional Vis…

Building robust vision systems for high-stakes domains such as remote sensing requires stronger visual reasoning than what single-pass inference typically provides; yet, retraining large models is often computationally expensive and data…

Model-based reasoning agents are ill-equipped to act in novel situations in which their model of the environment no longer sufficiently represents the world. We propose HYDRA - a framework for designing model-based agents operating in mixed…

To develop trustworthy Vision-Language Models (VLMs), it is essential to address adversarial robustness and hallucination mitigation, both of which impact factual accuracy in high-stakes applications such as defense and healthcare. Existing…

The advancement in large language models (LLMs) and large vision models has fueled the rapid progress in multi-modal vision-language reasoning capabilities. However, existing vision-language models (VLMs) remain challenged by compositional…

Vision Language Models (VLMs) have undergone significant advancements, particularly with the emergence of mobile-oriented VLMs, which offer a wide range of application scenarios. However, the substantial computational requirements for…

Recent vision-language models have strong perceptual ability but their implicit reasoning is hard to explain and easily generates hallucinations on complex queries. Compositional methods improve interpretability, but most rely on a single…

Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success remain largely opaque. Our analysis reveals that puzzling…

While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely open problem. In this…

The rise of Large Reasoning Models (LRMs) signifies a paradigm shift toward advanced computational reasoning. Yet, this progress disrupts traditional agent frameworks, traditionally anchored by execution-oriented Large Language Models…

Recently, to comprehensively improve Vision Language Models (VLMs) for Visual Question Answering (VQA), several methods have been proposed to further reinforce the inference capabilities of VLMs to independently tackle VQA tasks rather than…

Open-Vocabulary Multimodal Emotion Recognition (OV-MER) is inherently challenging due to the ambiguity of equivocal multimodal cues, which often stem from distinct unobserved situational dynamics. While Multimodal Large Language Models…

Recent advances in Multi-modal Large Language Models (MLLMs) target 3D spatial intelligence, yet the progress has been largely driven by post-training on curated benchmarks, leaving the inference-time approach relatively underexplored. In…

Recent advancements in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models' advanced reasoning ability. Traditional Vision-Language Models (VLMs) perform well in visual perception tasks…

Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking -- enabling models to monitor, evaluate, and control their reasoning processes for more adaptive and…

Multimodal large language models (MLLMs) that integrate visual and textual reasoning leverage chain-of-thought (CoT) prompting to tackle complex visual tasks, yet continue to exhibit visual hallucinations and an over-reliance on textual…

Attention is all we need as long as we have enough data. Even so, it is sometimes not easy to determine how much data is enough while the models are becoming larger and larger. In this paper, we propose HYDRA heads, lightweight pretrained…

Visual reasoning is dominated by end-to-end neural networks scaled to billions of model parameters and training examples. However, even the largest models struggle with compositional reasoning, generalization, fine-grained spatial and…

Automatic heuristic design (AHD) has emerged as a promising paradigm for solving NP-hard combinatorial optimization problems (COPs). Recent works show that large language models (LLMs), when integrated into well-designed frameworks (i.e.,…

Vision-and-Language Navigation (VLN) aims to enable embodied agents to follow natural language instructions and reach target locations in real-world environments. While prior methods often rely on either global scene representations or…

Visual reasoning (VR), which is crucial in many fields for enabling human-like visual understanding, remains highly challenging. Recently, compositional visual reasoning approaches, which leverage the reasoning abilities of large language…