Related papers: ChemVLR: Prioritizing Reasoning in Perception for …
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…
Visual Language Models (VLMs) show remarkable performance in visual reasoning tasks, successfully tackling college-level challenges that require high-level understanding of images. However, some recent reports of VLMs struggling to reason…
Large language models have demonstrated substantial advancements in reasoning capabilities. However, current Vision-Language Models (VLMs) often struggle to perform systematic and structured reasoning, especially when handling complex…
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…
The advent of Large Language Models (LLMs) has significantly reshaped the trajectory of the AI revolution. Nevertheless, these LLMs exhibit a notable limitation, as they are primarily adept at processing textual information. To address this…
Despite recent advances in video understanding, the capabilities of Large Video Language Models (LVLMs) to perform video-based causal reasoning remains underexplored, largely due to the absence of relevant and dedicated benchmarks for…
Large vision-language models (LVMs) hold a great promise for automating medical report generation, potentially reducing the burden of manual reporting. State-of-the-art (SOTA) research fine-tunes general LVMs with medical data to align…
Building on the success of text-based reasoning models like DeepSeek-R1, extending these capabilities to multimodal reasoning holds great promise. While recent works have attempted to adapt DeepSeek-R1-style reinforcement learning (RL)…
In this paper, we advance the study of AI-augmented reasoning in the context of Human-Computer Interaction (HCI), psychology and cognitive science, focusing on the critical task of visual perception. Specifically, we investigate the…
Recent studies suggest that transformer-based vision-language models (VLMs) capture the multimodality of concept processing in the human brain. However, a systematic evaluation exploring different types of VLM architectures and the role…
Recent advances in Large Language Models (LLMs) have demonstrated their remarkable capacity to process and reason over structured and unstructured data modalities beyond natural language. In this work, we explore the applications of Vision…
In this work, we introduce the Qwen-VL series, a set of large-scale vision-language models (LVLMs) designed to perceive and understand both texts and images. Starting from the Qwen-LM as a foundation, we endow it with visual capacity by the…
In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often causes models to lean towards language comprehension and…
Vision-Language Models (VLMs) excel at complex visual tasks such as VQA and chart understanding, yet recent work suggests they struggle with simple perceptual tests. We present an evaluation of vision-language models' capacity for nonlocal…
Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful…
Solving complex long-horizon robotic manipulation problems requires sophisticated high-level planning capabilities, the ability to reason about the physical world, and reactively choose appropriate motor skills. Vision-language models…
Mainstream vision-language models (VLMs) fundamentally struggle with severe optical ambiguities, such as reflections and transparent objects, due to the inherent limitations of standard RGB inputs. While polarization imaging captures…
The rapid development of multimodal large-language models (MLLMs) has significantly expanded the scope of visual language reasoning, enabling unified systems to interpret and describe complex visual content. However, applying these models…
The development of large language models and multi-modal models has enabled the appealing idea of generating novel molecules from text descriptions. Generative modeling would shift the paradigm from relying on large-scale chemical screening…
Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLVR), rewards only correct final answers, often propagating…