相关论文: Pixel-Level Reasoning Segmentation via Multi-turn …

Dialogue related Machine Reading Comprehension requires language models to effectively decouple and model multi-turn dialogue passages. As a dialogue development goes after the intentions of participants, its topic may not keep constant…

End-to-end text-image machine translation (TIMT), which directly translates textual content in images across languages, is crucial for real-world multilingual scene understanding. Despite advances in vision-language large models (VLLMs),…

While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, most LMMs default to verbalizing perceptual content into text, a strong limitation for tasks…

Interactive segmentation methods rely on user inputs to iteratively update the selection mask. A click specifying the object of interest is arguably the most simple and intuitive interaction type, and thereby the most common choice for…

Multimodal intent recognition poses significant challenges, requiring the incorporation of non-verbal modalities from real-world contexts to enhance the comprehension of human intentions. Existing benchmark datasets are limited in scale and…

As CLIP's global alignment limits its ability to capture fine-grained details, recent efforts have focused on enhancing its region-text alignment. However, current remote sensing (RS)-specific CLIP variants still inherit this limited…

Recent reinforcement-learning frameworks for visual perception policy usually incorporate intermediate reasoning chains expressed in natural language. Empirical observations indicate that such purely linguistic intermediate reasoning often…

Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation.…

Visual Question Answering (VQA) often requires coupling fine-grained perception with factual knowledge beyond the input image. Prior multimodal Retrieval-Augmented Generation (MM-RAG) systems improve factual grounding but lack an internal…

Modern recommendation systems typically follow two complementary paradigms: collaborative filtering, which models long-term user preferences from historical interactions, and conversational recommendation systems (CRS), which interact with…

Multimodal language models (MLLMs) are increasingly paired with vision tools (e.g., depth, flow, correspondence) to enhance visual reasoning. However, despite access to these tool-generated visual cues, MLLMs often fail to benefit from…

Evaluating vision-language models (VLMs) in scientific domains like mathematics and physics poses unique challenges that go far beyond predicting final answers. These domains demand conceptual understanding, symbolic reasoning, and…

Recent large language models (LLMs) achieve near-saturation accuracy on many established mathematical reasoning benchmarks, raising concerns about their ability to diagnose genuine reasoning competence. This saturation largely stems from…

Recent multimodal large language models (MLLMs) achieve strong performance on visual reasoning benchmarks, yet it remains unclear to what extent such performance reflects reasoning directly grounded in visual evidence. We introduce…

We introduce Meta-Reasoning Prompting (MRP), a novel and efficient system prompting method for large language models (LLMs) inspired by human meta-reasoning. Traditional in-context learning-based reasoning techniques, such as…

The rapid advancement of Large Vision Language Models (LVLMs) has demonstrated excellent abilities in various visual tasks. Building upon these developments, the thinking with images paradigm has emerged, enabling models to dynamically edit…

Multi-turn intent classification is notably challenging due to the complexity and evolving nature of conversational contexts. This paper introduces LARA, a Linguistic-Adaptive Retrieval-Augmentation framework to enhance accuracy in…

While Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language understanding, they still struggle with complex multi-step reasoning, often producing logically inconsistent or partially correct solutions.…

In the wake of Masked Image Modeling (MIM), a diverse range of plain, non-hierarchical Vision Transformer (ViT) models have been pre-trained with extensive datasets, offering new paradigms and significant potential for semantic…

Conversational AI has now reached billions of users, yet existing datasets capture only what people say, not what they think. We introduce ThoughtTrace, the first large-scale dataset that pairs real-world multi-turn human--AI conversations…