Related papers: AnchorSeg: Language Grounded Query Banks for Reaso…

We introduce VideoLISA, a video-based multimodal large language model designed to tackle the problem of language-instructed reasoning segmentation in videos. Leveraging the reasoning capabilities and world knowledge of large language…

Large Language Models store extensive factual knowledge acquired during large-scale pre-training. However, this knowledge is inherently static, reflecting only the state of the world at the time of training. Knowledge editing has emerged as…

Multi-modal Large Language Models (MLLMs) have demonstrated remarkable reasoning capability while lack explicit mechanisms for visual grounding and segmentation, creating a gap between cognitive reasoning and visual perception. To bridge…

Current frontier large-language models rely on reasoning to achieve state-of-the-art performance. Many existing interpretability are limited in this area, as standard methods have been designed to study single forward passes of a model…

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

In human reading and communication, individuals tend to engage in geospatial reasoning, which involves recognizing geographic entities and making informed inferences about their interrelationships. To mimic such cognitive process, current…

Free-text promptable 3D medical image segmentation offers an intuitive and clinically flexible interaction paradigm. However, current methods are highly sensitive to linguistic variability: minor changes in phrasing can cause substantial…

Large language models often reason beyond surface tokens, but the internal stage at which token-level information becomes abstract relational structure remains unclear. We investigate this question by analyzing how attention heads and…

Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive…

Abstract Meaning Representations (AMR) are a broad-coverage semantic formalism which represents sentence meaning as a directed acyclic graph. To train most AMR parsers, one needs to segment the graph into subgraphs and align each such…

Referring expression grounding is a core problem in visual grounding and is widely used as a diagnostic of spatial grounding and reasoning in vision and language models, yet most prior work focuses on natural images. In contrast, existing…

Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception to a deeper understanding of causal mechanisms. However, existing benchmarks rarely…

Visual grounding is essential for precise perception and reasoning in multimodal large language models (MLLMs), especially in medical imaging domains. While existing medical visual grounding benchmarks primarily focus on single-image…

Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Ideally, it can be a testbed for vision-and-language models to evaluate their understanding of the images and texts and their reasoning abilities…

Visual-textual correlations in the attention maps derived from text-to-image diffusion models are proven beneficial to dense visual prediction tasks, e.g., semantic segmentation. However, a significant challenge arises due to the input…

Text-to-image diffusion models have achieved remarkable progress in generating diverse and realistic images from textual descriptions. However, they still struggle with personalization, which requires adapting a pretrained model to depict…

The prosperity of Multimodal Large Language Models (MLLMs) has stimulated the demand for video reasoning segmentation, which aims to segment video objects based on human instructions. Previous studies rely on unidirectional and implicit…

Sequential labeling-based NER approaches restrict each word belonging to at most one entity mention, which will face a serious problem when recognizing nested entity mentions. In this paper, we propose to resolve this problem by modeling…

Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as…

Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in neuroscience. While modern large language models (LLMs) are increasingly used to model…