Related papers: CAVE: A Structured Credit Assignment Approach for …

Evaluating the alignment between textual prompts and generated images is critical for ensuring the reliability and usability of text-to-image (T2I) models. However, most existing evaluation methods rely on coarse-grained metrics or static…

Dramatic progress has been witnessed in basic vision tasks involving low-level perception, such as object recognition, detection, and tracking. Unfortunately, there is still an enormous performance gap between artificial vision systems and…

The advancement of Large Vision-Language Models (LVLMs) requires precise local region-based reasoning that faithfully grounds the model's logic in actual visual evidence. However, existing datasets face limitations in scalability due to…

Despite progress in Large Vision-Language Models (LVLMs), their capacity for visual reasoning is often limited by the binding problem: the failure to reliably associate perceptual features with their correct visual referents. This…

Visual token compression is widely used to accelerate large vision-language models (LVLMs) by pruning or merging visual tokens, yet its adversarial robustness remains unexplored. We show that existing encoder-based attacks cannot fully…

While Vision-language models (VLMs) have demonstrated remarkable performance across multi-modal tasks, their choice of vision encoders presents a fundamental weakness: their low-level features lack the robust structural and spatial…

Iterative Retrieval-Augmented Generation (iRAG) has emerged as a powerful paradigm for answering complex multi-hop questions by progressively retrieving and reasoning over external documents. However, current systems predominantly operate…

GRAFT is a structured multimodal benchmark designed to probe how well LLMs handle instruction following, visual reasoning, and tasks requiring tight visual textual alignment. The dataset is built around programmatically generated charts and…

Large multimodal models (LMMs) inherit the self-attention mechanism of pretrained language backbones, yet standard attention can exhibit suboptimal allocation, including cross-modal misallocation between textual and visual evidence and…

Advances in large reasoning models have shown strong performance on complex reasoning tasks by scaling test-time compute through extended reasoning. However, recent studies observe that in vision-dependent tasks, extended textual reasoning…

Universal Multimodal Retrieval requires unified embedding models capable of interpreting diverse user intents, ranging from simple keywords to complex compositional instructions. While Multimodal Large Language Models (MLLMs) possess strong…

Large Vision-Language Models (LVLMs) have shown exceptional performance in multimodal tasks, but their effectiveness in complex visual reasoning is still constrained, especially when employing Chain-of-Thought prompting techniques. In this…

A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for…

Reinforcement learning from verifiable rewards (RLVR), especially with Group Relative Policy Optimization (GRPO), has shown strong potential for improving the reasoning capabilities of large vision-language models (LVLMs). However, in…

Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors…

Existing visual reasoning datasets such as Visual Question Answering (VQA), often suffer from biases conditioned on the question, image or answer distributions. The recently proposed CLEVR dataset addresses these limitations and requires…

Multimodal reasoning in vision-language models (VLMs) typically relies on a two-stage process: supervised fine-tuning (SFT) and reinforcement learning (RL). In standard SFT, all tokens contribute equally to the loss, even though reasoning…

Geometric reasoning inherently requires "thinking with constructions" -- the dynamic manipulation of visual aids to bridge the gap between problem conditions and solutions. However, existing Multimodal Large Language Models (MLLMs) are…

The goal of a classification model is to assign the correct labels to data. In most cases, this data is not fully described by the given set of labels. Often a rich set of meaningful concepts exist in the domain that can much more precisely…

Recent advances in Multimodal Large Language Models (MLLMs) have shown impressive reasoning capabilities across vision-language tasks, yet still face the challenge of compute-difficulty mismatch. Through empirical analyses, we identify that…