Related papers: CRIT: Graph-Based Automatic Data Synthesis to Enha…

Current multimodal latent reasoning often relies on external supervision (e.g., auxiliary images), ignoring intrinsic visual attention dynamics. In this work, we identify a critical Perception Gap in distillation: student models frequently…

In the era of Vision-Language Models (VLMs), enhancing multimodal reasoning capabilities remains a critical challenge, particularly in handling ambiguous or complex visual inputs, where initial inferences often lead to hallucinations or…

Multimodal adaptation equips large language models (LLMs) with perceptual capabilities, but often weakens the reasoning ability inherited from language-only pretraining. This trade-off is especially pronounced in video-language models…

In recent literature, few-shot classification has predominantly been defined by the N-way k-shot meta-learning problem. Models designed for this purpose are usually trained to excel on standard benchmarks following a restricted setup,…

Recent advances in vision-language reasoning underscore the importance of thinking with images, where models actively ground their reasoning in visual evidence. Yet, prevailing frameworks treat visual actions as optional tools, boosting…

Multi-modal reasoning in visual question answering (VQA) has witnessed rapid progress recently. However, most reasoning models heavily rely on shortcuts learned from training data, which prevents their usage in challenging real-world…

While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-centric paradigm, limiting their applicability to complex visual…

Cross-modal entity linking refers to the ability to align entities and their attributes across different modalities. While cross-modal entity linking is a fundamental skill needed for real-world applications such as multimodal code…

Cross-domain scientific synthesis requires connecting mechanistic explanations across fragmented literature, a capability that remains challenging for both retrieval-based systems and unconstrained language models. While recent work has…

Visual reasoning is central to human cognition, enabling individuals to interpret and abstractly understand their environment. Although recent Multimodal Large Language Models (MLLMs) have demonstrated impressive performance across language…

Chain-of-Thought (CoT) has widely enhanced mathematical reasoning in Large Language Models (LLMs), but it still remains challenging for extending it to multimodal domains. Existing works either adopt a similar textual reasoning for image…

Multi-hop question answering (QA) is widely used to evaluate the reasoning capabilities of large language models, yet most benchmarks focus on final answer correctness and overlook intermediate reasoning, especially in long multimodal…

Visual perceptual tasks aim to predict human judgment of images (e.g., emotions invoked by images, image quality assessment). Unlike objective tasks such as object/scene recognition, perceptual tasks rely on subjective human assessments,…

Vision-Language Models (VLMs) are advancing multimodal AI, yet their performance consistency across tasks is underexamined. We benchmark CLIP, BLIP, and LXMERT across diverse datasets spanning retrieval, captioning, and reasoning. Our…

Recent advances in large language models have significantly improved textual reasoning through the effective use of Chain-of-Thought (CoT) and reinforcement learning. However, extending these successes to vision-language tasks remains…

Reinforcement Learning Finetuning (RFT) has significantly advanced the reasoning capabilities of large language models (LLMs) by enabling long chains of thought, self-correction, and effective tool use. While recent works attempt to extend…

Current large vision-language models (LVLMs) typically rely on text-only reasoning based on a single-pass visual encoding, which often leads to loss of fine-grained visual information. Recently the proposal of ''thinking with images''…

Reasoning about visual relationships is central to how humans interpret the visual world. This task remains challenging for current deep learning algorithms since it requires addressing three key technical problems jointly: 1) identifying…

Video Large Language Models (Video-LLMs) have recently shown strong performance in basic video understanding tasks, such as captioning and coarse-grained question answering, but struggle with compositional reasoning that requires multi-step…

Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs). Yet, its potential in multimodal large language models (MLLMs) remains largely untapped, hindered by the…