Related papers: 4DThinker: Thinking with 4D Imagery for Dynamic Sp…

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Multimodal learning has rapidly advanced visual understanding, largely via multimodal large language models (MLLMs) that use powerful LLMs as cognitive cores. In visual generation, however, these powerful core models are typically reduced…

Real world deployments often expose modern object recognition models to domain shifts that precipitate a severe drop in accuracy. Such shifts encompass (i) variations in low level image statistics, (ii) changes in object pose and viewpoint,…

Vision-Language Models (VLMs) have made significant strides in static image understanding but continue to face critical hurdles in spatiotemporal reasoning. A major bottleneck is "multi-image reasoning hallucination", where a massive…

Vision-Language-Action (VLA) models have shown promising capabilities for embodied intelligence, but most existing approaches rely on text-based chain-of-thought reasoning where visual inputs are treated as static context. This limits the…

Efficiently enhancing the reasoning capabilities of Vision-Language Models (VLMs) by merging them with Large Reasoning Models (LRMs) has emerged as a promising direction. However, existing methods typically operate at a coarse-grained layer…

Instruction-based image editing has emerged as a prominent research area, which, benefiting from image generation foundation models, have achieved high aesthetic quality, making instruction-following capability the primary challenge.…

Spatio-temporal reasoning is a core capability for Multimodal Large Language Models (MLLMs) operating in the real world. As such, evaluating it precisely has become an essential challenge. However, existing spatio-temporal reasoning…

Diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive (AR) LLMs. Recently, this paradigm has been extended to multimodal tasks, leading to the development of diffusion multimodal large language…

Humans can approach complex visual problems by mentally simulating intermediate visual steps, rather than reasoning through language alone. Inspired by this, several works on Vision-Language Models have recently explored chain-of-thought…

Vision-Language Models (VLMs) are known to struggle with spatial reasoning and visual alignment. To help overcome these limitations, we introduce iVISPAR, an interactive multimodal benchmark designed to evaluate the spatial reasoning…

Despite achieving significant progress in 2D image understanding, large multimodal models (LMMs) struggle in the physical world due to the lack of spatial representation. Typically, existing 3D LMMs mainly embed 3D positions as fixed…

Disentangled representations support a range of downstream tasks including causal reasoning, generative modeling, and fair machine learning. Unfortunately, disentanglement has been shown to be impossible without the incorporation of…

Existing evaluation frameworks for Multimodal Large Language Models (MLLMs) primarily focus on image reasoning or general video understanding tasks, largely overlooking the significant role of image context in video comprehension. To bridge…

Despite advances in Multimodal LLMs (MLLMs), their ability to reason over 3D structures and temporal dynamics remains limited, constrained by weak 4D perception and temporal understanding. Existing 3D and 4D Video Question Answering (VQA)…

Video understanding represents the most challenging frontier in computer vision, requiring models to reason about complex spatiotemporal relationships, long-term dependencies, and multimodal evidence. The recent emergence of Video-Large…

Large-scale 3D vision-language models (VLMs) like LLaVA-3D offer strong spatial reasoning but are difficult to deploy due to high computational costs. We propose a knowledge distillation framework that transfers spatial reasoning from a 7B…

Visual reasoning refers to the task of solving questions about visual information. Current visual reasoning methods typically employ pre-trained vision-language model (VLM) strategies or deep neural network approaches. However, existing…

Humans are able to accurately reason in 3D by gathering multi-view observations of the surrounding world. Inspired by this insight, we introduce a new large-scale benchmark for 3D multi-view visual question answering (3DMV-VQA). This…

Despite the rapid progress of multimodal large language models (MLLMs), they have largely overlooked the importance of visual processing. In a simple yet revealing experiment, we interestingly find that language-only models, when provided…