Related papers: Improving Visual Reasoning with Iterative Evidence…
Multimodal Large Language Models (MLLMs) achieve strong multimodal reasoning performance, yet we identify a recurring failure mode in long-form generation: as outputs grow longer, models progressively drift away from image evidence and fall…
Vision-Language Models (VLMs) often suffer from visual hallucinations: generating things that are not consistent with visual inputs and language shortcuts, where they skip the visual part and just rely on text priors. These issues arise…
Image scoring is a crucial task in numerous real-world applications. To trust a model's judgment, understanding its rationale is essential. This paper proposes a novel training method for Vision Language Models (VLMs) to generate not only…
Recently, reasoning-based MLLMs have achieved a degree of success in generating long-form textual reasoning chains. However, they still struggle with complex tasks that necessitate dynamic and iterative focusing on and revisiting of visual…
Recent large vision-language models (LVLMs) have demonstrated impressive reasoning ability by generating long chain-of-thought (CoT) responses. However, CoT reasoning in multimodal contexts is highly vulnerable to visual hallucination…
Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vision-language models (VLMs). We attribute this gap to two…
Despite the remarkable progress of Vision-Language Models (VLMs) in adopting "Thinking-with-Images" capabilities, accurately evaluating the authenticity of their reasoning process remains a critical challenge. Existing benchmarks mainly…
Multimodal Large Language Models (MLLMs) often struggle to accurately perceive fine-grained visual details, especially when targets are tiny or visually subtle. This challenge can be addressed through semantic-visual information fusion,…
Recent advances in visual-language machine learning models have demonstrated exceptional ability to use natural language and understand visual scenes by training on large, unstructured datasets. However, this training paradigm cannot…
We introduce a novel self-improving framework that enhances Embodied Visual Tracking (EVT) with Vision-Language Models (VLMs) to address the limitations of current active visual tracking systems in recovering from tracking failure. Our…
The cognitive faculty of visual reasoning necessitates the integration of multimodal perceptual processing and commonsense and external knowledge of the world. In recent years, a plethora of large vision-language models (LVLMs) have been…
Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…
Achieving human-like reasoning in deep learning models for complex tasks in unknown environments remains a critical challenge in embodied intelligence. While advanced vision-language models (VLMs) excel in static scene understanding, their…
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challenges in achieving complex reasoning tasks such as…
Multimodal Large Language Models (MLLMs) have achieved notable gains in various tasks by incorporating Chain-of-Thought (CoT) reasoning in language spaces. Recent work extends this direction by leveraging external tools for visual editing,…
Humans can robustly localize visual evidence and provide grounded answers even in noisy environments by identifying critical cues and then relating them to the full context in a bottom-up manner. Inspired by this, we propose DeepScan, a…
Recent advances in Vision-Language Models (VLMs) have benefited from Reinforcement Learning (RL) for enhanced reasoning. However, existing methods still face critical limitations, including the lack of low-level visual information and…
Vision-language models (VLMs) have achieved strong multimodal reasoning capabilities, but further improving them still relies heavily on large-scale human-constructed supervision for post-training. Such supervision is costly to obtain,…
Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful…
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…