Large Language Models (LLMs) have shown significant problem-solving capabilities across predictive and generative tasks in chemistry. However, their proficiency in multi-step chemical reasoning remains underexplored. We introduce a new challenge: molecular structure elucidation, which involves deducing a molecule's structure from various types of spectral data. Solving such a molecular puzzle, akin to solving crossword puzzles, poses reasoning challenges that require integrating clues from diverse sources and engaging in iterative hypothesis testing. To address this challenging problem with LLMs, we present \textbf{MolPuzzle}, a benchmark comprising 217 instances of structure elucidation, which feature over 23,000 QA samples presented in a sequential puzzle-solving process, involving three interlinked sub-tasks: molecule understanding, spectrum interpretation, and molecule construction. Our evaluation of 12 LLMs reveals that the best-performing LLM, GPT-4o, performs significantly worse than humans, with only a small portion (1.4\%) of its answers exactly matching the ground truth. However, it performs nearly perfectly in the first subtask of molecule understanding, achieving accuracy close to 100\%. This discrepancy highlights the potential of developing advanced LLMs with improved chemical reasoning capabilities in the other two sub-tasks.

Large multimodal models trained on natural documents, which interleave images and text, outperform models trained on image-text pairs on various multimodal benchmarks. However, the datasets used to train these models have not been released, and the collection process has not been fully specified. We introduce the OBELICS dataset, an open web-scale filtered dataset of interleaved image-text documents comprising 141 million web pages extracted from Common Crawl, 353 million associated images, and 115 billion text tokens. We describe the dataset creation process, present comprehensive filtering rules, and provide an analysis of the dataset's content. To show the viability of OBELICS, we train on the dataset vision and language models of 9 and 80 billion parameters, IDEFICS-9B and IDEFICS, and obtain competitive performance on different multimodal benchmarks. We release our dataset, models and code.

The healthcare and AI communities have witnessed a growing interest in the development of AI-assisted systems for automated diagnosis of Parkinson's Disease (PD), one of the most prevalent neurodegenerative disorders. However, the progress in this area has been significantly impeded by the absence of a unified, publicly available benchmark, which prevents comprehensive evaluation of existing PD analysis methods and the development of advanced models. This work overcomes these challenges by introducing YouTubePD -- the first publicly available multimodal benchmark designed for PD analysis. We crowd-source existing videos featured with PD from YouTube, exploit multimodal information including in-the-wild videos, audio data, and facial landmarks across 200+ subject videos, and provide dense and diverse annotations from clinical expert. Based on our benchmark, we propose three challenging and complementary tasks encompassing both discriminative and generative tasks, along with a comprehensive set of corresponding baselines. Experimental evaluation showcases the potential of modern deep learning and computer vision techniques, in particular the generalizability of the models developed on YouTubePD to real-world clinical settings, while revealing their limitations. We hope our work paves the way for future research in this direction.

Vision-language models (VLMs) have achieved remarkable success across multimodal tasks, yet their substantial computational demands hinder efficient deployment. Knowledge distillation (KD) has emerged as a powerful approach for building lightweight but competitive models, with strong evidence from both language and vision domains. However, its application to VLMs, particularly CLIP-style models, remains limited, often constrained to small-scale teachers and narrow evaluation tasks such as classification or retrieval. In this work, we present the first systematic study of distillation across a range of CLIP-style teacher models, ranging from standard baselines to large-scale state-of-the-art models. Contrary to trends observed in NLP and vision, we find that stronger teachers do not consistently yield better students; in fact, existing distillation frameworks often fail to scale, leading to degraded performance in downstream multimodal tasks such as visual question answering. Our findings challenge prevailing assumptions in KD and point toward new directions for designing parameter-efficient multimodal models.

Social media has amplified the reach of financial influencers known as "finfluencers," who share stock recommendations on platforms like YouTube. Understanding their influence requires analyzing multimodal signals like tone, delivery style, and facial expressions, which extend beyond text-based financial analysis. We introduce VideoConviction, a multimodal dataset with 6,000+ expert annotations, produced through 457 hours of human effort, to benchmark multimodal large language models (MLLMs) and text-based large language models (LLMs) in financial discourse. Our results show that while multimodal inputs improve stock ticker extraction (e.g., extracting Apple's ticker AAPL), both MLLMs and LLMs struggle to distinguish investment actions and conviction--the strength of belief conveyed through confident delivery and detailed reasoning--often misclassifying general commentary as definitive recommendations. While high-conviction recommendations perform better than low-conviction ones, they still underperform the popular S\&P 500 index fund. An inverse strategy--betting against finfluencer recommendations--outperforms the S\&P 500 by 6.8\% in annual returns but carries greater risk (Sharpe ratio of 0.41 vs. 0.65). Our benchmark enables a diverse evaluation of multimodal tasks, comparing model performance on both full video and segmented video inputs. This enables deeper advancements in multimodal financial research. Our code, dataset, and evaluation leaderboard are available under the CC BY-NC 4.0 license.

Large Language Models (LLMs) have shown significant problem-solving capabilities across predictive and generative tasks in chemistry. However, their proficiency in multi-step chemical reasoning remains underexplored. We introduce a new challenge: molecular structure elucidation, which involves deducing a molecule's structure from various types of spectral data. Solving such a molecular puzzle, akin to solving crossword puzzles, poses reasoning challenges that require integrating clues from diverse sources and engaging in iterative hypothesis testing. To address this challenging problem with LLMs, we present \textbf{MolPuzzle}, a benchmark comprising 217 instances of structure elucidation, which feature over 23,000 QA samples presented in a sequential puzzle-solving process, involving three interlinked sub-tasks: molecule understanding, spectrum interpretation, and molecule construction.

The reproduction of state-of-the-art multimodal LLM pre-training faces barriers at every stage of the pipeline, including high-quality data filtering, multimodal data mixture strategies, sequence packing techniques, and training frameworks. We introduce Open-Qwen2VL, a fully open-source 2B-parameter Multimodal Large Language Model pre-trained efficiently on 29M image-text pairs using only 220 A100-40G GPU hours. Our approach employs low-to-high dynamic image resolution and multimodal sequence packing to significantly enhance pre-training efficiency. The training dataset was carefully curated using both MLLM-based filtering techniques (e.g., MLM-Filter) and conventional CLIP-based filtering methods, substantially improving data quality and training efficiency. The Open-Qwen2VL pre-training is conducted on academic level 8xA100-40G GPUs at UCSB on 5B packed multimodal tokens, which is 0.36% of 1.4T multimodal pre-training tokens of Qwen2-VL. The final instruction-tuned Open-Qwen2VL outperforms partially-open state-of-the-art MLLM Qwen2-VL-2B on various multimodal benchmarks of MMBench, SEEDBench, MMstar, and MathVista, indicating the remarkable training efficiency of Open-Qwen2VL. We open-source all aspects of our work, including compute-efficient and data-efficient training details, data filtering methods, sequence packing scripts, pre-training data in WebDataset format, FSDP-based training codebase, and both base and instruction-tuned model checkpoints. We redefine "fully open" for multimodal LLMs as the complete release of: 1) the training codebase, 2) detailed data filtering techniques, and 3) all pre-training and supervised fine-tuning data used to develop the model.

Large multimodal models trained on natural documents, which interleave images and text, outperform models trained on image-text pairs on various multimodal benchmarks. However, the datasets used to train these models have not been released, and the collection process has not been fully specified. We introduce the OBELICS dataset, an open web-scale filtered dataset of interleaved image-text documents comprising 141 million web pages extracted from Common Crawl, 353 million associated images, and 115 billion text tokens. We describe the dataset creation process, present comprehensive filtering rules, and provide an analysis of the dataset's content. To show the viability of OBELICS, we train on the dataset vision and language models of 9 and 80 billion parameters, IDEFICS-9B and IDEFICS, and obtain competitive performance on different multimodal benchmarks. We release our dataset, models and code.

The healthcare and AI communities have witnessed a growing interest in the development of AI-assisted systems for automated diagnosis of Parkinson's Disease (PD), one of the most prevalent neurodegenerative disorders. However, the progress in this area has been significantly impeded by the absence of a unified, publicly available benchmark, which prevents comprehensive evaluation of existing PD analysis methods and the development of advanced models. This work overcomes these challenges by introducing YouTubePD -- the first publicly available multimodal benchmark designed for PD analysis. We crowd-source existing videos featured with PD from YouTube, exploit multimodal information including in-the-wild videos, audio data, and facial landmarks across 200 subject videos, and provide dense and diverse annotations from clinical expert. Based on our benchmark, we propose three challenging and complementary tasks encompassing both discriminative and generative tasks, along with a comprehensive set of corresponding baselines.

While the evaluation of multimodal English-centric models is an active area of research with numerous benchmarks, there is a profound lack of benchmarks or evaluation suites for low- and mid-resource languages. We introduce ZNO-Vision, a comprehensive multimodal Ukrainian-centric benchmark derived from standardized university entrance examination (ZNO). The benchmark consists of over 4,300 expert-crafted questions spanning 12 academic disciplines, including mathematics, physics, chemistry, and humanities. We evaluated the performance of both open-source models and API providers, finding that only a handful of models performed above baseline. Alongside the new benchmark, we performed the first evaluation study of multimodal text generation for the Ukrainian language: we measured caption generation quality on the Multi30K-UK dataset, translated the VQA benchmark into Ukrainian, and measured performance degradation relative to original English versions. Lastly, we tested a few models from a cultural perspective on knowledge of national cuisine. We believe our work will advance multimodal generation capabilities for the Ukrainian language and our approach could be useful for other low-resource languages.