The ability to perform multi-modal multi-hop reasoning by iteratively integrating information across various modalities and external knowledge is critical for addressing complex real-world challenges. However, existing Multi-modal Large Language Models (MLLMs) are predominantly limited to single-step reasoning, as existing benchmarks lack the complexity needed to evaluate and drive multi-hop abilities. To bridge this gap, we introduce MMhops, a novel, large-scale benchmark designed to systematically evaluate and foster multi-modal multi-hop reasoning. MMhops dataset comprises two challenging task formats, Bridging and Comparison, which necessitate that models dynamically construct complex reasoning chains by integrating external knowledge. To tackle the challenges posed by MMhops, we propose MMhops-R1, a novel multi-modal Retrieval-Augmented Generation (mRAG) framework for dynamic reasoning. Our framework utilizes reinforcement learning to optimize the model for autonomously planning reasoning paths, formulating targeted queries, and synthesizing multi-level information. Comprehensive experiments demonstrate that MMhops-R1 significantly outperforms strong baselines on MMhops, highlighting that dynamic planning and multi-modal knowledge integration are crucial for complex reasoning. Moreover, MMhops-R1 demonstrates strong generalization to tasks requiring fixed-hop reasoning, underscoring the robustness of our dynamic planning approach.

Video Large Language Models (Vid-LLMs) have made remarkable advancements in comprehending video content for QA dialogue. However, they struggle to extend this visual understanding to tasks requiring precise temporal localization, known as Video Temporal Grounding (VTG). To address this, we introduce Number-Prompt (NumPro), a novel method that empowers Vid-LLMs to bridge visual comprehension with temporal grounding by adding unique numerical identifiers to each video frame. Treating a video as a sequence of numbered frame images, NumPro transforms VTG into an intuitive process: flipping through manga panels in sequence. This allows Vid-LLMs to “read” event timelines, accurately linking visual content with cor responding temporal information. Our experiments demonstrate that NumPro significantly boosts VTG performance of top-tier Vid-LLMs without additional computational cost. Furthermore, fine-tuning on a NumPro-enhanced dataset defines a new state-of-the-art for VTG, surpassing previous top-performing methods by up to 6.9% in mIoU for moment retrieval and 8.5% in mAP for highlight detection. The code is available at https://github.com/yongliang-wu/NumPro.

Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of image information during understanding task, due to either image discretization or diffusion de-noising steps. To address this issue, we propose a novel Multi-Modal Auto-Regressive (MMAR) probabilistic modeling framework. Unlike discretization line of method, MMAR takes in continuous-valued image tokens to avoid information loss in an efficient way. Differing from diffusion-based approaches, we disentangle the diffusion process from auto-regressive backbone model by employing a lightweight diffusion head on top each auto-regressed image patch embedding. In this way, when the model transits from image generation to understanding through text generation, the backbone model’s hidden representation of the image is not limited to the last denoising step. To successfully train our method, we also propose a theoretically proven technique that addresses the numerical stability issue and a training strategy that balances the generation and understanding task goals. Extensive evaluations on 18 image understanding benchmarks show that MMAR significantly outperforms most of the existing joint multi-modal models, surpassing the method that employs pre-trained CLIP vision encoder. Meanwhile, MMAR is able to generate high quality images. We also show that our method is scalable with larger data and model size.

This paper introduces HarmonySet, a comprehensive dataset designed to advance video-music understanding. Harmony-Set consists of 48,328 diverse video-music pairs, annotated with detailed information on rhythmic synchronization, emotional alignment, thematic coherence, and cultural relevance. We propose a multi-step human-machine collaborative framework for efficient annotation, combining human insights with machine-generated descriptions to identify key transitions and assess alignment across multiple dimensions. Addition ally, we introduce a novel evaluation framework with tasks and metrics to assess the multi-dimensional alignment of video and music, including rhythm, emotion, theme, and cultural context. Our extensive experiments demonstrate that HarmonySet, along with the proposed evaluation framework, significantly improves the ability of multimodal models to capture and analyze the intricate relationships between video and music. Project page: https://harmonyset.github.io/.

Multi-modal Large language models (MLLMs) show remarkable ability in video understanding. Nevertheless, understanding long videos remains challenging as the models can only process a finite number of frames in a single inference, potentially omitting crucial visual information. To address the challenge, we propose generating multiple predictions through visual context sampling, followed by a scoring mechanism to select the final prediction. Specifically, we devise a bin-wise sampling strategy that enables MLLMs to generate diverse answers based on various combinations of keyframes, thereby enriching the visual context. To determine the final prediction from the sampled answers, we employ a self-reward by linearly combining three scores: (1) a frequency score indicating the prevalence of each option, (2) a marginal confidence score reflecting the inter-intra sample certainty of MLLM predictions, and (3) a reasoning score for different question types, including clue-guided answering for global questions and temporal self-refocusing for local questions. The frequency score ensures robustness through majority correctness, the confidence-aligned score reflects prediction certainty, and the typed-reasoning score addresses cases with sparse key visual information using tailored strategies. Experiments show that this approach covers the correct answer for a high percentage of long video questions, on seven datasets show that our method improves the performance of three MLLMs.

Preference alignment has emerged as an effective strategy to enhance the performance of Multimodal Large Language Models (MLLMs) following supervised fine-tuning. While existing preference alignment methods predominantly target hallucination factors, they overlook the factors essential for multi-modal comprehension capabilities, often narrowing their improvements on hallucination mitigation. To bridge this gap, we propose Instruction-oriented Preference Alignment (IPA), a scalable framework designed to automatically construct alignment preferences grounded in instruction fulfillment efficacy. Our method involves an automated preference construction coupled with a dedicated verification process that identifies instruction-oriented factors, avoiding significant variability in response representations. Additionally, IPA incorporates a progressive preference collection pipeline, further recalling challenging samples through model self-evolution and reference-guided refinement. Experiments conducted on Qwen2VL-7B demonstrate IPA's effectiveness across multiple benchmarks, including hallucination evaluation, visual question answering, and text understanding tasks, highlighting its capability to enhance general comprehension.

This paper aims to address the challenge of hallucinations in Multimodal Large Language Models (MLLMs) particularly for dense image captioning tasks. To tackle the challenge, we identify the current lack of a metric that finely measures the caption quality in concept level. We hereby introduce HalFscore, a novel metric built upon the language graph and is designed to evaluate both the accuracy and completeness of dense captions at a granular level. Additionally, we identify the root cause of hallucination as the model's over-reliance on its language prior. To address this, we propose PerturboLLaVA, which reduces the model's reliance on the language prior by incorporating adversarially perturbed text during training. This method enhances the model's focus on visual inputs, effectively reducing hallucinations and producing accurate, image-grounded descriptions without incurring additional computational overhead. PerturboLLaVA significantly improves the fidelity of generated captions, outperforming existing approaches in handling multimodal hallucinations and achieving improved performance across general multimodal benchmarks.

Long-form video understanding poses a significant challenge for video large language models (VideoLLMs) due to prohibitively high computational and memory demands. In this paper, We propose $\textbf{FlexSelect}$, a flexible and efficient token selection strategy for processing long videos. FlexSelect identifies and retains the most semantically relevant content by leveraging cross-modal attention patterns from a reference transformer layer. It comprises two key components: (1) $\textbf{a training-free token ranking pipeline}$ that leverages faithful cross-modal attention weights to estimate each video token’s importance, and (2) $\textbf{a rank-supervised lightweight selector}$ that is trained to replicate these rankings and filter redundant tokens. This generic approach can be seamlessly integrated into various VideoLLM architectures, such as LLaVA-Video, InternVL and Qwen-VL, serving as a plug-and-play module to extend their temporal context length. Empirically, FlexSelect delivers strong gains across multiple long-video benchmarks – including VideoMME, MLVU, LongVB, and LVBench. Morever, it achieves significant speed-ups ($\textit{e.g.,}$ up to 9 $\times$ on a LLaVA-Video-7B model), highlighting FlexSelect’s promise for efficient long-form video understanding. Project page: https://flexselect.github.io

Image captioning requires numerous annotated image-text pairs, resulting in substantial annotation costs. Recently, large models (e.g. diffusion models and large language models) have excelled in producing high-quality images and text. This potential can be harnessed to create synthetic image-text pairs for training captioning models. Synthetic data can improve cost and time efficiency in data collection, allow for customization to specific domains, bootstrap generalization capability for zero-shot performance, and circumvent privacy concerns associated with real-world data. However, existing methods struggle to attain satisfactory performance solely through synthetic data. We identify the issue as generated images from simple descriptions mostly capture a solitary perspective with limited context, failing to align with the intricate scenes prevalent in real-world imagery. To tackle this, we present an innovative pipeline that introduces multi-context data generation. Beginning with an initial text corpus, our approach employs a large language model to extract multiple sentences portraying the same scene from diverse viewpoints. These sentences are then condensed into a single sentence with multiple contexts. Subsequently, we generate intricate images using the condensed captions through diffusion models. Our model is exclusively trained on synthetic image-text pairs crafted through this process. The effectiveness of our pipeline is validated through experimental results in both the in-domain and cross-domain settings, where it achieves state-of-the-art performance on well-known datasets such as MSCOCO, Flickr30k, and NoCaps.

A large amount of User Generated Content (UGC) is uploaded to the Internet daily and displayed to people world-widely through the client side (mobile and PC). This requires the cropping algorithms to produce the aesthetic thumbnail within a specific aspect ratio on different devices. However, existing image cropping works mainly focus on landmark or landscape images, which fail to model the relations among the multi-objects with the complex background in UGC. Besides, previous methods merely consider the aesthetics of the cropped images while ignoring the content integrity, which is crucial for UGC cropping. In this paper, we propose a Spatial-Semantic Collaborative cropping network (S2CNet) for arbitrary user generated content accompanied by a new cropping benchmark. Specifically, we first mine the visual genes of the potential objects. Then, the suggested adaptive attention graph recasts this task as a procedure of information association over visual nodes. The underlying spatial and semantic relations are ultimately centralized to the crop candidate through differentiable message passing, which helps our network efficiently to preserve both the aesthetics and the content integrity. Extensive experiments on the proposed UGCrop5K and other public datasets demonstrate the superiority of our approach over state-of-the-art counterparts.

The analysis of the ubiquitous human-human interactions is pivotal for understanding humans as social beings. Existing human-human interaction datasets typically suffer from inaccurate body motions, lack of hand gestures and fine- grained textual descriptions. To better perceive and generate human-human interactions, we propose Inter-X, a currently largest human-human interaction dataset with accurate body movements and diverse interaction patterns, together with detailed hand gestures. The dataset includes

Humans constantly interact with their surrounding environments. Current human-centric generative models mainly focus on synthesizing humans plausibly interacting with static scenes and objects, while the dynamic human action-reaction synthesis for ubiquitous causal human-human interactions is less explored. Human-human interactions can be regarded as asymmetric with actors and reactors in atomic interaction periods. In this paper, we compre-hensively analyze the asymmetric, dynamic, synchronous, and detailed nature of human-human interactions and propose the first multi-setting human action-reaction synthe-sis benchmark to generate human reactions conditioned on given human actions. To begin with, we propose to an-notate the actor-reactor order of the interaction sequences for the NTU120, InterHuman, and Chi3D datasets. Based on them, a diffusion-based generative model with a Trans-former decoder architecture called ReGenNet together with an explicit distance-based interaction loss is proposed to predict human reactions in an online manner, where the future states of actors are unavailable to reactors. Quantitative and qualitative results show that our method can gener-ate instant and plausible human reactions compared to the baselines, and can generalize to unseen actor motions and viewpoint changes.

Existing Multimodal Large Language Models (MLLMs) follow the paradigm that perceives visual information by aligning visual features with the input space of Large Language Models (LLMs) and concatenating visual tokens with text tokens to form a unified sequence input for LLMs. These methods demonstrate promising results on various vision-language tasks but are limited by the high computational effort due to the extended input sequence resulting from the involvement of visual tokens. In this paper, instead of input space alignment, we propose a novel parameter space alignment paradigm that represents visual information as model weights. For each input image, we use a vision encoder to extract visual features, convert features into perceptual weights, and merge the perceptual weights with LLM's weights. In this way, the input of LLM does not require visual tokens, which reduces the length of the input sequence and greatly improves efficiency. Following this paradigm, we propose VLoRA with the perceptual weights generator. The perceptual weights generator is designed to convert visual features to perceptual weights with low-rank property, exhibiting a form similar to LoRA. The experimental results show that our VLoRA achieves comparable performance on various benchmarks for MLLMs, while significantly reducing the computational costs for both training and inference. Code and models are released at \url{https://github.com/FeipengMa6/VLoRA}.

Multi-modal video similarity evaluation is important for video recommendation systems such as video de-duplication, relevance matching, ranking, and diversity control. However, there still lacks a benchmark dataset that can support supervised training and accurate evaluation. In this paper, we propose the Tencent-MVSE dataset, which is the first benchmark dataset for the multi-modal video similarity evaluation task. The Tencent-MVSE dataset contains video pairs similarity annotations, and diverse metadata including Chinese title, automatic speech recognition (ASR) text, as well as human-annotated categories/tags. We provide a simple baseline with a multi-modal Transformer architecture to perform supervised multi-modal video similarity evaluation. We also explore pre-training strategies to make use of the unpaired data. The whole dataset as well as our baseline will be released to promote the development of the multi-modal video similarity evaluation. The dataset has been released in https://tencent-mvse.github.io/.

Video captioning is a challenging task since it requires generating sentences describing various diverse and complex videos. Existing video captioning models lack adequate visual representation due to the neglect of the existence of gaps between videos and texts. To bridge this gap, in this paper, we propose a CLIP4Caption framework that improves video captioning based on a CLIP-enhanced video-text matching network (VTM). This framework is taking full advantage of the information from both vision and language and enforcing the model to learn strongly text-correlated video features for text generation. Besides, unlike most existing models using LSTM or GRU as the sentence decoder, we adopt a Transformer structured decoder network to effectively learn the long-range visual and language dependency. Additionally, we introduce a novel ensemble strategy for captioning tasks. Experimental results demonstrate the effectiveness of our method on two datasets: 1) on MSR-VTT dataset, our method achieved a new state-of-the-art result with a significant gain of up to 10% in CIDEr; 2) on the private test data, our method ranking 2nd place in the ACM MM multimedia grand challenge 2021: Pre-training for Video Understanding Challenge. It is noted that our model is only trained on the MSR-VTT dataset.