Large Vision-Language Model (LVLM) has enhanced the performance of various downstream tasks in visual-language understanding. Most existing approaches encode images and videos into separate feature spaces, which are then fed as inputs to large language models. However, due to the lack of unified tokenization for images and videos, namely misalignment before projection, it becomes challenging for a Large Language Model (LLM) to learn multi-modal interactions from several poor projection layers.In this work, we unify visual representation into the language feature space to advance the foundational LLM towards a unified LVLM. As a result, we establish a simple but robust LVLM baseline, Video-LLaVA, which learns from a mixed dataset of images and videos, mutually enhancing each other.As a result, Video-LLaVA outperforms Video-ChatGPT by 5.8%, 9.9%, 18.6%, and 10.1% on MSRVTT, MSVD, TGIF, and ActivityNet, respectively. Additionally, our Video-LLaVA also achieves superior performances on a broad range of 9 image benchmarks.Notably, extensive experiments demonstrate that Video-LLaVA mutually benefits images and videos within a unified visual representation, outperforming models designed specifically for images or videos. We aim for this work to provide modest insights into the multi-modal inputs for the LLM.

Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. To date, most of the state-of-the-art TVR methods learn image-to-video transfer learning based on the large-scale pre-trained vision-language models (e.g., CLIP). However, fully fine-tuning these pre-trained models for TVR incurs prohibitively expensive computation cost. To this end, we propose to conduct efficient text-video Retrieval with a salient-and-correlated AdaPter (RAP), i.e., fine-tuning the pre-trained model with a few parameterized layers. To accommodate the text-video scenario, we equip our RAP with two indispensable characteristics including temporal sparsity and correlation. Specifically, we propose a low-rank modulation module to refine the per-image features from frozen CLIP backbone, which accentuates silent frames within the video features while alleviating temporal redundancy. Besides, we introduce an asynchronous self-attention mechanism which firstly selects top responsive visual patch and augments the correlation modeling between them with learnable temporal and patch offsets. Extensive experiments on four TVR datasets demonstrate that our RAP achieves superior or comparable performance compared to the fully fine-tuned counterpart and other parameter-efficient finetuning methods.

Temporal knowledge graph reasoning has emerged as a crucial task for answering time-dependent questions within a knowledge graph (KG).Despite tremendous progress, the present research is impeded by the sparsity of a temporal KG and an over-reliance on simple single-relational reasoning patterns. To overcome these challenges, we introduce MulQuestions, a new temporal KG reasoning benchmark featuring over 200k entities and 960k questions designed to facilitate complex, multi-relational and multi-hop reasoning. Additionally, we propose a new model adept at conducting pattern-aware and time-sensitive reasoning across temporal KGs. The model’s efficacy is confirmed through rigorous evaluations, showcasing its effectiveness in sparse data conditions and adeptness at handling questions with long reasoning chains. We have made our benchmark and model publicly accessible at [https://anonymous].

Long-context Multimodal Large Language Models (MLLMs) demand substantial computational resources for inference as the growth of their multimodal Key-Value (KV) cache, in response to increasing input lengths, challenges memory and time efficiency. Unlike single-modality LLMs that manage only textual contexts, the KV cache of long-context MLLMs includes representations from multiple images with temporal and spatial relationships and related textual contexts. The predominance of image tokens means traditional optimizations for LLMs’ KV caches are unsuitable for multimodal long-context settings, and no prior works have addressed this challenge.In this work, we introduce **LOOK-M**, a pioneering, fine-tuning-free approach that efficiently reduces the multimodal KV cache size while maintaining performance comparable to a full cache. We observe that during prompt prefill, the model prioritizes more textual attention over image features, and based on the multimodal interaction observation, a new proposed text-prior method is explored to compress the KV cache. Furthermore, to mitigate the degradation of image contextual information, we propose several compensatory strategies using KV pairs merging. **LOOK-M** demonstrates that with a significant reduction in KV Cache memory usage, such as reducing it by **80%** in some cases, it not only achieves approximately **1.3x** faster decoding but also maintains or even **enhances** performance across a variety of long context multimodal tasks.

This paper describes our system that participated in the SemEval-2020 task 4: Commonsense Validation and Explanation. For this task, it is obvious that external knowledge, such as Knowledge graph, can help the model understand commonsense in natural language statements. But how to select the right triples for statements remains unsolved, so how to reduce the interference of irrelevant triples on model performance is a research focus. This paper adopt a modified K-BERT as the language encoder, to enhance language representation through triples from knowledge graphs. Experiments show that our method is better than models without external knowledge, and is slightly better than the original K-BERT. We got an accuracy score of 0.97 in subtaskA, ranking 1/45, and got an accuracy score of 0.948, ranking 2/35.

Cross-lingual topic detection within text is a feasible solution to resolving the language barrier in accessing the information. This paper presents a Chinese-English cross-lingual topic corpus (CLTC), in which 90,000 Chinese articles and 90,000 English articles are organized within 150 topics. Compared with TDT corpora, CLTC has three advantages. First, CLTC is bigger in size. This makes it possible to evaluate the large-scale cross-lingual text clustering methods. Second, articles are evenly distributed within the topics. Thus it can be used to produce test datasets for different purposes. Third, CLTC can be used as a cross-lingual comparable corpus to develop methods for cross-lingual information access. A preliminary evaluation with CLTC corpus indicates that the corpus is effective in evaluating cross-lingual topic detection methods.