With the continuous emergence of various social media platforms frequently used in daily life, the multimodal meme understanding (MMU) task has been garnering increasing attention. MMU aims to explore and comprehend the meanings of memes from various perspectives by performing tasks such as metaphor recognition, sentiment analysis, intention detection, and offensiveness detection. Despite making progress, limitations persist due to the loss of fine-grained metaphorical visual clue and the neglect of multimodal text-image weak correlation. To overcome these limitations, we propose a multi-granular multimodal clue fusion model (MGMCF) to advance MMU. Firstly, we design an object-level semantic mining module to extract object-level image feature clues, achieving fine-grained feature clue extraction and enhancing the model's ability to capture metaphorical details and semantics. Secondly, we propose a brand-new global-local cross-modal interaction model to address the weak correlation between text and images. This model facilitates effective interaction between global multimodal contextual clues and local unimodal feature clues, strengthening their representations through a bidirectional cross-modal attention mechanism. Finally, we devise a dual-semantic guided training strategy to enhance the model's understanding and alignment of multimodal representations in the semantic space. Experiments conducted on the widely-used MET-MEME bilingual dataset demonstrate significant improvements over state-of-the-art baselines. Specifically, there is an 8.14% increase in precision for offensiveness detection task, and respective accuracy enhancements of 3.53%, 3.89%, and 3.52% for metaphor recognition, sentiment analysis, and intention detection tasks. These results, underpinned by in-depth analyses, underscore the effectiveness and potential of our approach for advancing MMU.

The current generation of large language models (LLMs) is typically designed for broad, general-purpose applications, while domain-specific LLMs, especially in vertical fields like medicine, remain relatively scarce. In particular, the development of highly efficient and practical LLMs for the medical domain is challenging due to the complexity of medical knowledge and the limited availability of high-quality data. To bridge this gap, we introduce Baichuan-M1, a series of large language models specifically optimized for medical applications. Unlike traditional approaches that simply continue pretraining on existing models or apply post-training to a general base model, Baichuan-M1 is trained from scratch with a dedicated focus on enhancing medical capabilities. Our model is trained on 20 trillion tokens and incorporates a range of effective training methods that strike a balance between general capabilities and medical expertise. As a result, Baichuan-M1 not only performs strongly across general domains such as mathematics and coding but also excels in specialized medical fields. We have open-sourced Baichuan-M1-14B, a mini version of our model, which can be accessed through the following links.

We introduce Baichuan-Omni-1.5, an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities. To achieve fluent and high-quality interaction across modalities without compromising the capabilities of any modality, we prioritized optimizing three key aspects. First, we establish a comprehensive data cleaning and synthesis pipeline for multimodal data, obtaining about 500B high-quality data (text, audio, and vision). Second, an audio-tokenizer (Baichuan-Audio-Tokenizer) has been designed to capture both semantic and acoustic information from audio, enabling seamless integration and enhanced compatibility with MLLM. Lastly, we designed a multi-stage training strategy that progressively integrates multimodal alignment and multitask fine-tuning, ensuring effective synergy across all modalities. Baichuan-Omni-1.5 leads contemporary models (including GPT4o-mini and MiniCPM-o 2.6) in terms of comprehensive omni-modal capabilities. Notably, it achieves results comparable to leading models such as Qwen2-VL-72B across various multimodal medical benchmarks.

We introduce Baichuan Alignment, a detailed analysis of the alignment techniques employed in the Baichuan series of models. This represents the industry's first comprehensive account of alignment methodologies, offering valuable insights for advancing AI research. We investigate the critical components that enhance model performance during the alignment process, including optimization methods, data strategies, capability enhancements, and evaluation processes. The process spans three key stages: Prompt Augmentation System(PAS), Supervised Fine-Tuning(SFT), and Preference Alignment. The problems encountered, the solutions applied, and the improvements made are thoroughly recorded. Through comparisons across well-established benchmarks, we highlight the technological advancements enabled by Baichuan Alignment. Baichuan-Instruct is an internal model, while Qwen2-Nova-72B and Llama3-PBM-Nova-70B are instruct versions of the Qwen2-72B and Llama-3-70B base models, optimized through Baichuan Alignment. Baichuan-Instruct demonstrates significant improvements in core capabilities, with user experience gains ranging from 17% to 28%, and performs exceptionally well on specialized benchmarks. In open-source benchmark evaluations, both Qwen2-Nova-72B and Llama3-PBM-Nova-70B consistently outperform their respective official instruct versions across nearly all datasets. This report aims to clarify the key technologies behind the alignment process, fostering a deeper understanding within the community. Llama3-PBM-Nova-70B model is available at https://huggingface.co/PKU-Baichuan-MLSystemLab/Llama3-PBM-Nova-70B.

Multimodal information extraction (IE) tasks have attracted increasing attention because many studies have shown that multimodal information benefits text information extraction. However, existing multimodal IE datasets mainly focus on sentence-level image-facilitated IE in English text, and pay little attention to video-based multimodal IE and fine-grained visual grounding. Therefore, in order to promote the development of multimodal IE, we constructed a multimodal multilingual multitask dataset, named M$^{3}$D, which has the following features: (1) It contains paired document-level text and video to enrich multimodal information; (2) It supports two widely-used languages, namely English and Chinese; (3) It includes more multimodal IE tasks such as entity recognition, entity chain extraction, relation extraction and visual grounding. In addition, our dataset introduces an unexplored theme, i.e., biography, enriching the domains of multimodal IE resources. To establish a benchmark for our dataset, we propose an innovative hierarchical multimodal IE model. This model effectively leverages and integrates multimodal information through a Denoised Feature Fusion Module (DFFM). Furthermore, in non-ideal scenarios, modal information is often incomplete. Thus, we designed a Missing Modality Construction Module (MMCM) to alleviate the issues caused by missing modalities. Our model achieved an average performance of 53.80% and 53.77% on four tasks in English and Chinese datasets, respectively, which set a reasonable standard for subsequent research. In addition, we conducted more analytical experiments to verify the effectiveness of our proposed module. We believe that our work can promote the development of the field of multimodal IE.

In the endeavor to make autonomous robots take actions, task planning is a major challenge that requires translating high-level task descriptions into long-horizon action sequences. Despite recent advances in language model agents, they remain prone to planning errors and limited in their ability to plan ahead. To address these limitations in robotic planning, we advocate a self-refining scheme that iteratively refines a draft plan until an equilibrium is reached. Remarkably, this process can be optimized end-to-end from an analytical perspective without the need to curate additional verifiers or reward models, allowing us to train self-refining planners in a simple supervised learning fashion. Meanwhile, a nested equilibrium sequence modeling procedure is devised for efficient closed-loop planning that incorporates useful feedback from the environment (or an internal world model). Our method is evaluated on the VirtualHome-Env benchmark, showing advanced performance with better scaling for inference computation. Based on their extensive world knowledge, LLM agents seem close to autonomously performing robotic tasks, such as in household scenarios. However, growing evidence shows that existing LLM agents struggle with task planning (Kaelbling & Lozano-Pérez, 2011) that decomposes a high-level task into mid-level actions. While this problem requires long-horizon planning as well as consideration of environmental feedback, LLMs are often limited by: (1) unidirectional dependency: due to autoregressive generation, previous tokens cannot attend to future tokens, resulting in limited ability to plan ahead (Wu et al., 2024a); (2) lack of error correction for existing outputs, unless with a heavy system 2; (3) fixed forward process hindering the allocation of more inference computation to further improve planning performance. These inherent limitations of LLMs lead to inefficiency in the closed-loop long-horizon robotic planning. To address above challenges of LLM planners in closed-loop long-horizon planning, we advocate the approach of self-refinement (Welleck et al., 2023; Shinn et al., 2023; Kim et al., 2023; Madaan et al., 2023) that iteratively improves a previously generated plan. The reasons behind are threefold: (1) bidirectional dependency: since the output is conditioned on a previous draft plan, it can attend to all tokens in the plan (from an old version), thus improving its ability to plan ahead; (2) internal error correction which allows implicit self-correction in a forward pass without an explicit, heavy system 2; (3) dynamic computation allocation by iterating through a self-refinement process until convergence.

Abstract: Non-negative Matrix Factorization (NMF) algorithm can only be used to find low rank approximation of original non-negative data while Concept Factorization (CF) algorithm extends matrix factorization to single non-linear kernel space, improving learning ability and adaptability of matrix factorization. In unsupervised environment, to design or select proper kernel function for specific dataset, a new algorithm called Globalized Multiple Kernel CF (GMKCF) was proposed. Multiple candidate kernel functions were input in the same time and learned in the CF framework based on global linear fusion, obtaining a clustering result with high quality and stability and solving the problem of kernel function selection that the CF faced. The convergence of the proposed algorithm was verified by solving the model with alternate iteration. The experimental results on several real databases show that the proposed algorithm outperforms comparison algorithms in data clustering, such as Kernel K-Means (KKM), Spectral Clustering (SC), Kernel CF (KCF), Co-regularized multi-view spectral clustering (Coreg), and Robust Multiple KKM (RMKKM).

Fine-grained sentiment analysis involves extracting and organizing sentiment elements from textual data. However, existing approaches often overlook issues of category semantic inclusion and overlap, as well as inherent structural patterns within the target sequence. This study introduces a generative sentiment analysis model. To address the challenges related to category semantic inclusion and overlap, a latent category distribution variable is introduced. By reconstructing the input of a variational autoencoder, the model learns the intensity of the relationship between categories and text, thereby improving sequence generation. Additionally, a trie data structure and constrained decoding strategy are utilized to exploit structural patterns, which in turn reduces the search space and regularizes the generation process. Experimental results on the Restaurant-ACOS and Laptop-ACOS datasets demonstrate a significant performance improvement compared to baseline models. Ablation experiments further confirm the effectiveness of latent category distribution and constrained decoding strategy.

Structured Sentiment Analysis (SSA) was cast as a problem of bi-lexical dependency graph parsing by prior studies. Multiple formulations have been proposed to construct the graph, which share several intrinsic drawbacks: (1) The internal structures of spans are neglected, thus only the boundary tokens of spans are used for relation prediction and span recognition, thus hindering the model's expressiveness; (2) Long spans occupy a significant proportion in the SSA datasets, which further exacerbates the problem of internal structure neglect. In this paper, we treat the SSA task as a dependency parsing task on partially-observed dependency trees, regarding flat spans without determined tree annotations as latent subtrees to consider internal structures of spans. We propose a two-stage parsing method and leverage TreeCRFs with a novel constrained inside algorithm to model latent structures explicitly, which also takes advantages of joint scoring graph arcs and headed spans for global optimization and inference. Results of extensive experiments on five benchmark datasets reveal that our method performs significantly better than all previous bi-lexical methods, achieving new state-of-the-art.

Existing cross-document event coreference resolution models, which either compute mention similarity directly or enhance mention representation by extracting event arguments (such as location, time, agent, and patient), lacking the ability to utilize document-level information. As a result, they struggle to capture long-distance dependencies. This shortcoming leads to their underwhelming performance in determining coreference for the events where their argument information relies on long-distance dependencies. In light of these limitations, we propose the construction of document-level Rhetorical Structure Theory (RST) trees and cross-document Lexical Chains to model the structural and semantic information of documents. Subsequently, cross-document heterogeneous graphs are constructed and GAT is utilized to learn the representations of events. Finally, a pair scorer calculates the similarity between each pair of events and co-referred events can be recognized using standard clustering algorithm. Additionally, as the existing cross-document event coreference datasets are limited to English, we have developed a large-scale Chinese cross-document event coreference dataset to fill this gap, which comprises 53,066 event mentions and 4,476 clusters. After applying our model on the English and Chinese datasets respectively, it outperforms all baselines by large margins.