In modern large language models (LLMs), increasing sequence lengths is a crucial challenge for enhancing their comprehension and coherence in handling complex tasks such as multi-modal question answering. However, handling long context sequences with LLMs is prohibitively costly due to the conventional attention mechanism's quadratic time and space complexity, and the context window size is limited by the GPU memory. Although recent works have proposed linear and sparse attention mechanisms to address this issue, their real-world applicability is often limited by the need to re-train pre-trained models. In response, we propose a novel approach, Hierarchically Pruned Attention (HiP), which simultaneously reduces the training and inference time complexity from $O(T^2)$ to $O(T \log T)$ and the space complexity from $O(T^2)$ to $O(T)$. To this end, we devise a dynamic sparse attention mechanism that generates an attention mask through a novel tree-search-like algorithm for a given query on the fly. HiP is training-free as it only utilizes the pre-trained attention scores to spot the positions of the top-$k$ most significant elements for each query. Moreover, it ensures that no token is overlooked, unlike the sliding window-based sub-quadratic attention methods, such as StreamingLLM. Extensive experiments on diverse real-world benchmarks demonstrate that HiP significantly reduces prompt (i.e., prefill) and decoding latency and memory usage while maintaining high generation performance with little or no degradation. As HiP allows pretrained LLMs to scale to millions of tokens on commodity GPUs with no additional engineering due to its easy plug-and-play deployment, we believe that our work will have a large practical impact, opening up the possibility to many long-context LLM applications previously infeasible.

Recently, Multimodal Large Language Models (MLLMs) have shown great promise in language-guided perceptual tasks such as recognition, segmentation, and object detection. However, their effectiveness in addressing visual cognition problems that require high-level reasoning is not well-established. One such challenge is abstract visual reasoning (AVR) - the cognitive ability to discern relationships among patterns in a set of images and extrapolate to predict subsequent patterns. This skill is crucial during the early neurodevelopmental stages of children. Inspired by the AVR tasks in Raven's Progressive Matrices (RPM) and Wechsler Intelligence Scale for Children (WISC), we propose a new dataset MaRs-VQA and a new benchmark VCog-Bench containing three datasets to evaluate the zero-shot AVR capability of MLLMs and compare their performance with existing human intelligent investigation. Our comparative experiments with different open-source and closed-source MLLMs on the VCog-Bench revealed a gap between MLLMs and human intelligence, highlighting the visual cognitive limitations of current MLLMs. We believe that the public release of VCog-Bench, consisting of MaRs-VQA, and the inference pipeline will drive progress toward the next generation of MLLMs with human-like visual cognition abilities. The code and datasets for our benchmark are at GitHub.com/IrohXu/VCog-Bench

Generative models have demonstrated human-level proficiency in various benchmarks across domains like programming, natural sciences, and general knowledge. Despite these promising results on competitive benchmarks, they still struggle with seemingly simple problem-solving tasks typically carried out by elementary-level students. How do state-of-the-art models perform on standardized tests designed to assess computational thinking and problem-solving skills at schools? In this paper, we curate a novel benchmark involving computational thinking tests grounded in elementary visual programming domains. Our initial results show that state-of-the-art models like GPT-4o and Llama3 barely match the performance of an average school student. To further boost the performance of these models, we fine-tune them using a novel synthetic data generation methodology. The key idea is to develop a comprehensive dataset using symbolic methods that capture different skill levels, ranging from recognition of visual elements to multi-choice quizzes to synthesis-style tasks. We showcase how various aspects of symbolic information in synthetic data help improve fine-tuned models' performance. We will release the full implementation and datasets to facilitate further research on enhancing computational thinking in generative models.

State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, particularly for LiDAR. Instead, recent works demonstrate that self-supervised pre-training with unlabeled data can improve detection accuracy with limited labels. Contemporary methods adapt best-practices for self-supervised learning from the image domain to point clouds (such as contrastive learning). However, publicly available 3D datasets are considerably smaller and less diverse than those used for image-based self-supervised learning, limiting their effectiveness. We do note, however, that such data is naturally collected in a multimodal fashion, often paired with images. Rather than pre-training with only self-supervised objectives, we argue that it is better to bootstrap point cloud representations using image-based foundation models trained on internet-scale image data. Specifically, we propose a shelf-supervised approach (e.g. supervised with off-the-shelf image foundation models) for generating zero-shot 3D bounding boxes from paired RGB and LiDAR data. Pre-training 3D detectors with such pseudo-labels yields significantly better semi-supervised detection accuracy than prior self-supervised pretext tasks. Importantly, we show that image-based shelf-supervision is helpful for training LiDAR-only and multi-modal (RGB + LiDAR) detectors. We demonstrate the effectiveness of our approach on nuScenes and WOD, significantly improving over prior work in limited data settings.

Large vision-language models (VLMs) have demonstrated remarkable abilities in understanding everyday content. However, their performance in the domain of art, particularly culturally rich art forms, remains less explored. As a pearl of human wisdom and creativity, art encapsulates complex cultural narratives and symbolism. In this paper, we offer the Pun Rebus Art Dataset, a multimodal dataset for art understanding deeply rooted in traditional Chinese culture. We focus on three primary tasks: identifying salient visual elements, matching elements with their symbolic meanings, and explanations for the conveyed messages. Our evaluation reveals that state-of-the-art VLMs struggle with these tasks, often providing biased and hallucinated explanations and showing limited improvement through in-context learning. By releasing the Pun Rebus Art Dataset, we aim to facilitate the development of VLMs that can better understand and interpret culturally specific content, promoting greater inclusiveness beyond English-based corpora.

There is a growing interest in utilizing large-scale language models (LLMs) to advance next-generation Recommender Systems (RecSys), driven by their outstanding language understanding and in-context learning capabilities. In this scenario, tokenizing (i.e., indexing) users and items becomes essential for ensuring a seamless alignment of LLMs with recommendations. While several studies have made progress in representing users and items through textual contents or latent representations, challenges remain in efficiently capturing high-order collaborative knowledge into discrete tokens that are compatible with LLMs. Additionally, the majority of existing tokenization approaches often face difficulties in generalizing effectively to new/unseen users or items that were not in the training corpus. To address these challenges, we propose a novel framework called TokenRec, which introduces not only an effective ID tokenization strategy but also an efficient retrieval paradigm for LLM-based recommendations. Specifically, our tokenization strategy, Masked Vector-Quantized (MQ) Tokenizer, involves quantizing the masked user/item representations learned from collaborative filtering into discrete tokens, thus achieving a smooth incorporation of high-order collaborative knowledge and a generalizable tokenization of users and items for LLM-based RecSys. Meanwhile, our generative retrieval paradigm is designed to efficiently recommend top-$K$ items for users to eliminate the need for the time-consuming auto-regressive decoding and beam search processes used by LLMs, thus significantly reducing inference time. Comprehensive experiments validate the effectiveness of the proposed methods, demonstrating that TokenRec outperforms competitive benchmarks, including both traditional recommender systems and emerging LLM-based recommender systems.

Large Language Models (LLMs) have an increasing impact on our lives with use cases such as chatbots, study support, coding support, ideation, writing assistance, and more. Previous studies have revealed linguistic biases in pronouns used to describe professions or adjectives used to describe men vs women. These issues have to some degree been addressed in updated LLM versions, at least to pass existing tests. However, biases may still be present in the models, and repeated use of gender stereotypical language may reinforce the underlying assumptions and are therefore important to examine further. This paper investigates gender biases in LLMs in relation to educational choices through an open-ended, true to user-case experimental design and a quantitative analysis. We investigate the biases in the context of four different cultures, languages, and educational systems (English/US/UK, Danish/DK, Catalan/ES, and Hindi/IN) for ages ranging from 10 to 16 years, corresponding to important educational transition points in the different countries. We find that there are significant and large differences in the ratio of STEM to non-STEM suggested education paths provided by chatGPT when using typical girl vs boy names to prompt lists of suggested things to become. There are generally fewer STEM suggestions in the Danish, Spanish, and Indian context compared to the English. We also find subtle differences in the suggested professions, which we categorise and report.

Large Language Models (LLMs) excel in natural language tasks but face limitations due to static training datasets, resulting in outdated or contextually shallow responses. Retrieval-Augmented Generation (RAG) addresses this by integrating real-time external knowledge, enhancing model accuracy and credibility, especially for knowledge-intensive tasks. However, RAG-enhanced LLMs struggle with long contexts, causing them to "choke" on information overload, compromising response quality. Recent RAG applications use hierarchical data structures for storing documents, organized at various levels of summarization and information density. In this context, we introduce HIRO (Hierarchical Information Retrieval Optimization), a novel querying approach for RAG applications using hierarchical structures for storing documents. HIRO employs DFS-based recursive similarity score calculation and branch pruning to minimize the context returned to the LLM without informational loss. HIRO outperforms existing querying mechanisms on the NarrativeQA dataset by an absolute performance gain of 10.85%.

General large language models enhanced with supervised fine-tuning and reinforcement learning from human feedback are increasingly popular in academia and industry as they generalize foundation models to various practical tasks in a prompt manner. To assist users in selecting the best model in practical application scenarios, i.e., choosing the model that meets the application requirements while minimizing cost, we introduce A-Eval, an application-driven LLMs evaluation benchmark for general large language models. First, we categorize evaluation tasks into five main categories and 27 sub-categories from a practical application perspective. Next, we construct a dataset comprising 678 question-and-answer pairs through a process of collecting, annotating, and reviewing. Then, we design an objective and effective evaluation method and evaluate a series of LLMs of different scales on A-Eval. Finally, we reveal interesting laws regarding model scale and task difficulty level and propose a feasible method for selecting the best model. Through A-Eval, we provide clear empirical and engineer guidance for selecting the best model, reducing barriers to selecting and using LLMs and promoting their application and development. Our benchmark is publicly available at https://github.com/UnicomAI/DataSet/tree/main/TestData/GeneralAbility.

Large Language Models (LLMs) can become outdated over time as they may lack updated world knowledge, leading to factual knowledge errors and gaps. Knowledge Editing (KE) aims to overcome this challenge using weight updates that do not require expensive retraining. We propose treating KE as an LLM alignment problem. Toward this goal, we introduce Knowledge Direct Preference Optimization (KDPO), a variation of the Direct Preference Optimization (DPO) that is more effective for knowledge modifications. Our method is based on an online approach that continually updates the knowledge stored in the model. We use the current knowledge as a negative sample and the new knowledge we want to introduce as a positive sample in a process called DPO. We also use teacher-forcing for negative sample generation and optimize using the positive sample, which helps maintain localized changes. We tested our KE method on various datasets and models, comparing it to several cutting-edge methods, with 100 and 500 sequential edits. Additionally, we conducted an ablation study comparing our method to the standard DPO approach. Our experimental results show that our modified DPO method allows for more refined KE, achieving similar or better performance compared to previous methods.