Search

Virtual locomotion technique (VLT) is a fundamental component of virtual reality (VR) systems that translates physical and controller inputs into virtual translational movements and viewpoint transitions. Poorly designed VLTs can result in discomfort, nausea, and reductions in task performance. Understanding the effectiveness of VLTs across various levels of interaction fidelity is crucial to enhance user experience and spatial awareness. The current study addressed a significant gap in VR design research and practice, as few previous efforts have been made to comprehensively evaluate the effectiveness of controller-based VLTs in virtual indoor environments. We conducted a user study in which participants navigated through two complex virtual environments, one focusing on exploratory tasks and the other on goal-oriented navigation. The findings offer insights into the trade-offs among spatial knowledge acquisition, wayfinding performance, cybersickness, and sense of presence, and have design implications for future VR interfaces., Comment: The work needs revision and will be updated later

Popularity prediction for information cascades has significant applications across various domains, including opinion monitoring and advertising recommendations. While most existing methods consider this as a discrete problem, popularity actually evolves continuously, exhibiting rich dynamic properties such as change rates and growth patterns. In this paper, we argue that popularity trajectory prediction is more practical, as it aims to forecast the entire trajectory of how popularity unfolds over arbitrary future time. This approach offers insights into both instantaneous popularity and the underlying dynamic properties. However, traditional methods for popularity trajectory prediction primarily rely on specific diffusion mechanism assumptions, which may not align well with real-world dynamics and compromise their performance. To address these limitations, we propose NODEPT, a novel approach based on neural ordinary differential equations (ODEs) for popularity trajectory prediction. NODEPT models the continuous dynamics of the underlying diffusion system using neural ODEs. We first employ an encoder to initialize the latent state representations of information cascades, consisting of two representation learning modules that capture the co-evolution structural characteristics and temporal patterns of cascades from different perspectives. More importantly, we then introduce an ODE-based generative module that learns the dynamics of the diffusion system in the latent space. Finally, a decoder transforms the latent state into the prediction of the future popularity trajectory. Our experimental results on three real-world datasets demonstrate the superiority and rationality of the proposed NODEPT method., Comment: The time complexity analysis in section 4.4 contains error; we overlooked the impact of the memory module

The impressive capabilities of large language models (LLMs) have attracted extensive interests of applying LLMs to medical field. However, the complex nature of clinical environments presents significant hallucination challenges for LLMs, hindering their widespread adoption. In this paper, we address these hallucination issues in the context of Medical Information Extraction (MIE) tasks by introducing ALternate Contrastive Decoding (ALCD). We begin by redefining MIE tasks as an identify-and-classify process. We then separate the identification and classification functions of LLMs by selectively masking the optimization of tokens during fine-tuning. During the inference stage, we alternately contrast output distributions derived from sub-task models. This approach aims to selectively enhance the identification and classification capabilities while minimizing the influence of other inherent abilities in LLMs. Additionally, we propose an alternate adaptive constraint strategy to more effectively adjust the scale and scope of contrastive tokens. Through comprehensive experiments on two different backbones and six diverse medical information extraction tasks, ALCD demonstrates significant improvements in resolving hallucination issues compared to conventional decoding methods., Comment: Accepted by EMNLP 2024 Findings

Instructional documents are rich sources of knowledge for completing various tasks, yet their unique challenges in conversational question answering (CQA) have not been thoroughly explored. Existing benchmarks have primarily focused on basic factual question-answering from single narrative documents, making them inadequate for assessing a model`s ability to comprehend complex real-world instructional documents and provide accurate step-by-step guidance in daily life. To bridge this gap, we present InsCoQA, a novel benchmark tailored for evaluating large language models (LLMs) in the context of CQA with instructional documents. Sourced from extensive, encyclopedia-style instructional content, InsCoQA assesses models on their ability to retrieve, interpret, and accurately summarize procedural guidance from multiple documents, reflecting the intricate and multi-faceted nature of real-world instructional tasks. Additionally, to comprehensively assess state-of-the-art LLMs on the InsCoQA benchmark, we propose InsEval, an LLM-assisted evaluator that measures the integrity and accuracy of generated responses and procedural instructions.

Reinforcement Learning (RL) has the potential to enable extreme off-road mobility by circumventing complex kinodynamic modeling, planning, and control by simulated end-to-end trial-and-error learning experiences. However, most RL methods are sample-inefficient when training in a large amount of manually designed simulation environments and struggle at generalizing to the real world. To address these issues, we introduce Verti-Selector (VS), an automatic curriculum learning framework designed to enhance learning efficiency and generalization by selectively sampling training terrain. VS prioritizes vertically challenging terrain with higher Temporal Difference (TD) errors when revisited, thereby allowing robots to learn at the edge of their evolving capabilities. By dynamically adjusting the sampling focus, VS significantly boosts sample efficiency and generalization within the VW-Chrono simulator built on the Chrono multi-physics engine. Furthermore, we provide simulation and physical results using VS on a Verti-4-Wheeler platform. These results demonstrate that VS can achieve 23.08% improvement in terms of success rate by efficiently sampling during training and robustly generalizing to the real world.

The prosperity of social media platforms has raised the urgent demand for semantic-rich services, e.g., event and storyline attribution. However, most existing research focuses on clip-level event understanding, primarily through basic captioning tasks, without analyzing the causes of events across an entire movie. This is a significant challenge, as even advanced multimodal large language models (MLLMs) struggle with extensive multimodal information due to limited context length. To address this issue, we propose a Two-Stage Prefix-Enhanced MLLM (TSPE) approach for event attribution, i.e., connecting associated events with their causal semantics, in movie videos. In the local stage, we introduce an interaction-aware prefix that guides the model to focus on the relevant multimodal information within a single clip, briefly summarizing the single event. Correspondingly, in the global stage, we strengthen the connections between associated events using an inferential knowledge graph, and design an event-aware prefix that directs the model to focus on associated events rather than all preceding clips, resulting in accurate event attribution. Comprehensive evaluations of two real-world datasets demonstrate that our framework outperforms state-of-the-art methods.

The China Jinping underground Laboratory (CJPL) is an excellent location for studying solar, terrestrial, and supernova neutrinos due to its 2400-meter vertical rock overburden. Its unparalleled depth gives an opportunity to investigate the cosmic-ray muons with exceptionally high average energy at $\sim360$ GeV. This paper details a study of muon-related backgrounds based on 1178 days of data collected by the 1-ton prototype neutrino detector used for the Jinping Neutrino Experiment (JNE) since 2017. The apparent effects of detectors' finite size on the measured result are first discussed in detail. The analysis of 493 cosmic-ray muon candidates and $13.6\pm5.7$ cosmogenic neutron candidates, along with a thorough evaluation of detection efficiency and uncertainties, gives a muon flux of $(3.56\pm0.16_{\mathrm{stat.}}\pm0.10_{\mathrm{syst.}})\times10^{-10}~\mathrm{cm}^{-2}\mathrm{s^{-1}}$ and a cosmogenic neutron yield of $(3.37\pm 1.41_{\mathrm{stat.}}\pm 0.31_{\mathrm{sys.}}) \times 10^{-4}~\mathrm{\mu}^{-1} \mathrm{g}^{-1} \mathrm{cm}^{2}$ in LAB-based liquid scintillator.

Self-supervised learning is a powerful approach for developing traversability models for off-road navigation, but these models often struggle with inputs unseen during training. Existing methods utilize techniques like evidential deep learning to quantify model uncertainty, helping to identify and avoid out-of-distribution terrain. However, always avoiding out-of-distribution terrain can be overly conservative, e.g., when novel terrain can be effectively analyzed using a physics-based model. To overcome this challenge, we introduce Physics-Informed Evidential Traversability (PIETRA), a self-supervised learning framework that integrates physics priors directly into the mathematical formulation of evidential neural networks and introduces physics knowledge implicitly through an uncertainty-aware, physics-informed training loss. Our evidential network seamlessly transitions between learned and physics-based predictions for out-of-distribution inputs. Additionally, the physics-informed loss regularizes the learned model, ensuring better alignment with the physics model. Extensive simulations and hardware experiments demonstrate that PIETRA improves both learning accuracy and navigation performance in environments with significant distribution shifts., Comment: Submitted to RA-L. Video: https://youtu.be/OTnNZ96oJRk

Off-road navigation on vertically challenging terrain, involving steep slopes and rugged boulders, presents significant challenges for wheeled robots both at the planning level to achieve smooth collision-free trajectories and at the control level to avoid rolling over or getting stuck. Considering the complex model of wheel-terrain interactions, we develop an end-to-end Reinforcement Learning (RL) system for an autonomous vehicle to learn wheeled mobility through simulated trial-and-error experiences. Using a custom-designed simulator built on the Chrono multi-physics engine, our approach leverages Proximal Policy Optimization (PPO) and a terrain difficulty curriculum to refine a policy based on a reward function to encourage progress towards the goal and penalize excessive roll and pitch angles, which circumvents the need of complex and expensive kinodynamic modeling, planning, and control. Additionally, we present experimental results in the simulator and deploy our approach on a physical Verti-4-Wheeler (V4W) platform, demonstrating that RL can equip conventional wheeled robots with previously unrealized potential of navigating vertically challenging terrain.

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially in long-term, dense video frame streaming scenarios. Although learnable approaches like Q-Former and Perceiver Resampler have been developed to reduce the vision token burden, they overlook the context causally modeled by LLMs (i.e., key-value cache), potentially leading to missed visual cues when addressing user queries. In this paper, we introduce a novel approach to reduce vision compute by leveraging redundant vision tokens "skipping layers" rather than decreasing the number of vision tokens. Our method, VideoLLM-MoD, is inspired by mixture-of-depths LLMs and addresses the challenge of numerous vision tokens in long-term or streaming video. Specifically, for each transformer layer, we learn to skip the computation for a high proportion (e.g., 80\%) of vision tokens, passing them directly to the next layer. This approach significantly enhances model efficiency, achieving approximately \textasciitilde42\% time and \textasciitilde30\% memory savings for the entire training. Moreover, our method reduces the computation in the context and avoid decreasing the vision tokens, thus preserving or even improving performance compared to the vanilla model. We conduct extensive experiments to demonstrate the effectiveness of VideoLLM-MoD, showing its state-of-the-art results on multiple benchmarks, including narration, forecasting, and summarization tasks in COIN, Ego4D, and Ego-Exo4D datasets.

This paper studies the problem of learning Bayesian networks from continuous observational data, generated according to a linear Gaussian structural equation model. We consider an $\ell_0$-penalized maximum likelihood estimator for this problem which is known to have favorable statistical properties but is computationally challenging to solve, especially for medium-sized Bayesian networks. We propose a new coordinate descent algorithm to approximate this estimator and prove several remarkable properties of our procedure: the algorithm converges to a coordinate-wise minimum, and despite the non-convexity of the loss function, as the sample size tends to infinity, the objective value of the coordinate descent solution converges to the optimal objective value of the $\ell_0$-penalized maximum likelihood estimator. Finite-sample statistical consistency guarantees are also established. To the best of our knowledge, our proposal is the first coordinate descent procedure endowed with optimality and statistical guarantees in the context of learning Bayesian networks. Numerical experiments on synthetic and real data demonstrate that our coordinate descent method can obtain near-optimal solutions while being scalable.

Inverter-based volt-var control is studied in this paper. One key issue in DRL-based approaches is the limited measurement deployment in active distribution networks, which leads to problems of a partially observable state and unknown reward. To address those problems, this paper proposes a robust DRL approach with a conservative critic and a surrogate reward. The conservative critic utilizes the quantile regression technology to estimate conservative state-action value function based on the partially observable state, which helps to train a robust policy; the surrogate rewards of power loss and voltage violation are designed that can be calculated from the limited measurements. The proposed approach optimizes the power loss of the whole network and the voltage profile of buses with measurable voltages while indirectly improving the voltage profile of other buses. Extensive simulations verify the effectiveness of the robust DRL approach in different limited measurement conditions, even when only the active power injection of the root bus and less than 10% of bus voltages are measurable.

Objective. Evaluate the feasibility of Virtual Reality (VR) wayfinding training with aging adults, and examine the impact of the training on wayfinding performance. Design. Design involved wayfinding tasks in a study with three groups: active VR training, passive video training, and no training, assigned randomly. The training featured 5 tasks in a digital version of a real building. Post-training assessments had 10 tasks in this building, half familiar from training and half new. The study was double-blinded, with each intervention lasting 10 minutes. Participants. A convenience sample of 49 participants; inclusion criteria: age >58, unfamiliar with the building; exclusion criteria: mobility or vision impairments, history of motion sickness, or medical implants. Outcomes. Time spent and Distance traveled on each wayfinding task with a fixed 10-min limit. Results. Participants in VR group reported moderate usability (63.82, SD=14.55) with respect to the training intervention and high Self Location (3.71, SD=0.94). There were no differences in task performance among the groups in the similar tasks. In the new tasks, compared to the control condition, Time spent on tasks was marginally significantly reduced in the VR group; Distance traveled to finish tasks was also reduced in the VR group, and marginally significantly reduced in the Video training group. No differences were found between VR and Video conditions. No adverse effects were reported during or post intervention. Conclusions. This study provides preliminary evidence that VR training can effectively improve wayfinding performance in older adults with no reported adverse effect.

As an essential resource management problem in network virtualization, virtual network embedding (VNE) aims to allocate the finite resources of physical network to sequentially arriving virtual network requests (VNRs) with different resource demands. Since this is an NP-hard combinatorial optimization problem, many efforts have been made to provide viable solutions. However, most existing approaches have either ignored the admission control of VNRs, which has a potential impact on long-term performances, or not fully exploited the temporal and topological features of the physical network and VNRs. In this paper, we propose a deep Hierarchical Reinforcement Learning approach to learn a joint Admission Control and Resource Allocation policy for VNE, named HRL-ACRA. Specifically, the whole VNE process is decomposed into an upper-level policy for deciding whether to admit the arriving VNR or not and a lower-level policy for allocating resources of the physical network to meet the requirement of VNR through the HRL approach. Considering the proximal policy optimization as the basic training algorithm, we also adopt the average reward method to address the infinite horizon problem of the upper-level agent and design a customized multi-objective intrinsic reward to alleviate the sparse reward issue of the lower-level agent. Moreover, we develop a deep feature-aware graph neural network to capture the features of VNR and physical network and exploit a sequence-to-sequence model to generate embedding actions iteratively. Finally, extensive experiments are conducted in various settings, and show that HRL-ACRA outperforms state-of-the-art baselines in terms of both the acceptance ratio and long-term average revenue. Our code is available at \url{https://github.com/GeminiLight/hrl-acra}., Comment: Accepted by IEEE Transactions on Services Computing (TSC)

Large language models (LLMs) excel in generating coherent text, but they often struggle with context awareness, leading to inaccuracies in tasks requiring faithful adherence to provided information. We introduce FastMem, a novel method designed to enhance instruction fine-tuned LLMs' context awareness through fast memorization of the prompt. FastMem maximizes the likelihood of the prompt before inference by updating only the last Feed-Forward Network (FFN) module. This targeted approach ensures efficient optimization without overfitting, significantly improving the model's ability to comprehend and accurately follow the context. Our experiments demonstrate substantial gains in reading comprehension, text summarization and adherence to output structures. For instance, FastMem improves the accuracy of Llama 3-8B-Inst on the NQ-SWAP dataset from 59.1% to 71.6%, and reduces the output structure failure rate of Qwen 1.5-4B-Chat from 34.9% to 25.5%. Extensive experimental results highlight FastMem's potential to offer a robust solution to enhance the reliability and accuracy of LLMs in various applications. Our code is available at: https://github.com/IAAR-Shanghai/FastMem

Despite the significant progress of large language models (LLMs) in various tasks, they often produce factual errors due to their limited internal knowledge. Retrieval-Augmented Generation (RAG), which enhances LLMs with external knowledge sources, offers a promising solution. However, these methods can be misled by irrelevant paragraphs in retrieved documents. Due to the inherent uncertainty in LLM generation, inputting the entire document may introduce off-topic information, causing the model to deviate from the central topic and affecting the relevance of the generated content. To address these issues, we propose the Retrieve-Plan-Generation (RPG) framework. RPG generates plan tokens to guide subsequent generation in the plan stage. In the answer stage, the model selects relevant fine-grained paragraphs based on the plan and uses them for further answer generation. This plan-answer process is repeated iteratively until completion, enhancing generation relevance by focusing on specific topics. To implement this framework efficiently, we utilize a simple but effective multi-task prompt-tuning method, enabling the existing LLMs to handle both planning and answering. We comprehensively compare RPG with baselines across 5 knowledge-intensive generation tasks, demonstrating the effectiveness of our approach.

With the rising popularity of Transformer-based large language models (LLMs), reducing their high inference costs has become a significant research focus. One effective approach is to compress the long input contexts. Existing methods typically leverage the self-attention mechanism of the LLM itself for context compression. While these methods have achieved notable results, the compression process still involves quadratic time complexity, which limits their applicability. To mitigate this limitation, we propose the In-Context Former (IC-Former). Unlike previous methods, IC-Former does not depend on the target LLMs. Instead, it leverages the cross-attention mechanism and a small number of learnable digest tokens to directly condense information from the contextual word embeddings. This approach significantly reduces inference time, which achieves linear growth in time complexity within the compression range. Experimental results indicate that our method requires only 1/32 of the floating-point operations of the baseline during compression and improves processing speed by 68 to 112 times while achieving over 90% of the baseline performance on evaluation metrics. Overall, our model effectively reduces compression costs and makes real-time compression scenarios feasible., Comment: Accepted by EMNLP2024(Findings)

Last year has witnessed the re-flourishment of tag-aware recommender systems supported by the LLM-enriched tags. Unfortunately, though large efforts have been made, current solutions may fail to describe the diversity and uncertainty inherent in user preferences with only tag-driven profiles. Recently, with the development of geometry-based techniques, e.g., box embedding, diversity of user preferences now could be fully modeled as the range within a box in high dimension space. However, defect still exists as these approaches are incapable of capturing high-order neighbor signals, i.e., semantic-rich multi-hop relations within the user-tag-item tripartite graph, which severely limits the effectiveness of user modeling. To deal with this challenge, in this paper, we propose a novel algorithm, called BoxGNN, to perform the message aggregation via combination of logical operations, thereby incorporating high-order signals. Specifically, we first embed users, items, and tags as hyper-boxes rather than simple points in the representation space, and define two logical operations to facilitate the subsequent process. Next, we perform the message aggregation mechanism via the combination of logical operations, to obtain the corresponding high-order box representations. Finally, we adopt a volume-based learning objective with Gumbel smoothing techniques to refine the representation of boxes. Extensive experiments on two publicly available datasets and one LLM-enhanced e-commerce dataset have validated the superiority of BoxGNN compared with various state-of-the-art baselines. The code is released online

People's social relationships are often manifested through their surroundings, with certain objects or interactions acting as symbols for specific relationships, e.g., wedding rings, roses, hugs, or holding hands. This brings unique challenges to recognizing social relationships, requiring understanding and capturing the essence of these contexts from visual appearances. However, current methods of social relationship understanding rely on the basic classification paradigm of detected persons and objects, which fails to understand the comprehensive context and often overlooks decisive social factors, especially subtle visual cues. To highlight the social-aware context and intricate details, we propose a novel approach that recognizes \textbf{Con}textual \textbf{So}cial \textbf{R}elationships (\textbf{ConSoR}) from a social cognitive perspective. Specifically, to incorporate social-aware semantics, we build a lightweight adapter upon the frozen CLIP to learn social concepts via our novel multi-modal side adapter tuning mechanism. Further, we construct social-aware descriptive language prompts (e.g., scene, activity, objects, emotions) with social relationships for each image, and then compel ConSoR to concentrate more intensively on the decisive visual social factors via visual-linguistic contrasting. Impressively, ConSoR outperforms previous methods with a 12.2\% gain on the People-in-Social-Context (PISC) dataset and a 9.8\% increase on the People-in-Photo-Album (PIPA) benchmark. Furthermore, we observe that ConSoR excels at finding critical visual evidence to reveal social relationships.

This study contributes to the ongoing exploration of methods to enhance the environmental design, cognitive function, and overall wellbeing, primarily focusing on understanding the modulation of human cognitive performance by artificial lighting conditions. In this investigation, participants (N=35) engaged with two distinct architectural contexts, each featuring five different lighting conditions within a virtual environment during specific daytime scenarios. Responding to a series of cognitive memory tests, we measured participant test scores and the corresponding reaction time. The study's findings, particularly in Backward Digit Span Tasks (BDST) and Visual Memory Tasks (VMT), indicate that diverse lighting conditions significantly impacted cognitive performance at different times of the day. Notably, the BDST scores were mainly affected by lighting conditions in the afternoon session, whereas the VMT scores were primarily influenced in the morning sessions. This research offers support for architects and engineers as they develop lighting designs that are sensitive to the cognitive performance of occupants. It highlights the advantages of utilizing VR simulations in the AEC industry to assess the impact of lighting designs on users. Further research can lead to the development of lighting systems that can promote better cognitive function and overall wellbeing.

In the quest for artificial general intelligence, Multi-modal Large Language Models (MLLMs) have emerged as a focal point in recent advancements. However, the predominant focus remains on developing their capabilities in static image understanding. The potential of MLLMs in processing sequential visual data is still insufficiently explored, highlighting the absence of a comprehensive, high-quality assessment of their performance. In this paper, we introduce Video-MME, the first-ever full-spectrum, Multi-Modal Evaluation benchmark of MLLMs in Video analysis. Our work distinguishes from existing benchmarks through four key features: 1) Diversity in video types, spanning 6 primary visual domains with 30 subfields to ensure broad scenario generalizability; 2) Duration in temporal dimension, encompassing both short-, medium-, and long-term videos, ranging from 11 seconds to 1 hour, for robust contextual dynamics; 3) Breadth in data modalities, integrating multi-modal inputs besides video frames, including subtitles and audios, to unveil the all-round capabilities of MLLMs; 4) Quality in annotations, utilizing rigorous manual labeling by expert annotators to facilitate precise and reliable model assessment. 900 videos with a total of 254 hours are manually selected and annotated by repeatedly viewing all the video content, resulting in 2,700 question-answer pairs. With Video-MME, we extensively evaluate various state-of-the-art MLLMs, including GPT-4 series and Gemini 1.5 Pro, as well as open-source image models like InternVL-Chat-V1.5 and video models like LLaVA-NeXT-Video. Our experiments reveal that Gemini 1.5 Pro is the best-performing commercial model, significantly outperforming the open-source models. Our dataset along with these findings underscores the need for further improvements in handling longer sequences and multi-modal data. Project Page: https://video-mme.github.io, Comment: Project Page: https://video-mme.github.io

Large Language Models (LLMs) have demonstrated exceptional text understanding. Existing works explore their application in text embedding tasks. However, there are few works utilizing LLMs to assist multimodal representation tasks. In this work, we investigate the potential of LLMs to enhance multimodal representation in multimodal item-to-item (I2I) recommendations. One feasible method is the transfer of Multimodal Large Language Models (MLLMs) for representation tasks. However, pre-training MLLMs usually requires collecting high-quality, web-scale multimodal data, resulting in complex training procedures and high costs. This leads the community to rely heavily on open-source MLLMs, hindering customized training for representation scenarios. Therefore, we aim to design an end-to-end training method that customizes the integration of any existing LLMs and vision encoders to construct efficient multimodal representation models. Preliminary experiments show that fine-tuned LLMs in this end-to-end method tend to overlook image content. To overcome this challenge, we propose a novel training framework, NoteLLM-2, specifically designed for multimodal representation. We propose two ways to enhance the focus on visual information. The first method is based on the prompt viewpoint, which separates multimodal content into visual content and textual content. NoteLLM-2 adopts the multimodal In-Content Learning method to teach LLMs to focus on both modalities and aggregate key information. The second method is from the model architecture, utilizing a late fusion mechanism to directly fuse visual information into textual information. Extensive experiments have been conducted to validate the effectiveness of our method., Comment: 19 pages, 5 figures

Recent years have witnessed the prosperity of knowledge graph based recommendation system (KGRS), which enriches the representation of users, items, and entities by structural knowledge with striking improvement. Nevertheless, its unaffordable computational cost still limits researchers from exploring more sophisticated models. We observe that the bottleneck for training efficiency arises from the knowledge graph, which is plagued by the well-known issue of knowledge explosion. Recently, some works have attempted to slim the inflated KG via summarization techniques. However, these summarized nodes may ignore the collaborative signals and deviate from the facts that nodes in knowledge graph represent symbolic abstractions of entities from the real-world. To this end, in this paper, we propose a novel approach called KGTrimmer for knowledge graph pruning tailored for recommendation, to remove the unessential nodes while minimizing performance degradation. Specifically, we design an importance evaluator from a dual-view perspective. For the collective view, we embrace the idea of collective intelligence by extracting community consensus based on abundant collaborative signals, i.e. nodes are considered important if they attract attention of numerous users. For the holistic view, we learn a global mask to identify the valueless nodes from their inherent properties or overall popularity. Next, we build an end-to-end importance-aware graph neural network, which injects filtered knowledge to enhance the distillation of valuable user-item collaborative signals. Ultimately, we generate a pruned knowledge graph with lightweight, stable, and robust properties to facilitate the following-up recommendation task. Extensive experiments are conducted on three publicly available datasets to prove the effectiveness and generalization ability of KGTrimmer.

Last year has witnessed the considerable interest of Large Language Models (LLMs) for their potential applications in recommender systems, which may mitigate the persistent issue of data sparsity. Though large efforts have been made for user-item graph augmentation with better graph-based recommendation performance, they may fail to deal with the dynamic graph recommendation task, which involves both structural and temporal graph dynamics with inherent complexity in processing time-evolving data. To bridge this gap, in this paper, we propose a novel framework, called DynLLM, to deal with the dynamic graph recommendation task with LLMs. Specifically, DynLLM harnesses the power of LLMs to generate multi-faceted user profiles based on the rich textual features of historical purchase records, including crowd segments, personal interests, preferred categories, and favored brands, which in turn supplement and enrich the underlying relationships between users and items. Along this line, to fuse the multi-faceted profiles with temporal graph embedding, we engage LLMs to derive corresponding profile embeddings, and further employ a distilled attention mechanism to refine the LLM-generated profile embeddings for alleviating noisy signals, while also assessing and adjusting the relevance of each distilled facet embedding for seamless integration with temporal graph embedding from continuous time dynamic graphs (CTDGs). Extensive experiments on two real e-commerce datasets have validated the superior improvements of DynLLM over a wide range of state-of-the-art baseline methods., Comment: 11 pages, 5 figures

We study the problem of learning directed acyclic graphs from continuous observational data, generated according to a linear Gaussian structural equation model. State-of-the-art structure learning methods for this setting have at least one of the following shortcomings: i) they cannot provide optimality guarantees and can suffer from learning sub-optimal models; ii) they rely on the stringent assumption that the noise is homoscedastic, and hence the underlying model is fully identifiable. We overcome these shortcomings and develop a computationally efficient mixed-integer programming framework for learning medium-sized problems that accounts for arbitrary heteroscedastic noise. We present an early stopping criterion under which we can terminate the branch-and-bound procedure to achieve an asymptotically optimal solution and establish the consistency of this approximate solution. In addition, we show via numerical experiments that our method outperforms state-of-the-art algorithms and is robust to noise heteroscedasticity, whereas the performance of some competing methods deteriorates under strong violations of the identifiability assumption. The software implementation of our method is available as the Python package \emph{micodag}.

People enjoy sharing "notes" including their experiences within online communities. Therefore, recommending notes aligned with user interests has become a crucial task. Existing online methods only input notes into BERT-based models to generate note embeddings for assessing similarity. However, they may underutilize some important cues, e.g., hashtags or categories, which represent the key concepts of notes. Indeed, learning to generate hashtags/categories can potentially enhance note embeddings, both of which compress key note information into limited content. Besides, Large Language Models (LLMs) have significantly outperformed BERT in understanding natural languages. It is promising to introduce LLMs into note recommendation. In this paper, we propose a novel unified framework called NoteLLM, which leverages LLMs to address the item-to-item (I2I) note recommendation. Specifically, we utilize Note Compression Prompt to compress a note into a single special token, and further learn the potentially related notes' embeddings via a contrastive learning approach. Moreover, we use NoteLLM to summarize the note and generate the hashtag/category automatically through instruction tuning. Extensive validations on real scenarios demonstrate the effectiveness of our proposed method compared with the online baseline and show major improvements in the recommendation system of Xiaohongshu., Comment: Published as a WWW'24 full paper

Knowledge graph completion (KGC) is a widely used method to tackle incompleteness in knowledge graphs (KGs) by making predictions for missing links. Description-based KGC leverages pre-trained language models to learn entity and relation representations with their names or descriptions, which shows promising results. However, the performance of description-based KGC is still limited by the quality of text and the incomplete structure, as it lacks sufficient entity descriptions and relies solely on relation names, leading to sub-optimal results. To address this issue, we propose MPIKGC, a general framework to compensate for the deficiency of contextualized knowledge and improve KGC by querying large language models (LLMs) from various perspectives, which involves leveraging the reasoning, explanation, and summarization capabilities of LLMs to expand entity descriptions, understand relations, and extract structures, respectively. We conducted extensive evaluation of the effectiveness and improvement of our framework based on four description-based KGC models and four datasets, for both link prediction and triplet classification tasks., Comment: Accepted by LREC-COLING 2024

Model editing aims to precisely alter the behaviors of large language models (LLMs) in relation to specific knowledge, while leaving unrelated knowledge intact. This approach has proven effective in addressing issues of hallucination and outdated information in LLMs. However, the potential of using model editing to modify knowledge in the medical field remains largely unexplored, even though resolving hallucination is a pressing need in this area. Our observations indicate that current methods face significant challenges in dealing with specialized and complex knowledge in medical domain. Therefore, we propose MedLaSA, a novel Layer-wise Scalable Adapter strategy for medical model editing. MedLaSA harnesses the strengths of both adding extra parameters and locate-then-edit methods for medical model editing. We utilize causal tracing to identify the association of knowledge in neurons across different layers, and generate a corresponding scale set from the association value for each piece of knowledge. Subsequently, we incorporate scalable adapters into the dense layers of LLMs. These adapters are assigned scaling values based on the corresponding specific knowledge, which allows for the adjustment of the adapter's weight and rank. The more similar the content, the more consistent the scale between them. This ensures precise editing of semantically identical knowledge while avoiding impact on unrelated knowledge. To evaluate the editing impact on the behaviours of LLMs, we propose two model editing studies for medical domain: (1) editing factual knowledge for medical specialization and (2) editing the explanatory ability for complex knowledge. We build two novel medical benchmarking datasets and introduce a series of challenging and comprehensive metrics. Extensive experiments on medical LLMs demonstrate the editing efficiency of MedLaSA, without affecting unrelated knowledge., Comment: Accepted by CIKM 2024

Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This method addresses common LLM limitations, including outdated information and the tendency to produce inaccurate "hallucinated" content. However, the evaluation of RAG systems is challenging, as existing benchmarks are limited in scope and diversity. Most of the current benchmarks predominantly assess question-answering applications, overlooking the broader spectrum of situations where RAG could prove advantageous. Moreover, they only evaluate the performance of the LLM component of the RAG pipeline in the experiments, and neglect the influence of the retrieval component and the external knowledge database. To address these issues, this paper constructs a large-scale and more comprehensive benchmark, and evaluates all the components of RAG systems in various RAG application scenarios. Specifically, we have categorized the range of RAG applications into four distinct types-Create, Read, Update, and Delete (CRUD), each representing a unique use case. "Create" refers to scenarios requiring the generation of original, varied content. "Read" involves responding to intricate questions in knowledge-intensive situations. "Update" focuses on revising and rectifying inaccuracies or inconsistencies in pre-existing texts. "Delete" pertains to the task of summarizing extensive texts into more concise forms. For each of these CRUD categories, we have developed comprehensive datasets to evaluate the performance of RAG systems. We also analyze the effects of various components of the RAG system, such as the retriever, the context length, the knowledge base construction, and the LLM. Finally, we provide useful insights for optimizing the RAG technology for different scenarios., Comment: 40 Pages

Information extraction (IE) aims to extract structural knowledge from plain natural language texts. Recently, generative Large Language Models (LLMs) have demonstrated remarkable capabilities in text understanding and generation. As a result, numerous works have been proposed to integrate LLMs for IE tasks based on a generative paradigm. To conduct a comprehensive systematic review and exploration of LLM efforts for IE tasks, in this study, we survey the most recent advancements in this field. We first present an extensive overview by categorizing these works in terms of various IE subtasks and techniques, and then we empirically analyze the most advanced methods and discover the emerging trend of IE tasks with LLMs. Based on a thorough review conducted, we identify several insights in technique and promising research directions that deserve further exploration in future studies. We maintain a public repository and consistently update related works and resources on GitHub (\href{https://github.com/quqxui/Awesome-LLM4IE-Papers}{LLM4IE repository}), Comment: The article has been accepted by Frontiers of Computer Science (FCS), with the DOI: {10.1007/s11704-024-40555-y}. You can cite the FCS version

In the realm of e-commerce search, the significance of semantic matching cannot be overstated, as it directly impacts both user experience and company revenue. Along this line, query rewriting, serving as an important technique to bridge the semantic gaps inherent in the semantic matching process, has attached wide attention from the industry and academia. However, existing query rewriting methods often struggle to effectively optimize long-tail queries and alleviate the phenomenon of "few-recall" caused by semantic gap. In this paper, we present BEQUE, a comprehensive framework that Bridges the sEmantic gap for long-tail QUEries. In detail, BEQUE comprises three stages: multi-instruction supervised fine tuning (SFT), offline feedback, and objective alignment. We first construct a rewriting dataset based on rejection sampling and auxiliary tasks mixing to fine-tune our large language model (LLM) in a supervised fashion. Subsequently, with the well-trained LLM, we employ beam search to generate multiple candidate rewrites, and feed them into Taobao offline system to obtain the partial order. Leveraging the partial order of rewrites, we introduce a contrastive learning method to highlight the distinctions between rewrites, and align the model with the Taobao online objectives. Offline experiments prove the effectiveness of our method in bridging semantic gap. Online A/B tests reveal that our method can significantly boost gross merchandise volume (GMV), number of transaction (#Trans) and unique visitor (UV) for long-tail queries. BEQUE has been deployed on Taobao, one of most popular online shopping platforms in China, since October 2023., Comment: WWW Industry

Hallucination is a big shadow hanging over the rapidly evolving Multimodal Large Language Models (MLLMs), referring to the phenomenon that the generated text is inconsistent with the image content. In order to mitigate hallucinations, existing studies mainly resort to an instruction-tuning manner that requires retraining the models with specific data. In this paper, we pave a different way, introducing a training-free method named Woodpecker. Like a woodpecker heals trees, it picks out and corrects hallucinations from the generated text. Concretely, Woodpecker consists of five stages: key concept extraction, question formulation, visual knowledge validation, visual claim generation, and hallucination correction. Implemented in a post-remedy manner, Woodpecker can easily serve different MLLMs, while being interpretable by accessing intermediate outputs of the five stages. We evaluate Woodpecker both quantitatively and qualitatively and show the huge potential of this new paradigm. On the POPE benchmark, our method obtains a 30.66%/24.33% improvement in accuracy over the baseline MiniGPT-4/mPLUG-Owl. The source code is released at https://github.com/BradyFU/Woodpecker., Comment: 16 pages, 7 figures. Code Website: https://github.com/BradyFU/Woodpecker

The large-scale visual-language pre-trained model, Contrastive Language-Image Pre-training (CLIP), has significantly improved image captioning for scenarios without human-annotated image-caption pairs. Recent advanced CLIP-based image captioning without human annotations follows a text-only training paradigm, i.e., reconstructing text from shared embedding space. Nevertheless, these approaches are limited by the training/inference gap or huge storage requirements for text embeddings. Given that it is trivial to obtain images in the real world, we propose CLIP-guided text GAN (CgT-GAN), which incorporates images into the training process to enable the model to "see" real visual modality. Particularly, we use adversarial training to teach CgT-GAN to mimic the phrases of an external text corpus and CLIP-based reward to provide semantic guidance. The caption generator is jointly rewarded based on the caption naturalness to human language calculated from the GAN's discriminator and the semantic guidance reward computed by the CLIP-based reward module. In addition to the cosine similarity as the semantic guidance reward (i.e., CLIP-cos), we further introduce a novel semantic guidance reward called CLIP-agg, which aligns the generated caption with a weighted text embedding by attentively aggregating the entire corpus. Experimental results on three subtasks (ZS-IC, In-UIC and Cross-UIC) show that CgT-GAN outperforms state-of-the-art methods significantly across all metrics. Code is available at https://github.com/Lihr747/CgtGAN., Comment: Accepted at ACM MM 2023

Over the last half century, the main application of Brain Computer Interfaces, BCIs has been controlling wheelchairs and neural prostheses or generating text or commands for people with restricted mobility. There has been very limited attention in the field to applications for computer aided design, despite the potential of BCIs to provide a new form of environmental interaction. In this paper we introduce the development and application of Neuron, a novel BCI tool that enables designers with little experience in neuroscience or computer programming to gain access to neurological data, along with established metrics relevant to design, create BCI interaction prototypes, both with digital onscreen objects and physical devices, and evaluate designs based on neurological information and record measurements for further analysis. After discussing the BCI tool development, the article presents its capabilities through two case studies, along with a brief evaluation of the tool performance and a discussion of implications, limitations, and future improvement.

This paper presents a novel approach to assessing human lighting adjustment behavior and preference in diverse lighting conditions through the evaluation of emotional feedback and behavioral data using VR. Participants (n= 27) were exposed to different lighting (n=17) conditions with different levels of illuminance and correlated color temperature (CCT) with a randomized order in a virtual office environment. Results from this study significantly advanced our understanding of preferred lighting conditions in virtual reality environments, influenced by a variety of factors such as illuminance, color temperature, order of presentation, and participant demographics. Through a comprehensive analysis of user adjustment profiles, we obtained insightful data that can guide the optimization of lighting design across various settings.

Multimodal entity linking (MEL) task, which aims at resolving ambiguous mentions to a multimodal knowledge graph, has attracted wide attention in recent years. Though large efforts have been made to explore the complementary effect among multiple modalities, however, they may fail to fully absorb the comprehensive expression of abbreviated textual context and implicit visual indication. Even worse, the inevitable noisy data may cause inconsistency of different modalities during the learning process, which severely degenerates the performance. To address the above issues, in this paper, we propose a novel Multi-GraIned Multimodal InteraCtion Network $\textbf{(MIMIC)}$ framework for solving the MEL task. Specifically, the unified inputs of mentions and entities are first encoded by textual/visual encoders separately, to extract global descriptive features and local detailed features. Then, to derive the similarity matching score for each mention-entity pair, we device three interaction units to comprehensively explore the intra-modal interaction and inter-modal fusion among features of entities and mentions. In particular, three modules, namely the Text-based Global-Local interaction Unit (TGLU), Vision-based DuaL interaction Unit (VDLU) and Cross-Modal Fusion-based interaction Unit (CMFU) are designed to capture and integrate the fine-grained representation lying in abbreviated text and implicit visual cues. Afterwards, we introduce a unit-consistency objective function via contrastive learning to avoid inconsistency and model degradation. Experimental results on three public benchmark datasets demonstrate that our solution outperforms various state-of-the-art baselines, and ablation studies verify the effectiveness of designed modules., Comment: Accepted by KDD 2023

Affordance-centric Question-driven Task Completion (AQTC) for Egocentric Assistant introduces a groundbreaking scenario. In this scenario, through learning instructional videos, AI assistants provide users with step-by-step guidance on operating devices. In this paper, we present a solution for enhancing video alignment to improve multi-step inference. Specifically, we first utilize VideoCLIP to generate video-script alignment features. Afterwards, we ground the question-relevant content in instructional videos. Then, we reweight the multimodal context to emphasize prominent features. Finally, we adopt GRU to conduct multi-step inference. Through comprehensive experiments, we demonstrate the effectiveness and superiority of our method, which secured the 2nd place in CVPR'2023 AQTC challenge. Our code is available at https://github.com/zcfinal/LOVEU-CVPR23-AQTC., Comment: 5 pages, 1 figure, technical report for track3 of CVPR 2023 LOVEU challenge

Recently, Multimodal Large Language Model (MLLM) represented by GPT-4V has been a new rising research hotspot, which uses powerful Large Language Models (LLMs) as a brain to perform multimodal tasks. The surprising emergent capabilities of MLLM, such as writing stories based on images and OCR-free math reasoning, are rare in traditional multimodal methods, suggesting a potential path to artificial general intelligence. To this end, both academia and industry have endeavored to develop MLLMs that can compete with or even better than GPT-4V, pushing the limit of research at a surprising speed. In this paper, we aim to trace and summarize the recent progress of MLLMs. First of all, we present the basic formulation of MLLM and delineate its related concepts, including architecture, training strategy and data, as well as evaluation. Then, we introduce research topics about how MLLMs can be extended to support more granularity, modalities, languages, and scenarios. We continue with multimodal hallucination and extended techniques, including Multimodal ICL (M-ICL), Multimodal CoT (M-CoT), and LLM-Aided Visual Reasoning (LAVR). To conclude the paper, we discuss existing challenges and point out promising research directions. In light of the fact that the era of MLLM has only just begun, we will keep updating this survey and hope it can inspire more research. An associated GitHub link collecting the latest papers is available at https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models., Comment: Project page:https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models

Graph Neural Networks (GNNs) have been broadly applied in many urban applications upon formulating a city as an urban graph whose nodes are urban objects like regions or points of interest. Recently, a few enhanced GNN architectures have been developed to tackle heterophily graphs where connected nodes are dissimilar. However, urban graphs usually can be observed to possess a unique spatial heterophily property; that is, the dissimilarity of neighbors at different spatial distances can exhibit great diversity. This property has not been explored, while it often exists. To this end, in this paper, we propose a metric, named Spatial Diversity Score, to quantitatively measure the spatial heterophily and show how it can influence the performance of GNNs. Indeed, our experimental investigation clearly shows that existing heterophilic GNNs are still deficient in handling the urban graph with high spatial diversity score. This, in turn, may degrade their effectiveness in urban applications. Along this line, we propose a Spatial Heterophily Aware Graph Neural Network (SHGNN), to tackle the spatial diversity of heterophily of urban graphs. Based on the key observation that spatially close neighbors on the urban graph present a more similar mode of difference to the central node, we first design a rotation-scaling spatial aggregation module, whose core idea is to properly group the spatially close neighbors and separately process each group with less diversity inside. Then, a heterophily-sensitive spatial interaction module is designed to adaptively capture the commonality and diverse dissimilarity in different spatial groups. Extensive experiments on three real-world urban datasets demonstrate the superiority of our SHGNN over several its competitors., Comment: Accepted by KDD 2023

Finding multiple temporal relationships among locations can benefit a bunch of urban applications, such as dynamic offline advertising and smart public transport planning. While some efforts have been made on finding static relationships among locations, little attention is focused on studying time-aware location relationships. Indeed, abundant location-based human activities are time-varying and the availability of these data enables a new paradigm for understanding the dynamic relationships in a period among connective locations. To this end, we propose to study a new problem, namely multi-Temporal relationship inference among locations (Trial for short), where the major challenge is how to integrate dynamic and geographical influence under the relationship sparsity constraint. Specifically, we propose a solution to Trial with a graph learning scheme, which includes a spatially evolving graph neural network (SEENet) with two collaborative components: spatially evolving graph convolution module (SEConv) and spatially evolving self-supervised learning strategy (SE-SSL). SEConv performs the intra-time aggregation and inter-time propagation to capture the multifaceted spatially evolving contexts from the view of location message passing. In addition, SE-SSL designs time-aware self-supervised learning tasks in a global-local manner with additional evolving constraint to enhance the location representation learning and further handle the relationship sparsity. Finally, experiments on four real-world datasets demonstrate the superiority of our method over several state-of-the-art approaches., Comment: Accepted by KDD 2023. Code and data: https://github.com/agave233/SEENet