93 accepted papers
Diffusion Transformers (DiTs) excel at generation, but their global self-attention makes controllable, reference-image-based editing a distinct challenge. Unlike U-Nets, naively injecting local appearance into a DiT can disrupt its holistic scene structure. We address this by proposing the first tra…
Expressive performance rendering (EPR) and automatic piano transcription (APT) are fundamental yet inverse tasks in music information retrieval: EPR generates expressive performances from symbolic scores, while APT recovers scores from performances. Despite their dual nature, prior work has addresse…
Large Language Models (LLMs) exhibit impressive capabilities, but remain susceptible to a growing spectrum of safety risks, including jailbreaks, toxic content, hallucinations, and bias. Existing defenses often address only a single threat type or resort to rigid outright rejection, sacrificing user
Although Vision Language Models (VLMs) exhibit strong perceptual abilities and impressive visual reasoning, they struggle with attention to detail and precise action planning in complex, dynamic environments, leading to subpar performance. Real-world tasks typically require complex interactions, adv
Universal grasping with multi-fingered dexterous hands is a fundamental challenge in robotic manipulation. While recent approaches successfully learn closed-loop grasping policies using reinforcement learning (RL), the inherent difficulty of high-dimensional, long-horizon exploration necessitates co…
Robot imitation learning is often hindered by the high cost of collecting large-scale, real-world data. This challenge is especially significant for low-cost robots designed for home use, as they must be both user-friendly and affordable. To address this, we propose the EasyMimic framework, a lowcos…
Open cross-domain federated graph learning facilitates collaborative learning among clients from distinct graph domains while preserving privacy. However, severe structure and feature heterogeneity in open scenarios exacerbates the multiplicative amplification of structural and feature noises within
Next-token prediction serves as the foundational learning task that enables reasoning in LLMs. But what should the learning task be when aiming to equip MLLMs with temporal reasoning capabilities over video inputs? Existing tasks such as video captioning primarily promote modality alignment, while v…
Despite progress, Vision-Language-Action models (VLAs) are limited by a scarcity of large-scale, diverse robot data. While human manipulation videos offer a rich alternative, existing methods are forced to choose between small, precisely-labeled datasets and vast in-the-wild footage with unreliable
Modern foundation models such as large language models (LLMs) require a massive amount of computational and memory resources. We propose a new framework to convert such LLMs into a reduced-dimension latent structure. Our method extends a local activation-aware tensor decomposition to a global attent
While Key-Value (KV) cache succeeds in reducing redundant computations in auto-regressive models, it introduces significant memory overhead, limiting its practical deployment in long-sequence scenarios. Existing KV retrieval methods attempt to mitigate this by dynamically retaining only a subset of…
Recent advancements in Large Language Models have increasingly demonstrated their potential for event reasoning. However, LLMs still struggle with this task due to inadequate modeling of event structures. Although introducing schema knowledge has been shown to improve event reasoning performance, ex
Vision-Language-Action (VLA) models provide a promising paradigm for robot learning by integrating visual perception with language-guided policy learning. However, most existing approaches rely on 2D visual inputs to perform actions in 3D physical environments, creating a significant gap between per
Token-level adaptive computation seeks to reduce inference cost by allocating more computation to harder tokens and less to easier ones. However, prior work is primarily evaluated on natural-language benchmarks using task-level metrics, where token-level difficulty is unobservable and confounded wit…
Existing Vision-Language-Action (VLA) models struggle with complex manipulation tasks requiring high dexterity and generalization, primarily due to their reliance on synthetic data with significant sim-to-real gaps or limited teleoperated demonstrations. To address this bottleneck, we propose levera…
Image Aesthetic Assessment (IAA) predicts an image’s overall aesthetic score, yet aesthetic is influenced by multiple attributes whose relative importance varies with image content and usage scenarios. Under end-to-end training with only overall-score supervision, attribute signals are blended, whic…
Dialogue agents powered by Large Language Models (LLMs) show superior performance in various tasks. Despite the better user understanding and human-like responses, their **lack of controllability** remains a key challenge, often leading to unfocused conversations or task failure. To address this, we…
Prompt learning has demonstrated promising results in fine-tuning pre-trained multimodal models. However, the performance improvement is limited when applied to more complex and fine-grained tasks. The reason is that most existing methods directly optimize the parameters involved in the prompt gener…
Graph-based social recommendation (SR) models suffer from various noises of the social graphs, hindering their recommendation performances. Either graph-level redundancy or graph-level missing will indeed influence the social graph structures, further influencing the message propagation procedure of…
Fine-tuning large language models on private data for downstream applications poses significant privacy risks in potentially exposing sensitive information. Several popular community platforms now offer convenient distribution of a large variety of pre-trained models, allowing anyone to publish with…
Controlling the spatial and semantic structure of diffusion-generated images remains a challenge. Existing methods like ControlNet rely on handcrafted condition maps and retraining, limiting flexibility and generalization. Inversion-based approaches offer stronger alignment but incur high inference…
Fine-tuning foundation models has emerged as a powerful approach for generating objects with specific desired properties. Reinforcement learning (RL) provides an effective framework for this purpose, enabling models to generate outputs that maximize a given reward function. However, in many applicat…
Among various temporal knowledge graph (TKG) extrapolation methods, rule-based approaches stand out for their explicit rules and transparent reasoning paths. However, the vast search space for rule extraction poses a challenge in identifying high-quality logic rules. To navigate this challenge, we e…
Prior approaches to lead instrument detection primarily analyze mixture audio, limited to coarse classifications and lacking generalization ability. This paper presents a novel approach to lead instrument detection in multitrack music audio by crafting expertly annotated datasets and designing a nov…
Textbook reading has long dominated classical poetry education in Chinese-speaking communities. However, research has shown that extensive text-based learning can lead to learner disengagement and a less pleasant experience. This paper aims to improve the experience of classical Chinese poetry learn
When completing knowledge-intensive tasks, humans sometimes need an answer and a corresponding reference passage for auxiliary reading. Previous methods required obtaining pre-segmented article chunks through additional retrieval models. This paper explores leveraging the parameterized knowledge sto…
Human motion generation involves synthesizing coherent human motion sequences conditioned on diverse multimodal inputs and holds significant potential for real-world applications. Despite recent advancements, existing vision-language-motion models (VLMMs) remain limited in achieving this goal. In th…
Open-world knowledge graph completion (KGC) aims to infer novel facts by enriching existing graphs with external knowledge sources while maintaining semantic consistency under the open-world assumption (OWA). Generation-based KGC methods leverage the inherent strengths of large language models (LLMs
To address the deficiencies in chart types and the limited scope of chart tasks in existing datasets, we conducted a comprehensive review of current data collection methodologies. By integrating manual annotation with data generation leveraging GPT-4, we developed a dataset that includes 21 diverse…
In this paper, we introduce OmniStyle-1M, a large-scale paired style transfer dataset comprising over one million content-style-stylized image triplets across 1,000 diverse style categories, each enhanced with textual descriptions and instruction prompts. We show that OmniStyle-1M can not only impro…
Large language models (LLMs) pose significant risks due to the potential for generating harmful content or users attempting to evade guardrails. Existing studies have developed LLM-based guard models designed to moderate the input and output of threat LLMs, ensuring adherence to safety policies by b…
Hand-eye calibration is an important task in vision-guided robotic systems and is crucial for determining the transformation matrix between the camera coordinate system and the robot end-effector. Existing methods, for multi-view robotic systems, usually rely on accurate geometric models or manual a
Current singing voice synthesis systems often struggle in multi-singer scenarios due to limited training data that only includes a few singers. Existing zero-shot multi-singer singing voice synthesis systems are criticized for their reliance on global timbre embeddings from single reference audio, w…
Inspired by the recent success of LLMs, the field of human motion understanding has increasingly shifted toward developing large motion models. Despite some progress, current efforts remain far from achieving truly generalist models, primarily due to the lack of massive high-quality data. To address…
Style transfer enables the seamless integration of artistic styles from a style image into a content image, resulting in visually striking and aesthetically enriched outputs. Despite numerous advances in this field, existing methods did not explicitly focus on the signature style, which represents…
Temporal Video Grounding (TVG), the task of locating specific video segments based on language queries, is a core challenge in long-form video understanding. While recent Large Vision-Language Models (LVLMs) have shown early promise in tackling TVG through supervised fine-tuning (SFT), their ability…
We present a unified framework for automatic multitrack music arrangement that enables a single pre-trained symbolic music model to handle diverse arrangement scenarios, including reinterpretation, simplification, and additive generation. At its core is a segment-level reconstruction objective opera…
Auto-regressive language Models (LMs) assign significant attention to the first token, even if it is not semantically important, which is known as **attention sink**. This phenomenon has been widely adopted in applications such as streaming/long context generation, KV cache optimization, inference a…
The goal of document-level relation extraction (RE) is to identify relations between entities that span multiple sentences. Recently, incomplete labeling in document-level RE has received increasing attention, and some studies have used methods such as positive-unlabeled learning to tackle this issu…
Temporal knowledge graph (TKG) reasoning has two settings: interpolation reasoning and extrapolation reasoning. Both of them draw plenty of research interest and have great significance. Methods of the former de-emphasize the temporal correlations among facts sequences, while methods of the latter r…
Language Language Models (LLMs) face safety concerns due to potential misuse by malicious users. Recent red-teaming efforts have identified adversarial suffixes capable of jailbreaking LLMs using the gradient-based search algorithm Greedy Coordinate Gradient (GCG). However, GCG struggles with comput…
Acoustic foundation models, fine-tuned for Automatic Speech Recognition (ASR), suffer from performance degradation in wild acoustic test settings when deployed in real-world scenarios. Stabilizing online Test-Time Adaptation (TTA) under these conditions remains an open and unexplored question. Exist…
A multimodal large language model (MLLM) agent can receive instructions, capture images, retrieve histories from memory, and decide which tools to use. Nonetheless, red-teaming efforts have revealed that adversarial images/prompts can jailbreak an MLLM and cause unaligned behaviors. In this work, we…
Traditional applications of natural language processing (NLP) in healthcare have predominantly focused on patient-centered services, enhancing patient interactions and care delivery, such as through medical dialogue systems. However, the potential of NLP to benefit inexperienced doctors, particularl…
Piano audio-to-score transcription (A2S) is an important yet underexplored task with extensive applications for music composition, practice, and analysis. However, existing end-to-end piano A2S systems faced difficulties in retrieving bar-level information such as key and time signatures, and have b…
In the realm of cross-network tasks, graph domain adaptation is an effective tool due to its ability to transfer abundant labels from nodes in the source domain to those in the target domain. Existing adversarial domain adaptation methods mainly focus on domain-wise alignment. These approaches, whil…
The emergence of various medical large language models (LLMs) in the medical domain has highlighted the need for unified evaluation standards, as manual evaluation of LLMs proves to be time-consuming and labor-intensive. To address this issue, we introduce MedBench, a comprehensive benchmark for the…
Transformer-based methods have gone mainstream in multimodal sequential learning. The intra and inter modality interactions are captured by the query-key associations of multi-head attention. In this way, the calculated multimodal contexts (attentional results) are expected to be relevant to the que…
In the realm of music AI, arranging rich and structured multi-track accompaniments from a simple lead sheet presents significant challenges. Such challenges include maintaining track cohesion, ensuring long-term coherence, and optimizing computational efficiency. In this paper, we introduce a novel…
Text-conditioned image-to-video generation (TI2V) aims to synthesize a realistic video starting from a given image (e.g. a woman's photo) and a text description (e.g. "a woman is drinking water."). Existing TI2V frameworks often require costly training on video-text datasets and specific model desig…
Temporal knowledge graph extrapolation has become a prominent area of study interest in recent years. Numerous methods for extrapolation have been put forth, mining query-relevant information from history to generate forecasts. However, existing approaches normally do not discriminate between causal…
Extrapolation reasoning on Temporal Knowledge Graphs (TKGs) aims to predict future events from a set of historical Knowledge Graphs (KGs) in a chronological order. The temporally adjacent facts in TKGs naturally form event sequences, implying informative temporal event dependencies. Recently, many e…
"In this paper, we propose UniCode, a novel approach within the domain of multimodal large language models (MLLMs) that learns a unified codebook to efficiently tokenize visual, text, and potentially other types of signals. This innovation addresses a critical limitation in existing MLLMs: their rel…
Explaining the singability of lyrics is an important but missing ability of language models (LMs) in song lyrics generation. This ability allows songwriters to quickly assess if LM-generated lyrics can be sung harmoniously with melodies and helps singers align lyrics with melodies during practice. T…
Network traffic classification is important for network security and management. State-of-the-art classifiers use deep learning techniques to automatically extract feature vectors from the traffic, which however lose important context of the communication sessions and encapsulated text semantics. In…
Aspect-based sentiment analysis (ABSA) aims to align aspects and corresponding sentiment expressions, so as to identify the sentiment polarities of specific aspects. Most existing ABSA methods focus on mining syntactic or semantic information, which still suffers from noisy interference introduced b…
Visual temporal-aligned translation aims to transform the visual sequence into natural words, including important applicable tasks such as lipreading and fingerspelling recognition. However, various performance habits of specific words by different speakers or signers can lead to visual ambiguity, w…
Current video captioning efforts most focus on describing a single video while the need for captioning videos in groups has increased considerably. In this study, we propose a new task, group video captioning, which aims to infer the desired content among a group of target videos and describe it wit…
Traditional federated learning (FL) algorithms, such as FedAvg, fail to handle non-i.i.d data because they learn a global model by simply averaging biased local models that are trained on non-i.i.d local data, therefore failing to model the global data distribution. In this paper, we present a nove…
Key information extraction (KIE) from scanned documents has gained increasing attention because of its applications in various domains. Although promising results have been achieved by some recent KIE approaches, they are usually built based on discriminative models, which lack the ability to handle…
Multi-task learning (MTL) has emerged as a promising approach for sharing inductive bias across multiple tasks to enable more efficient learning in text classification. However, training all tasks simultaneously often yields degraded performance of each task than learning them independently, since d…
Multi-media communications facilitate global interaction among people. However, despite researchers exploring cross-lingual translation techniques such as machine translation and audio speech translation to overcome language barriers, there is still a shortage of cross-lingual studies on visual spee…
Phonation modes play a vital role in voice quality evaluation and vocal health diagnosis. Existing studies on phonation modes cover feature analysis and classification of vowels, which does not apply to real-life scenarios. In this paper, we define the phonation mode detection (PMD) problem, which e…
Music rearrangement is a common music practice of reconstructing and reconceptualizing a piece using new composition or instrumentation styles, which is also an important task of automatic music generation. Existing studies typically model the mapping from a source piece to a target piece via superv…
Visual segmentation from language queries has attracted significant research interest. Despite the effectiveness, existing works require expensive labeling and suffer severe degradation when deployed to an unseen domain. In this paper, we investigate a novel task Cross-domain Query-based Visual Segm…
The development of general-domain neural machine translation (NMT) methods has advanced significantly in recent years, but the lack of naturalness and musical constraints in the outputs makes them unable to produce singable lyric translations. This paper bridges the singability quality gap by formal…
Conditional generative models typically demand large annotated training sets to achieve high-quality synthesis. As a result, there has been significant interest in designing models that perform plug-and-play generation, i.e., to use a predefined or pretrained model, which is not explicitly trained o…
Audio-visual text generation aims to understand multi-modality contents and translate them into texts. Although various transfer learning techniques of text generation have been proposed, they focused on uni-modal analysis (e.g. text-to-text, visual-to-text) and lack consideration of multi-modal con…
Large Language models (LLMs) possess the capability to engage In-context Learning (ICL) by leveraging a few demonstrations pertaining to a new downstream task as conditions. However, this particular learning paradigm suffers from high instability stemming from substantial variances induced by factor…
The task of spoken video grounding aims to localize moments in videos that are relevant to descriptive spoken queries. However, extracting semantic information from speech and modeling the cross-modal correlation pose two critical challenges. Previous studies solve them by representing spoken querie…
We leverage standards-compliant beam training measurements from commercial-of-the-shelf (COTS) 802.11ad/ay devices for localization of a moving object. Two technical challenges need to be addressed: (1) the beam training measurements are intermittent due to beam scanning overhead control and content…
Document-level relation extraction (RE) aims to identify relations between entities across multiple sentences. Most previous methods focused on document-level RE under full supervision. However, in real-world scenario, it is expensive and difficult to completely label all relations in a document bec…
Domain adaptation (DA) aims to transfer the knowledge of a well-labeled source domain to facilitate unlabeled target learning. When turning to specific tasks such as indoor (Wi-Fi) localization, it is essential to learn a cross-domain regressor to mitigate the domain shift. This paper proposes a nov…
Generating shapes using natural language can enable new ways of imagining and creating the things around us. While significant recent progress has been made in text-to-image generation, text-to-shape generation remains a challenging problem due to the unavailability of paired text and shape data at…
Most recent research about automatic music transcription (AMT) uses convolutional neural networks and recurrent neural networks to model the mapping from music signals to symbolic notation. Based on a high-resolution piano transcription system, we explore the possibility of incorporating another pow…
Human intelligence has shown remarkably lower latency and higher precision than most AI systems when processing non-stationary streaming data in real-time. Numerous neuroscience studies suggest that such abilities may be driven by internal predictive modeling. In this paper, we explore the possibili…
Abstractive dialogue summarization has recently been receiving more attention. We propose a coarse-to-fine model for generating abstractive dialogue summaries, and introduce a fact-aware reinforcement learning (RL) objective that improves the fact consistency between the dialogue and the generated s…
Paraphrase generation is a longstanding NLP task and achieves great success with the aid of large corpora. However, transferring a paraphrasing model to another domain encounters the problem of domain shifting especially when the data is sparse. At the same time, widely using large pre-trained langu…
Recent advances in generative adversarial networks (GANs) have led to remarkable achievements in face image synthesis. While methods that use style-based GANs can generate strikingly photorealistic face images, it is often difficult to control the characteristics of the generated faces in a meaningf…
Temporal factors are tied to the growth of facts in realistic applications, such as the progress of diseases and the development of political situation, therefore, research on Temporal Knowledge Graph (TKG) attracks much attention. In TKG, relation patterns inherent with temporality are required to…
Dual-Encoders is a promising mechanism for answer retrieval in question answering (QA) systems. Currently most conventional Dual-Encoders learn the semantic representations of questions and answers merely through matching score. Researchers proposed to introduce the QA interaction features in scorin…
Current generative dialogue systems tend to produce generic dialog responses, which lack useful information and semantic coherence. An promising method to alleviate this problem is to integrate knowledge triples from knowledge base. However, current approaches mainly augment Seq2Seq framework with k…
Perception of time from sequentially acquired sensory inputs is rooted in everyday behaviors of individual organisms. Yet, most algorithms for time-series modeling fail to learn dynamics of random event timings directly from visual or audio inputs, requiring timing annotations during training that a…
This paper presents a domain adaptation model for sound event detection. A common challenge for sound event detection is how to deal with the mismatch among different datasets. Typically, the performance of a model will decrease if it is tested on a dataset which is different from the one that the m…
Lying at the core of human intelligence, relational thinking is characterized by initially relying on innumerable unconscious percepts pertaining to relations between new sensory signals and prior knowledge, consequently becoming a recognizable concept or object through coupling and transformation o…
Modern face alignment methods have become quite accurate at predicting the locations of facial landmarks, but they do not typically estimate the uncertainty of their predicted locations nor predict whether landmarks are visible. In this paper, we present a novel framework for jointly predicting land…
Features that capture textural patterns of a certain class of images are crucial for texture segmentation tasks. This paper introduces a data-centric approach to efficiently extract and represent textural information, which adapts to a wide variety of textures. Based on the strong self-similarities…
Long Short-Term Memory (LSTM) has been proven an efficient way to model sequential data, because of its ability to overcome the gradient diminishing problem during training. However, due to the limited memory capacity in LSTM cells, LSTM is weak in capturing long-time dependency in sequential data.…
Lyrics-to-audio alignment is to automatically align the lyrical words with the mixed singing audio (singing voice+musical accompaniment). Such alignment can be achieved with an automatic speech recognition (ASR) system. We propose to adapt the acoustic model of a speech recognizer towards solo singi…
Acoustic Scene Classification (ASC) is one of the core research problems in the field of Computational Sound Scene Analysis. In this work, we present SubSpectralNet, a novel model which captures discriminative features by incorporating frequency band-level differences to model soundscapes. Using mel…
Household energy monitoring via smart-meters motivates the problem of disaggregating the total energy usage signal into the component energy usage and operating patterns of individual appliances. While energy disaggregation enables useful analytics, it also raises privacy concerns because sensitive…
It is standard to assume a low-dimensional structure in estimating a high-dimensional density. However, popular methods, such as probabilistic principal component analysis, scale poorly computationally. We introduce a novel empirical Bayes method that we term geometric density estimation (GEODE) an…
Learning of low dimensional structure in multidimensional data is a canonical problem in machine learning. One common approach is to suppose that the observed data are close to a lower-dimensional smooth manifold. There are a rich variety of manifold learning methods available, which allow mapping…