108 accepted papers
Graph-based attention deficit hyperactivity disorder (ADHD) detection methods have been extensively studied, but comparatively less attention has been paid to short-term brain functional reorganization. In this paper, we propose an ADHD disease detection model based on short- and long-term brain fun…
Diffusion-based language models (dLLMs) have emerged as a promising alternative to traditional autoregressive LLMs by enabling parallel token generation and significantly reducing inference latency. However, existing sampling strategies for dLLMs, such as confidence-based or semi-autoregressive deco…
Inferring cellular trajectories from destructive snapshots is complicated by the challenges of stochasticity and non-conservative mass dynamics such as cell proliferation and apoptosis. Existing unbalanced Optimal Transport (OT) methods treat mass as a continuous fluid, performing inference at the p…
Drag-Based Image Editing (DBIE), which allows users to manipulate images by directly dragging objects within them, has recently attracted much attention from the community. However, it faces two key challenges: (i) point-based drag is often highly ambiguous and difficult to align with user intention
We present DuPO, a dual learning-based preference optimization framework that generates annotation-free feedback via the generalized duality. DuPO addresses two key limitations: Reinforcement Learning with Verifiable Rewards (RLVR)’s reliance on costly labels and applicability restricted to verifiab…
Existing humanoid control systems often rely on teleoperation or modular generation pipelines that separate language understanding from physical execution. However, the former is entirely human-driven, and the latter lacks tight alignment between language commands and physical behaviors. In this pap
Human interaction is inherently multimodal and full-duplex: we listen while watching, speak while acting, and fluidly adapt to turn-taking and interruptions. Realizing these capabilities is essential for building models simulating humans. We present ELLSA (End-to-end Listen, Look, Speak and Act), wh…
Machine unlearning, which aims to efficiently remove the influence of specific data from trained models, is crucial for upholding data privacy regulations like the ``right to be forgotten". However, existing research predominantly evaluates unlearning methods on relatively balanced forget sets. This…
Diffusion policies are a powerful paradigm for robot learning, but their training is often inefficient. A key reason is that networks must relearn fundamental spatial concepts, such as translations and rotations, from scratch for every new task. To alleviate this redundancy, we propose embedding geo…
Geometry-preserving dimension reduction is critical for single-cell transcriptomics, where low-dimensional distances should reflect biological divergence between cell types along the transcriptomic manifold. Due to inadequate metrics, the global structure is not sufficiently preserved in the low-dim…
This paper pays attention to open-vocabulary 3D object affordance grounding (OVAG), which aims to localize affordance regions on 3D objects by leveraging interaction images or textual instructions. Most existing methods treat interaction images as sources of external affordance knowledge and align t…
Cooperative 3D perception via Vehicle-to-Everything communication is a promising paradigm for enhancing autonomous driving, offering extended sensing horizons and occlusion resolution. However, the practical deployment of existing methods is hindered at long distances by two critical bottlenecks: th
The latest progress in text-to-3D generative models makes it possible to generate high-quality 3D content. Recent text-to-3D large model have achieved remarkable breakthroughs in multi-view consistency. However, their effectiveness is often affected by inherent biases, resulting in sensitivity to de
Passive models for long video understanding typically rely on a ``watch-it-all'' paradigm, processing data uniformly regardless of query difficulty, causing input complexity to scale linearly with video duration. Although interactive frameworks have emerged, they often rely on global pre-scanning, f…
In this paper, we aim to create physical digital twins of deformable objects under interaction. Existing methods focus more on the physical learning of current state modeling, but generalize worse to future prediction. This is because existing methods ignore the intrinsic physical properties of defo
Fine-grained perception of multimodal information is critical for advancing human–AI interaction. With recent progress in audio–visual technologies, Omni Language Models (OLMs), capable of processing audio and video signals in parallel, have emerged as a promising paradigm for achieving richer unde…
Recent advances in multimodal large language models (MLLMs) have demonstrated substantial potential in video understanding. However, existing benchmarks fail to comprehensively evaluate synergistic reasoning capabilities across audio and visual modalities, often neglecting either one of the modaliti…
Generating high-quality physically based rendering (PBR) materials is important to achieve realistic rendering in the downstream tasks, yet it remains challenging due to the intertwined effects of materials and lighting. While existing methods have made breakthroughs by incorporating material decomp
Speech-to-Speech (S2S) models have shown promising dialogue capabilities, but their ability to handle paralinguistic cues—such as emotion, tone, and speaker attributes—and to respond appropriately in both content and style remains underexplored. Progress is further hindered by the scarcity of high-q…
Personalizing 3D scenes from a single reference image enables intuitive user-guided editing, which requires achieving both multi-view consistency across perspectives and referential consistency with the input image. However, these goals are particularly challenging due to the viewpoint bias caused b
3D Gaussian Splatting (3DGS) has demonstrated impressive Novel View Synthesis (NVS) results in a real-time rendering manner. During training, it relies heavily on the average magnitude of view-space positional gradients to grow Gaussians to reduce rendering loss. However, this average operation smoo
Diffusion policy has shown impressive performance in robotic manipulation tasks while struggling with out-of-distribution shifts and limited demonstrations. Recent advances primarily focus on improving geometric or perceptual representations for diffusion policy. However, these approaches rely heavi
Safety-critical scenarios are central to evaluating autonomous driving systems, yet their rarity in naturalistic logs makes simulation-based stress testing indispensable. Most scenario generation methods treat surrounding agents as adversaries, but they either (i) induce failures without explicitly …
Evaluating LLM forecasting capabilities is constrained by a fundamental tension: prospective evaluation offers methodological rigor but prohibitive latency, while retrospective forecasting (RF)—evaluating on already-resolved events—faces rapidly shrinking clean evaluation data as SOTA models possess
Segment Anything Model (SAM)-based approaches have shown strong potential for biomedical image segmentation. However, these methods often struggle to preserve spatial consistency in 3D electron microscopy (3D-EM) data and still require extensive manual annotation. We propose Spatial-SAM, a spatially
Multimodal time series forecasting has garnered significant attention for its potential to provide more robust and accurate predictions than traditional single-modality models by leveraging rich information inherent in other modalities. However, due to fundamental challenges in modality alignment, e…
Carotid ultrasound is crucial for the assessment of cerebrovascular health, particularly the internal carotid artery (ICA). While previous research has explored automating carotid ultrasound, none has tackled the challenging ICA. This is primarily due to its deep location, tortuous course, and signi…
Impedance-based control represents a prevalent strategy in the powered transfemoral prostheses because of its ability to reproduce natural walking. However, most existing studies have developed impedance-based prosthesis controllers for specific tasks, while creating a task-adaptive controller for v
Recognizing human actions under low illumination is challenging due to the limited high-quality data and weak recognition backbones. To this end, we propose Modality Fusion Dark-to-Light (MFDL), a two-stage framework to simultaneously enhance the invisibility of poorly-lit videos and strengthen reco…
Determining the direction of relationships between variables is fundamental for understanding complex systems across scientific domains. While observational data can uncover relationships between variables, it cannot distinguish between cause and effect without experimental interventions. To effecti…
LLM-based text-to-speech(TTS) system has becoming the new trend and SOTA due to its high naturalness and zero-shot capability. However, it relies heavily on training data, usually requires at least thousands hours of labeled audio. In this report, we describe how to use pretrained CosyVoice model, t…
The reality gap between simulation and real-world dynamics critically hinders the deployment of robust humanoid locomotion policies, as policies trained in a single simulator often overfit to domain-specific dynamics. To address this challenge, we propose CROSSER (Inverse Dynamics-Guided Cross-Simul
Despite the rapid development of Chinese vision-language models (VLMs), most existing Chinese vision-language (VL) datasets are constructed on Western-centric images from existing English VL datasets. The cultural bias in the images makes these datasets unsuitable for evaluating VLMs in Chinese cult…
Several recent studies have attempted to autoregressively generate continuous speech representations without discrete speech tokens by combining diffusion and autoregressive models, yet they often face challenges with excessive computational loads or suboptimal outcomes. In this work, we propose Dif…
Image generation has achieved remarkable progress with the development of large-scale text-to-image models, especially diffusion-based models. However, generating human images with plausible details, such as faces or hands, remains challenging due to insufficient supervision of local regions during…
Traditional speaker verification system aims at distinguish speaker identity in real world audio, and has achieved satisfying performance in many scenarios. However, it is also very vulnerable, and can be easily attacked by voice anonymization system. In this report, we describe how to fast adapt a…
Multi-modal multi-party conversation (MMC) is a less studied yet important topic of research due to that it well fits real-world scenarios and thus potentially has more widely-used applications. Compared with the traditional multi-modal conversations, MMC requires stronger character-centered underst…
Achieving general agile whole-body control on humanoid robots remains a major challenge due to diverse motion demands and data conflicts. While existing frameworks excel in training single motion-specific policies, they struggle to generalize across highly varied behaviors due to conflicting control…
Large Language Models (LLMs) demonstrate human-level or even superior language abilities, effectively modeling syntactic structures, yet the specific computational units responsible remain unclear. A key question is whether LLM behavioral capabilities stem from mechanisms akin to those in the human…
Dialogue serves as the most natural manner of human-computer interaction (HCI). Recent advancements in speech language models (SLM), have significantly enhanced speech-based conversational AI. However, these models are limited to turn-based conversation, lacking the ability to interact with humans i…
Large language models (LLMs) are equipped with increasingly extended context windows recently, yet their long context understanding capabilities over long dependency tasks remain fundamentally limited and underexplored. This gap is especially significant in many real-world long-context applications…
We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1,000 meticulously curated audio-question-answer triplets, collected from real-world internet videos and refined through ite…
Accurate temporal prediction is the bridge between comprehensive scene understanding and embodied artificial intelligence. However, predicting multiple fine-grained states of scene at multiple temporal scales is difficult for vision-language models. We formalize the Multi‐Scale Temporal Prediction (…
Triangle meshes are fundamental to 3D applications. Current automatic mesh generation methods typically rely on intermediate representations that lack the continuous surface quality inherent to meshes. Converting these representations into meshes produces dense, suboptimal outputs. Although recent a…
The rapid advancement of multi-modal language models (MLLMs) like GPT-4o has propelled the development of Omni language models, designed to process and proactively respond to continuous streams of multi-modal data. Despite their potential, evaluating their real-world interactive capabilities in stre…
This paper explores a novel perspective to speech quality assessment by leveraging natural language descriptions, offering richer, more nuanced insights than traditional numerical scoring methods. Natural language feedback provides instructive recommendations and detailed evaluations, yet existing d…
This paper pays attention to Weakly Supervised Affordance Grounding (WSAG) task that aims to train model to identify affordance regions using human-object interaction images and egocentric images without the need for costly pixel-level annotations. Most existing methods usually consider the affordan…
In order to enable fluid and natural human-machine speech interaction, existing full-duplex conversational systems often adopt modular architectures with auxiliary components such as voice activity detectors, interrupters, conversation state predictors, or multiple LLMs. These systems, however, suff…
Generative models have shown significant achievements in audio generation tasks. However, existing models struggle with complex and detailed prompts, leading to potential performance degradation. We hypothesize that this problem stems from the simplicity and scarcity of the training data. This work…
Generating accurate sounds for complex audio-visual scenes is challenging, especially in the presence of multiple objects and sound sources. In this paper, we propose an interactive object-aware audio generation model that grounds sound generation in user-selected visual objects within images. Our m…
Generating ultra-long sequences with large language models (LLMs) has become increasingly crucial but remains a highly time-intensive task, particularly for sequences up to 100K tokens. While traditional speculative decoding methods exist, simply extending their generation limits fails to accelerate…
Recent advancements in large audio language models (LALMs) have demonstrated impressive results and promising prospects in universal understanding and reasoning across speech, music, and general sound. However, these models still lack the ability to recognize their knowledge boundaries and refuse to…
As an important direction of embodied intelligence, 3D Visual Grounding has attracted much attention, aiming to identify 3D objects matching the given language description. Most existing methods often follow a two-stage process, i.e., first detecting proposal objects and identifying the right object…
Recent researches on video large language models (VideoLLM) predominantly focus on model architectures and training datasets, leaving the interaction format between the user and the model under-explored. In existing works, users often interact with VideoLLMs by using the entire video and a query as
Recent advancements in large-scale video-language models have shown significant potential for real-time planning and detailed interactions. However, their high computational demands and the scarcity of annotated datasets limit their practicality for academic researchers. In this work, we introduce V…
To promote the deployment of scenario understanding in the real world, Open-Vocabulary Scene Graph Generation (OV-SGG) has attracted much attention recently, aiming to generalize beyond the limited number of relation categories labeled during training and detect those unseen relations during inferen…
The Latin square completion (LSC) problem aims to assign n symbols to the empty cells of a partially filled Latin square such that in each row and each column, each symbol appears exactly once. In this paper, we propose a swap relaxation-based fast local search algorithm called SRLS for solving the…
The front-end is a critical component of English text-to-speech (TTS) systems, responsible for extracting linguistic features that are essential for a text-to-speech model to synthesize speech, such as prosodies and phonemes. The English TTS front-end typically consists of a text normalization (TN)…
Universal sound separation (USS) is a task to separate arbitrary sounds from an audio mixture. Existing USS systems are capable of separating arbitrary sources, given a few examples of the target sources as queries. However, separating arbitrary sounds with a single system is challenging, and the ro…
This paper presents a study on the design and control of a novel soft-rigid lower limb exoskeleton robot. First, based on anatomy, a novel exoskeleton structure design is proposed that applies Curl Pneumatic Artificial Muscles (CPAMs) to lower limb joints to actuate lower limb movement, and transmit…
Despite progress in multimodal large language models (MLLMs), the challenge of interpreting long-form videos in response to linguistic queries persists, largely due to the inefficiency in temporal grounding and limited pre-trained context window size. In this work, we introduce Temporal Grounding Br…
Environment awareness is crucial for enhancing walking safety and stability of amputee wearing powered prosthesis when crossing uneven terrains such as stairs and obstacles. However, existing environmental perception systems for prosthesis only provide terrain types and corresponding parameters, whi…
Music editing primarily entails the modification of instrument tracks or remixing in the whole, which offers a novel reinterpretation of the original piece through a series of operations. These music processing methods hold immense potential across various applications but demand substantial experti…
Recently, various studies have leveraged Large Language Models (LLMs) to help decision-making and planning in environments and try to align the LLMs’ knowledge with the world conditions. Nonetheless, the capacity of LLMs to continuously acquire environmental knowledge and adapt in an open world rema…
This paper surveys and organizes research works of medical dialog systems, which is an important yet challenging task. Although these systems have been surveyed in the medical community from an application perspective, a systematic review from a rigorous technical perspective has to date remained no…
With the huge success of GPT models in natural language processing, there is a growing interest in applying language modeling approaches to speech tasks. Currently, the dominant architecture in speech-to-speech translation (S2ST) remains the encoder-decoder paradigm, creating a need to investigate t…
Scene Graph Generation (SGG) provides basic language representation of visual scenes, requiring models to grasp complex and diverse semantics between objects. This complexity and diversity in SGG leads to underrepresentation, where parts of triplet labels are rare or even unseen during training, res…
Speech encompasses a wealth of information, including but not limited to content, paralinguistic, and environmental information. This comprehensive nature of speech significantly impacts communication and is crucial for human-computer interaction. Chat-Oriented Large Language Models (LLMs), known fo…
Recently we have witnessed the rapid development of video question answering models. However, most models can only handle simple videos in terms of temporal reasoning, and their performance tends to drop when answering temporal-reasoning questions on long and informative videos. To tackle this prob…
Time series pre-training has recently garnered wide attention for its potential to reduce labeling expenses and benefit various downstream tasks. Prior methods are mainly based on pre-training techniques well-acknowledged in vision or language, such as masked modeling and contrastive learning. Howev…
Deep models have demonstrated remarkable performance in time series forecasting. However, due to the partially-observed nature of real-world applications, solely focusing on the target of interest, so-called endogenous variables, is usually insufficient to guarantee accurate forecasting. Notably, a…
Speech understanding as an element of the more generic video understanding using audio-visual large language models (av-LLMs) is a crucial yet understudied aspect. This paper proposes video-SALMONN, a single end-to-end av-LLM for video processing, which can understand not only visual frame sequences…
Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acoustic, and fine acoustic modelings. Yet, sampling with the MusicLM requires processing through these LMs one by one to obt…
ReLU networks have remained the default choice for models in the area of image prediction despite their well-established spectral bias towards learning low frequencies faster, and consequently their difficulty of reproducing high frequency visual details. As an alternative, sin networks showed promi…
Visual-audio navigation (VAN) is attracting more and more attention from the robotic community due to its broad applications, e.g., household robots and rescue robots. In this task, an embodied agent must search for and navigate to the sound source with egocentric visual and audio observations. Howe
We introduce CDBert, a new learning paradigm that enhances the semantics understanding ability of the Chinese PLMs with dictionary knowledge and structure of Chinese characters. We name the two core modules of CDBert as Shuowen and Jiezi, where Shuowen refers to the process of retrieving the most ap…
Streaming voice conversion (VC) is the task of converting the voice of one person to another in real-time. Previous streaming VC methods use phonetic posteriorgrams (PPGs) extracted from automatic speech recognition (ASR) systems to represent speaker-independent information. However, PPGs lack the p…
VQA is an ambitious task aiming to answer any image-related question. However, in reality, it is hard to build such a system once for all since the needs of users are continuously updated, and the system has to implement new functions. Thus, Continual Learning (CL) ability is a must in developing ad…
Video-grounded dialogue understanding is a challenging problem that requires machine to perceive, parse and reason over situated semantics extracted from weakly aligned video and dialogues. Most existing benchmarks treat both modalities the same as a frame-independent visual understanding task, whil…
"Cognitive science has shown that humans perceive videos in terms of events separated by the state changes of dominant subjects. State changes trigger new events and are one of the most useful among the large amount of redundant information perceived. However, previous research focuses on the overal…
Gait phase-based control is a trending research topic for walking-aid robots, especially robotic lower-limb prostheses. Gait phase estimation is a challenge for gait phase-based control. Previous researches used the integration or the differential of the human's thigh angle to estimate the gait phas
Researchers are currently making progress in unifying the entire gait cycle of powered prostheses by using a human-inspired phase variable, but constructing a robust phase variable to more accurately estimate the gait phase and desired joint trajectories of prostheses during varying walking speeds r
It is still a pipe dream that personal AI assistants on the phone and AR glasses can assist our daily life in addressing our questions like “how to adjust the date for this watch?” and “how to set its heating duration? (while pointing at an oven)”. The queries used in conventional tasks (i.e. Video…
With the increasing popularity of speech synthesis products, the industry has put forward more requirements for personalized speech synthesis: (1) How to use low-resource, easily accessible data to clone a person’s voice. (2) How to clone a person’s voice while controlling the style and prosody. To…
We study video-grounded dialogue generation, where a response is generated based on the dialogue context and the associated video. The primary challenges of this task lie in (1) the difficulty of integrating video data into pre-trained language models (PLMs) which presents obstacles to exploiting th…
Firstly, in the letter [1], there is a missing citation in Section II, part B, the first sentence. It should be “In a manner similar to [2], [3], speed estimation was achieved by a double-pendulum model.” In our previous version [1], speed estimation was based on the principles in [3]. We also refer
Although deep learning and end-to-end models have been widely used and shown their superiority in automatic speech recognition (ASR) and text-to-speech (TTS) synthesis, state-of-the-art forced alignment (FA) models are still based on hidden Markov model (HMM). HMM has limited view of contextual info…
Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all autonomous-driving systems. Existing image- and video-based driving datasets, however, fall short of capturing the mutable nature of the real world. In this paper, we introduce the largest syntheti…
Annotation conversion is an effective way to construct datasets under new annotation guidelines based on existing datasets with little human labour. Previous work has been limited in conversion between tree-structured datasets and mainly focused on feature-based models which are not easily applicabl…
We propose two improvements to target-speaker voice activity detection (TS-VAD), the core component in our proposed speaker diarization system that was submitted to the 2022 Multi-Channel Multi-Party Meeting Transcription (M2MeT) challenge. These techniques are designed to handle multi-speaker conve…
A music mashup combines audio elements from two or more songs to create a new work. To reduce the time and effort required to make them, researchers have developed algorithms that predict the compatibility of audio elements. Prior work has focused on mixing unaltered excerpts, but advances in source…
Dubbing is a post-production process of re-recording actors’ dialogues, which is extensively used in filmmaking and video production. It is usually performed manually by professional voice actors who read lines with proper prosody, and in synchronization with the pre-recorded videos. In this work, w…
Venipuncture is an indispensable procedure for both diagnosis and treatment. In this paper, unlike existing solutions that fully or partially rely on professional assistance, a compact robotic system integrating both novel hardware and software developments is introduced. The hardware consists of a…
This paper presents a novel supervised approach to detecting the chorus segments in popular music. Traditional approaches to this task are mostly unsupervised, with pipelines designed to target some quality that is assumed to define "chorusness," which usually means seeking the loudest or most frequ…
In this paper, we propose a hybrid text normalization system using multi-head self-attention. The system combines the advantages of a rule-based model and a neural model for text preprocessing tasks. Previous studies in Mandarin text normalization usually use a set of hand-written rules, which are h…
In Mandarin text-to-speech (TTS) system, the front-end text processing module significantly influences the intelligibility and naturalness of synthesized speech. Building a typical pipeline-based front-end which consists of multiple individual components requires extensive efforts. In this paper, we…
Source separation is the task of separating an audio recording into individual sound sources. Source separation is fundamental for computational auditory scene analysis. Previous work on source separation has focused on separating particular sound classes such as speech and music. Much previous work…
To leverage crowd-sourced data to train multi-speaker text-to-speech (TTS) models that can synthesize clean speech for all speakers, it is essential to learn disentangled representations which can independently control the speaker identity and background noise in generated signals. However, learning…
This paper proposes a neural end-to-end text-to-speech (TTS) model which can control latent attributes in the generated speech that are rarely annotated in the training data, such as speaking style, accent, background noise, and recording conditions. The model is formulated as a conditional generati…
Although end-to-end text-to-speech (TTS) models such as Tacotron have shown excellent results, they typically require a sizable set of high-quality <;text, audio> pairs for training, which are expensive to collect. In this paper, we propose a semi-supervised training framework to improve the data ef…
This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms, followed by a modified WaveNet model acting as a voc…
In this work, we propose “global style tokens” (GSTs), a bank of embeddings that are jointly trained within Tacotron, a state-of-the-art end-to-end speech synthesis system. The embeddings are trained with no explicit labels, yet learn to model a large range of acoustic expressiveness. GSTs lead to a…
We present an extension to the Tacotron speech synthesis architecture that learns a latent embedding space of prosody, derived from a reference acoustic representation containing the desired prosody. We show that conditioning Tacotron on this learned embedding space results in synthesized audio that…
Robust and far-field speech recognition is critical to enable true hands-free communication. In far-field conditions, signals are attenuated due to distance. To improve robustness to loudness variation, we introduce a novel frontend called per-channel energy normalization (PCEN). The key ingredient…
The phase response of noisy speech has largely been ignored, but recent research shows the importance of phase for perceptual speech quality. A few phase enhancement approaches have been developed. These systems, however, require a separate algorithm for enhancing the magnitude response. In this pap…
Supervised speech separation has achieved considerable success recently. Typically, a deep neural network (DNN) is used to estimate an ideal time-frequency mask, and clean speech is produced by feeding the mask-weighted output to a resynthesizer in a subsequent step. So far, the success of DNN-based…
Speaker identification (SID) in cochannel speech, where two speakers are talking simultaneously over a single recording channel, is a challenging problem. Previous studies address this problem in the anechoic environment under the Gaussian mixture model (GMM) framework. On the other hand, cochannel…
This paper presents an approach for improving the perceptual quality of speech separated from background noise at low signal-to-noise ratios. Our approach uses two stages of deep neural networks, where the first stage estimates the ideal ratio mask that separates speech from noise, and the second st…