Mu Yang

Mu Yang, Naoyuki Kanda, Xiaofei Wang et al. · cmu

End-to-end speech translation (ST) for conversation recordings involves several under-explored challenges such as speaker diarization (SD) without accurate word time stamps and handling of overlapping speech in a streaming fashion. In this work, we propose DiariST, the first streaming ST and SD solution. It is built upon a neural transducer-based streaming ST system and integrates token-level serialized output training and t-vector, which were originally developed for multi-talker speech recognition. Due to the absence of evaluation benchmarks in this area, we develop a new evaluation dataset, DiariST-AliMeeting, by translating the reference Chinese transcriptions of the AliMeeting corpus into English. We also propose new metrics, called speaker-agnostic BLEU and speaker-attributed BLEU, to measure the ST quality while taking SD accuracy into account. Our system achieves a strong ST and SD capability compared to offline systems based on Whisper, while performing streaming inference for overlapping speech. To facilitate the research in this new direction, we release the evaluation data, the offline baseline systems, and the evaluation code.

Xiyang Wang, Shouzheng Qi, Jieyou Zhao et al.

This paper introduces MCTrack, a new 3D multi-object tracking method that achieves state-of-the-art (SOTA) performance across KITTI, nuScenes, and Waymo datasets. Addressing the gap in existing tracking paradigms, which often perform well on specific datasets but lack generalizability, MCTrack offers a unified solution. Additionally, we have standardized the format of perceptual results across various datasets, termed BaseVersion, facilitating researchers in the field of multi-object tracking (MOT) to concentrate on the core algorithmic development without the undue burden of data preprocessing. Finally, recognizing the limitations of current evaluation metrics, we propose a novel set that assesses motion information output, such as velocity and acceleration, crucial for downstream tasks. The source codes of the proposed method are available at this link: https://github.com/megvii-research/MCTrack}{https://github.com/megvii-research/MCTrack

Mu Yang, Ram C. M. C. Shekar, Okim Kang et al.

This study is focused on understanding and quantifying the change in phoneme and prosody information encoded in the Self-Supervised Learning (SSL) model, brought by an accent identification (AID) fine-tuning task. This problem is addressed based on model probing. Specifically, we conduct a systematic layer-wise analysis of the representations of the Transformer layers on a phoneme correlation task, and a novel word-level prosody prediction task. We compare the probing performance of the pre-trained and fine-tuned SSL models. Results show that the AID fine-tuning task steers the top 2 layers to learn richer phoneme and prosody representation. These changes share some similarities with the effects of fine-tuning with an Automatic Speech Recognition task. In addition, we observe strong accent-specific phoneme representations in layer 9. To sum up, this study provides insights into the understanding of SSL features and their interactions with fine-tuning tasks.

Xiyang Wang, Xinlin Wang, Tingguang Zhou et al.

Current end-to-end autonomous driving systems are fundamentally limited by a mismatch between temporal causal reasoning and global trajectory consistency. Autoregressive (AR) models capture interaction-aware temporal dependencies via causal factorization, but their step-wise decoding leads to error accumulation and suboptimal global structure. In contrast, diffusion models optimize trajectories globally but lack explicit causal constraints, making them unreliable in interactive and safety-critical scenarios. This dichotomy reveals a deeper issue: existing methods treat causal modeling and global optimization as separate paradigms, without a principled way to unify them within a single trajectory distribution. To address this, we propose ChainFlow-VLA, which unifies causal generation and global refinement within a unified probabilistic framework. We formulate planning as a mixture over AR-induced modes and learn Vision-Language Model (VLM)-conditioned residual distributions over these modes. An autoregressive generator (Chain) produces a discrete set of causal trajectory modes, followed by a diffusion-based refiner (Flow) that leverages VLM hidden states as semantic priors to perform mode-conditioned correction in residual space while preserving causal structure. This straightforward conditioning seamlessly injects high-level scene understanding into fine-grained trajectory adjustments. Experiments demonstrate that ChainFlow-VLA achieves robust planning in ambiguous and long-tail scenarios, achieving a state-of-the-art score of 94.85 on the NAVSIM v1 leaderboard, matching human-level performance (94.8). Code will be available at https://github.com/AFARI-Research/ChainFlow-VLA.

Mu Yang, Andros Tjandra, Chunxi Liu et al.

Neural network pruning compresses automatic speech recognition (ASR) models effectively. However, in multilingual ASR, language-agnostic pruning may lead to severe performance drops on some languages because language-agnostic pruning masks may not fit all languages and discard important language-specific parameters. In this work, we present ASR pathways, a sparse multilingual ASR model that activates language-specific sub-networks ("pathways"), such that the parameters for each language are learned explicitly. With the overlapping sub-networks, the shared parameters can also enable knowledge transfer for lower-resource languages via joint multilingual training. We propose a novel algorithm to learn ASR pathways, and evaluate the proposed method on 4 languages with a streaming RNN-T model. Our proposed ASR pathways outperform both dense models and a language-agnostically pruned model, and provide better performance on low-resource languages compared to the monolingual sparse models.

Minqing Huang, Yujiao Xiang, Zihan Liang et al.

Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing reasoning mechanisms still struggle to provide planning-oriented intermediate representations: textual Chain-of-Thought (CoT) fails to preserve continuous spatiotemporal structure, while latent world reasoning remains difficult to use as a direct condition for action generation. In this paper, we propose CoWorld-VLA, a multi-expert world reasoning framework for autonomous driving, where world representations serve as explicit conditions to guide action planning. CoWorld-VLA extracts complementary world information through multi-source supervision and encodes it into expert tokens within the VLA, thereby providing planner-accessible conditioning signals. Specifically, we construct four types of tokens: semantic interaction, geometric structure, dynamic evolution, and ego trajectory tokens, which respectively model interaction intent, spatial structure, future temporal dynamics, and behavioral goals. During action generation, CoWorld-VLA employs a diffusion-based hierarchical multi-expert fusion planner, which is coupled with scene context throughout the joint denoising process to generate continuous ego trajectories. Experiments show that CoWorld-VLA achieves competitive results in both future scene generation and planning on the NAVSIM v1 benchmark, demonstrating strong performance in collision avoidance and trajectory accuracy. Ablation studies further validate the complementarity of expert tokens and their effectiveness as planning conditions for action generation. Code will be available at https://github.com/potatochip1211/CoWorld-VLA.

Dongxu Wei, Qi Xu, Zhiqi Li et al.

3D scene generation has long been dominated by 2D multi-view or video diffusion models. This is due not only to the lack of scene-level 3D latent representation, but also to the fact that most scene-level 3D visual data exists in the form of multi-view images or videos, which are naturally compatible with 2D diffusion architectures. Typically, these 2D-based approaches degrade 3D spatial extrapolation to 2D temporal extension, which introduces two fundamental issues: (i) representing 3D scenes via 2D views leads to significant representation redundancy, and (ii) latent space rooted in 2D inherently limits the spatial consistency of the generated 3D scenes. In this paper, we propose, for the first time, to perform 3D scene generation directly within an implicit 3D latent space to address these limitations. First, we repurpose frozen 2D representation encoders to construct our 3D Representation Autoencoder (3DRAE), which grounds view-coupled 2D semantic representations into a view-decoupled 3D latent representation. This enables representing 3D scenes observed from arbitrary numbers of views--at any resolution and aspect ratio--with fixed complexity and rich semantics. Then we introduce 3D Diffusion Transformer (3DDiT), which performs diffusion modeling in this 3D latent space, achieving remarkably efficient and spatially consistent 3D scene generation while supporting diverse conditioning configurations. Moreover, since our approach directly generates a 3D scene representation, it can be decoded to images and optional point maps along arbitrary camera trajectories without requiring per-trajectory diffusion sampling pass, which is common in 2D-based approaches.

Chin-Tung Lin, Mu Yang

Many social media users prefer consuming content in the form of videos rather than text. However, in order for content creators to produce videos with a high click-through rate, much editing is needed to match the footage to the music. This posts additional challenges for more amateur video makers. Therefore, we propose a novel attention-based model VMT (Video-Music Transformer) that automatically generates piano scores from video frames. Using music generated from models also prevent potential copyright infringements that often come with using existing music. To the best of our knowledge, there is no work besides the proposed VMT that aims to compose music for video. Additionally, there lacks a dataset with aligned video and symbolic music. We release a new dataset composed of over 7 hours of piano scores with fine alignment between pop music videos and MIDI files. We conduct experiments with human evaluation on VMT, SeqSeq model (our baseline), and the original piano version soundtrack. VMT achieves consistent improvements over the baseline on music smoothness and video relevance. In particular, with the relevance scores and our case study, our model has shown the capability of multimodality on frame-level actors' movement for music generation. Our VMT model, along with the new dataset, presents a promising research direction toward composing the matching soundtrack for videos. We have released our code at https://github.com/linchintung/VMT

Bohan Li, Jiazhe Guo, Hongsi Liu et al.

Generating high-fidelity, controllable, and annotated training data is critical for autonomous driving. Existing methods typically generate a single data form directly from a coarse scene layout, which not only fails to output rich data forms required for diverse downstream tasks but also struggles to model the direct layout-to-data distribution. In this paper, we introduce UniScene, the first unified framework for generating three key data forms - semantic occupancy, video, and LiDAR - in driving scenes. UniScene employs a progressive generation process that decomposes the complex task of scene generation into two hierarchical steps: (a) first generating semantic occupancy from a customized scene layout as a meta scene representation rich in both semantic and geometric information, and then (b) conditioned on occupancy, generating video and LiDAR data, respectively, with two novel transfer strategies of Gaussian-based Joint Rendering and Prior-guided Sparse Modeling. This occupancy-centric approach reduces the generation burden, especially for intricate scenes, while providing detailed intermediate representations for the subsequent generation stages. Extensive experiments demonstrate that UniScene outperforms previous SOTAs in the occupancy, video, and LiDAR generation, which also indeed benefits downstream driving tasks. Project page: https://arlo0o.github.io/uniscene/

Jianbo Zhao, Taiyu Ban, Zhihao Liu et al.

Accurate and efficient modeling of agent interactions is essential for trajectory generation, the core of autonomous driving systems. Existing methods, scene-centric, agent-centric, and query-centric frameworks, each present distinct advantages and drawbacks, creating an impossible triangle among accuracy, computational time, and memory efficiency. To break this limitation, we propose Directional Rotary Position Embedding (DRoPE), a novel adaptation of Rotary Position Embedding (RoPE), originally developed in natural language processing. Unlike traditional relative position embedding (RPE), which introduces significant space complexity, RoPE efficiently encodes relative positions without explicitly increasing complexity but faces inherent limitations in handling angular information due to periodicity. DRoPE overcomes this limitation by introducing a uniform identity scalar into RoPE's 2D rotary transformation, aligning rotation angles with realistic agent headings to naturally encode relative angular information. We theoretically analyze DRoPE's correctness and efficiency, demonstrating its capability to simultaneously optimize trajectory generation accuracy, time complexity, and space complexity. Empirical evaluations compared with various state-of-the-art trajectory generation models, confirm DRoPE's good performance and significantly reduced space complexity, indicating both theoretical soundness and practical effectiveness. The video documentation is available at https://drope-traj.github.io/.

Jianbo Zhao, Taiyu Ban, Xiyang Wang et al.

Controllable trajectory generation guided by high-level semantic decisions, termed meta-actions, is crucial for autonomous driving systems. A significant limitation of existing frameworks is their reliance on invariant meta-actions assigned over fixed future time intervals, causing temporal misalignment with the actual behavior trajectories. This misalignment leads to irrelevant associations between the prescribed meta-actions and the resulting trajectories, disrupting task coherence and limiting model performance. To address this challenge, we introduce Autoregressive Meta-Actions, an approach integrated into autoregressive trajectory generation frameworks that provides a unified and precise definition for meta-action-conditioned trajectory prediction. Specifically, We decompose traditional long-interval meta-actions into frame-level meta-actions, enabling a sequential interplay between autoregressive meta-action prediction and meta-action-conditioned trajectory generation. This decomposition ensures strict alignment between each trajectory segment and its corresponding meta-action, achieving a consistent and unified task formulation across the entire trajectory span and significantly reducing complexity. Moreover, we propose a staged pre-training process to decouple the learning of basic motion dynamics from the integration of high-level decision control, which offers flexibility, stability, and modularity. Experimental results validate our framework's effectiveness, demonstrating improved trajectory adaptivity and responsiveness to dynamic decision-making scenarios. We provide the video document and dataset, which are available at https://arma-traj.github.io/.

Mu Yang, Kevin Hirschi, Stephen D. Looney et al.

Current leading mispronunciation detection and diagnosis (MDD) systems achieve promising performance via end-to-end phoneme recognition. One challenge of such end-to-end solutions is the scarcity of human-annotated phonemes on natural L2 speech. In this work, we leverage unlabeled L2 speech via a pseudo-labeling (PL) procedure and extend the fine-tuning approach based on pre-trained self-supervised learning (SSL) models. Specifically, we use Wav2vec 2.0 as our SSL model, and fine-tune it using original labeled L2 speech samples plus the created pseudo-labeled L2 speech samples. Our pseudo labels are dynamic and are produced by an ensemble of the online model on-the-fly, which ensures that our model is robust to pseudo label noise. We show that fine-tuning with pseudo labels achieves a 5.35% phoneme error rate reduction and 2.48% MDD F1 score improvement over a labeled-samples-only fine-tuning baseline. The proposed PL method is also shown to outperform conventional offline PL methods. Compared to the state-of-the-art MDD systems, our MDD solution produces a more accurate and consistent phonetic error diagnosis. In addition, we conduct an open test on a separate UTD-4Accents dataset, where our system recognition outputs show a strong correlation with human perception, based on accentedness and intelligibility.

Mu Yang, Shaojin Ding, Tianlong Chen et al.

This work presents a lifelong learning approach to train a multilingual Text-To-Speech (TTS) system, where each language was seen as an individual task and was learned sequentially and continually. It does not require pooled data from all languages altogether, and thus alleviates the storage and computation burden. One of the challenges of lifelong learning methods is "catastrophic forgetting": in TTS scenario it means that model performance quickly degrades on previous languages when adapted to a new language. We approach this problem via a data-replay-based lifelong learning method. We formulate the replay process as a supervised learning problem, and propose a simple yet effective dual-sampler framework to tackle the heavily language-imbalanced training samples. Through objective and subjective evaluations, we show that this supervised learning formulation outperforms other gradient-based and regularization-based lifelong learning methods, achieving 43% Mel-Cepstral Distortion reduction compared to a fine-tuning baseline.

Mingyu Derek Ma, Jiao Sun, Mu Yang et al.

We present EventPlus, a temporal event understanding pipeline that integrates various state-of-the-art event understanding components including event trigger and type detection, event argument detection, event duration and temporal relation extraction. Event information, especially event temporal knowledge, is a type of common sense knowledge that helps people understand how stories evolve and provides predictive hints for future events. EventPlus as the first comprehensive temporal event understanding pipeline provides a convenient tool for users to quickly obtain annotations about events and their temporal information for any user-provided document. Furthermore, we show EventPlus can be easily adapted to other domains (e.g., biomedical domain). We make EventPlus publicly available to facilitate event-related information extraction and downstream applications.

Kung-Hsiang Huang, Mu Yang, Nanyun Peng

Biomedical event extraction is critical in understanding biomolecular interactions described in scientific corpus. One of the main challenges is to identify nested structured events that are associated with non-indicative trigger words. We propose to incorporate domain knowledge from Unified Medical Language System (UMLS) to a pre-trained language model via Graph Edge-conditioned Attention Networks (GEANet) and hierarchical graph representation. To better recognize the trigger words, each sentence is first grounded to a sentence graph based on a jointly modeled hierarchical knowledge graph from UMLS. The grounded graphs are then propagated by GEANet, a novel graph neural networks for enhanced capabilities in inferring complex events. On BioNLP 2011 GENIA Event Extraction task, our approach achieved 1.41% F1 and 3.19% F1 improvements on all events and complex events, respectively. Ablation studies confirm the importance of GEANet and hierarchical KG.

Rujun Han, I-Hung Hsu, Mu Yang et al.

We propose a novel deep structured learning framework for event temporal relation extraction. The model consists of 1) a recurrent neural network (RNN) to learn scoring functions for pair-wise relations, and 2) a structured support vector machine (SSVM) to make joint predictions. The neural network automatically learns representations that account for long-term contexts to provide robust features for the structured model, while the SSVM incorporates domain knowledge such as transitive closure of temporal relations as constraints to make better globally consistent decisions. By jointly training the two components, our model combines the benefits of both data-driven learning and knowledge exploitation. Experimental results on three high-quality event temporal relation datasets (TCR, MATRES, and TB-Dense) demonstrate that incorporated with pre-trained contextualized embeddings, the proposed model achieves significantly better performances than the state-of-the-art methods on all three datasets. We also provide thorough ablation studies to investigate our model.

Prashanth Gurunath Shivakumar, Mu Yang, Panayiotis Georgiou

Decoding speaker's intent is a crucial part of spoken language understanding (SLU). The presence of noise or errors in the text transcriptions, in real life scenarios make the task more challenging. In this paper, we address the spoken language intent detection under noisy conditions imposed by automatic speech recognition (ASR) systems. We propose to employ confusion2vec word feature representation to compensate for the errors made by ASR and to increase the robustness of the SLU system. The confusion2vec, motivated from human speech production and perception, models acoustic relationships between words in addition to the semantic and syntactic relations of words in human language. We hypothesize that ASR often makes errors relating to acoustically similar words, and the confusion2vec with inherent model of acoustic relationships between words is able to compensate for the errors. We demonstrate through experiments on the ATIS benchmark dataset, the robustness of the proposed model to achieve state-of-the-art results under noisy ASR conditions. Our system reduces classification error rate (CER) by 20.84% and improves robustness by 37.48% (lower CER degradation) relative to the previous state-of-the-art going from clean to noisy transcripts. Improvements are also demonstrated when training the intent detection models on noisy transcripts.

Mu Yang, Zheng-Hao Liu, Ze-Di Cheng et al.

A well-trained deep neural network is shown to gain capability of simultaneously restoring two kinds of images, which are completely destroyed by two distinct scattering medias respectively. The network, based on the U-net architecture, can be trained by blended dataset of speckles-reference images pairs. We experimentally demonstrate the power of the network in reconstructing images which are strongly diffused by glass diffuser or multi-mode fiber. The learning model further shows good generalization ability to reconstruct images that are distinguished from the training dataset. Our work facilitates the study of optical transmission and expands machine learning's application in optics.