arXiv subjects

Yun Hong

Publications and source records attributed to Yun Hong.

8 recordsLinked to original sources

arXiv2026

Sequential Trajectories and Simultaneous Blending: Multi-Emotion Modeling for Instruction-Following TTS

Natural-language instructions enable flexible control of synthesized speech, yet emotional TTS systems primarily model a single utterance-level affect, leaving multi-emotion control underexplored. We study two complementary multi-emotion TTS tasks: emotion trajectory, which spans several ordered affective stages, and emotion blending, in which multiple emotions coexist throughout an utterance. These tasks expose a supervision mismatch: supervised fine-tuning (SFT) does not explicitly evaluate emotion features, while single-emotion rewards provide neither structure-aware feedback for trajectory completion nor pair-aware feedback for blending. We introduce HybridEmo, a post-training framework that initializes both tasks with SFT and then aligns the speech-token policy through Group Relative Policy Optimization using a sample-aware hybrid reward. For trajectory samples, segment-aligned consistency combines average and weakest-stage evidence to preserve the correctness and completeness of prescribed stages. For blending samples, a GMM-based reward combines frame-level support from the union of target-emotion anchors in an offline emotion space with an utterance-level weaker-target margin. Both branches share an ASR reward and are routed within a unified policy. On MultiEmo-Test, HybridEmo significantly improves trajectory correctness and blending intensity, without a noticeable degradation in speaker similarity. Human evaluation prefers HybridEmo to CosyVoice 3 and EmoVoice-0.5B, with nearly balanced preferences against Qwen3-TTS.

cs.CL↗

arXiv2026

Learning A Unified Risk Map for Autonomous Driving in Partially Observable Environments

Occlusion-aware prediction remains a critical challenge in autonomous driving due to the inherent uncertainty of unobserved regions. Existing approaches either overestimate risk based on reachable states or struggle to predict accurate trajectories under high occlusion uncertainty. To address these limitations, we propose a unified risk map modeling and learning framework for partially observable environments. Our method integrates traffic flow risk and collision risk through spatiotemporal modeling, enabling fine-grained assessment of occlusion-induced hazards. To address the scarcity of scenarios involving occluded interactions, we introduce a diffusion-based scenario generation framework that produces realistic yet adversarial scenarios. We integrate the modeling and learning of a unified risk map into a framework that supports risk-aware planning under partial observability. Experiments on the Waymo Open Motion Dataset show that our method significantly outperforms the state-of-the-art occlusion-aware baseline, improving minimum time-to-collision by 0.78 times and average time-to-collision by 1.67 times. The proposed framework offers a comprehensive and practical solution for risk-aware planning in partially observable environments.

cs.RO↗

arXiv2026

FreezeEmpath: Efficient Training for Empathetic Spoken Chatbots with Frozen LLMs

Empathy is essential for fostering natural interactions in spoken dialogue systems, as it enables machines to recognize the emotional tone of human speech and deliver empathetic responses. Recent research has made significant progress in developing empathetic spoken chatbots based on large language models (LLMs). However, several challenges still exist when training such models, including reliance on costly empathetic speech instruction data and a lack of emotional expressiveness in the generated speech. Finetuning LLM with cross-modal empathetic instruction data may also lead to catastrophic forgetting and a degradation of its general capability. To address these challenges, we propose FreezeEmpath, an end-to-end empathetic spoken chatbot trained in a simple and efficient manner. The entire training process relies solely on existing speech instruction data and speech emotion recognition (SER) data, while keeping the LLM's parameters frozen. Experiments demonstrate that FreezeEmpath is able to generate emotionally expressive speech and outperforms other empathetic models in empathetic dialogue, SER, and SpokenQA tasks, demonstrating the effectiveness of our training strategy.

cs.CL↗

arXiv2026

Efficient Training for Cross-lingual Speech Language Models

Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data and the difficulty in expanding to more languages. In this paper, we introduce Cross-lingual Speech Language Model (CSLM), an efficient training method for cross-lingual speech LLMs based on discrete speech tokens. We propose a novel alignment strategy that achieves cross-modal and cross-lingual alignment through continual pre-training. By conducting instruction fine-tuning following a speech-text interleaved chain-of-modality generation process, we enhance modal alignment at a finer granularity, thereby improving generation quality and reducing latency. CSLM aligns different modalities and languages simultaneously without the need for massive speech data, thus exhibiting good language scalability. Evaluations on cross-modal tasks, mono-lingual conversational tasks, and cross-lingual conversational tasks demonstrate CSLM's strong cross-modal alignment capabilities and general task abilities. (Code is available at: https://github.com/ictnlp/CSLM)

cs.CL↗

arXiv2026

Hotspot Images from Magnetic Reconnection Processes in the plunging Region of a Kerr Black Hole

Employing the hotspot imaging technique, this work investigates the plasma motion trajectories prior to and following the Comisso-Asenjo mechanism within the plunging region. After a concise overview of the magnetic reconnection process in the plunging region of a Kerr black hole, we present the hotspot model and the associated imaging methodology. Through numerical simulations, we separately examine the hotspot images in the plunging region under three conditions: no magnetic reconnection, with magnetic reconnection, and when the escape condition fails. These outcomes are also contrasted with hotspot images in the circular orbit zone. Our findings reveal that for hotspot images without magnetic reconnection, when the plasma follows plunging orbits, the flare strength gradually declines; conversely, for circular orbits, the flare strength remains approximately constant. Additionally, we observe that the signal indicative of energy extraction is less conspicuous in the plunging region compared to the circular orbit region.

gr-qc↗

arXiv2025

SolarZip: An Efficient and Adaptive Compression Framework for Solar EUV Imaging Data

Context: With the advancement of solar physics research, next-generation solar space missions and ground-based telescopes face significant challenges in efficiently transmitting and/or storing large-scale observational data. Aims: We develop an efficient compression and evaluation framework for solar EUV data, specifically optimized for Solar Orbiter Extreme Ultraviolet Imager (EUI) data, significantly reducing data volume while preserving scientific usability. Methods: We systematically evaluated four error-bounded lossy compressors across two EUI datasets. However, the existing methods cannot perfectly handle the EUI datasets (with continuously changing distance and significant resolution differences). Motivated by this, we develop an adaptive hybrid compression strategy with optimized interpolation predictors. Moreover, we designed a two-stage evaluation framework integrating distortion analysis with downstream scientific workflows, ensuring that observational analysis is not affected at high compression ratios. Results: Our framework SolarZip achieved up to 800x reduction for Full Sun Imager (FSI) data and 500x for High Resolution Imager (HRI$_{\text{EUV}}$) data. It significantly outperformed both traditional and advanced algorithms, achieving 3-50x higher compression ratios than traditional algorithms, surpassing the second-best algorithm by up to 30%. Simulation experiments verified that SolarZip can reduce data transmission time by up to 270x while ensuring the preservation of scientific usability. Conclusions: The SolarZip framework significantly enhances solar observational data compression efficiency while preserving scientific usability by dynamically selecting optimal compression methods based on observational scenarios and user requirements. This provides a promising data management solution for deep space missions like Solar Orbiter.

astro-ph.IM↗

arXiv2024

Hashing based Contrastive Learning for Virtual Screening

Virtual screening (VS) is a critical step in computer-aided drug discovery, aiming to identify molecules that bind to a specific target receptor like protein. Traditional VS methods, such as docking, are often too time-consuming for screening large-scale molecular databases. Recent advances in deep learning have demonstrated that learning vector representations for both proteins and molecules using contrastive learning can outperform traditional docking methods. However, given that target databases often contain billions of molecules, real-valued vector representations adopted by existing methods can still incur significant memory and time costs in VS. To address this problem, in this paper we propose a hashing-based contrastive learning method, called DrugHash, for VS. DrugHash treats VS as a retrieval task that uses efficient binary hash codes for retrieval. In particular, DrugHash designs a simple yet effective hashing strategy to enable end-to-end learning of binary hash codes for both protein and molecule modalities, which can dramatically reduce the memory and time costs with higher accuracy compared with existing methods. Experimental results show that DrugHash can outperform existing methods to achieve state-of-the-art accuracy, with a memory saving of 32$\times$ and a speed improvement of 3.5$\times$.

cs.AI↗

arXiv2019

Thermodynamics and weak cosmic censorship conjecture of the torus-like black hole

After studying the energy-momentum relation of charged particles' Hamilton-Jacobi equations, we discuss the laws of thermodynamics and the weak cosmic censorship conjecture in torus-like black holes. We find that both the first law of thermodynamic as well as the weak cosmic censorship conjecture are valid in both the normal phase space and extended phase space. However, the second law of thermodynamics is only valid in the normal phase space. Our results show that the first law and weak cosmic censorship conjecture do not depend on the phase spaces while the second law depends. What's more, we find that the shift of the metric function that determines the event horizon take the same form in different phase spaces, indicating that the weak cosmic censorship conjecture is independent of the phase space.

hep-th↗