Showing 1–50 of 111 results for author: Mai, J

Global boundedness and stabilization for a three-component reaction-diffusion model with dual-dependent motility

Authors: Hai-Yang Jin, Jingyi Mai

Abstract: In this paper, we consider the initial-boundary value problem of a three-component reaction-diffusion system with dual-dependent motility, which depends on both the chemical concentration and the nutrient level. We systematically establish the global existence, boundedness, and asymptotic behavior of the classical solutions to the system with no-flux boundary conditions through classified discussi… ▽ More In this paper, we consider the initial-boundary value problem of a three-component reaction-diffusion system with dual-dependent motility, which depends on both the chemical concentration and the nutrient level. We systematically establish the global existence, boundedness, and asymptotic behavior of the classical solutions to the system with no-flux boundary conditions through classified discussion and by exploiting specific structural properties of the motility function. In turn, by comparing the results obtained in the distinct cases, we demonstrate that the solution converges to different constant steady states, thereby indicating the crucial role of the dual-dependent motility function in the long-term behavior of the system. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Demonstrating advantages of dynamic quantum circuits on a hybrid superconducting qubit-cavity processor

Authors: Hongbo Wu, Ling Hu, Jiasheng Mai, Munan Zhang, Libo Zhang, Yanyan Cai, Xiaowei Deng, Pan Zheng, Zhongchu Ni, Song Liu, Kun Fang, Dapeng Yu, Yuan Xu

Abstract: Dynamic quantum circuits (DQCs) provide a hardware-efficient route to quantum computing by reducing physical-qubit overhead and compressing circuit topology through mid-circuit measurements, qubit reset and reuse, and classical feed-forward control. Here, we demonstrate the advantages of DQCs on a single hybrid superconducting qubit-cavity processor by implementing a hierarchy of algorithms with i… ▽ More Dynamic quantum circuits (DQCs) provide a hardware-efficient route to quantum computing by reducing physical-qubit overhead and compressing circuit topology through mid-circuit measurements, qubit reset and reuse, and classical feed-forward control. Here, we demonstrate the advantages of DQCs on a single hybrid superconducting qubit-cavity processor by implementing a hierarchy of algorithms with increasing complexity. This hybrid architecture consists of a high-dimensional cavity qudit serving as the computational register and a dispersively coupled superconducting transmon ancilla that is repeatedly measured, reset, and reused to enable dynamic control. Using this device, we implement a 10-bit Bernstein-Vazirani algorithm with an average success probability of 82%, surpassing state-of-the-art dynamic and static implementations in both scale and performance; an 8-bit quantum phase-estimation protocol with estimation errors below 10-3; and the first dynamic-circuit implementation of Shor's algorithm on a superconducting platform, factoring 15 over all coprime bases with squared statistical overlap values above 99.8%. These results provide concrete benchmarks for future DQC implementations and highlight the versatile advantages of DQCs with the hybrid qubit-qudit architecture, establishing it as a promising route toward scalable, programmable quantum computation. △ Less

Submitted 5 August, 2026; originally announced August 2026.

Comments: 17 pages, 10 figures

EgoPlay: Event-Triggered Video Editing for Egocentric Streams

Authors: Jinjie Mai, Gordon Guocheng Qian, Willi Menapace, Arpit Sahni, Chaoyang Wang, Ashkan Mirzaei, Runjia Li, Sergey Tulyakov, Bernard Ghanem, Peter Wonka, Rameen Abdal

Abstract: We introduce EgoPlay, an event-triggered video-to-video editor for egocentric streams, obtained by fine-tuning a pretrained V2V diffusion transformer on event-conditioned data built primarily from Ego4D. Given a monocular video and an event-triggered prompt of the form "when X happens, do Y," EgoPlay infers whether and when event X occurs, preserves pre-event frames, and applies edit Y only to the… ▽ More We introduce EgoPlay, an event-triggered video-to-video editor for egocentric streams, obtained by fine-tuning a pretrained V2V diffusion transformer on event-conditioned data built primarily from Ego4D. Given a monocular video and an event-triggered prompt of the form "when X happens, do Y," EgoPlay infers whether and when event X occurs, preserves pre-event frames, and applies edit Y only to the post-event continuation. Rather than cascading a separate event detector with an editor, EgoPlay learns event recognition, temporal restraint, and pixel-level editing jointly in a single end-to-end model, while also handling negative and multi-event prompts. To support this, we construct a large-scale dataset of 106K event-triggered clip-prompt pairs spanning positive triggers, fabricated-trigger negatives, and multi-event prompts. We then train a bidirectional video diffusion editor with event-triggered supervision and derive a causal variant for chunk-by-chunk streamable inference. We further introduce an event-aware evaluation protocol that separately measures post-trigger editing quality, pre-trigger preservation, and false-trigger robustness. On the Ego4D benchmark, EgoPlay substantially outperforms EgoEdit, the state-of-the-art instruction-based egocentric video editing baseline, with relative gains of 17.7%, 16.9%, and 16.4% in editing quality, visual quality, and background consistency. It also surpasses a VLM-guided detector-editor baseline by 15.7%, 14.5%, and 13.5% on the same metrics, while using less than half the GPU memory. △ Less

Submitted 27 July, 2026; originally announced July 2026.

Comments: Accepted to SIGGRAPH Asia 2026 as a Conference Paper. Project page: https://egoplay2026.github.io/egoplay

LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications

Authors: Daniela Rojas, Abdulwahab Albassam, Aidan G. Leung, Jett Ngo, Ryan Luo, Peter R. Quawas, Junpyung Kim, Kangkai Liang, Mansi Nanavati, Jonathan Mai, Meng-Chi Tsai, Yun-Tong Tsai, Yize Chen, Yuanyuan Shi

Abstract: Large language models (LLMs) and agentic AI systems have evolved from natural language tasks to using external tools to plan, retrieve, and act in technical domains. In smart grids, recent work applies agentic schemes to forecasting, optimization, and control, wrapping trusted solvers behind language interfaces and orchestrating multi-step workflows. The literature lacks a unified approach to desi… ▽ More Large language models (LLMs) and agentic AI systems have evolved from natural language tasks to using external tools to plan, retrieve, and act in technical domains. In smart grids, recent work applies agentic schemes to forecasting, optimization, and control, wrapping trusted solvers behind language interfaces and orchestrating multi-step workflows. The literature lacks a unified approach to designing and evaluating such systems. LLMs can produce numerically plausible yet physically infeasible outputs, evaluation protocols vary across tasks, and the boundary between what the model should and should not compute is implicit. This paper presents a solver-grounded design principle: a numerical result is reported only when it originates from a trusted tool and passes explicit verification. We review the building blocks of LLM and agentic AI systems for power systems: prompting strategies and agentic architectures. We instantiate the principle in four case studies: wind power forecasting, EV charging scheduling, power flow analysis, and contingency diagnosis, each comparing an LLM-only baseline against its solver-grounded counterpart on identical data and metrics. EVAgent reproduces the CVXPY optimum while reducing LLM-only unmet energy by 7.5-9.5x, and GridDebugAgent repairs 17/39 contingency cases while reducing total violations by 52.3%. We propose a four-group evaluation framework spanning task utility, solver-grounded correctness, faithfulness and safe failure, and cost and latency. A consistent division of labor emerges: the agentic system reliably orchestrates, retrieves, and explains, while trusted tools compute and a verification gate decides what is reported. △ Less

Submitted 20 July, 2026; originally announced July 2026.

Comments: 28 pages, 11 figures, 6 tables; plus supplementary material. Review/tutorial article

Final assessment of radioactive impurities in the JUNO detector

Authors: Thomas Adam, Fengpeng An, Costas Andreopoulos, Giuseppe Andronico, Nikolay Anfimov, Vito Antonelli, Tatiana Antoshkina, João Pedro Athayde Marcondes de André, Didier Auguste, Nikita Balashov, Andrea Barresi, Davide Basilico, Eric Baussan, Marco Beretta, Antonio Bergnoli, Nikita Bessonov, Daniel Bick, Lukas Bieger, Svetlana Biktemerova, Thilo Birkenfeld, Simon Blyth, Manuel Böhles, Anastasia Bolshakova, Mathieu Bongrand, Matteo Borghesi , et al. (549 additional authors not shown)

Abstract: The Jiangmen Underground Neutrino Observatory (JUNO) collaboration has completed the construction of the 20,000-ton liquid scintillator detector and the associated muon veto detector system. To meet the physics objectives, the materials used in the detector must exhibit low radioactive contamination. The single-event rate in the fiducial volume (R $<$ 17.2 m) of the scintillator is required to be… ▽ More The Jiangmen Underground Neutrino Observatory (JUNO) collaboration has completed the construction of the 20,000-ton liquid scintillator detector and the associated muon veto detector system. To meet the physics objectives, the materials used in the detector must exhibit low radioactive contamination. The single-event rate in the fiducial volume (R $<$ 17.2 m) of the scintillator is required to be approximately 7 Hz for energies above 0.7 MeV, resulting in an accidental coincidence background of about 1 event per day for reactor neutrino physics analyses. Since the beginning of the construction phase, we have screened the natural radioactivity content of thousands of materials, to select those that meet the design background budget. The radioactive impurity concentrations of the materials ultimately used in the JUNO detector are summarized in this paper. The construction of the entire detector and the subsequent filling of the liquid scintillator were completed in August 2025. From the initial data, the total count rate of natural radioactivity within the detector's fiducial volume has met the requirements and is sufficient to support the reactor antineutrino analysis. △ Less

Submitted 19 July, 2026; originally announced July 2026.

A Low-energy Threshold and Multi-messenger Trigger System for the JUNO Experiment

Authors: Thomas Adam, Fengpeng An, Costas Andreopoulos, Giuseppe Andronico, Nikolay Anfimov, Vito Antonelli, Tatiana Antoshkina, João Pedro Athayde Marcondes de André, Didier Auguste, Nikita Balashov, Andrea Barresi, Davide Basilico, Eric Baussan, Marco Beretta, Antonio Bergnoli, Nikita Bessonov, Daniel Bick, Lukas Bieger, Svetlana Biktemerova, Thilo Birkenfeld, Simon Blyth, Manuel Boehles, Anastasia Bolshakova, Mathieu Bongrand, Matteo Borghesi , et al. (543 additional authors not shown)

Abstract: The Jiangmen Underground Neutrino Observatory (JUNO) is a 20-kiloton liquid scintillator neutrino detector, located 650 meters (1800 m.w.e.) underground in Jiangmen, Guangdong, China. JUNO is primarily designed for reactor neutrino measurements and has been taking data since 2025. With the largest mass of its kind and an excellent energy resolution, JUNO is a leading observatory for high-precision… ▽ More The Jiangmen Underground Neutrino Observatory (JUNO) is a 20-kiloton liquid scintillator neutrino detector, located 650 meters (1800 m.w.e.) underground in Jiangmen, Guangdong, China. JUNO is primarily designed for reactor neutrino measurements and has been taking data since 2025. With the largest mass of its kind and an excellent energy resolution, JUNO is a leading observatory for high-precision measurements of MeV neutrinos. The standard global trigger system serves as the primary trigger for JUNO. We present a newly developed multi-messenger trigger system that extends the capabilities of the global trigger by providing a lower energy threshold and an independent monitoring capability. During the 2025 operation, it achieved an effective energy threshold of approximately 110 +/- 10 keV, providing a lower threshold configuration suitable for low-energy event analysis. The system shows the potential to further reduce the threshold to well below 100 keV. Based on the multi-messenger trigger system, an astrophysical monitor has been developed to receive and process external alerts from other messengers, such as gravitational-wave observations. A Transient Neutrino Burst Monitor is integrated to detect short-time-scale neutrino burst events and enables real-time monitoring of transient astrophysical phenomena. The system is sensitive to neutrino bursts from core-collapse supernovae within a distance of about 250 kpc. △ Less

Submitted 15 July, 2026; originally announced July 2026.

Comments: 29 pages, 19 figures, 3 tables

WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS

Authors: Sihang Nie, Jinxin Ji, Xiaofen Xing, Deyi Tuo, Chengbin Jin, Jialong Mai, Xiangmin Xu

Abstract: While recent Large Language Model (LLM)-based Text-to-Speech (TTS) systems have achieved remarkable naturalness, they predominantly rely on implicit end-to-end generation paradigms, resulting in coarse-grained control. In scenarios demanding precise stylistic interventions and strict temporal alignment, such as audiobook narration and video dubbing, the inability to explicitly manipulate word-leve… ▽ More While recent Large Language Model (LLM)-based Text-to-Speech (TTS) systems have achieved remarkable naturalness, they predominantly rely on implicit end-to-end generation paradigms, resulting in coarse-grained control. In scenarios demanding precise stylistic interventions and strict temporal alignment, such as audiobook narration and video dubbing, the inability to explicitly manipulate word-level acoustic attributes remains a critical bottleneck. This limitation is primarily amplified by the severe scarcity of fine-grained annotated datasets and the architectural challenge of integrating multi-dimensional control signals into discrete autoregressive generation. To address this, we propose a unified framework for highly precise word-level control. First, we construct WordVoice-5A, a massive 4.7k-hour bilingual dataset featuring five-dimensional word-level annotations (duration, boundary, energy, pitch and tone) developed through a rigorous linguistically-guided pipeline. Second, we introduce WordVoice to transform the implicit generation process into an explicit, highly controllable paradigm. Specifically, we introduce a bound-token mechanism within the LLM to formulate an explicit ``acoustic planning'' process, enabling adaptive multi-task prosodic planning and flexible manual intervention. Furthermore, we augment the token-to-waveform stage with a fine-grained acoustic modulation module, bridging the resolution gap to strictly align word-level attributes between highly compressed discrete tokens and continuous waveforms. Extensive experiments demonstrate that WordVoice achieves superior, decoupled control over multiple acoustic dimensions while maintaining competitive zero-shot synthesis stability. The code and audio samples are publicly available at https://xxh333.github.io/wordvoice-demo/. △ Less

Submitted 7 July, 2026; originally announced July 2026.

Comments: 10 pages, 4 figures, 6 tables; Preprint

A Large-Scale Sparse Multiobjective Optimization Algorithm Based on Optimal Performance Scores

Authors: Jia-Lin Mai, Min-Rong Chen, Guo-Qiang Zeng, Xiang Liu, Jian Weng

Abstract: Large-scale sparse multiobjective optimization problems (LSSMOPs) involve a large number of decision variables and Pareto optimal solutions with only a few nonzero variables. However, as the number of decision variables grows, it becomes increasingly challenging to accurately identify the nonzero variables, and optimization performance is adversely affected. To address these issues, this paper pro… ▽ More Large-scale sparse multiobjective optimization problems (LSSMOPs) involve a large number of decision variables and Pareto optimal solutions with only a few nonzero variables. However, as the number of decision variables grows, it becomes increasingly challenging to accurately identify the nonzero variables, and optimization performance is adversely affected. To address these issues, this paper proposes an evolutionary algorithm for LSSMOPs. Specifically, we propose a new initialization method capable of generating scores that accurately reflect the importance of variables, and an initial mask vector template that can locate nonzero variables. This leads to the generation of a high-quality initial population. Additionally, this paper introduces a new strategy to calculate the mutation probability for each variable and a novel optimization for real variables based on the Pareto-guided normal distribution, enabling the population to avoid being trapped in local optima and quickly converge to the global optimum. Experimental results from eight benchmark problems and three real-world applications demonstrate that the proposed algorithm achieves superior performance compared with state-of-the-art algorithms. △ Less

Submitted 6 July, 2026; originally announced July 2026.

Comments: 21 pages, 16 figures

MotionAtlas: Detailed Region Captioning for Motion-Centric Videos

Authors: Weisong Liu, Haochen Wang, Kuan Gao, Yuhao Wang, Yikang Zhou, Zhongwei Ren, Jacky Mai, Anna Wang, Yanwei Li, Jason Li, Zhaoxiang Zhang

Abstract: We propose MotionAtlas, a system for detailed captioning of motion-centric videos, comprising (1) a dedicated human-annotated benchmark, (2) a scalable, high-quality pipeline to construct training samples, and (3) a family of powerful Video-MLLMs. Unlike conventional global motion captioning datasets, we focus on region-aware motion captioning: given a video and a spatiotemporal mask, the model ge… ▽ More We propose MotionAtlas, a system for detailed captioning of motion-centric videos, comprising (1) a dedicated human-annotated benchmark, (2) a scalable, high-quality pipeline to construct training samples, and (3) a family of powerful Video-MLLMs. Unlike conventional global motion captioning datasets, we focus on region-aware motion captioning: given a video and a spatiotemporal mask, the model generates precise descriptions of motion within the target region, thereby alleviating visual clutter and motion entanglement and enabling reliable, quantifiable evaluation. Concretely, we first build MotionAtlas-Bench, a comprehensive benchmark comprising 2,073 multiple-choice questions, meticulously annotated for a curated set of high-quality, motion-centric videos, to evaluate fine-grained motion understanding of the objects in question. Second, we design a rigorous and scalable data pipeline that leverages self-bootstrap refinement to suppress fine-grained hallucinations, yielding 159k high-quality motion captioning data. Third, we design a tailored training data composition strategy, which achieves consistent and substantial performance gains across diverse baseline Video-MLLMs, including Molmo2 and Qwen3-VL. For instance, MotionAtlas-4B surpasses Qwen3-VL-4B by an average of 5.2 percentage points across general motion benchmarks. The benchmark, dataset, and code have been released. △ Less

Submitted 28 June, 2026; originally announced June 2026.

Comments: Accepted to ECCV 2026. Project page: https://kagura-0001.github.io/projects/MotionAtlas

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

Authors: Yueyi Sun, Yuhao Wang, Jason Li, Ye Tian, Tao Zhang, Jacky Mai, Yihan Wang, Haochen Wang, Jinbin Bai, Ling Yang, Yunhai Tong

Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limits their efficiency for perception tasks that require captioning multiple regions. In this work, we propose PerceptionDLM, a multimodal diffusion language model optimized for efficient parallel region perception. Built u… ▽ More Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limits their efficiency for perception tasks that require captioning multiple regions. In this work, we propose PerceptionDLM, a multimodal diffusion language model optimized for efficient parallel region perception. Built upon PerceptionDLM-Base, a strong foundational baseline that achieves state-of-the-art performance among open-source diffusion MLLMs, our architecture fully leverages the parallel decoding nature of DLMs. Specifically, we introduce efficient prompting and structured attention masking to enable simultaneous perception of multiple masked regions, allowing the model to generate region descriptions in parallel at both the sequence and token levels. This design significantly improves inference efficiency compared with existing approaches that process regions sequentially. To systematically evaluate the parallelism property of visual perception capability for DLMs, we construct a new Parallel Detailed Localized Captioning Benchmark (ParaDLC-Bench) by scaling the DLC-Bench to include multiple region masks per image, enabling joint evaluation of both caption quality and inference efficiency. Experiments demonstrate that PerceptionDLM maintains competitive performance in region captioning while achieving substantial speed improvements for multi-region perception tasks. Our results highlight the potential of multimodal diffusion language models for efficient, parallel visual perception. To the best of our knowledge, we are the first to achieve parallel region caption and perception by leveraging the advantages of diffusion language models. Code, models, and datasets are released. △ Less

Submitted 17 June, 2026; originally announced June 2026.

Comments: Code available at https://github.com/MSALab-PKU/PerceptionDLM

NVMOS: Non-Verbal Vocalization Quality Assessment in Speech

Authors: Jialong Mai, Jinxin Ji, Xiaofen Xing, Wencui Liu, Xiangmin Xu

Abstract: Non-verbal vocalizations (NVs), such as laughter, sighs, and coughs, are important acoustic cues for emotion and intent. Existing speech quality assessment methods typically focus on overall naturalness, while non-verbal TTS evaluations mainly examine whether a target NV appears with the correct type and position. However, the perceptual quality of NV events themselves remains underexplored. To ad… ▽ More Non-verbal vocalizations (NVs), such as laughter, sighs, and coughs, are important acoustic cues for emotion and intent. Existing speech quality assessment methods typically focus on overall naturalness, while non-verbal TTS evaluations mainly examine whether a target NV appears with the correct type and position. However, the perceptual quality of NV events themselves remains underexplored. To address this gap, we construct an NV-MOS dataset containing outputs from multiple NV-TTS systems and naturally occurring NV samples, with ratings collected from three acoustic experts on a perceptual quality scale. We further analyze audio-capable multimodal large language models such as Gemini and find clear inconsistencies between their scores and expert ratings. These results suggest that general-purpose multimodal models cannot reliably replace human judgments for NV quality assessment. We then propose NVMOS, to our knowledge the first model that can reliably predict the perceptual quality of NV events in speech. Experimental results show that, with a local NV-event focusing module, NVMOS reaches expert-level or stronger agreement with human MOS. △ Less

Submitted 14 June, 2026; originally announced June 2026.

Comments: 6 pages. Code and model: https://github.com/yongaifadian1/NVMOS

Improving Human Diving Endurance with a Field-Deployable, Untethered Exoskeleton

Authors: Zhihao Zhou, Zhenmeng Ju, Rui Yang, Chenxi Zhang, Zhihao Zhou, Ming Xu, Enhao Zheng, Dongjie Jiang, Lecheng Ruan, Jingeng Mai, Qining Wang

Abstract: Human endurance in underwater locomotion is fundamentally restricted by high energetic demands to overcome drag and the finite supply of self-contained breathing gas. While exoskeleton technology can reduce the metabolic cost of humans in terrestrial locomotion, its potential to enhance human endurance during underwater diving remains entirely unexplored. Here, we present DiveMate, a field-deploya… ▽ More Human endurance in underwater locomotion is fundamentally restricted by high energetic demands to overcome drag and the finite supply of self-contained breathing gas. While exoskeleton technology can reduce the metabolic cost of humans in terrestrial locomotion, its potential to enhance human endurance during underwater diving remains entirely unexplored. Here, we present DiveMate, a field-deployable, untethered exoskeleton designed to improve human diving endurance via adaptive kick assistance in real-world underwater environments. During naturalistic diving, DiveMate increases the travel distance using a given energy (breathing gas) by 42.9% and extends dive duration by 54.9% through reducing gas consumption rate. Marked reductions in muscle activation indicate a decrease in physiological exertion, with the net gas consumption rate decreasing by 47.0%. Kinematic characteristics and regularity improvements further underpin efficient energy economy. These results suggest that applying exoskeleton assistance is beneficial for improving human diving endurance and augmenting their ability to explore the aquatic world. This study extends the application frontier of exoskeletons and provides a potential reference for the design and assessment of future underwater assistive devices. △ Less

Submitted 10 June, 2026; originally announced June 2026.

UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing

Authors: Xinming Wei, Chao Jin, Tuo Dai, Yinmin Zhong, Shan Yu, Chengxu Yang, Bingyang Wu, Zili Zhang, Jing Mai, Qianchao Zhu, Zhouyang Li, Yuliang Liu, Guojie Luo

Abstract: Large-scale expert parallelism (EP) is becoming pivotal for training and serving frontier MoE models, but it also amplifies device-level expert load imbalance into compute stragglers, token all-to-all bottlenecks, and activation-memory spikes. Existing balancers redistribute experts periodically based on historical load, which becomes unreliable for production deployments with non-stationary load… ▽ More Large-scale expert parallelism (EP) is becoming pivotal for training and serving frontier MoE models, but it also amplifies device-level expert load imbalance into compute stragglers, token all-to-all bottlenecks, and activation-memory spikes. Existing balancers redistribute experts periodically based on historical load, which becomes unreliable for production deployments with non-stationary load patterns. We present UltraEP, the first exact-load, real-time balancer for large-EP MoE training and serving prefill on rack-scale nodes (RSNs). Leveraging the extended scale-up connectivity among dozens of GPUs within RSNs, UltraEP rebalances every microbatch and layer on critical paths, which requires nontrivial co-design of plan solving and expert replication communication to minimize exposed overhead. To this end, UltraEP eagerly reacts to post-gating load with an efficient quota-driven planner, and executes the resulting irregular expert-state transfers with RSN-native persistent tile streaming and relay-based fan-out mitigation. We evaluate UltraEP in a multi-RSN deployment of up to 256 GPUs, using cutting-edge MoE models from 106B to 671B parameters. Averaged across training and serving, UltraEP achieves 94.3% of the force-balanced ideal throughput, delivering 1.49$\times$ improvement over no-balancing, while reducing the final inter-rank imbalance from 1.30$-$4.01 to 1.01$-$1.04. △ Less

Submitted 18 June, 2026; v1 submitted 2 June, 2026; originally announced June 2026.

Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation

Authors: Junjie Wang, Xinghua Lou, Jason Li, Ye Tian, Keyu Chen, Yulin Li, Bin Kang, Jacky Mai, Yanwei Li, Zhuotao Tian, Liqiang Nie

Abstract: Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm limits their ability to handle complex prompts requiring iterative refinement. To enable multi-round Reflective Visual Generation (RVG), we formalize the Reason-Reflect-Rectify (R^3) loop as a core framework and introdu… ▽ More Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm limits their ability to handle complex prompts requiring iterative refinement. To enable multi-round Reflective Visual Generation (RVG), we formalize the Reason-Reflect-Rectify (R^3) loop as a core framework and introduce R^3-Bench, a benchmark of over 600 expert-annotated instances that quantifies iterative reasoning and rectification capabilities. Evaluation on R^3-Bench reveals a critical gap: while state-of-the-art models can identify generation errors, they fail to generate actionable rectification instructions. To bridge this gap, we propose R^3-Refiner, a dual-stage framework leveraging Group Relative Policy Optimization (GRPO) and a Hierarchical Reward Mechanism (HRM) to better align rectification with reflective reasoning. Experiments show that R^3-Refiner achieves significant improvements on R^3-Bench (+12.0% in Reflective Verdict Score, +9.0% in Rectification Score), and can be seamlessly integrated with various MLLMs to enhance the generation quality of different T2I models on GenEval++ and T2I-CompBench. Code is available at https://github.com/xiaomoguhz/R3-Bench. △ Less

Submitted 19 May, 2026; originally announced May 2026.

Embedded underwater front-end electronics for the 3-inch photomultipliers in the JUNO experiment

Authors: Cédric Cerna, Miao He, Xiaoshan Jiang, Juan Pedro Ochoa-Ricoux, Frédéric Perrot, Angel Abusleme, Thomas Adam, Fengpeng An, Costas Andreopoulos, Giuseppe Andronico, João Pedro Athayde Marcondes de André, Nikolay Anfimov, Vito Antonelli, Tatiana Antoshkina, Didier Auguste, Nikita Balashov, Andrea Barresi, Davide Basilico, Eric Baussan, Marco Beretta, Antonio Bergnoli, Nikita Bessonov, Daniel Bick, Lukas Bieger, Svetlana Biktemerova , et al. (576 additional authors not shown)

Abstract: The Jiangmen Underground Neutrino Observatory (JUNO) is a 20-kton liquid scintillator-based, low-radioactivity, multi-purpose neutrino detector located 693 meters (1800 m.w.e.) underground in the Guangdong province, China. To detect scintillation light produced in the target, the detector is equipped with 17,612 20-inch photomultipliers (PMTs), forming the Large PMT system (LPMT). In addition, 25,… ▽ More The Jiangmen Underground Neutrino Observatory (JUNO) is a 20-kton liquid scintillator-based, low-radioactivity, multi-purpose neutrino detector located 693 meters (1800 m.w.e.) underground in the Guangdong province, China. To detect scintillation light produced in the target, the detector is equipped with 17,612 20-inch photomultipliers (PMTs), forming the Large PMT system (LPMT). In addition, 25,600 3-inch photomultipliers (the Small Photomultiplier System or SPMT) are deployed in the gaps between the LPMTs. This paper presents the design and performance of the underwater front-end electronics developed for the SPMT system. It details the individual electronics boards and their key components, the inter-board interfaces, the system-level design, and the firmware architecture that supports data acquisition and control. It also outlines mechanical and thermal integration, board validation procedures, and system performance metrics. The readout chain includes digitization of 128 PMT channels per unit, synchronized time-stamping, charge measurement, event packaging, and bandwidth management. Comprehensive validation confirms the system's readiness to meet JUNO's stringent physics goals. The underwater electronics achieve noise levels as low as 0.04 photoelectrons with minimal crosstalk (below 0.4%) and a bandwidth of 57 MB/s, ensuring reliable single photo-electron detection and operation under high-rate conditions. The SPMT system has now been fully integrated and installed in JUNO. Its commissioning and physics performance will be reported in a future publication. △ Less

Submitted 1 June, 2026; v1 submitted 28 April, 2026; originally announced April 2026.

Comments: Submitted to Nucl. Instrum. Methods Phys. Res. A

MAGIC-TTS: Fine-Grained Controllable Speech Synthesis with Explicit Local Duration and Pause Control

Authors: Jialong Mai, Xiaofen Xing, Xiangmin Xu

Abstract: Fine-grained local timing control is still absent from modern text-to-speech systems: existing approaches typically provide only utterance-level duration or global speaking-rate control, while precise token-level timing manipulation remains unavailable. To the best of our knowledge, MAGIC-TTS is the first TTS model with explicit local timing control over token-level content duration and pause. MAG… ▽ More Fine-grained local timing control is still absent from modern text-to-speech systems: existing approaches typically provide only utterance-level duration or global speaking-rate control, while precise token-level timing manipulation remains unavailable. To the best of our knowledge, MAGIC-TTS is the first TTS model with explicit local timing control over token-level content duration and pause. MAGIC-TTS is enabled by explicit token-level duration conditioning, carefully prepared high-confidence duration supervision, and training mechanisms that correct zero-value bias and make the model robust to missing local controls. On our timing-control benchmark, MAGIC-TTS substantially improves token-level duration and pause following over spontaneous synthesis. Even when no timing control is provided, MAGIC-TTS maintains natural high-quality synthesis. We further evaluate practical local editing with a scenario-based benchmark covering navigation guidance, guided reading, and accessibility-oriented code reading. In this setting, MAGIC-TTS realizes a reproducible uniform-timing baseline and then moves the edited regions toward the requested local targets with low mean bias. These results show that explicit fine-grained controllability can be implemented effectively in a high-quality TTS system and can support realistic local timing-editing applications. △ Less

Submitted 27 April, 2026; v1 submitted 22 April, 2026; originally announced April 2026.

Comments: Release MAGIC-TTS code, pretrained models, and demo: https://github.com/yongaifadian1/MAGIC-TTS, https://huggingface.co/maimai11/MAGIC-TTS, https://yongaifadian1.github.io/MAGIC-TTS/

Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning

Authors: Jiayao Mai, Bangyan Liao, Zhenjun Zhao, Yingping Zeng, Haoang Li, Javier Civera, Tailin Wu, Yi Zhou, Peidong Liu

Abstract: The Homotopy paradigm, a general principle for solving challenging problems, appears across diverse domains such as robust optimization, global optimization, polynomial root-finding, and sampling. Practical solvers for these problems typically follow a predictor-corrector (PC) structure, but rely on hand-crafted heuristics for step sizes and iteration termination, which are often suboptimal and ta… ▽ More The Homotopy paradigm, a general principle for solving challenging problems, appears across diverse domains such as robust optimization, global optimization, polynomial root-finding, and sampling. Practical solvers for these problems typically follow a predictor-corrector (PC) structure, but rely on hand-crafted heuristics for step sizes and iteration termination, which are often suboptimal and task-specific. To address this, we unify these problems under a single framework, which enables the design of a general neural solver. Building on this unified view, we propose Neural Predictor-Corrector (NPC), which replaces hand-crafted heuristics with automatically learned policies. NPC formulates policy selection as a sequential decision-making problem and leverages reinforcement learning to automatically discover efficient strategies. To further enhance generalization, we introduce an amortized training mechanism, enabling one-time offline training for a class of problems and efficient online inference on new instances. Experiments on four representative homotopy problems demonstrate that our method generalizes effectively to unseen instances. It consistently outperforms classical and specialized baselines in efficiency while demonstrating superior stability across tasks, highlighting the value of unifying homotopy methods into a single neural framework. △ Less

Submitted 2 February, 2026; originally announced February 2026.

A biased-erasure cavity qubit with hardware-efficient quantum error detection

Authors: Jiasheng Mai, Qiyu Liu, Xiaowei Deng, Yanyan Cai, Zhongchu Ni, Libo Zhang, Ling Hu, Pan Zheng, Song Liu, Yuan Xu, Dapeng Yu

Abstract: Erasure qubits are beneficial for quantum error correction due to their relaxed threshold requirements. While dual-rail erasure qubits have been demonstrated with a strong error hierarchy in circuit quantum electrodynamics, biased-erasure qubits -- where erasures originate predominantly from one logical basis state -- offer further advantages. Here, we realize a hardware-efficient biased-erasure q… ▽ More Erasure qubits are beneficial for quantum error correction due to their relaxed threshold requirements. While dual-rail erasure qubits have been demonstrated with a strong error hierarchy in circuit quantum electrodynamics, biased-erasure qubits -- where erasures originate predominantly from one logical basis state -- offer further advantages. Here, we realize a hardware-efficient biased-erasure qubit encoded in the vacuum and two-photon Fock states of a single microwave cavity. The qubit exhibits an erasure bias ratio of over 265. By using a transmon ancilla for logical measurements and mid-circuit erasure detections, we achieve logical state assignment errors below 1% and convert over 99.3% leakage errors into detected erasures. After postselection against erasures, we achieve effective logical relaxation and dephasing rates of $(6.2~\mathrm{ms})^{-1}$ and $(3.1~\mathrm{ms})^{-1}$, respectively, which exceed the erasure error rate by factors of 31 and 15, establishing a strong error hierarchy within the logical subspace. These postselected error rates indicate a coherence gain of about 6.0 beyond the break-even point set by the best physical qubit encoded in the two lowest Fock states in the cavity. Moreover, randomized benchmarking with interleaved erasure detections reveals a residual logical gate error of 0.29%. This work establishes a compact and hardware-efficient platform for biased-erasure qubits, promising concatenations into outer-level stabilizer codes toward fault-tolerant quantum computation. △ Less

Submitted 29 January, 2026; originally announced January 2026.

Comments: Main text: 10 pages, 4 figures; Supplementary material: 14 pages, 9 figures, 2 tables

EasyV2V: A High-quality Instruction-based Video Editing Framework

Authors: Jinjie Mai, Chaoyang Wang, Guocheng Gordon Qian, Willi Menapace, Sergey Tulyakov, Bernard Ghanem, Peter Wonka, Ashkan Mirzaei

Abstract: While image editing has advanced rapidly, video editing remains less explored, facing challenges in consistency, control, and generalization. We study the design space of data, architecture, and control, and introduce \emph{EasyV2V}, a simple and effective framework for instruction-based video editing. On the data side, we compose existing experts with fast inverses to build diverse video pairs, l… ▽ More While image editing has advanced rapidly, video editing remains less explored, facing challenges in consistency, control, and generalization. We study the design space of data, architecture, and control, and introduce \emph{EasyV2V}, a simple and effective framework for instruction-based video editing. On the data side, we compose existing experts with fast inverses to build diverse video pairs, lift image edit pairs into videos via single-frame supervision and pseudo pairs with shared affine motion, mine dense-captioned clips for video pairs, and add transition supervision to teach how edits unfold. On the model side, we observe that pretrained text-to-video models possess editing capability, motivating a simplified design. Simple sequence concatenation for conditioning with light LoRA fine-tuning suffices to train a strong model. For control, we unify spatiotemporal control via a single mask mechanism and support optional reference images. Overall, EasyV2V works with flexible inputs, e.g., video+text, video+mask+text, video+mask+reference+text, and achieves state-of-the-art video editing results, surpassing concurrent and commercial systems. Project page: https://snap-research.github.io/easyv2v/ △ Less

Submitted 18 December, 2025; originally announced December 2025.

Comments: Project page: https://snap-research.github.io/easyv2v/

First measurement of reactor neutrino oscillations at JUNO

Authors: Angel Abusleme, Thomas Adam, Kai Adamowicz, David Adey, Shakeel Ahmad, Rizwan Ahmed, Timo Ahola, Sebastiano Aiello, Fengpeng An, Guangpeng An, Costas Andreopoulos, Giuseppe Andronico, João Pedro Athayde Marcondes de André, Nikolay Anfimov, Vito Antonelli, Tatiana Antoshkina, Burin Asavapibhop, Didier Auguste, Margherita Buizza Avanzini, Andrej Babic, Jingzhi Bai, Weidong Bai, Nikita Balashov, Roberto Barbera, Andrea Barresi , et al. (1114 additional authors not shown)

Abstract: Neutrino oscillations, a quantum effect manifesting at macroscopic scales, are governed by lepton flavor mixing angles and neutrino mass-squared differences that are fundamental parameters of particle physics, representing phenomena beyond the Standard Model. Precision measurements of these parameters are essential for testing the completeness of the three-flavor framework, determining the mass or… ▽ More Neutrino oscillations, a quantum effect manifesting at macroscopic scales, are governed by lepton flavor mixing angles and neutrino mass-squared differences that are fundamental parameters of particle physics, representing phenomena beyond the Standard Model. Precision measurements of these parameters are essential for testing the completeness of the three-flavor framework, determining the mass ordering of neutrinos, and probing possible new physics. The Jiangmen Underground Neutrino Observatory (JUNO) is a 20 kton liquid-scintillator detector located 52.5 km from multiple reactor cores, designed to resolve the interference pattern of reactor neutrinos with sub-percent precision. Here we report, using the first 59.1 days of data collected since detector completion in August 2025, the first simultaneous high-precision determination of two neutrino oscillation parameters, $\sin^2 θ_{12} = 0.3092\,\pm\,0.0087$ and $Δm^2_{21} = (7.50\,\pm\,0.12)\times10^{-5}\;{\rm eV}^2$ for the normal mass ordering scenario, improving the precision by a factor of 1.6 relative to the combination of all previous measurements. These results advance the basic understanding of neutrinos, validate the detector's design, and confirm JUNO's readiness for its primary goal of resolving the neutrino mass ordering with a larger dataset. The rapid achievement with a short exposure highlights JUNO's potential to push the frontiers of precision neutrino physics and paves the way for its broad scientific program. △ Less

Submitted 18 November, 2025; originally announced November 2025.

Comments: 30 pages, 11 figures

Initial performance results of the JUNO detector

Authors: Angel Abusleme, Thomas Adam, Kai Adamowicz, David Adey, Shakeel Ahmad, Rizwan Ahmed, Timo Ahola, Sebastiano Aiello, Fengpeng An, Guangpeng An, Costas Andreopoulos, Giuseppe Andronico, João Pedro Athayde Marcondes de André, Nikolay Anfimov, Vito Antonelli, Tatiana Antoshkina, Burin Asavapibhop, Didier Auguste, Margherita Buizza Avanzini, Andrej Babic, Jingzhi Bai, Weidong Bai, Nikita Balashov, Roberto Barbera, Andrea Barresi , et al. (1114 additional authors not shown)

Abstract: The Jiangmen Underground Neutrino Observatory (JUNO) started physics data taking on 26 August 2025. JUNO consists of a 20-kton liquid scintillator central detector, surrounded by a 35 kton water pool serving as a Cherenkov veto, and almost 1000 m$^2$ of plastic scintillator veto on top. The detector is located in a shallow underground laboratory with an overburden of 1800 m.w.e. This paper present… ▽ More The Jiangmen Underground Neutrino Observatory (JUNO) started physics data taking on 26 August 2025. JUNO consists of a 20-kton liquid scintillator central detector, surrounded by a 35 kton water pool serving as a Cherenkov veto, and almost 1000 m$^2$ of plastic scintillator veto on top. The detector is located in a shallow underground laboratory with an overburden of 1800 m.w.e. This paper presents the performance results of the detector, extensively studied during the commissioning of the water phase, the subsequent liquid scintillator filling phase, and the first physics runs. The liquid scintillator achieved an attenuation length of 20.6 m at 430 nm, while the high coverage PMT system and scintillator together yielded about 1785 photoelectrons per MeV of energy deposit at the detector centre, measured using the 2.223 MeV $γ$ from neutron captures on hydrogen with an Am-C calibration source. The reconstructed energy resolution is 3.4% for two 0.511 MeV $γ$ at the detector centre and 2.9% for the 0.93 MeV quenched Po-214 alpha decays from natural radioactive sources. The energy nonlinearity is calibrated to better than 1%. Intrinsic contaminations of U-238 and Th-232 in the liquid scintillator are below 10$^{-16}$ g/g, assuming secular equilibrium. The water Cherenkov detector achieves a muon detection efficiency better than 99.9% for muons traversing the liquid scintillator volume. During the initial science runs, the data acquisition duty cycle exceeded 97.8%, demonstrating the excellent stability and readiness of JUNO for high-precision neutrino physics. △ Less

Submitted 18 November, 2025; originally announced November 2025.

Comments: 38 pages, 23 figures

Prospects for geoneutrino detection with JUNO

Authors: Thomas Adam, Shakeel Ahmad, Rizwan Ahmed, Fengpeng An, João Pedro Athayde Marcondes de André, Costas Andreopoulos, Giuseppe Andronico, Nikolay Anfimov, Vito Antonelli, Tatiana Antoshkina, Didier Auguste, Marcel Büchner, Weidong Bai, Nikita Balashov, Andrea Barresi, Davide Basilico, Eric Baussan, Marco Beretta, Antonio Bergnoli, Nikita Bessonov, Daniel Bick, Lukas Bieger, Svetlana Biktemerova, Thilo Birkenfeld, Simon Blyth , et al. (605 additional authors not shown)

Abstract: Geoneutrinos, which are antineutrinos emitted during the decay of long-lived radioactive elements inside Earth, serve as a unique tool for studying the composition and heat budget of our planet. The Jiangmen Underground Neutrino Observatory (JUNO) experiment in China, which has recently completed construction, is expected to collect a sample comparable in size to the entire existing world geoneutr… ▽ More Geoneutrinos, which are antineutrinos emitted during the decay of long-lived radioactive elements inside Earth, serve as a unique tool for studying the composition and heat budget of our planet. The Jiangmen Underground Neutrino Observatory (JUNO) experiment in China, which has recently completed construction, is expected to collect a sample comparable in size to the entire existing world geoneutrino dataset in less than a year. This paper presents an updated estimation of sensitivity to geoneutrinos of JUNO using the best knowledge available to date about the experimental site, the surrounding nuclear reactors, the detector response uncertainties, and the constraints expected from the TAO satellite detector. To facilitate comparison with present and future geological models, our results cover a wide range of predicted signal strengths. Despite the significant background from reactor antineutrinos, the experiment will measure the total geoneutrino flux with a precision comparable to that of existing experiments within its first few years, ultimately achieving a world-leading precision of about 8% over ten years. The large statistics of JUNO will also allow separation of the Uranium-238 and Thorium-232 contributions with unprecedented precision, providing crucial constraints on models of formation and composition of Earth. Observation of the mantle signal above the lithospheric flux will be possible but challenging. For models with the highest predicted mantle concentrations of heat-producing elements, a 3-sigma detection over six years requires knowledge of the lithospheric flux to within 15%. Together with complementary measurements from other locations, the geoneutrino results of JUNO will offer cutting-edge, high-precision insights into the interior of Earth, of fundamental importance to both the geoscience and neutrino physics communities. △ Less

Submitted 10 November, 2025; originally announced November 2025.

Comments: 32 pages, with 13 figures and 5 tables

Scattering Induced Mode Chirality in Ring Resonators

Authors: Haochen Yan, Xu Guo, Arghadeep Pal, Xiaoyuan Huang, Alekhya Ghosh, Lewis Hill, Shuangyou Zhang, Nivedita Vishnukumar, Toby Bi, Masoud Kheyri, Jianming Mai, Hao Zhang, Yaojing Zhang, Jolly Xavier, Haihua Fan, Kok Wai Cheah, Peter Littlewood, Pascal DelHaye

Abstract: Non-Hermitian physics can be used to break time reversal symmetry and is important for interactions in a wide range of systems, from active matter and neural networks to metamaterials and non-equilibrium thermodynamics. In integrated photonic devices, non-Hermitian physics can be used for direction-dependent light propagation, reconfigurable light paths, selective energy localization and optical i… ▽ More Non-Hermitian physics can be used to break time reversal symmetry and is important for interactions in a wide range of systems, from active matter and neural networks to metamaterials and non-equilibrium thermodynamics. In integrated photonic devices, non-Hermitian physics can be used for direction-dependent light propagation, reconfigurable light paths, selective energy localization and optical isolators. In this work, we report previously unexplored direction-dependent mode splitting in ring microresonators, achieved by adding multiple scatterers around the cavity. Through experiments, simulations, and theoretical modeling, we unveil the underlying physics that changes the resonance shapes in resonant systems with backscattering. By engineering the spatial configuration of the scatterers, we can produce a predictable and repeatable direction-dependent mode splitting, enabling new ways to route light through optical resonators and photonic networks. In addition, the direction dependent mode-splitting can be used for precise near-field measurements, enhancing traditional sensing in integrated photonic chips. △ Less

Submitted 10 November, 2025; originally announced November 2025.

Design, waterproofing, and mass production of the 3-inch PMT frontend system of JUNO

Authors: Jilei Xu, Miao He, Cédric Cerna, Yongbo Huang, Thomas Adam, Shakeel Ahmad, Rizwan Ahmed, Fengpeng An, Costas Andreopoulos, Giuseppe Andronico, João Pedro Athayde Marcondes de André, Nikolay Anfimov, Vito Antonelli, Tatiana Antoshkina, Didier Auguste, Weidong Bai, Nikita Balashov, Andrea Barresi, Davide Basilico, Eric Baussan, Marco Beretta, Antonio Bergnoli, Nikita Bessonov, Daniel Bick, Lukas Bieger , et al. (609 additional authors not shown)

Abstract: Over 25,600 3-inch photomultiplier tubes (PMTs) have been instrumented for the central detector of the Jiangmen Underground Neutrino Observatory. Each PMT is equipped with a high-voltage divider and a frontend cable with waterproof sealing. Groups of sixteen PMTs are connected to the underwater frontend readout electronics via specialized multi-channel waterproof connectors. This paper outlines th… ▽ More Over 25,600 3-inch photomultiplier tubes (PMTs) have been instrumented for the central detector of the Jiangmen Underground Neutrino Observatory. Each PMT is equipped with a high-voltage divider and a frontend cable with waterproof sealing. Groups of sixteen PMTs are connected to the underwater frontend readout electronics via specialized multi-channel waterproof connectors. This paper outlines the design and mass production processes for the high-voltage divider, the cable and connector, as well as the waterproof potting of the PMT bases. The results of the acceptance tests of all the integrated PMTs are also presented. △ Less

Submitted 22 January, 2026; v1 submitted 7 October, 2025; originally announced October 2025.

Autonomous quantum error correction beyond break-even and its metrological application

Authors: Zhongchu Ni, Ling Hu, Yanyan Cai, Libo Zhang, Jiasheng Mai, Xiaowei Deng, Pan Zheng, Song Liu, Shi-Biao Zheng, Yuan Xu, Dapeng Yu

Abstract: The ability to extend the lifetime of a logical qubit beyond that of the best physical qubit available within the same system, i.e., the break-even point, is a prerequisite for building practical quantum computers. So far, this point has been exceeded through active quantum error correction (QEC) protocols, where a logical error is corrected by measuring its syndrome and then performing an adaptiv… ▽ More The ability to extend the lifetime of a logical qubit beyond that of the best physical qubit available within the same system, i.e., the break-even point, is a prerequisite for building practical quantum computers. So far, this point has been exceeded through active quantum error correction (QEC) protocols, where a logical error is corrected by measuring its syndrome and then performing an adaptive correcting operation. Autonomous QEC (AQEC), without the need for such resource-consuming measurement-feedback control, has been demonstrated in several experiments, but none of which has unambiguously reached the break-even point. Here, we present an unambiguous demonstration of beyond-break-even AQEC in a circuit quantum electrodynamics system, where a photonic logical qubit encoded in a superconducting microwave cavity is protected against photon loss through autonomous error correction, enabled by engineered dissipation. Under the AQEC protection, the logical qubit achieves a lifetime surpassing that of the best physical qubit available in the system by 18\%. We further employ this AQEC protocol to enhance the precision for measuring a slight frequency shift, achieving a metrological gain of 6.3 dB over that using the most robust Fock-state superposition. These results illustrate that the demonstrated AQEC procedure not only represents a crucial step towards fault-tolerant quantum computation but also offers advantages for building robust quantum sensors. △ Less

Submitted 30 September, 2025; originally announced September 2025.

Comments: Main text: 10 pages, 4 figures; Supplementary material: 18 pages, 13 figures, 2 tables

SD-RetinaNet: Topologically Constrained Semi-Supervised Retinal Lesion and Layer Segmentation in OCT

Authors: Botond Fazekas, Guilherme Aresta, Philipp Seeböck, Julia Mai, Ursula Schmidt-Erfurth, Hrvoje Bogunović

Abstract: Optical coherence tomography (OCT) is widely used for diagnosing and monitoring retinal diseases, such as age-related macular degeneration (AMD). The segmentation of biomarkers such as layers and lesions is essential for patient diagnosis and follow-up. Recently, semi-supervised learning has shown promise in improving retinal segmentation performance. However, existing methods often produce anatom… ▽ More Optical coherence tomography (OCT) is widely used for diagnosing and monitoring retinal diseases, such as age-related macular degeneration (AMD). The segmentation of biomarkers such as layers and lesions is essential for patient diagnosis and follow-up. Recently, semi-supervised learning has shown promise in improving retinal segmentation performance. However, existing methods often produce anatomically implausible segmentations, fail to effectively model layer-lesion interactions, and lack guarantees on topological correctness. To address these limitations, we propose a novel semi-supervised model that introduces a fully differentiable biomarker topology engine to enforce anatomically correct segmentation of lesions and layers. This enables joint learning with bidirectional influence between layers and lesions, leveraging unlabeled and diverse partially labeled datasets. Our model learns a disentangled representation, separating spatial and style factors. This approach enables more realistic layer segmentations and improves lesion segmentation, while strictly enforcing lesion location in their anatomically plausible positions relative to the segmented layers. We evaluate the proposed model on public and internal datasets of OCT scans and show that it outperforms the current state-of-the-art in both lesion and layer segmentation, while demonstrating the ability to generalize layer segmentation to pathological cases using partially annotated training data. Our results demonstrate the potential of using anatomical constraints in semi-supervised learning for accurate, robust, and trustworthy retinal biomarker segmentation. △ Less

Submitted 25 September, 2025; originally announced September 2025.

MNV-17: A High-Quality Performative Mandarin Dataset for Nonverbal Vocalization Recognition in Speech

Authors: Jialong Mai, Jinxin Ji, Xiaofen Xing, Chen Yang, Weidong Chen, Jingyuan Xing, Xiangmin Xu

Abstract: Mainstream Automatic Speech Recognition (ASR) systems excel at transcribing lexical content, but largely fail to recognize nonverbal vocalizations (NVs) embedded in speech, such as sighs, laughs, and coughs. This capability is important for a comprehensive understanding of human communication, as NVs convey crucial emotional and intentional cues. Progress in NV-aware ASR has been hindered by the l… ▽ More Mainstream Automatic Speech Recognition (ASR) systems excel at transcribing lexical content, but largely fail to recognize nonverbal vocalizations (NVs) embedded in speech, such as sighs, laughs, and coughs. This capability is important for a comprehensive understanding of human communication, as NVs convey crucial emotional and intentional cues. Progress in NV-aware ASR has been hindered by the lack of high-quality, well-annotated datasets. To address this gap, we introduce MNV-17, a 7.55-hour performative Mandarin speech dataset. Unlike most existing corpora that rely on model-based detection, MNV-17's performative nature ensures high-fidelity, clearly articulated NV instances. To the best of our knowledge, MNV-17 provides the most extensive set of nonverbal vocalization categories, comprising 17 distinct and well-balanced classes of common NVs. We benchmarked MNV-17 on four mainstream ASR architectures, evaluating their joint performance on semantic transcription and NV classification. The dataset and the pretrained model checkpoints will be made publicly available to facilitate future research in expressive ASR. △ Less

Submitted 24 September, 2025; v1 submitted 19 September, 2025; originally announced September 2025.

Comments: Official dataset available at: https://github.com/yongaifadian1/MNV-17. Submitted to ICASSP 2026

Temporal and Rotational Calibration for Event-Centric Multi-Sensor Systems

Authors: Jiayao Mai, Xiuyuan Lu, Kuan Dai, Shaojie Shen, Yi Zhou

Abstract: Event cameras generate asynchronous signals in response to pixel-level brightness changes, offering a sensing paradigm with theoretically microsecond-scale latency that can significantly enhance the performance of multi-sensor systems. Extrinsic calibration is a critical prerequisite for effective sensor fusion; however, the configuration that involves event cameras remains an understudied topic.… ▽ More Event cameras generate asynchronous signals in response to pixel-level brightness changes, offering a sensing paradigm with theoretically microsecond-scale latency that can significantly enhance the performance of multi-sensor systems. Extrinsic calibration is a critical prerequisite for effective sensor fusion; however, the configuration that involves event cameras remains an understudied topic. In this paper, we propose a motion-based temporal and rotational calibration framework tailored for event-centric multi-sensor systems, eliminating the need for dedicated calibration targets. Our method uses as input the rotational motion estimates obtained from event cameras and other heterogeneous sensors, respectively. Different from conventional approaches that rely on event-to-frame conversion, our method efficiently estimates angular velocity from normal flow observations, which are derived from the spatio-temporal profile of event data. The overall calibration pipeline adopts a two-step approach: it first initializes the temporal offset and rotational extrinsics by exploiting kinematic correlations in the spirit of Canonical Correlation Analysis (CCA), and then refines both temporal and rotational parameters through a joint non-linear optimization using a continuous-time parametrization in SO(3). Extensive evaluations on both publicly available and self-collected datasets validate that the proposed method achieves calibration accuracy comparable to target-based methods, while exhibiting superior stability over purely CCA-based methods, and highlighting its precision, robustness and flexibility. To facilitate future research, our implementation will be made open-source. Code: https://github.com/NAIL-HNU/EvMultiCalib. △ Less

Submitted 17 August, 2025; originally announced August 2025.

Comments: 8 pages, 5 figures

ACM Class: I.2.9

Parallel GPT: Harmonizing the Independence and Interdependence of Acoustic and Semantic Information for Zero-Shot Text-to-Speech

Authors: Jingyuan Xing, Zhipeng Li, Jialong Mai, Xiaofen Xing, Xiangmin Xu

Abstract: Advances in speech representation and large language models have enhanced zero-shot text-to-speech (TTS) performance. However, existing zero-shot TTS models face challenges in capturing the complex correlations between acoustic and semantic features, resulting in a lack of expressiveness and similarity. The primary reason lies in the complex relationship between semantic and acoustic features, whi… ▽ More Advances in speech representation and large language models have enhanced zero-shot text-to-speech (TTS) performance. However, existing zero-shot TTS models face challenges in capturing the complex correlations between acoustic and semantic features, resulting in a lack of expressiveness and similarity. The primary reason lies in the complex relationship between semantic and acoustic features, which manifests independent and interdependent aspects.This paper introduces a TTS framework that combines both autoregressive (AR) and non-autoregressive (NAR) modules to harmonize the independence and interdependence of acoustic and semantic information. The AR model leverages the proposed Parallel Tokenizer to synthesize the top semantic and acoustic tokens simultaneously. In contrast, considering the interdependence, the Coupled NAR model predicts detailed tokens based on the general AR model's output. Parallel GPT, built on this architecture, is designed to improve zero-shot text-to-speech synthesis through its parallel structure. Experiments on English and Chinese datasets demonstrate that the proposed model significantly outperforms the quality and efficiency of the synthesis of existing zero-shot TTS models. Speech demos are available at https://t1235-ch.github.io/pgpt/. △ Less

Submitted 28 August, 2025; v1 submitted 6 August, 2025; originally announced August 2025.

Comments: Submitted to IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)

Quantum-Enhanced Dark Matter Search Using Cat States

Authors: Pan Zheng, Yanyan Cai, Bin Xu, Shengcheng Wen, Libo Zhang, Zhongchu Ni, Jiasheng Mai, Yanjie Zeng, Lin Lin, Ling Hu, Xiaowei Deng, Song Liu, Jing Shu, Yuan Xu, Dapeng Yu

Abstract: Quantum metrology has recently emerged as a powerful approach for dark matter (DM) searches, particularly using nonclassical bosonic states in microwave cavities that are sensitive to weak signals. Nonclassical cat states - macroscopic superpositions of coherent states featuring sub-Planck interference structures - offer promising advantages for high-precision measurements. However, their practica… ▽ More Quantum metrology has recently emerged as a powerful approach for dark matter (DM) searches, particularly using nonclassical bosonic states in microwave cavities that are sensitive to weak signals. Nonclassical cat states - macroscopic superpositions of coherent states featuring sub-Planck interference structures - offer promising advantages for high-precision measurements. However, their practical utility in DM search remains unexplored. Here, we report the first experimental application of four-component cat states within a high-quality superconducting microwave cavity to search for dark photons, a potential DM candidate. We demonstrate an 8.1-fold enhancement in the signal photon rate and constrain the dark photon kinetic mixing angle to an unprecedented $ε< 7.32 \times 10^{-16}$ near 6.44~GHz (26.6~$μ$eV). By employing a parametric sideband drive to actively tune the cavity frequency, we achieve dark photon searches and background subtraction across multiple frequency bins, yielding a sensitivity at the $10^{-16}$ level within a 100~kHz bandwidth. Our cat-assisted DM (CaD) search and frequency-scanning techniques demonstrate substantial improvements over previous results, promising potential implications in quantum-enhanced searches for new physics. △ Less

Submitted 8 May, 2026; v1 submitted 31 July, 2025; originally announced July 2025.

Comments: Main text: 8 pages, 4 figures; Supplement: 15 pages, 13 figures, 5 tables

Journal ref: Phys. Rev. Lett. 136, 171002 (2026)

TTS-1 Technical Report

Authors: Oleg Atamanenko, Anna Chalova, Joseph Coombes, Nikki Cope, Phillip Dang, Zhifeng Deng, Jimmy Du, Michael Ermolenko, Feifan Fan, Yufei Feng, Cheryl Fichter, Pavel Filimonov, Louis Fischer, Kylan Gibbs, Valeria Gusarova, Pavel Karpik, Andreas Assad Kottner, Ian Lee, Oliver Louie, Jasmine Mai, Mikhail Mamontov, Suri Mao, Nurullah Morshed, Igor Poletaev, Florin Radu , et al. (7 additional authors not shown)

Abstract: We introduce Inworld TTS-1, a set of two Transformer-based autoregressive text-to-speech (TTS) models. Our largest model, TTS-1-Max, has 8.8B parameters and is designed for utmost quality and expressiveness in demanding applications. TTS-1 is our most efficient model, with 1.6B parameters, built for real-time speech synthesis and on-device use cases. By scaling train-time compute and applying a se… ▽ More We introduce Inworld TTS-1, a set of two Transformer-based autoregressive text-to-speech (TTS) models. Our largest model, TTS-1-Max, has 8.8B parameters and is designed for utmost quality and expressiveness in demanding applications. TTS-1 is our most efficient model, with 1.6B parameters, built for real-time speech synthesis and on-device use cases. By scaling train-time compute and applying a sequential process of pre-training, fine-tuning, and RL-alignment of the speech-language model (SpeechLM) component, both models achieve state-of-the-art performance on a variety of benchmarks, demonstrating exceptional quality relying purely on in-context learning of the speaker's voice. Inworld TTS-1 and TTS-1-Max can generate high-resolution 48 kHz speech with low latency, and support 11 languages with fine-grained emotional control and non-verbal vocalizations through audio markups. We additionally open-source our training and modeling code under an MIT license. △ Less

Submitted 22 July, 2025; originally announced July 2025.

Comments: 20 pages, 10 figures. For associated modeling and training code, see https://github.com/inworld-ai/tts

Faster Lifting for Ordered Domains with Predecessor Relations

Authors: Kuncheng Zou, Jiahao Mai, Yonggang Zhang, Yuyi Wang, Ondřej Kuželka, Yuanhong Wang, Yi Chang

Abstract: We investigate lifted inference on ordered domains with predecessor relations, where the elements of the domain respect a total (cyclic) order, and every element has a distinct (clockwise) predecessor. Previous work has explored this problem through weighted first-order model counting (WFOMC), which computes the weighted sum of models for a given first-order logic sentence over a finite domain. In… ▽ More We investigate lifted inference on ordered domains with predecessor relations, where the elements of the domain respect a total (cyclic) order, and every element has a distinct (clockwise) predecessor. Previous work has explored this problem through weighted first-order model counting (WFOMC), which computes the weighted sum of models for a given first-order logic sentence over a finite domain. In WFOMC, the order constraint is typically encoded by the linear order axiom introducing a binary predicate in the sentence to impose a linear ordering on the domain elements. The immediate and second predecessor relations are then encoded by the linear order predicate. Although WFOMC with the linear order axiom is theoretically tractable, existing algorithms struggle with practical applications, particularly when the predecessor relations are involved. In this paper, we treat predecessor relations as a native part of the axiom and devise a novel algorithm that inherently supports these relations. The proposed algorithm not only provides an exponential speedup for the immediate and second predecessor relations, which are known to be tractable, but also handles the general k-th predecessor relations. The extensive experiments on lifted inference tasks and combinatorics math problems demonstrate the efficiency of our algorithm, achieving speedups of a full order of magnitude. △ Less

Submitted 25 July, 2025; originally announced July 2025.

Diffusion-Based Imaginative Coordination for Bimanual Manipulation

Authors: Huilin Xu, Jian Ding, Jiakun Xu, Ruixiang Wang, Jun Chen, Jinjie Mai, Yanwei Fu, Bernard Ghanem, Feng Xu, Mohamed Elhoseiny

Abstract: Bimanual manipulation is crucial in robotics, enabling complex tasks in industrial automation and household services. However, it poses significant challenges due to the high-dimensional action space and intricate coordination requirements. While video prediction has been recently studied for representation learning and control, leveraging its ability to capture rich dynamic and behavioral informa… ▽ More Bimanual manipulation is crucial in robotics, enabling complex tasks in industrial automation and household services. However, it poses significant challenges due to the high-dimensional action space and intricate coordination requirements. While video prediction has been recently studied for representation learning and control, leveraging its ability to capture rich dynamic and behavioral information, its potential for enhancing bimanual coordination remains underexplored. To bridge this gap, we propose a unified diffusion-based framework for the joint optimization of video and action prediction. Specifically, we propose a multi-frame latent prediction strategy that encodes future states in a compressed latent space, preserving task-relevant features. Furthermore, we introduce a unidirectional attention mechanism where video prediction is conditioned on the action, while action prediction remains independent of video prediction. This design allows us to omit video prediction during inference, significantly enhancing efficiency. Experiments on two simulated benchmarks and a real-world setting demonstrate a significant improvement in the success rate over the strong baseline ACT using our method, achieving a \textbf{24.9\%} increase on ALOHA, an \textbf{11.1\%} increase on RoboTwin, and a \textbf{32.5\%} increase in real-world experiments. Our models and code are publicly available at https://github.com/return-sleep/Diffusion_based_imaginative_Coordination. △ Less

Submitted 15 July, 2025; originally announced July 2025.

Comments: 15 pages, including 10 figures and 16 tables. Accepted at ICCV 2025

Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation

Authors: Jialong Mai, Xiaofen Xing, Yawei Li, Weidong Chen, Zhipeng Li, Jingyuan Xing, Xiangmin Xu

Abstract: Recent research has focused on applying speech large language model (SLLM) to improve speech emotion recognition (SER). However, the inherently high frame rate in speech modality severely limits the signal processing and understanding capabilities of SLLM. For example, a SLLM with a 4K context window can only process 80 seconds of audio at 50Hz feature sampling rate before reaching its capacity li… ▽ More Recent research has focused on applying speech large language model (SLLM) to improve speech emotion recognition (SER). However, the inherently high frame rate in speech modality severely limits the signal processing and understanding capabilities of SLLM. For example, a SLLM with a 4K context window can only process 80 seconds of audio at 50Hz feature sampling rate before reaching its capacity limit. Input token compression methods used in SLLM overlook the continuity and inertia of emotions across multiple conversation turns. This paper proposes a Dynamic Parameter Memory (DPM) mechanism with contextual semantics and sentence-level emotion encoding, enabling processing of unlimited-length audio with limited context windows in SLLM. Specifically, DPM progressively encodes sentence-level information and emotions into a temporary LoRA module during inference to effectively "memorize" the contextual information. We trained an emotion SLLM as a backbone and incorporated our DPM into inference for emotion recognition in conversation (ERC). Experimental results on the IEMOCAP dataset show that DPM significantly improves the emotion recognition capabilities of SLLM when processing long audio sequences, achieving state-of-the-art performance. △ Less

Submitted 24 September, 2025; v1 submitted 11 July, 2025; originally announced July 2025.

Comments: submitted to ICLR 2026

MSC Class: 68T50 ACM Class: I.2.7; H.5.2

A Universal Framework for Large-Scale Multi-Objective Optimization Based on Particle Drift and Diffusion

Authors: Jia-Cheng Li, Min-Rong Chen, Guo-Qiang Zeng, Jian Weng, Man Wang, Jia-Lin Mai

Abstract: Large-scale multi-objective optimization poses challenges to existing evolutionary algorithms in maintaining the performances of convergence and diversity because of high dimensional decision variables. Inspired by the motion of particles in physics, we propose a universal framework for large-scale multi-objective optimization based on particle drift and diffusion to solve these challenges in this… ▽ More Large-scale multi-objective optimization poses challenges to existing evolutionary algorithms in maintaining the performances of convergence and diversity because of high dimensional decision variables. Inspired by the motion of particles in physics, we propose a universal framework for large-scale multi-objective optimization based on particle drift and diffusion to solve these challenges in this paper. This framework innovatively divides the optimization process into three sub-stages: two coarse-tuning sub-stages and one fine-tuning sub-stage. Different strategies of drift-diffusion operations are performed on the guiding solutions according to the current sub-stage, ingeniously simulating the movement of particles under diverse environmental conditions. Finally, representative evolutionary algorithms are embedded into the proposed framework, and their effectiveness are evaluated through comparative experiments on various large-scale multi-objective problems with 1000 to 5000 decision variables. Moreover, comparative algorithms are conducted on neural network training problems to validate the effectiveness of the proposed framework in the practical problems. The experimental results demonstrate that the framework proposed in this paper significantly enhances the performance of convergence and diversity of MOEAs, and improves the computational efficiency of algorithms in solving large-scale multi-objective optimization problems. △ Less

Submitted 18 September, 2025; v1 submitted 8 July, 2025; originally announced July 2025.

Comments: There are several details related to operators are imprecise.To uphold the principle of accuracy, we have decided to retract the article for now

Computational Thinking Reasoning in Large Language Models

Authors: Kechi Zhang, Ge Li, Jia Li, Huangzhao Zhang, Jingjing Xu, Hao Zhu, Lecheng Wang, Jia Li, Yihong Dong, Jing Mai, Bin Gu, Zhi Jin

Abstract: While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they often struggle with complex tasks that require specific thinking paradigms, such as divide-and-conquer and procedural deduction, \etc Previous researches integrate external, reliable tools to alleviate logical inconsistencies and hallucinations in LLMs' problem-solving processes. However, we argue that the… ▽ More While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they often struggle with complex tasks that require specific thinking paradigms, such as divide-and-conquer and procedural deduction, \etc Previous researches integrate external, reliable tools to alleviate logical inconsistencies and hallucinations in LLMs' problem-solving processes. However, we argue that the root challenge is more profound: LLMs lack the complex thinking paradigms (\ie, computational thinking) during reasoning. In this paper, we propose Computational Thinking Model (CTM), a novel framework that incorporates computational thinking paradigms into LLMs. This framework enables LLMs to reformulate complex problems through decomposition, abstraction, reduction, and simulation, among other techniques. Specifically, live code execution is seamlessly integrated into the reasoning process, allowing CTM to think by computing. CTM directly instills computational thinking objectives into LLMs through tailored reinforcement learning rewards, which encourages problem simplification, modular planning, and iterative verification. We conduct extensive evaluations on multiple code generation and mathematical benchmarks. The results demonstrate that CTM outperforms conventional reasoning models and tool-augmented baselines in terms of accuracy, interpretability, and generalizability. We hope this study offers valuable insights for AI reasoning, where LLMs can transform problems into robust, verifiable, and scalable computational workflows, much like computer scientists do. △ Less

Submitted 3 June, 2025; v1 submitted 3 June, 2025; originally announced June 2025.

MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder

Authors: Bowen Zhang, Congchao Guo, Geng Yang, Hang Yu, Haozhe Zhang, Heidi Lei, Jialong Mai, Junjie Yan, Kaiyue Yang, Mingqi Yang, Peikai Huang, Ruiyang Jin, Sitan Jiang, Weihua Cheng, Yawei Li, Yichen Xiao, Yiying Zhou, Yongmao Zhang, Yuan Lu, Yucen He

Abstract: We introduce MiniMax-Speech, an autoregressive Transformer-based Text-to-Speech (TTS) model that generates high-quality speech. A key innovation is our learnable speaker encoder, which extracts timbre features from a reference audio without requiring its transcription. This enables MiniMax-Speech to produce highly expressive speech with timbre consistent with the reference in a zero-shot manner, w… ▽ More We introduce MiniMax-Speech, an autoregressive Transformer-based Text-to-Speech (TTS) model that generates high-quality speech. A key innovation is our learnable speaker encoder, which extracts timbre features from a reference audio without requiring its transcription. This enables MiniMax-Speech to produce highly expressive speech with timbre consistent with the reference in a zero-shot manner, while also supporting one-shot voice cloning with exceptionally high similarity to the reference voice. In addition, the overall quality of the synthesized audio is enhanced through the proposed Flow-VAE. Our model supports 32 languages and demonstrates excellent performance across multiple objective and subjective evaluations metrics. Notably, it achieves state-of-the-art (SOTA) results on objective voice cloning metrics (Word Error Rate and Speaker Similarity) and has secured the top position on the public TTS Arena leaderboard. Another key strength of MiniMax-Speech, granted by the robust and disentangled representations from the speaker encoder, is its extensibility without modifying the base model, enabling various applications such as: arbitrary voice emotion control via LoRA; text to voice (T2V) by synthesizing timbre features directly from text description; and professional voice cloning (PVC) by fine-tuning timbre features with additional data. We encourage readers to visit https://minimax-ai.github.io/tts_tech_report for more examples. △ Less

Submitted 12 May, 2025; originally announced May 2025.

Burstiness and interpersonal foraging between human infants and caregivers in the vocal domain

Authors: VPS Ritwika, Sara Schneider, Lukas D. Lopez, Jeffrey Mai, Ajay Gopinathan, Christopher T. Kello, Anne S. Warlaumont

Abstract: Vocal responses from caregivers are believed to promote more frequent and more advanced infant vocalizations. However, studies that examine this relationship typically do not account for the fact that infant and adult vocalizations are distributed in hierarchical clusters over the course of the day. These bursts and lulls create a challenge for accurately detecting the effects of adult input at im… ▽ More Vocal responses from caregivers are believed to promote more frequent and more advanced infant vocalizations. However, studies that examine this relationship typically do not account for the fact that infant and adult vocalizations are distributed in hierarchical clusters over the course of the day. These bursts and lulls create a challenge for accurately detecting the effects of adult input at immediate turn-by-turn timescales within real-world behavior, as adult responses tend to happen during already occurring bursts of infant vocalizations. Analyzing daylong audio recordings of real-world vocal communication between human infants (ages 3, 6, 9, and 18 months) and their adult caregivers, we first show that both infant and caregiver vocalization events are clustered in time, as evidenced by positive correlations between successive inter-event intervals (IEIs). We propose an approach informed by flight time analyses in foraging studies to assess whether the timing of a vocal agent's next vocalization is modified by inputs from another vocal agent, controlling for the first agent's previous IEI. For both infants and adults, receiving a social response predicts that the individual will vocalize again sooner than they would have in the absence of a response. Overall, our results are consistent with a view of infant-caregiver vocal interactions as an 'interpersonal foraging' process with inherent multi-scale dynamics wherein social responses are among the resources the individuals are foraging for. The analytic approaches introduced here have broad utility to study communication in other modalities, contexts, and species. △ Less

Submitted 20 May, 2025; v1 submitted 2 May, 2025; originally announced May 2025.

Comments: 48 pages total containing main text (Figures 1-4, 17 pages including references) and supplemental pdf (Appendices 1-7, including Figures 1-31 and Tables 1-13)

Can Video Diffusion Model Reconstruct 4D Geometry?

Authors: Jinjie Mai, Wenxuan Zhu, Haozhe Liu, Bing Li, Cheng Zheng, Jürgen Schmidhuber, Bernard Ghanem

Abstract: Reconstructing dynamic 3D scenes (i.e., 4D geometry) from monocular video is an important yet challenging problem. Conventional multiview geometry-based approaches often struggle with dynamic motion, whereas recent learning-based methods either require specialized 4D representation or sophisticated optimization. In this paper, we present Sora3R, a novel framework that taps into the rich spatiotemp… ▽ More Reconstructing dynamic 3D scenes (i.e., 4D geometry) from monocular video is an important yet challenging problem. Conventional multiview geometry-based approaches often struggle with dynamic motion, whereas recent learning-based methods either require specialized 4D representation or sophisticated optimization. In this paper, we present Sora3R, a novel framework that taps into the rich spatiotemporal priors of large-scale video diffusion models to directly infer 4D pointmaps from casual videos. Sora3R follows a two-stage pipeline: (1) we adapt a pointmap VAE from a pretrained video VAE, ensuring compatibility between the geometry and video latent spaces; (2) we finetune a diffusion backbone in combined video and pointmap latent space to generate coherent 4D pointmaps for every frame. Sora3R operates in a fully feedforward manner, requiring no external modules (e.g., depth, optical flow, or segmentation) or iterative global alignment. Extensive experiments demonstrate that Sora3R reliably recovers both camera poses and detailed scene geometry, achieving performance on par with state-of-the-art methods for dynamic 4D reconstruction across diverse scenarios. △ Less

Submitted 26 March, 2025; originally announced March 2025.

4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding

Authors: Wenxuan Zhu, Bing Li, Cheng Zheng, Jinjie Mai, Jun Chen, Letian Jiang, Abdullah Hamdi, Sara Rojas Martinez, Chia-Wen Lin, Mohamed Elhoseiny, Bernard Ghanem

Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive 2D image/video understanding capabilities. However, there are no publicly standardized benchmarks to assess the abilities of MLLMs in understanding the 4D objects (3D objects with temporal evolution over time). In this paper, we introduce 4D-Bench, the first benchmark to evaluate the capabilities of MLLMs in 4D object understand… ▽ More Multimodal Large Language Models (MLLMs) have demonstrated impressive 2D image/video understanding capabilities. However, there are no publicly standardized benchmarks to assess the abilities of MLLMs in understanding the 4D objects (3D objects with temporal evolution over time). In this paper, we introduce 4D-Bench, the first benchmark to evaluate the capabilities of MLLMs in 4D object understanding, featuring tasks in 4D object Question Answering (4D object QA) and 4D object captioning. 4D-Bench provides 4D objects with diverse categories, high-quality annotations, and tasks necessitating multi-view spatial-temporal understanding, different from existing 2D image/video-based benchmarks. With 4D-Bench, we evaluate a wide range of open-source and closed-source MLLMs. The results from the 4D object captioning experiment indicate that MLLMs generally exhibit weaker temporal understanding compared to their appearance understanding, notably, while open-source models approach closed-source performance in appearance understanding, they show larger performance gaps in temporal understanding. 4D object QA yields surprising findings: even with simple single-object videos, MLLMs perform poorly, with state-of-the-art GPT-4o achieving only 63\% accuracy compared to the human baseline of 91\%. These findings highlight a substantial gap in 4D object understanding and the need for further advancements in MLLMs. △ Less

Submitted 22 March, 2025; originally announced March 2025.

Quantum squeezing amplification with a weak Kerr nonlinear oscillator

Authors: Yanyan Cai, Xiaowei Deng, Libo Zhang, Zhongchu Ni, Jiasheng Mai, Peihao Huang, Pan Zheng, Ling Hu, Song Liu, Yuan Xu, Dapeng Yu

Abstract: Quantum squeezed states, with reduced quantum noise, have been widely utilized in quantum sensing and quantum error correction applications. However, generating and manipulating these nonclassical states with a large squeezing degree typically requires strong nonlinearity, which inevitably induces additional decoherence that diminishes the overall performance. Here, we demonstrate the generation a… ▽ More Quantum squeezed states, with reduced quantum noise, have been widely utilized in quantum sensing and quantum error correction applications. However, generating and manipulating these nonclassical states with a large squeezing degree typically requires strong nonlinearity, which inevitably induces additional decoherence that diminishes the overall performance. Here, we demonstrate the generation and amplification of squeezed states in a superconducting microwave cavity with weak Kerr nonlinearity. By subtly engineering an off-resonant microwave drive, we observe cyclic dynamics of the quantum squeezing evolution for various Fock states |N> with N up to 6 in displaced frame of the cavity. Furthermore, we deterministically realize quantum squeezing amplification by alternately displacing the Kerr oscillator using the Trotterization technique, achieving a maximum squeezing degree of 14.6 dB and squeezing rate of 0.28 MHz. Our hardware-efficient displacement-enhanced squeezing operations provide an alternative pathway for generating large squeezed states, promising potential applications in quantum-enhanced sensing and quantum information processing. △ Less

Submitted 11 March, 2025; originally announced March 2025.

Comments: Main text: 8 pages, 4 figures; Supplementary material: 9 pages, 11 figures, 2 tables

Journal ref: Nat. Commun. 17, 970 (2026)

Simulation of the Background from $^{13}$C$(α, n)^{16}$O Reaction in the JUNO Scintillator

Authors: JUNO Collaboration, Thomas Adam, Kai Adamowicz, Shakeel Ahmad, Rizwan Ahmed, Sebastiano Aiello, Fengpeng An, Costas Andreopoulos, Giuseppe Andronico, Nikolay Anfimov, Vito Antonelli, Tatiana Antoshkina, João Pedro Athayde Marcondes de André, Didier Auguste, Weidong Bai, Nikita Balashov, Andrea Barresi, Davide Basilico, Eric Baussan, Marco Beretta, Antonio Bergnoli, Nikita Bessonov, Daniel Bick, Lukas Bieger, Svetlana Biktemerova , et al. (608 additional authors not shown)

Abstract: Large-scale organic liquid scintillator detectors are highly efficient in the detection of MeV-scale electron antineutrinos. These signal events can be detected through inverse beta decay on protons, which produce a positron accompanied by a neutron. A noteworthy background for antineutrinos coming from nuclear power reactors and from the depths of the Earth (geoneutrinos) is generated by ($α, n$)… ▽ More Large-scale organic liquid scintillator detectors are highly efficient in the detection of MeV-scale electron antineutrinos. These signal events can be detected through inverse beta decay on protons, which produce a positron accompanied by a neutron. A noteworthy background for antineutrinos coming from nuclear power reactors and from the depths of the Earth (geoneutrinos) is generated by ($α, n$) reactions. In organic liquid scintillator detectors, $α$ particles emitted from intrinsic contaminants such as $^{238}$U, $^{232}$Th, and $^{210}$Pb/$^{210}$Po, can be captured on $^{13}$C nuclei, followed by the emission of a MeV-scale neutron. Three distinct interaction mechanisms can produce prompt energy depositions preceding the delayed neutron capture, leading to a pair of events correlated in space and time within the detector. Thus, ($α, n$) reactions represent an indistinguishable background in liquid scintillator-based antineutrino detectors, where their expected rate and energy spectrum are typically evaluated via Monte Carlo simulations. This work presents results from the open-source SaG4n software, used to calculate the expected energy depositions from the neutron and any associated de-excitation products. Also simulated is a detailed detector response to these interactions, using a dedicated Geant4-based simulation software from the JUNO experiment. An expected measurable $^{13}$C$(α, n)^{16}$O event rate and reconstructed prompt energy spectrum with associated uncertainties, are presented in the context of JUNO, however, the methods and results are applicable and relevant to other organic liquid scintillator neutrino detectors. △ Less

Submitted 2 May, 2025; v1 submitted 2 March, 2025; originally announced March 2025.

Comments: 25 pages, 14 figures, 4 tables

AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay

Authors: Ziyi Tang, Zechuan Chen, Jiarui Yang, Jiayao Mai, Yongsen Zheng, Keze Wang, Jinrui Chen, Liang Lin

Abstract: Alpha mining, a critical component in quantitative investment, focuses on discovering predictive signals for future asset returns in increasingly complex financial markets. However, the pervasive issue of alpha decay, where factors lose their predictive power over time, poses a significant challenge for alpha mining. Traditional methods like genetic programming face rapid alpha decay from overfitt… ▽ More Alpha mining, a critical component in quantitative investment, focuses on discovering predictive signals for future asset returns in increasingly complex financial markets. However, the pervasive issue of alpha decay, where factors lose their predictive power over time, poses a significant challenge for alpha mining. Traditional methods like genetic programming face rapid alpha decay from overfitting and complexity, while approaches driven by Large Language Models (LLMs), despite their promise, often rely too heavily on existing knowledge, creating homogeneous factors that worsen crowding and accelerate decay. To address this challenge, we propose AlphaAgent, an autonomous framework that effectively integrates LLM agents with ad hoc regularizations for mining decay-resistant alpha factors. AlphaAgent employs three key mechanisms: (i) originality enforcement through a similarity measure based on abstract syntax trees (ASTs) against existing alphas, (ii) hypothesis-factor alignment via LLM-evaluated semantic consistency between market hypotheses and generated factors, and (iii) complexity control via AST-based structural constraints, preventing over-engineered constructions that are prone to overfitting. These mechanisms collectively guide the alpha generation process to balance originality, financial rationale, and adaptability to evolving market conditions, mitigating the risk of alpha decay. Extensive evaluations show that AlphaAgent outperforms traditional and LLM-based methods in mitigating alpha decay across bull and bear markets, consistently delivering significant alpha in Chinese CSI 500 and US S&P 500 markets over the past four years. Notably, AlphaAgent showcases remarkable resistance to alpha decay, elevating the potential for yielding powerful factors. △ Less

Submitted 8 June, 2025; v1 submitted 23 February, 2025; originally announced February 2025.

Comments: 9 pages; Code is available at: https://github.com/RndmVariableQ/AlphaAgent

FullStack Bench: Evaluating LLMs as Full Stack Coders

Authors: Bytedance-Seed-Foundation-Code-Team, :, Yao Cheng, Jianfeng Chen, Jie Chen, Li Chen, Liyu Chen, Wentao Chen, Zhengyu Chen, Shijie Geng, Aoyan Li, Bo Li, Bowen Li, Linyi Li, Boyi Liu, Jiaheng Liu, Kaibo Liu, Qi Liu, Shukai Liu, Siyao Liu, Tianyi Liu, Tingkai Liu, Yongfei Liu, Rui Long, Jing Mai , et al. (31 additional authors not shown)

Abstract: As the capabilities of code large language models (LLMs) continue to expand, their applications across diverse code intelligence domains are rapidly increasing. However, most existing datasets only evaluate limited application domains. To address this gap, we have developed a comprehensive code evaluation dataset FullStack Bench focusing on full-stack programming, which encompasses a wide range of… ▽ More As the capabilities of code large language models (LLMs) continue to expand, their applications across diverse code intelligence domains are rapidly increasing. However, most existing datasets only evaluate limited application domains. To address this gap, we have developed a comprehensive code evaluation dataset FullStack Bench focusing on full-stack programming, which encompasses a wide range of application domains (e.g., basic programming, data analysis, software engineering, mathematics, and machine learning). Besides, to assess multilingual programming capabilities, in FullStack Bench, we design real-world instructions and corresponding unit test cases from 16 widely-used programming languages to reflect real-world usage scenarios rather than simple translations. Moreover, we also release an effective code sandbox execution tool (i.e., SandboxFusion) supporting various programming languages and packages to evaluate the performance of our FullStack Bench efficiently. Comprehensive experimental results on our FullStack Bench demonstrate the necessity and effectiveness of our FullStack Bench and SandboxFusion. △ Less

Submitted 12 May, 2025; v1 submitted 30 November, 2024; originally announced December 2024.

Comments: 26 pages

TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks

Authors: Jinjie Mai, Wenxuan Zhu, Sara Rojas, Jesus Zarzar, Abdullah Hamdi, Guocheng Qian, Bing Li, Silvio Giancola, Bernard Ghanem

Abstract: Neural radiance fields (NeRFs) generally require many images with accurate poses for accurate novel view synthesis, which does not reflect realistic setups where views can be sparse and poses can be noisy. Previous solutions for learning NeRFs with sparse views and noisy poses only consider local geometry consistency with pairs of views. Closely following \textit{bundle adjustment} in Structure-fr… ▽ More Neural radiance fields (NeRFs) generally require many images with accurate poses for accurate novel view synthesis, which does not reflect realistic setups where views can be sparse and poses can be noisy. Previous solutions for learning NeRFs with sparse views and noisy poses only consider local geometry consistency with pairs of views. Closely following \textit{bundle adjustment} in Structure-from-Motion (SfM), we introduce TrackNeRF for more globally consistent geometry reconstruction and more accurate pose optimization. TrackNeRF introduces \textit{feature tracks}, \ie connected pixel trajectories across \textit{all} visible views that correspond to the \textit{same} 3D points. By enforcing reprojection consistency among feature tracks, TrackNeRF encourages holistic 3D consistency explicitly. Through extensive experiments, TrackNeRF sets a new benchmark in noisy and sparse view reconstruction. In particular, TrackNeRF shows significant improvements over the state-of-the-art BARF and SPARF by $\sim8$ and $\sim1$ in terms of PSNR on DTU under various sparse and noisy view setups. The code is available at \href{https://tracknerf.github.io/}. △ Less

Submitted 20 August, 2024; originally announced August 2024.

Comments: ECCV 2024 (supplemental pages included)

Specialized curricula for training vision-language models in retinal image analysis

Authors: Robbie Holland, Thomas R. P. Taylor, Christopher Holmes, Sophie Riedl, Julia Mai, Maria Patsiamanidi, Dimitra Mitsopoulou, Paul Hager, Philip Müller, Hendrik P. N. Scholl, Hrvoje Bogunović, Ursula Schmidt-Erfurth, Daniel Rueckert, Sobha Sivaprasad, Andrew J. Lotery, Martin J. Menten

Abstract: Clinicians spend a significant amount of time reviewing medical images and transcribing their findings regarding patient diagnosis, referral and treatment in text form. Vision-language models (VLMs), which automatically interpret images and summarize their findings as text, have enormous potential to alleviate clinical workloads and increase patient access to high-quality medical care. While found… ▽ More Clinicians spend a significant amount of time reviewing medical images and transcribing their findings regarding patient diagnosis, referral and treatment in text form. Vision-language models (VLMs), which automatically interpret images and summarize their findings as text, have enormous potential to alleviate clinical workloads and increase patient access to high-quality medical care. While foundational models have stirred considerable interest in the medical community, it is unclear whether their general capabilities translate to real-world clinical utility. In this work, we demonstrate that OpenAI's ChatGPT-4o model, in addition to two foundation VLMs designed for medical use, markedly underperform compared to practicing ophthalmologists on specialist tasks crucial to the care of patients with age-related macular degeneration (AMD). To address this, we initially identified the essential capabilities required for image-based clinical decision-making, and then developed a curriculum to selectively train VLMs in these skills. The resulting model, RetinaVLM, can be instructed to write reports that significantly outperform those written by leading foundation medical VLMs and ChatGPT-4o in disease staging (F1 score of 0.63 vs. 0.33) and patient referral (0.67 vs. 0.50), and approaches the diagnostic performance of junior ophthalmologists (who achieve 0.77 and 0.78 on the respective tasks). Furthermore, in a single-blind reader study two senior ophthalmologists with up to 32 years of experience found RetinaVLM's reports were found to be substantially more accurate than those by ChatGPT-4o (64.3% vs. 14.3%). These results reinforce that our curriculum-based approach provides a blueprint towards specializing foundation medical VLMs for real-world clinical tasks. △ Less

Submitted 24 February, 2025; v1 submitted 11 July, 2024; originally announced July 2024.

Comments: Under review at npj Digital Medicine

Hybrid Structure-from-Motion and Camera Relocalization for Enhanced Egocentric Localization

Authors: Jinjie Mai, Abdullah Hamdi, Silvio Giancola, Chen Zhao, Bernard Ghanem

Abstract: We built our pipeline EgoLoc-v1, mainly inspired by EgoLoc. We propose a model ensemble strategy to improve the camera pose estimation part of the VQ3D task, which has been proven to be essential in previous work. The core idea is not only to do SfM for egocentric videos but also to do 2D-3D matching between existing 3D scans and 2D video frames. In this way, we have a hybrid SfM and camera reloca… ▽ More We built our pipeline EgoLoc-v1, mainly inspired by EgoLoc. We propose a model ensemble strategy to improve the camera pose estimation part of the VQ3D task, which has been proven to be essential in previous work. The core idea is not only to do SfM for egocentric videos but also to do 2D-3D matching between existing 3D scans and 2D video frames. In this way, we have a hybrid SfM and camera relocalization pipeline, which can provide us with more camera poses, leading to higher QwP and overall success rate. Our method achieves the best performance regarding the most important metric, the overall success rate. We surpass previous state-of-the-art, the competitive EgoLoc, by $1.5\%$. The code is available at \url{https://github.com/Wayne-Mai/egoloc_v1}. △ Less

Submitted 10 July, 2024; originally announced July 2024.

Comments: 1st place winner of the 2024 Ego4D-Ego-Exo4D Challenge in VQ3D

$(ω, α, n)$-sensitivity and limit sets of zero entropy homeomorphisms on the square

Authors: Jiehua Mai, Enhui Shi, Kesong Yan, Fanping Zeng

Abstract: For a homeomorphism $f$ of a compact metric space $X$ and a positive integer $n\geq 2$, we introduce the notion of $(ω, α, n)$-sensitivity of $f$, which describes such a kind of chaos: there is some $c>0$ such that for any $x\in X$ and any open neighborhood $U$ of $x$, there are points $\{x_i\}_{i=1}^n$ and $\{y_i\}_{i=1}^n$ in $U$ such that both the collection of $ω$-limit sets $ω(x_i, f)$ and th… ▽ More For a homeomorphism $f$ of a compact metric space $X$ and a positive integer $n\geq 2$, we introduce the notion of $(ω, α, n)$-sensitivity of $f$, which describes such a kind of chaos: there is some $c>0$ such that for any $x\in X$ and any open neighborhood $U$ of $x$, there are points $\{x_i\}_{i=1}^n$ and $\{y_i\}_{i=1}^n$ in $U$ such that both the collection of $ω$-limit sets $ω(x_i, f)$ and that of the $α$-limit sets $α(y_i, f)$ are pairwise $c$-separated. Then we construct a class of homeomorphisms of the square $[-1, 1]^2$ which are $(ω, α, n)$-sensitive for any $n\geq 2$ and have zero topological entropies. To investigate further the complexity of zero entropy homeomorphisms by using limit sets, we analyze in depth the limit sets of square homeomorphisms by the boundary permeating technique. Specially, we prove that for any given set of points $Y\equiv\{y_{n1}, y_{n2}:n\in\mathbb N\}$ in $(-1, 1)^2$ which satisfies some loosely technical conditions, and for any given family of pairwise disjoint countable dense subsets $\{W_n:n\in\mathbb N\}$ of $(-1, 1)^2-Y$, there is a zero entropy homeomorphism $f$ on the square $[-1, 1]^2$ such that $ω(x, f)=\{y_{n1}\}$ and $α(x, f)=\{y_{n2}\}$ for any $n$ and any $x\in W_n$. △ Less

Submitted 9 July, 2024; originally announced July 2024.

A new construction of counterexamples to the bounded orbit conjecture

Authors: Jiehua Mai, Enhui Shi, Kesong Yan, Fanping Zeng

Abstract: The bounded orbit conjecture says that every homeomorphism on the plane with each of its orbits being bounded must have a fixed point. Brouwer's translation theorem asserts that the conjecture is true for orientation preserving homeomorphisms, but Boyles' counterexample shows that it is false for the orientation reversing case. In this paper, we give a more comprehensible construction of counterex… ▽ More The bounded orbit conjecture says that every homeomorphism on the plane with each of its orbits being bounded must have a fixed point. Brouwer's translation theorem asserts that the conjecture is true for orientation preserving homeomorphisms, but Boyles' counterexample shows that it is false for the orientation reversing case. In this paper, we give a more comprehensible construction of counterexamples to the conjecture. Roughly speaking, we construct an orientation reversing homeomorphisms $f$ on the square $J^2=[-1, 1]^2$ with $ω(x, f)=\{(-1. 1), (1, 1)\}$ and $α(x, f)=\{(-1. -1), (1, -1)\}$ for each $x\in (-1, 1)^2$. Then by a semi-conjugacy defined by pushing an appropriate part of $\partial J^2$ into $(-1, 1)^2$, $f$ induces a homeomorphism on the plane, which is a counterexample. △ Less

Submitted 9 April, 2025; v1 submitted 24 June, 2024; originally announced June 2024.

Vivid-ZOO: Multi-View Video Generation with Diffusion Model

Authors: Bing Li, Cheng Zheng, Wenxuan Zhu, Jinjie Mai, Biao Zhang, Peter Wonka, Bernard Ghanem

Abstract: While diffusion models have shown impressive performance in 2D image/video generation, diffusion-based Text-to-Multi-view-Video (T2MVid) generation remains underexplored. The new challenges posed by T2MVid generation lie in the lack of massive captioned multi-view videos and the complexity of modeling such multi-dimensional distribution. To this end, we propose a novel diffusion-based pipeline tha… ▽ More While diffusion models have shown impressive performance in 2D image/video generation, diffusion-based Text-to-Multi-view-Video (T2MVid) generation remains underexplored. The new challenges posed by T2MVid generation lie in the lack of massive captioned multi-view videos and the complexity of modeling such multi-dimensional distribution. To this end, we propose a novel diffusion-based pipeline that generates high-quality multi-view videos centered around a dynamic 3D object from text. Specifically, we factor the T2MVid problem into viewpoint-space and time components. Such factorization allows us to combine and reuse layers of advanced pre-trained multi-view image and 2D video diffusion models to ensure multi-view consistency as well as temporal coherence for the generated multi-view videos, largely reducing the training cost. We further introduce alignment modules to align the latent spaces of layers from the pre-trained multi-view and the 2D video diffusion models, addressing the reused layers' incompatibility that arises from the domain gap between 2D and multi-view data. In support of this and future research, we further contribute a captioned multi-view video dataset. Experimental results demonstrate that our method generates high-quality multi-view videos, exhibiting vivid motions, temporal coherence, and multi-view consistency, given a variety of text prompts. △ Less

Submitted 12 June, 2024; originally announced June 2024.

Comments: Our project page is at https://hi-zhengcheng.github.io/vividzoo/