Tootfinder

Data or Language Supervision: What Makes CLIP Better than DINO?
Yiming Liu, Yuhui Zhang, Dhruba Ghosh, Ludwig Schmidt, Serena Yeung-Levy
https://arxiv.org/abs/2510.11835 https:/…

Data or Language Supervision: What Makes CLIP Better than DINO?
CLIP outperforms self-supervised models like DINO as vision encoders for vision-language models (VLMs), but it remains unclear whether this advantage stems from CLIP's language supervision or its much larger training data. To disentangle these factors, we pre-train CLIP and DINO under controlled settings -- using the same architecture, dataset, and training configuration -- achieving similar ImageNet accuracy. Embedding analysis shows that CLIP captures high-level semantics (e.g., object catego…

Photo-$z$ Estimation with Normalizing Flow
Yiming Ren, Kwan Chuen Chan, Le Zhang, Yin Li, Haolin Zhang, Ruiyu Song, Yan Gong, Xian-Min Meng, Xingchen Zhou
https://arxiv.org/abs/2510.10032

Photo-$z$ Estimation with Normalizing Flow
Accurate photometric redshift (photo-$z$) estimation is a key challenge in cosmology, as uncertainties in photo-$z$ directly limit the scientific return of large-scale structure and weak lensing studies, especially in upcoming Stage IV surveys. The problem is particularly severe for faint galaxies with sparse spectroscopic training data. In this work, we introduce nflow-$z$, a novel photo-$z$ estimation method using the powerful machine learning technique of normalizing flow (NF). nflow-$z$ exp…

Experimental Characterization and Dynamic Modeling of THz Channels Under Fog Conditions
Jiaobiao Zhao, Kefeng Huang, Xiaoxiang Li, Mingxia Zhang, Peian Li, Jie Yang, Wenbo Liu, Yiming Zhao, Weidong Hu, Jianjun Ma
https://arxiv.org/abs/2510.09906

Experimental Characterization and Dynamic Modeling of THz Channels Under Fog Conditions
The terahertz (THz) band is a promising candidate for sixth-generation wireless networks, but its deploymen in outdoor environments is challenged by meteorological phenomena, particularly fog, which imposes variable and difficult-to-predict channel degradation. This article introduces dynamic channel model for the THz band explicitly driven by the time-evolving droplet size distribution (DSD) of fog, integrating real-time microphysical sensing to capture variations in the fog microstructure. Ex…

Topologically-protected superluminal pair annihilation in photonic time crystals
Liang Zhang, Chenhao Pan, Jinze He, Danni Chen, Zirui Zhao, Qingqing Cheng, Yiming Pan
https://arxiv.org/abs/2510.08995 …

Topologically-protected superluminal pair annihilation in photonic time crystals
Photonic time crystals (PTCs) - dielectric media whose permittivity is periodically modulated in time - map to a Dirac equation with an imaginary mass, opening a momentum gap (k-gap) where modes grow or decay exponentially. Here, we introduce a sequence of temporal Jackiw-Rebbi kinks that act as a programmable flip of the Dirac mass, exchanging the amplifying and decaying in-gap modes. By launching two seeded pulses with a controlled relative phase, we demonstrate topological pair annihilation …

A 3D Generation Framework from Cross Modality to Parameterized Primitive
Yiming Liang, Huan Yu, Zili Wang, Shuyou Zhang, Guodong Yi, Jin Wang, Jianrong Tan
https://arxiv.org/abs/2510.08656

A 3D Generation Framework from Cross Modality to Parameterized Primitive
Recent advancements in AI-driven 3D model generation have leveraged cross modality, yet generating models with smooth surfaces and minimizing storage overhead remain challenges. This paper introduces a novel multi-stage framework for generating 3D models composed of parameterized primitives, guided by textual and image inputs. In the framework, A model generation algorithm based on parameterized primitives, is proposed, which can identifies the shape features of the model constituent elements, …

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/6]:
- OT Score: An OT based Confidence Score for Source Free Unsupervised Domain Adaptation
Yiming Zhang, Sitong Liu, Alex Cloninger

IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol
Ningyuan Yang, Guanliang Lyu, Mingchen Ma, Yiyi Lu, Yiming Li, Zhihui Gao, Hancheng Ye, Jianyi Zhang, Tingjun Chen, Yiran Chen
https://arxiv.org/abs/2510.01260

IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol
The integration of Large Language Models (LLMs) with Internet-of-Things (IoT) systems faces significant challenges in hardware heterogeneity and control complexity. The Model Context Protocol (MCP) emerges as a critical enabler, providing standardized communication between LLMs and physical devices. We propose IoT-MCP, a novel framework that implements MCP through edge-deployed servers to bridge LLMs and IoT ecosystems. To support rigorous evaluation, we introduce IoT-MCP Bench, the first bench…

InfiR2: A Comprehensive FP8 Training Recipe for Reasoning-Enhanced Language Models
Wenjun Wang, Shuo Cai, Congkai Xie, Mingfa Feng, Yiming Zhang, Zhen Li, Kejing Yang, Ming Li, Jiannong Cao, Yuan Xie, Hongxia Yang
https://arxiv.org/abs/2509.22536

InfiR2: A Comprehensive FP8 Training Recipe for Reasoning-Enhanced Language Models
The immense computational cost of training Large Language Models (LLMs) presents a major barrier to innovation. While FP8 training offers a promising solution with significant theoretical efficiency gains, its widespread adoption has been hindered by the lack of a comprehensive, open-source training recipe. To bridge this gap, we introduce an end-to-end FP8 training recipe that seamlessly integrates continual pre-training and supervised fine-tuning. Our methodology employs a fine-grained, hybri…

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
Yukun Chen, Boheng Li, Yu Yuan, Leyi Qi, Yiming Li, Tianwei Zhang, Zhan Qin, Kui Ren
https://arxiv.org/abs/2509.23871

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
Knowledge distillation (KD) is a vital technique for deploying deep neural networks (DNNs) on resource-constrained devices by transferring knowledge from large teacher models to lightweight student models. While teacher models from third-party platforms may undergo security verification (\eg, backdoor detection), we uncover a novel and critical threat: distillation-conditional backdoor attacks (DCBAs). DCBA injects dormant and undetectable backdoors into teacher models, which become activated i…

The development of a high granular crystal calorimeter prototype of VLAST
Yanshuo Zhang, Qian Chen, Dengyi Chen, Jianguo Liu, Yiming Hu, Yunlong Zhang, Yifeng Wei, Zhongtao Shen, Changqing Feng, Jianhua Guo, Shubin Liu, Guangshun Huang, Xiaolian Wang, Zizong Xu
https://arxiv.org/abs/2509.24851

The development of a high granular crystal calorimeter prototype of VLAST
Very Large Area gamma-ray Space Telescope (VLAST) is the next-generation flagship space observatory for high-energy gamma-ray detection proposed by China. The observation energy range covers from MeV to TeV and beyond, with acceptance of 10 m^2sr. The calorimeter serves as a crucial subdetector of VLAST, responsible for high-precision energy measurement and electron/proton discrimination. This discrimination capability is essential for accurately identifying gamma-ray events among the backgroun…

Replaced article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- pEBR: A Probabilistic Approach to Embedding Based Retrieval
Han Zhang, Yunjing Jiang, Mingming Li, Yiming Qiu Haowei Yuan, Wen-Yun Yang

SN 2025coe: A Triple-Peaked Calcium-Strong Transient from A White-Dwarf Progenitor
Chun Chen, Ning-Chen Sun, Qiang Xi, Samaporn Tinyanont, David Aguado, Ismael P\'erez-Fournon, Fr\'ed\'erick Poidevin, Justyn R. Maund, Amit Kumar, Junjie Jin, Yiming Mao, Beichuan Wang, Yu Zhang, Zhen Guo, Wenxiong Li, C\'esar Rojas-Bravo, Rong-Feng Shen, Lingzhi Wang, Ziyang Wang, Guoying Zhao, Jie Zheng, Yinan Zhu, David L\'opez Fern\'andez-Nespral, Alicia L\'opez-Oramas, Ze…

SN 2025coe: A Triple-Peaked Calcium-Strong Transient from A White-Dwarf Progenitor
SN 2025coe is a calcium-strong transient located at an extremely large projected offset $\sim$39.3 kpc from the center of its host, the nearby early-type galaxy NGC 3277 at a distance of $\sim$25.5 Mpc. In this paper, we present multi-band photometric and spectroscopic observations spanning $\sim$100 days post-discovery. Its multi-band light curves display three distinct peaks: (1) an initial peak at $t \approx 1.6$ days attributed to shock cooling emission, (2) a secondary peak of $M_{R, \, pe…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[7/12]:
- CIE: Controlling Language Model Text Generations Using Continuous Signals
Vinay Samuel, Harshita Diddee, Yiming Zhang, Daphne Ippolito

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
Xiang Deng, Jeff Da, Edwin Pan, Yannis Yiming He, Charles Ide, Kanak Garg, Niklas Lauffer, Andrew Park, Nitin Pasari, Chetan Rane, Karmini Sampath, Maya Krishnan, Srivatsa Kundurthy, Sean Hendryx, Zifan Wang, Chen Bo Calvin Zhang, Noah Jacobson, Bing Liu, Brad Kenstler
https://

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
We introduce SWE-Bench Pro, a substantially more challenging benchmark that builds upon the best practices of SWE-BENCH [25], but is explicitly designed to capture realistic, complex, enterprise-level problems beyond the scope of SWE-BENCH. SWE-BENCH PRO contains 1,865 problems sourced from a diverse set of 41 actively maintained repositories spanning business applications, B2B services, and developer tools. The benchmark is partitioned into a public set with open access to problems sourced fro…

Can Audio Large Language Models Verify Speaker Identity?
Yiming Ren, Xuenan Xu, Baoxiang Li, Shuai Wang, Chao Zhang
https://arxiv.org/abs/2509.19755 https://

Can Audio Large Language Models Verify Speaker Identity?
This paper investigates adapting Audio Large Language Models (ALLMs) for speaker verification (SV). We reformulate SV as an audio question-answering task and conduct comprehensive zero-shot evaluations on public benchmarks, showing that current ALLMs have limited zero-shot SV capability and often struggle in diverse acoustic conditions. To address this challenge, we perform supervised fine-tuning on speaker verification data. A rule-based hard pair sampling strategy is proposed to construct mor…

SN 2024aecx: Double-Peaked Light Curves and Rapid Evolution in a Nearby Type IIb Supernova
Qiang Xi, Ning-Chen Sun, David Aguado, Ismael P'erez-Fournon, Fr'ed'erick Poidevin, Junjie Jin, Yiming Mao, Zexi Niu, Beichuan Wang, Yu Zhang, Kuntal Misra, Divyanshu Janghel, Justyn R. Maund, Amit Kumar, Samaporn Tinyanont, Liang-Duan Liu, Yu-Hao Zhang, Bhavya Ailawadhi, Monalisa Dubey, Zhen Guo, Anshika Gupta, Min He, Dhruv Jain, Debalina Kar, Wenxiong Li, Joe D. Lyman, Haiyang Mu, …

SN 2024aecx: Double-Peaked Light Curves and Rapid Evolution in a Nearby Type IIb Supernova
SN 2024aecx is a nearby ($\sim$11 Mpc) Type IIb SN discovered within $\sim$1 d after explosion. In this paper we report high-cadence photometric and spectroscopic follow-up observations, conducted from as early as 0.27 d post discovery out to the nebular phase at 158.4 d. We analyze the environment of SN 2024aecx and derive a new distance, metallicity and host extinction. The light curve exhibits a hot and luminous shock-cooling peak at the first few days, followed by a main peak with very rapi…

SSNet: Flexible and robust channel extrapolation for fluid antenna systems enabled by an self-supervised learning framework
Yuan Gao, Yiming Liu, Runze Yu, Shengli Liu, Yanliang Jin, Shunqing Zhang, Shugong Xu, Xiaoli Chu
https://arxiv.org/abs/2509.17797

SSNet: Flexible and robust channel extrapolation for fluid antenna systems enabled by an self-supervised learning framework
Fluid antenna systems (FAS) signify a pivotal advancement in 6G communication by enhancing spectral efficiency and robustness. However, obtaining accurate channel state information (CSI) in FAS poses challenges due to its complex physical structure. Traditional methods, such as pilot-based interpolation and compressive sensing, are not only computationally intensive but also lack adaptability. Current extrapolation techniques relying on rigid parametric models do not accommodate the dynamic env…

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
Jane Luo, Xin Zhang, Steven Liu, Jie Wu, Yiming Huang, Yangyu Huang, Chengyu Yin, Ying Xin, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Qi Chen, Scarlett Li, Mao Yang
https://arxiv.org/abs/2509.16198

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
Large language models excel at function- and file-level code generation, yet generating complete repositories from scratch remains a fundamental challenge. This process demands coherent and reliable planning across proposal- and implementation-level stages, while natural language, due to its ambiguity and verbosity, is ill-suited for faithfully representing complex software structures. To address this, we introduce the Repository Planning Graph (RPG), a persistent representation that unifies pr…

Enhancing Retrieval Augmentation via Adversarial Collaboration
Letian Zhang, Guanghao Meng, Xudong Ren, Yiming Wang, Shu-Tao Xia
https://arxiv.org/abs/2509.14750 https://…

Enhancing Retrieval Augmentation via Adversarial Collaboration
Retrieval-augmented Generation (RAG) is a prevalent approach for domain-specific LLMs, yet it is often plagued by "Retrieval Hallucinations"--a phenomenon where fine-tuned models fail to recognize and act upon poor-quality retrieved documents, thus undermining performance. To address this, we propose the Adversarial Collaboration RAG (AC-RAG) framework. AC-RAG employs two heterogeneous agents: a generalist Detector that identifies knowledge gaps, and a domain-specialized Resolver that provides …

Direct Simultaneous Translation Activation for Large Audio-Language Models
Pei Zhang, Yiming Wang, Jialong Tang, Baosong Yang, Rui Wang, Derek F. Wong, Fei Huang
https://arxiv.org/abs/2509.15692

Direct Simultaneous Translation Activation for Large Audio-Language Models
Simultaneous speech-to-text translation (Simul-S2TT) aims to translate speech into target text in real time, outputting translations while receiving source speech input, rather than waiting for the entire utterance to be spoken. Simul-S2TT research often modifies model architectures to implement read-write strategies. However, with the rise of large audio-language models (LALMs), a key challenge is how to directly activate Simul-S2TT capabilities in base models without additional architectural …

Terahretz Channel Modeling in ULEO Satellite-to-Ground Communications
Mingxia Zhang, Wanzhu Chang, Jie Yang, Hong Liang, Yiming Zhao, Houjun Sun, Jianjun Ma
https://arxiv.org/abs/2509.12769

Terahretz Channel Modeling in ULEO Satellite-to-Ground Communications
The exponential growth in satellite data traffic demands communication systems exceeding current microwave capacity limitations, while the terahertz (THz) frequency band (0.1-10 THz) offers unprecedented bandwidth potential with superior weather resilience compared to optical systems, particularly when combined with ultra-low Earth orbit (ULEO) satellite deployments below 300 km altitude. This article presents comprehensive channel modeling and performance evaluation for ULEO-THz satellite-to-g…