arXiv subjects

Congcong Wang

Publications and source records attributed to Congcong Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Kimi k1.5: Scaling Reinforcement Learning with LLMs

Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learning (RL) unlocks a new axis for the continued improvement of artificial intelligence, with the promise that large language models (LLMs) can scale their training data by learning to explore with rewards. However, prior published work has not produced competitive results. In light of this, we report on the training practice of Kimi k1.5, our latest multi-modal LLM trained with RL, including its RL training techniques, multi-modal data recipes, and infrastructure optimization. Long context scaling and improved policy optimization methods are key ingredients of our approach, which establishes a simplistic, effective RL framework without relying on more complex techniques such as Monte Carlo tree search, value functions, and process reward models. Notably, our system achieves state-of-the-art reasoning performance across multiple benchmarks and modalities -- e.g., 77.5 on AIME, 96.2 on MATH 500, 94-th percentile on Codeforces, 74.9 on MathVista -- matching OpenAI's o1. Moreover, we present effective long2short methods that use long-CoT techniques to improve short-CoT models, yielding state-of-the-art short-CoT reasoning results -- e.g., 60.8 on AIME, 94.6 on MATH500, 47.3 on LiveCodeBench -- outperforming existing short-CoT models such as GPT-4o and Claude Sonnet 3.5 by a large margin (up to +550%).

cs.AI↗

arXiv2025

Simulation of radiation damage effect on silicon detectors using RASER

Silicon detectors play a crucial role in high energy physics experiments. In future high energy physics experiments, silicon detectors will be exposed to extremely high fluence environment, which can significantly affect their performance. It is important to understand the electrical behavior of detectors after irradiation. In this study, an irradiation simulation framework is constructed in RASER to simulate leakage current and charge collection effciency. The defect parameters are obtained from the Hamburg penta trap model (HPTM). Based on this work, we predict the similar silicon inner tracker which under a ten-year CEPC Higgs mode run can still maintain over 90% charge collection efficiency.

physics.ins-det↗

arXiv2024

Charge Collection Performance of 4H-SiC LGAD

The 4H-SiC material exhibits good detection performance, but there are still many problems like signal distortion and poor signal quality. The 4H-SiC low gain avalanche detector (LGAD) has been fabricated for the first time to solve these problems, which named SICAR (SIlicon CARbide). The results of electrical characteristics and charge collection performance of the 4H-SiC LGAD are reported. The influence of different metal thicknesses on the leakage current of the device is studied.~By optimizing the fabrication process, the leakage current of the detector is reduced by four orders of magnitude. The experimental results confirm this 4H-SiC LGAD has an obvious gain structure, the gain factor of the SICAR is reported to be about 2 at 150 V. The charge collection efficiency (CCE) of the device was analyzed using $α$ particle incidence of 5.54 MeV, and the CCE is 90\% @100~V. This study provides a novel 4H-SiC LGAD radiation detector for application in the field of high energy particle physics.

physics.ins-det↗

arXiv2024

High precision proton beam monitor system concept design on CSNS based on SiC

A high precision beam monitor system based on silicon carbide PIN sensor is designed for China Spallation Neutron Source 1.6 GeV proton beam to monitor the proton beam fluence.The concept design of the beam monitor system is finished together with front-end electronics with silicon carbide PIN sensors, readout system and mechanical system.Several tests are performed to study the performance of each component of the system.The charge collection of the SiC PIN sensors after proton radiation is studied with 80 MeV proton beam for continuous running. Research on the performance of the front-end electronics and readout system is finished for better data acquisition.The uncertainty of proton beam fluence is below 1% in the beam monitor system.

physics.acc-ph↗

arXiv2023

Electric Field Measurement by Edge Transient Current Technique on Silicon Low Gain Avalanche Detector

A novel methodology, named the diffusion profile method, is proposed in this research to measure the electric field of a low gain avalanche detector (LGAD).The proposed methodology utilizes the maximum of the time derivative of the edge transient current technique (edge-TCT) test waveform to quantify the dispersion of the light-induced carriers. This method introduces the estimation of the elongation of the carrier cluster caused by diffusion and the divergence of the electric field force during its drift along the detector. The effectiveness of the diffusion profile method is demonstrated through the analysis of both simulated and measured edge-TCT waveforms. Experimental data was collected from a laser scan performed on an LGAD detector along its thickness direction.A simulation procedure has been developed in RASER (RAdiation SEmiconductoR) to generate signals from LGAD.An assumption of immediate one-step carrier multiplication is introduced to simplify the avalanche process.Simulation results were compared with transient current data at the waveform level and showed a favorable match. Both simulation and experimental results have shown that the diffusion profile method could be applied to certain edge-TCT facilities as an alternative of electric field measurement.

physics.ins-det↗

arXiv2023

Design and simulation of a novel 4H-SiC LGAD timing device

Silicon-based fast time detectors have been widely used in high energy physics, nuclear physics, space exploration and other fields in recent years. However, silicon detectors often require complex low-temperature systems when operating in irradiation environment, and their detection performance decrease with the increase of irradiation dose. Compared with silicon, silicon carbide (SiC) has a wider bandgap, higher atomic displacement energy, saturated electron drift velocity and thermal conductivity. Simultaneously, the low gain avalanche detector avoids crosstalk and high noise from high multiplication due to its moderate gain, and thus can maintain a high detector signal without increasing noise. Thus, the 4H-SiC particle detector, especially the low gain avalanche detector has the potential to detect the minimal ionized particles (MIPs) under extreme irradiation and high temperature environments. In this work, the emphasis was placed on the design of a 4H-SiC Low Gain Avalanche Detector (LGAD), especially the epitaxial structure and technical process which played the main roles. In addition, a simulation tool--RASER(RAdiation SEmiconductoR) was developed to simulate the performances including the electrical properties and time resolution of the 4H-SiC LGAD we proposed. The working voltage and gain effectiveness of the LGAD were verified by the simulation of electrical performances. The time resolution of the LGAD is (35.0 $\pm$ 0.2) ps under the electrical field of -800 V, which is better than that of the 4H-SiC PIN detector.

physics.ins-det↗

arXiv2023

Coping with low data availability for social media crisis message categorisation

During crisis situations, social media allows people to quickly share information, including messages requesting help. This can be valuable to emergency responders, who need to categorise and prioritise these messages based on the type of assistance being requested. However, the high volume of messages makes it difficult to filter and prioritise them without the use of computational techniques. Fully supervised filtering techniques for crisis message categorisation typically require a large amount of annotated training data, but this can be difficult to obtain during an ongoing crisis and is expensive in terms of time and labour to create. This thesis focuses on addressing the challenge of low data availability when categorising crisis messages for emergency response. It first presents domain adaptation as a solution for this problem, which involves learning a categorisation model from annotated data from past crisis events (source domain) and adapting it to categorise messages from an ongoing crisis event (target domain). In many-to-many adaptation, where the model is trained on multiple past events and adapted to multiple ongoing events, a multi-task learning approach is proposed using pre-trained language models. This approach outperforms baselines and an ensemble approach further improves performance...

cs.CL↗

arXiv2023

STA: Self-controlled Text Augmentation for Improving Text Classifications

Despite recent advancements in Machine Learning, many tasks still involve working in low-data regimes which can make solving natural language problems difficult. Recently, a number of text augmentation techniques have emerged in the field of Natural Language Processing (NLP) which can enrich the training data with new examples, though they are not without their caveats. For instance, simple rule-based heuristic methods are effective, but lack variation in semantic content and syntactic structure with respect to the original text. On the other hand, more complex deep learning approaches can cause extreme shifts in the intrinsic meaning of the text and introduce unwanted noise into the training data. To more reliably control the quality of the augmented examples, we introduce a state-of-the-art approach for Self-Controlled Text Augmentation (STA). Our approach tightly controls the generation process by introducing a self-checking procedure to ensure that generated examples retain the semantic content of the original text. Experimental results on multiple benchmarking datasets demonstrate that STA substantially outperforms existing state-of-the-art techniques, whilst qualitative analysis reveals that the generated examples are both lexically diverse and semantically reliable.

cs.CL↗

arXiv2022

Leakage current simulations of Low Gain Avalanche Diode with improved Radiation Damage Modeling

We report precise TCAD simulations of IHEP-IME-v1 Low Gain Avalanche Diode (LGAD) calibrated by secondary ion mass spectroscopy (SIMS). Our setup allows us to evaluate the leakage current, capacitance, and breakdown voltage of LGAD, which agree with measurements' results before irradiation. And we propose an improved LGAD Radiation Damage Model (LRDM) which combines local acceptor removal with global deep energy levels. The LRDM is applied to the IHEP-IME-v1 LGAD and able to predict the leakage current well at -30 $^{\circ}$C after an irradiation fluence of $ Φ_{eq}=2.5 \times 10^{15} ~n_{eq}/cm^{2}$. The charge collection efficiency (CCE) is under development.

physics.ins-det↗

arXiv2022

Simulation of the 4H-SiC Low Gain Avalanche Diode

Silicon Carbide device (4H-SiC) has potential radiation hardness, high saturated carrier velocity and low temperature sensitivity theoretically. The Silicon Low Gain Avalanche Diode (LGAD) has been verified to have excellent time performance. Therefore, the 4H-SiC LGAD is introduced in this work for application to detect the Minimum Ionization Particles (MIPs). We provide guidance to determine the thickness and doping level of the gain layer after an analytical analysis. The gain layer thickness $d_{gain}=0.5~μm$ is adopted in our design. We design two different types of 4H-SiC LGAD which have two types electric field, and the corresponding leakage current, capacitance and gain are simulated by TCAD tools. Through analysis of the simulation results, the advantages and disadvantages are discussed for two types of 4H-SiC LGAD.

physics.ins-det↗

arXiv2022

Time Resolution of the 4H-SiC PIN Detector

We address the determination of the time resolution for the $\rm 100~μm$ 4H-SiC PIN detectors fabricated by Nanjing University (NJU). The time response to $\rm β$ particles from a $\rm ^{90}$Sr source is investigated for the detection of the minimum ionizing particles (MIPs). We study the influence of different reverse voltages, which correspond to different carrier velocities and device sizes, and how this correlates with the detector capacitance. We determine a time resolution $\rm (94\pm1)~ps$ for $\rm 100~μm$ 4H-SiC PIN detector. A fast simulation software, termed RASER (RAdiation SEmiconductoR), is developed, and validated by comparing the waveform obtained from simulated and measured data. The simulated time resolution is $\rm (73\pm 1)~ps$ after considering the intrinsic leading contributions of the detector to time resolution.

physics.ins-det↗

arXiv2022

Timing performance simulation for 3D 4H-SiC detector

To meet high radiation challenge for detectors in future high-energy physics, a novel 3D 4H-SiC detector was investigated. SiC detectors could potentially operate in radiation harsh and room temperature environment because of its high thermal conductivity and high atomic displacement threshold energy. 3D structure, which decouples thickness and distance between electrodes, further improves timing performance and radiation hardness of the detector. We developed a simulation software - RASER (RAdiation SEmiconductoR) to simulate the time resolution of planar and 3D 4H-SiC detectors with different parameters and structures, and the reliability of the software is verified by comparing time resolution results of simulation with data. The rough time resolution of 3D 4H-SiC detector was estimated, and the simulation parameters could be used as guideline to 3D 4H-SiC detector design and optimization.

physics.ins-det↗

arXiv2021

UCD-CS at TREC 2021 Incident Streams Track

In recent years, the task of mining important information from social media posts during crises has become a focus of research for the purposes of assisting emergency response (ES). The TREC Incident Streams (IS) track is a research challenge organised for this purpose. The track asks participating systems to both classify a stream of crisis-related tweets into humanitarian aid related information types and estimate their importance regarding criticality. The former refers to a multi-label information type classification task and the latter refers to a priority estimation task. In this paper, we report on the participation of the University College Dublin School of Computer Science (UCD-CS) in TREC-IS 2021. We explored a variety of approaches, including simple machine learning algorithms, multi-task learning techniques, text augmentation, and ensemble approaches. The official evaluation results indicate that our runs achieve the highest scores in many metrics. To aid reproducibility, our code is publicly available at https://github.com/wangcongcong123/crisis-mtl.

cs.CL↗

arXiv2021

Transformer-based Multi-task Learning for Disaster Tweet Categorisation

Social media has enabled people to circulate information in a timely fashion, thus motivating people to post messages seeking help during crisis situations. These messages can contribute to the situational awareness of emergency responders, who have a need for them to be categorised according to information types (i.e. the type of aid services the messages are requesting). We introduce a transformer-based multi-task learning (MTL) technique for classifying information types and estimating the priority of these messages. We evaluate the effectiveness of our approach with a variety of metrics by submitting runs to the TREC Incident Streams (IS) track: a research initiative specifically designed for disaster tweet classification and prioritisation. The results demonstrate that our approach achieves competitive performance in most metrics as compared to other participating runs. Subsequently, we find that an ensemble approach combining disparate transformer encoders within our approach helps to improve the overall effectiveness to a significant extent, achieving state-of-the-art performance in almost every metric. We make the code publicly available so that our work can be reproduced and used as a baseline for the community for future work in this domain.

cs.CL↗

arXiv2021

Crisis Domain Adaptation Using Sequence-to-sequence Transformers

User-generated content (UGC) on social media can act as a key source of information for emergency responders in crisis situations. However, due to the volume concerned, computational techniques are needed to effectively filter and prioritise this content as it arises during emerging events. In the literature, these techniques are trained using annotated content from previous crises. In this paper, we investigate how this prior knowledge can be best leveraged for new crises by examining the extent to which crisis events of a similar type are more suitable for adaptation to new events (cross-domain adaptation). Given the recent successes of transformers in various language processing tasks, we propose CAST: an approach for Crisis domain Adaptation leveraging Sequence-to-sequence Transformers. We evaluate CAST using two major crisis-related message classification datasets. Our experiments show that our CAST-based best run without using any target data achieves the state of the art performance in both in-domain and cross-domain contexts. Moreover, CAST is particularly effective in one-to-one cross-domain adaptation when trained with a larger language model. In many-to-one adaptation where multiple crises are jointly used as the source domain, CAST further improves its performance. In addition, we find that more similar events are more likely to bring better adaptation performance whereas fine-tuning using dissimilar events does not help for adaptation. To aid reproducibility, we open source our code to the community.

cs.CL↗

arXiv2021

AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?

With the unprecedented developments in deep learning, automatic segmentation of main abdominal organs seems to be a solved problem as state-of-the-art (SOTA) methods have achieved comparable results with inter-rater variability on many benchmark datasets. However, most of the existing abdominal datasets only contain single-center, single-phase, single-vendor, or single-disease cases, and it is unclear whether the excellent performance can generalize on diverse datasets. This paper presents a large and diverse abdominal CT organ segmentation dataset, termed AbdomenCT-1K, with more than 1000 (1K) CT scans from 12 medical centers, including multi-phase, multi-vendor, and multi-disease cases. Furthermore, we conduct a large-scale study for liver, kidney, spleen, and pancreas segmentation and reveal the unsolved segmentation problems of the SOTA methods, such as the limited generalization ability on distinct medical centers, phases, and unseen diseases. To advance the unsolved problems, we further build four organ segmentation benchmarks for fully supervised, semi-supervised, weakly supervised, and continual learning, which are currently challenging and active research topics. Accordingly, we develop a simple and effective method for each benchmark, which can be used as out-of-the-box methods and strong baselines. We believe the AbdomenCT-1K dataset will promote future in-depth research towards clinical applicable abdominal organ segmentation methods. The datasets, codes, and trained models are publicly available at https://github.com/JunMa11/AbdomenCT-1K.

cs.CV↗

arXiv2021

Multi-task transfer learning for finding actionable information from crisis-related messages on social media

The Incident streams (IS) track is a research challenge aimed at finding important information from social media during crises for emergency response purposes. More specifically, given a stream of crisis-related tweets, the IS challenge asks a participating system to 1) classify what the types of users' concerns or needs are expressed in each tweet, known as the information type (IT) classification task and 2) estimate how critical each tweet is with regard to emergency response, known as the priority level prediction task. In this paper, we describe our multi-task transfer learning approach for this challenge. Our approach leverages state-of-the-art transformer models including both encoder-based models such as BERT and a sequence-to-sequence based T5 for joint transfer learning on the two tasks. Based on this approach, we submitted several runs to the track. The returned evaluation results show that our runs substantially outperform other participating runs in both IT classification and priority level prediction.

cs.CL↗

arXiv2021

Stereo Correspondence and Reconstruction of Endoscopic Data Challenge

The stereo correspondence and reconstruction of endoscopic data sub-challenge was organized during the Endovis challenge at MICCAI 2019 in Shenzhen, China. The task was to perform dense depth estimation using 7 training datasets and 2 test sets of structured light data captured using porcine cadavers. These were provided by a team at Intuitive Surgical. 10 teams participated in the challenge day. This paper contains 3 additional methods which were submitted after the challenge finished as well as a supplemental section from these teams on issues they found with the dataset.

cs.CV↗