Chen Bin
YOU?
Author Swipe
View article: Parameter-Free Neural Lens Blur Rendering for High-Fidelity Composites
Parameter-Free Neural Lens Blur Rendering for High-Fidelity Composites Open
Consistent and natural camera lens blur is important for seamlessly blending 3D virtual objects into photographed real-scenes. Since lens blur typically varies with scene depth, the placement of virtual objects and their corresponding blur…
View article: Parameter-Free Neural Lens Blur Rendering for High-Fidelity Composites
Parameter-Free Neural Lens Blur Rendering for High-Fidelity Composites Open
Consistent and natural camera lens blur is important for seamlessly blending 3D virtual objects into photographed real-scenes. Since lens blur typically varies with scene depth, the placement of virtual objects and their corresponding blur…
View article: Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design
Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design Open
Text-conditioned molecular generation aims to translate natural-language descriptions into chemical structures, enabling scientists to specify functional groups, scaffolds, and physicochemical constraints without handcrafted rules. Diffusi…
View article: Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design
Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design Open
Text-conditioned molecular generation aims to translate natural-language descriptions into chemical structures, enabling scientists to specify functional groups, scaffolds, and physicochemical constraints without handcrafted rules. Diffusi…
View article: Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design
Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design Open
Text-conditioned molecular generation aims to translate natural-language descriptions into chemical structures, enabling scientists to specify functional groups, scaffolds, and physicochemical constraints without handcrafted rules. Diffusi…
View article: CCDC 2427891: Experimental Crystal Structure Determination
CCDC 2427891: Experimental Crystal Structure Determination Open
An entry from the Cambridge Structural Database, the world’s repository for small molecule crystal structures. The entry contains experimental data from a crystal diffraction study. The deposited dataset for this entry is freely available …
View article: Megaodynerus flavogaster Long, Chen & Li 2025, sp. nov.
Megaodynerus flavogaster Long, Chen & Li 2025, sp. nov. Open
Megaodynerus flavogaster Long, Chen & Li sp. nov.Figs 2–12Material examined.Holotype • ♀, China, Anhui, Lu’ an City, Jinzhai County, Tiantangzhai Town, 31°10'23"N, 115°49'29"E, alt. 703 m, 15 May 2023, Yin-Qiao Zhang l…
View article: Simulation Degradation Datasets for Health Prognosis of a Control Moment Gyroscope's Flywheel system
Simulation Degradation Datasets for Health Prognosis of a Control Moment Gyroscope's Flywheel system Open
This presents the dataset used for health prognosis of Control Moment Gyroscope (CMG)'s flywheel system. The dataset is collected from Simulink model of a flywheel system with electrical and mechanical degradation by Beihang Automatic Test…
View article: CCDC 2467210: Experimental Crystal Structure Determination
CCDC 2467210: Experimental Crystal Structure Determination Open
An entry from the Cambridge Structural Database, the world’s repository for small molecule crystal structures. The entry contains experimental data from a crystal diffraction study. The deposited dataset for this entry is freely available …
View article: Megaodynerus Gusenleitner 2012
Megaodynerus Gusenleitner 2012 Open
GenusMegaodynerusGusenleitner, 2012Megaodynerus Gusenleitner, 2012: 1048; Bai et al. 2021: 388.Type species.Megaodynerus maximus Gusenleitner, 2012, by subsequent designation of Gusenleitner 2013: 127.…
View article: Incidence and risk factors of abnormal liver function and anti-tuberculosis drug-induced liver injury: a multicenter retrospective study involving 482 chinese pediatric tuberculosis patients
Incidence and risk factors of abnormal liver function and anti-tuberculosis drug-induced liver injury: a multicenter retrospective study involving 482 chinese pediatric tuberculosis patients Open
The incidence of abnormal liver function and ATDILI differed. By considering laboratory indicators and clinical practice, early identification and detection of abnormal liver function in children during anti-TB treatment, along with timely…
View article: Megaodynerus Gusenleitner 2012
Megaodynerus Gusenleitner 2012 Open
GenusMegaodynerusGusenleitner, 2012 Megaodynerus Gusenleitner, 2012: 1048; Bai et al. 2021: 388. Type species. Megaodynerus maximus Gusenleitner, 2012, by subsequent designation of Gusenleitner 2013: 127. Diagnosis. This genus is notable f…
View article: Megaodynerus flavogaster Long, Chen & Li 2025, sp. nov.
Megaodynerus flavogaster Long, Chen & Li 2025, sp. nov. Open
Megaodynerus flavogaster Long, Chen & Li sp. nov. Figs 2–12 Material examined. Holotype • ♀, China, Anhui, Lu’ an City, Jinzhai County, Tiantangzhai Town, 31°10'23"N, 115°49'29"E, alt. 703 m, 15 May 2023, Yin-Qiao Zhang leg. (IOZCAS). Para…
View article: SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models
SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models Open
Evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer workflows. Existing benchmarks often focus on algorithmic proble…
View article: SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models
SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models Open
Evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer workflows. Existing benchmarks often focus on algorithmic proble…
View article: The Exospace Weather Frontier
The Exospace Weather Frontier Open
Space weather is among the most powerful and least understood forces shaping planetary atmospheres. In our Solar System, we observe its effects directly: atmospheric escape, chemical disruption, and spectacular auroral displays. Yet for ex…
View article: Diffusion Index Forecast with Tensor Data
Diffusion Index Forecast with Tensor Data Open
In this paper, we consider diffusion index forecast with both tensor and non-tensor predictors, where the tensor structure is preserved with a Canonical Polyadic (CP) tensor factor model. When the number of non-tensor predictors is small, …
View article: Diffusion Index Forecast with Tensor Data
Diffusion Index Forecast with Tensor Data Open
In this paper, we consider diffusion index forecast with both tensor and non-tensor predictors, where the tensor structure is preserved with a Canonical Polyadic (CP) tensor factor model. When the number of non-tensor predictors is small, …
View article: KAT-Coder Technical Report
KAT-Coder Technical Report Open
Recent advances in large language models (LLMs) have enabled progress in agentic coding, where models autonomously reason, plan, and act within interactive software development workflows. However, bridging the gap between static text-based…
View article: MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds
MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds Open
The rapid advancement of large language models has intensified public concerns about the potential misuse. Therefore, it is important to build trustworthy AI-generated text detection systems. Existing methods neglect stylistic modeling and…
View article: OpenRLHF: A Ray-based Easy-to-use, Scalable and High-performance RLHF Framework
OpenRLHF: A Ray-based Easy-to-use, Scalable and High-performance RLHF Framework Open
Large Language Models (LLMs) fine-tuned via Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) significantly improve the alignment of human-AI values and further raise the upper boun…
View article: Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors
Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors Open
The misuse of large language models (LLMs), such as academic plagiarism, has driven the development of detectors to identify LLM-generated texts. To bypass these detectors, paraphrase attacks have emerged to purposely rewrite these texts t…
View article: Multimodal machine learning framework for predicting and enhancing higher education using reinforcement learning and graph neural networks
Multimodal machine learning framework for predicting and enhancing higher education using reinforcement learning and graph neural networks Open
There has been a growing emphasis on intelligent educational systems to foster student success, with universities working to aid timely interventions and personalized learning. This study is based upon the primary research problem of devel…
View article: Multimodal machine learning framework for predicting and enhancing higher education using reinforcement learning and graph neural networks
Multimodal machine learning framework for predicting and enhancing higher education using reinforcement learning and graph neural networks Open
There has been a growing emphasis on intelligent educational systems to foster student success, with universities working to aid timely interventions and personalized learning. This study is based upon the primary research problem of devel…
View article: LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter
LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter Open
Blind face restoration from low-quality (LQ) images is a challenging task that requires not only high-fidelity image reconstruction but also the preservation of facial identity. While diffusion models like Stable Diffusion have shown promi…
View article: Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs
Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs Open
Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations: …
View article: On QFT in Klein space
On QFT in Klein space Open
In this paper, we investigate the quantum field theory in Klein space that has two time directions. To study the canonical quantization, we select the ``length of time" $q$ as the evolution direction of the system. In our novel constructio…
View article: FaSDiff: Balancing Perception and Semantics in Face Compression via Stable Diffusion Priors
FaSDiff: Balancing Perception and Semantics in Face Compression via Stable Diffusion Priors Open
With the increasing deployment of facial image data across a wide range of applications, efficient compression tailored to facial semantics has become critical for both storage and transmission. While recent learning-based face image compr…
View article: Age of Information Analysis for NOMA-Assisted Grant-Free Transmissions with Randomly Arrived Packets
Age of Information Analysis for NOMA-Assisted Grant-Free Transmissions with Randomly Arrived Packets Open
This paper investigates the application of non-orthogonal multiple access (NOMA) to grant-free transmissions to reduce the age of information (AoI) in uplink status update systems, where multiple sources upload their {status updates} to {a…
View article: Knowledge-Decoupled Synergetic Learning: An MLLM based Collaborative Approach to Few-shot Multimodal Dialogue Intention Recognition
Knowledge-Decoupled Synergetic Learning: An MLLM based Collaborative Approach to Few-shot Multimodal Dialogue Intention Recognition Open
Few-shot multimodal dialogue intention recognition is a critical challenge in the e-commerce domainn. Previous methods have primarily enhanced model classification capabilities through post-training techniques. However, our analysis reveal…