arXiv subjects

Shanshan Li

Publications and source records attributed to Shanshan Li.

At least 19 recordsLinked to original sources

arXiv2026

QoS-Aware RACH Preamble Slicing via Quota-Projected Branching Deep Reinforcement Learning

Quality-of-service (QoS)-aware random access requires adaptive allocation of a finite random access channel (RACH) preamble budget across heterogeneous traffic and access procedures. This paper proposes QP-BD3QN-RACH, a quota-projected branching deep reinforcement learning controller for mixed two-step (2RA) and four-step (4RA) contention-based random access. Four action branches correspond to the delay-sensitive and delay-tolerant 2RA/4RA preamble pools. A branching dueling Double DQN selects pool-specific multipliers, and deterministic quota projection converts them to nonnegative integer allocations that preserve the preamble budget. With five actions per branch, the controller represents 625 pre-projection branch-action tuples using 20 branch-action outputs. Evaluation covers five arrival loads, cross-method comparison under nominal seed 42, six-seed sensitivity of QP-BD3QN-RACH, and targeted ablations. Across the five-load grid, its mean direction-aligned differences relative to four comparators are positive: 5.74 to 8.21 percentage points for success/collision, 1.23 to 1.92 percentage points for fallback, 0.35 to 0.68 percentage points for blocking, and 0.128 to 0.456 decision intervals for successful-access delay. Load-wise results exhibit metric-dependent tradeoffs, particularly under intermediate and overload conditions.

cs.NI↗

arXiv2026

Student Competency Assessment and Presentation Methods Based on Algorithm Courses

This full research paper describes the assessment and presentation of student competencies in algorithm courses, grounded in the CC2020 competency model. With the growing emphasis on bridging the gap between academic training and industry demands, competency-based education, which integrates knowledge, skills, and dispositions, has become pivotal in computer science education. To bridge the gap, we need to develop a comprehensive framework to evaluate competencies (knowledge, skills, and dispositions) in computer science education. The research aims to analyze learning behavior patterns, design methods for competency assessment in algorithm courses, and evaluate the difficulty of course experiments to inform curriculum design. We collected programming experiment and written assignment data from 169 students, adapting it to the xAPI specification for unified analysis. In this work, Markov process modeling was employed to analyze behavioral sequences, revealing cognitive patterns during programming tasks. Multiple methods were applied to quantify competencies (knowledge, skills, dispositions) and identify distinct student clusters. Course difficulty was quantified using proactiveness metrics derived from submission timeliness. This work contributes a scalable framework for competency assessment in algorithm courses and offers actionable insights for personalized teaching and curriculum optimization. Practically, it enables instructors to tailor interventions based on student clusters and optimize task difficulty. Future work will integrate more students' performance to validate competency models and extend the framework to broader computer science curricula.

cs.CY↗

arXiv2026

IncreRTL: Traceability-Guided Incremental RTL Generation under Requirement Evolution

Large language models (LLMs) have shown promise in generating RTL code from natural-language descriptions, but existing methods remain static and struggle to adapt to evolving design requirements, potentially causing structural drift and costly full regeneration. We propose IncreRTL, a LLM-driven framework for incremental RTL generation under requirement evolution. By constructing requirement-code traceability links to locate and regenerate affected code segments, IncreRTL achieves accurate and consistent updates. Evaluated on our newly constructed EvoRTL-Bench, IncreRTL demonstrates notable improvements in regeneration consistency and efficiency, advancing LLM-based RTL generation toward practical engineering deployment.

cs.SE↗

arXiv2026

A Generalist Model Including Evolved Star Mass and Age

Determining precise stellar ages and masses for evolved giants is crucial for Galactic archaeology but challenged by spectral degeneracies. Gaia's low-resolution XP spectra offer a unique opportunity to infer these parameters on a massive scale using data-driven methods. We extend a transformer-based astronomical foundation model to evolved stars, establishing a unified framework to simultaneously predict atmospheric parameters ($T_{\mathrm{eff}}$, $\log g$, $[\mathrm{M}/\mathrm{H}]$) and evolutionary labels (mass, age) with physical consistency. Treating spectra as token sequences, we integrated mass and age into the model's vocabulary. The model is trained on Gaia XP spectra cross-matched with the APOGEE DR17 DistMass catalog. Our generative approach enables flexible input handling, including spectral inpainting and parameter-to-spectrum generation. On an independent test set, the model achieves a prediction scatter of $\sigma \approx 0.114 \, M_{\odot}$ for mass and $\sigma \approx 1.334$ Gyr for age. Beyond numerical accuracy, it successfully reproduces the giant branch's mass-luminosity relation and autonomously disentangles interstellar extinction from intrinsic temperature variations without explicit physical priors. It also robustly recovers missing spectral data and estimates reliable uncertainties. Validating that foundation models can internalize stellar physics from data, this physically-aware, probabilistic framework offers a powerful tool for unraveling Milky Way history using large-scale spectroscopic surveys.

astro-ph.SR↗

arXiv2026

LookBench: A Live and Holistic Open Benchmark for Fashion Image Retrieval

In this paper, we present LookBench (We use the term "look" to reflect retrieval that mirrors how people shop -- finding the exact item, a close substitute, or a visually consistent alternative.), a live, holistic and challenging benchmark for fashion image retrieval in real e-commerce settings. LookBench includes both recent product images sourced from live websites and AI-generated fashion images, reflecting contemporary trends and use cases. Each test sample is time-stamped and we intend to update the benchmark periodically, enabling contamination-aware evaluation aligned with declared training cutoffs. Grounded in our fine-grained attribute taxonomy, LookBench covers single-item and outfit-level retrieval across. Our experiments reveal that LookBench poses a significant challenge on strong baselines, with many models achieving below $60\%$ Recall@1. Our proprietary model achieves the best performance on LookBench, and we release an open-source counterpart that ranks second, with both models attaining state-of-the-art results on legacy Fashion200K evaluations. LookBench is designed to be updated semi-annually with new test samples and progressively harder task variants, providing a durable measure of progress. We publicly release our leaderboard, dataset, evaluation code, and trained models.

cs.CV↗

arXiv2025

MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning

Traditional workflow-based agents exhibit limited intelligence when addressing real-world problems requiring tool invocation. Tool-integrated reasoning (TIR) agents capable of autonomous reasoning and tool invocation are rapidly emerging as a powerful approach for complex decision-making tasks involving multi-step interactions with external environments. In this work, we introduce MindWatcher, a TIR agent integrating interleaved thinking and multimodal chain-of-thought (CoT) reasoning. MindWatcher can autonomously decide whether and how to invoke diverse tools and coordinate their use, without relying on human prompts or workflows. The interleaved thinking paradigm enables the model to switch between thinking and tool calling at any intermediate stage, while its multimodal CoT capability allows manipulation of images during reasoning to yield more precise search results. We implement automated data auditing and evaluation pipelines, complemented by manually curated high-quality datasets for training, and we construct a benchmark, called MindWatcher-Evaluate Bench (MWE-Bench), to evaluate its performance. MindWatcher is equipped with a comprehensive suite of auxiliary reasoning tools, enabling it to address broad-domain multimodal problems. A large-scale, high-quality local image retrieval database, covering eight categories including cars, animals, and plants, endows model with robust object recognition despite its small size. Finally, we design a more efficient training infrastructure for MindWatcher, enhancing training speed and hardware utilization. Experiments not only demonstrate that MindWatcher matches or exceeds the performance of larger or more recent models through superior tool invocation, but also uncover critical insights for agent training, such as the genetic inheritance phenomenon in agentic RL.

cs.AI↗

arXiv2025

Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model

Recent strides in video generation have paved the way for unified audio-visual generation. In this work, we present Seedance 1.5 pro, a foundational model engineered specifically for native, joint audio-video generation. Leveraging a dual-branch Diffusion Transformer architecture, the model integrates a cross-modal joint module with a specialized multi-stage data pipeline, achieving exceptional audio-visual synchronization and superior generation quality. To ensure practical utility, we implement meticulous post-training optimizations, including Supervised Fine-Tuning (SFT) on high-quality datasets and Reinforcement Learning from Human Feedback (RLHF) with multi-dimensional reward models. Furthermore, we introduce an acceleration framework that boosts inference speed by over 10X. Seedance 1.5 pro distinguishes itself through precise multilingual and dialect lip-syncing, dynamic cinematic camera control, and enhanced narrative coherence, positioning it as a robust engine for professional-grade content creation. Seedance 1.5 pro is now accessible on Volcano Engine at https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?type=GenVideo.

cs.CV↗

arXiv2025

TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making

In daily life, people often move through spaces to find objects that meet their needs, posing a key challenge in embodied AI. Traditional Demand-Driven Navigation (DDN) handles one need at a time but does not reflect the complexity of real-world tasks involving multiple needs and personal choices. To bridge this gap, we introduce Task-Preferenced Multi-Demand-Driven Navigation (TP-MDDN), a new benchmark for long-horizon navigation involving multiple sub-demands with explicit task preferences. To solve TP-MDDN, we propose AWMSystem, an autonomous decision-making system composed of three key modules: BreakLLM (instruction decomposition), LocateLLM (goal selection), and StatusMLLM (task monitoring). For spatial memory, we design MASMap, which combines 3D point cloud accumulation with 2D semantic mapping for accurate and efficient environmental understanding. Our Dual-Tempo action generation framework integrates zero-shot planning with policy-based fine control, and is further supported by an Adaptive Error Corrector that handles failure cases in real time. Experiments demonstrate that our approach outperforms state-of-the-art baselines in both perception accuracy and navigation robustness.

cs.RO↗

arXiv2025

A Grey Literature Review of AI-Native Applications

Background: The rapid advancement of large language models (LLMs) has given rise to AI-native applications, a new paradigm in software engineering that fundamentally redefines how software is designed, developed, and evolved. Despite their growing prominence, AI-native applications still lack a unified engineering definition and architectural blueprint, leaving practitioners without systematic guidance for system design, quality assurance, and technology selection. Objective: This study seeks to establish a comprehensive understanding of AI-native applications by identifying their defining characteristics, key quality attributes, and typical technology stacks, as well as by clarifying the opportunities and challenges they present. Method: We conducted a grey literature review, integrating conceptual perspectives retrieved from targeted Google and Bing searches with practical insights derived from leading open-source projects on GitHub. A structured protocol encompassing source selection, quality assessment, and thematic analysis was applied to synthesize findings across heterogeneous sources. Results: We finally identified 106 studies based on the selection criteria. The analysis reveals that AI-native applications are distinguished by two core pillars: the central role of AI as the system's intelligence paradigm and their inherently probabilistic, non-deterministic nature. Critical quality attributes include reliability, usability, performance efficiency, and AI-specific observability. In addition, a typical technology stack has begun to emerge, comprising LLM orchestration frameworks, vector databases, and AI-native observability platforms. These systems emphasize response quality, cost-effectiveness, and outcome predictability, setting them apart from conventional software systems. Conclusion: This study is the first to propose a dual-layered engineering blueprint...

cs.SE↗

arXiv2025

StyDeco: Unsupervised Style Transfer with Distilling Priors and Semantic Decoupling

Diffusion models have emerged as the dominant paradigm for style transfer, but their text-driven mechanism is hindered by a core limitation: it treats textual descriptions as uniform, monolithic guidance. This limitation overlooks the semantic gap between the non-spatial nature of textual descriptions and the spatially-aware attributes of visual style, often leading to the loss of semantic structure and fine-grained details during stylization. In this paper, we propose StyDeco, an unsupervised framework that resolves this limitation by learning text representations specifically tailored for the style transfer task. Our framework first employs Prior-Guided Data Distillation (PGD), a strategy designed to distill stylistic knowledge without human supervision. It leverages a powerful frozen generative model to automatically synthesize pseudo-paired data. Subsequently, we introduce Contrastive Semantic Decoupling (CSD), a task-specific objective that adapts a text encoder using domain-specific weights. CSD performs a two-class clustering in the semantic space, encouraging source and target representations to form distinct clusters. Extensive experiments on three classic benchmarks demonstrate that our framework outperforms several existing approaches in both stylistic fidelity and structural preservation, highlighting its effectiveness in style transfer with semantic preservation. In addition, our framework supports a unique de-stylization process, further demonstrating its extensibility. Our code is vailable at https://github.com/QuanjianSong/StyDeco.

cs.CV↗

arXiv2025

Photometric redshift estimation for emission line galaxies of DESI Legacy Imaging Surveys by CNN-MLP

Emission Line Galaxies (ELGs) are crucial for cosmological studies, particularly in understanding the large-scale structure of the Universe and the role of dark energy. ELGs form an essential component of the target catalogue for the Dark Energy Spectroscopic Instrument (DESI), a major astronomical survey. However, the accurate selection of ELGs for such surveys is challenging due to the inherent uncertainties in determining their redshifts with photometric data. In order to improve the accuracy of photometric redshift estimation for ELGs, we propose a novel approach CNN-MLP that combines Convolutional Neural Networks (CNNs) with Multilayer Perceptrons (MLPs). This approach integrates both images and photometric data derived from the DESI Legacy Imaging Surveys Data Release 10. By leveraging the complementary strengths of CNNs (for image data processing) and MLPs (for photometric feature integration), the CNN-MLP model achieves a $\sigma_{\mathrm{NMAD}}$ (normalised median absolute deviation) of 0.0140 and an outlier fraction of 2.57%. Compared to other models, CNN-MLP demonstrates a significant improvement in the accuracy of ELG photometric redshift estimation, which directly benefits the target selection process for DESI. In addition, we explore the photometric redshifts of different galaxy types (Starforming, Starburst, AGN, Broadline). Furthermore, this approach will contribute to more reliable photometric redshift estimation in ongoing and future large-scale sky surveys (e.g. LSST, CSST, Euclid), enhancing the overall efficiency of cosmological research and galaxy surveys.

astro-ph.IM↗

arXiv2025

ChiseLLM: Unleashing the Power of Reasoning LLMs for Chisel Agile Hardware Development

The growing demand for Domain-Specific Architecture (DSA) has driven the development of Agile Hardware Development Methodology (AHDM). Hardware Construction Language (HCL) like Chisel offers high-level abstraction features, making it an ideal language for HCL-Based AHDM. While Large Language Models (LLMs) excel in code generation tasks, they still face challenges with Chisel generation, particularly regarding syntax correctness and design variability. Recent reasoning models have significantly enhanced code generation capabilities through test-time scaling techniques. However, we found that reasoning models without domain adaptation cannot bring substantial benefits to Chisel code generation tasks. This paper presents ChiseLLM, a solution comprising data processing and transformation, prompt-guided reasoning trace synthesis, and domain-adapted model training. We constructed high-quality datasets from public RTL code resources and guided the model to adopt structured thinking patterns through prompt enhancement methods. Experiments demonstrate that our ChiseLLM-7B and ChiseLLM-32B models improved syntax correctness by 18.85% and 26.32% respectively over base models, while increasing variability design ability by 47.58% compared to baseline reasoning models. Our datasets and models are publicly available, providing high-performance, cost-effective models for HCL-Based AHDM, and offering an effective baseline for future research. Github repository: https://github.com/observerw/ChiseLLM

cs.AI↗

arXiv2025

Who is in Charge here? Understanding How Runtime Configuration Affects Software along with Variables&Constants

Runtime misconfiguration can lead to software performance degradation and even cause failure. Developers typically perform sanity checks during the configuration parsing stage to prevent invalid parameter values. However, we discovered that even valid values that pass these checks can also lead to unexpected severe consequences. Our study reveals the underlying reason: the value of runtime configuration parameters may interact with other constants and variables when propagated and used, altering its original effect on software behavior. Consequently, parameter values may no longer be valid when encountering complex runtime environments and workloads. Therefore, it is extremely challenging for users to properly configure the software before it starts running. This paper presents the first comprehensive and in-depth study (to the best of our knowledge) on how configuration affects software at runtime through the interaction with constants, and variables (PCV Interaction). Parameter values represent user intentions, constants embody developer knowledge, and variables are typically defined by the runtime environment and workload. This interaction essentially illustrates how different roles jointly determine software behavior. In this regard, we studied 705 configuration parameters from 10 large-scale software systems. We reveal that a large portion of configuration parameters interact with constants/variables after parsing. We analyzed the interaction patterns and their effects on software runtime behavior. Furthermore, we highlighted the risks of PCV interaction and identified potential issues behind specific interaction patterns. Our findings expose the "double edge" of PCV interaction, providing new insights and motivating the development of new automated techniques to help users configure software appropriately and assist developers in designing better configurations.

cs.SE↗

arXiv2025

Enhancing the Accuracy and Comprehensibility in Architectural Tactics Detection via Small Model-Augmented Prompt Engineering

Architectural tactics (ATs), as the concrete implementation of architectural decisions in code, address non-functional requirements of software systems. Due to the implicit nature of architectural knowledge in code implementation, developers may risk inadvertently altering or removing these tactics during code modifications or optimizations. Such unintended changes can trigger architectural erosion, gradually undermining the system's original design. While many researchers have proposed machine learning-based methods to improve the accuracy of detecting ATs in code, the black-box nature and the required architectural domain knowledge pose significant challenges for developers in verifying the results. Effective verification requires not only accurate detection results but also interpretable explanations that enhance their comprehensibility. However, this is a critical gap in current research. Large language models (LLMs) can generate easily interpretable ATs detection comments if they have domain knowledge. Fine-tuning LLMs to acquire domain knowledge faces challenges such as catastrophic forgetting and hardware constraints. Thus, we propose Prmt4TD, a small model-augmented prompting framework to enhance the accuracy and comprehensibility of ATs detection. Combining fine-tuned small models with In-Context Learning can also reduce fine-tuning costs while equipping the LLM with additional domain knowledge. Prmt4TD can leverage the remarkable processing and reasoning capabilities of LLMs to generate easily interpretable ATs detection results. Our evaluation results demonstrate that Prmt4TD achieves accuracy (\emph{F1-score}) improvement of 13\%-23\% on the ATs balanced dataset and enhances the comprehensibility of the detection results.

cs.SE↗

arXiv2025

A Survey on Memory-Efficient Transformer-Based Model Training in AI for Science

Scientific research faces high costs and inefficiencies with traditional methods, but the rise of deep learning and large language models (LLMs) offers innovative solutions. This survey reviews transformer-based LLM applications across scientific fields such as biology, medicine, chemistry, and meteorology, underscoring their role in advancing research. However, the continuous expansion of model size has led to significant memory demands, hindering further development and application of LLMs for science. This survey systematically reviews and categorizes memory-efficient pre-training techniques for large-scale transformers, including algorithm-level, system-level, and hardware-software co-optimization. Using AlphaFold 2 as an example, we demonstrate how tailored memory optimization methods can reduce storage needs while preserving prediction accuracy. By bridging model efficiency and scientific application needs, we hope to provide insights for scalable and cost-effective LLM training in AI for science.

cs.LG↗

arXiv2024

Unseen Horizons: Unveiling the Real Capability of LLM Code Generation Beyond the Familiar

Recently, large language models (LLMs) have shown strong potential in code generation tasks. However, there are still gaps before they can be fully applied in actual software development processes. Accurately assessing the code generation capabilities of large language models has become an important basis for evaluating and improving the models. Some existing works have constructed datasets to evaluate the capabilities of these models. However, the current evaluation process may encounter the illusion of "Specialist in Familiarity", primarily due to three gaps: the exposure of target code, case timeliness, and dependency availability. The fundamental reason for these gaps is that the code in current datasets may have been extensively exposed and exercised during the training phase, and due to the continuous training and development of LLM, their timeliness has been severely compromised. The key to solve the problem is to, as much as possible, evaluate the LLMs using code that they have not encountered before. Thus, the fundamental idea in this paper is to draw on the concept of code obfuscation, changing code at different levels while ensuring the functionality and output. To this end, we build a code-obfuscation based benchmark OBFUSEVAL. We first collect 1,354 raw cases from five real-world projects, including function description and code. Then we use three-level strategy (symbol, structure and semantic) to obfuscate descriptions, code and context dependencies. We evaluate four LLMs on OBFU- SEVAL and compared the effectiveness of different obfuscation strategy. We use official test suites of these projects to evaluate the generated code. The results show that after obfuscation, the average decrease ratio of test pass rate can up to 62.5%.

cs.SE↗

arXiv2024

Lagrangian Mean Curvature Flow in Pseudo-Euclidean Space II

In this paper, we consider the mean curvature flow of entire Lagrangian graphs with initial data in the pseudo-Euclidean space, which is related to the special Lagrangian parabolic equation. We show that the parabolic equation \eqref{11} has a smooth solution $u(x,t)$ for three corresponding nonlinear equations between the Monge-Amp$\grave{e}$re type equation($\tau=0$) and the special Lagrangian parabolic equation($\tau=\frac{\pi}{2}$). Furthermore, we get the bound of $D^lu$, $l=\{3,4,5,\cdots\}$ for $\tau=\frac{\pi}{4}$ and the decay estimates of the higher order derivatives when $0<\tau<\frac{\pi}{4}$ and $\frac{\pi}{4}<\tau<\frac{\pi}{2}$. We also prove that $u(x,t)$ converges to smooth self-expanding solutions of \eqref{12}.

math.DG↗

arXiv2024

Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation

Retrieval-augmented code generation utilizes Large Language Models as the generator and significantly expands their code generation capabilities by providing relevant code, documentation, and more via the retriever. The current approach suffers from two primary limitations: 1) information redundancy. The indiscriminate inclusion of redundant information can result in resource wastage and may misguide generators, affecting their effectiveness and efficiency. 2) preference gap. Due to different optimization objectives, the retriever strives to procure code with higher ground truth similarity, yet this effort does not substantially benefit the generator. The retriever and the generator may prefer different golden code, and this gap in preference results in a suboptimal design. Additionally, differences in parameterization knowledge acquired during pre-training result in varying preferences among different generators. To address these limitations, in this paper, we propose RRG (Retrieve, Refactor, Generate), a novel framework for effective and efficient code generation. This framework introduces a code refactorer module between the retriever and the generator to bridge them. The refactoring process transforms the raw retrieved code into a more concise, efficient, and model-friendly version. It eliminates redundant information and noise, reducing the input length. Consequently, the generator receives higher-quality context, enabling it to produce more accurate results with lower inference costs. We conducted comprehensive experiments on multiple datasets. In the experiments, we confirmed the existence of a preference gap between the retriever and the generator, and RRG effectively bridges this gap. Specifically, RRG achieved significant performance improvements, with increases of up to 28% on EM, 13% on BLEU, and 6.8% on CodeBLEU.

cs.SE↗