arXiv subjects

Linwei Li

Publications and source records attributed to Linwei Li.

12 recordsLinked to original sources

arXiv2026

Condensed PIPG Sequential Convex Optimization for Reusable-Rocket Powered Landing with Strong Aerodynamics

Reusable-rocket powered landing under strong aerodynamics couples variable mass, free final time, and bounded aerodynamic controls through nonlinear velocity-frame dynamics. This paper develops a condensed proportional--integral projected-gradient (PIPG) sequential-convex method whose principal contribution is an exact reduced-space inner architecture. Because the problem contains only six terminal hard equalities and no state path constraints, 217 nodal-state variables and 210 trapezoidal dynamics equalities are eliminated from the 31-node convex subproblem, leaving 101 primal variables and six terminal equalities. Row-orthogonal preconditioning, fixed-size matrix--vector products, and nodewise circular-epigraph projections then yield a customized PIPG kernel. Physical consistency of the angle-dependent axial force is maintained by gradually releasing drag sensitivity between the reference squared angle and an epigraph variable $A$, together with a convex tightness term. A pointwise Hamiltonian argument shows that the fully released limiting subproblem admits a tight optimum satisfying $A=\alpha^2+\beta^2$. Deterministic annealing, two-stage inner accuracy, and a rejected-on-failure threefold extrapolation are secondary outer-loop accelerators.

math.OC↗

arXiv2026

Process Reward Informed Tree Rollout for Effective Multi-Turn RL

Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories for advantage estimation. In long-horizon agentic tasks, such a uniform rollout strategy can waste budget on uninformative dead-end attempts, while promising intermediate states do not receive sufficient exploration. The multi-turn structure of agentic trajectories, with interleaved actions and observations, naturally supports organizing a trajectory group as a tree, where each turn serves as a decision point for exploration. This perspective reframes effective exploration as the problem of deciding where to branch. We propose Process-Scorer Guided Adaptive Tree Rollout (PATR), a quality-aware rollout framework for multi-turn agent RL. PATR uses task-appropriate process feedback to score partial trajectories, selectively branches from promising states, reuses shared prefixes, and conservatively stops degenerate paths to reduce wasted sampling. The resulting rollout groups remain compatible with standard policy optimization while providing more efficient exploration under the same training budget. We evaluate PATR on FrozenLake and the challenging SWE-Bench, which is largely unexplored by prior tree-rollout agent RL methods. Experiments show that PATR improves performance by up to +5.0 points on SWE-Bench and +9.3 points on FrozenLake, highlighting process-guided tree rollouts as an effective strategy for scalable multi-turn RL.

cs.CL↗

arXiv2026

Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning

Large reasoning models improve with more test-time computation, but often overthink, producing unnecessarily long chains-of-thought that raise cost without improving accuracy. Prior reinforcement learning approaches typically rely on a single outcome reward with trajectory-level length penalties, which cannot distinguish essential from redundant reasoning steps and therefore yield blunt compression. Although recent work incorporates step-level signals, such as offline pruning, supervised data construction, or verifier-based intermediate rewards, reasoning length is rarely treated as an explicit step-level optimization objective during RL. We propose Step-wise Adaptive Penalization (SWAP), a fine-grained framework that allocates length reduction across steps based on intrinsic contribution. We estimate step importance from the model's on-policy log-probability improvement toward the correct answer, then treat excess length as a penalty mass redistributed to penalize low-importance steps more heavily while preserving high-importance reasoning. We optimize with a unified outcome-process advantage within group-relative policy optimization. Extensive experiments demonstrate that SWAP reduces reasoning length by 64.3% on average while improving accuracy by 5.7% relative to the base model.

cs.CL↗

arXiv2025

Quantum separability criteria from bipartite systems to multipartite systems based on generalized Bloch representation

Quantum entanglement serves as a fundamental resource in quantum information theory. This paper presents a comprehensive framework of separability criteria for detecting bipartite and multipartite entanglements. We construct a novel parameterized extended correlation tensor via the generalized Bloch representation under an arbitrary orthogonal basis, which improves the performance of entanglement detection. Moreover, we employ the generalized matrix unfolding to generalize the extended correlation tensor construction to multipartite systems, obtaining separability criteria for multipartite entanglement. Detailed examples demonstrate that our separability criteria exhibit enhanced capability in detecting entanglement.

quant-ph↗

arXiv2025

IPBench: Benchmarking the Knowledge of Large Language Models in Intellectual Property

Intellectual Property (IP) is a highly specialized domain that integrates technical and legal knowledge, making it inherently complex and knowledge-intensive. Recent advancements in LLMs have demonstrated their potential to handle IP-related tasks, enabling more efficient analysis, understanding, and generation of IP-related content. However, existing datasets and benchmarks focus narrowly on patents or cover limited aspects of the IP field, lacking alignment with real-world scenarios. To bridge this gap, we introduce IPBench, the first comprehensive IP task taxonomy and a large-scale bilingual benchmark encompassing 8 IP mechanisms and 20 distinct tasks, designed to evaluate LLMs in real-world IP scenarios. We benchmark 17 main LLMs, ranging from general purpose to domain-specific, including chat-oriented and reasoning-focused models, under zero-shot, few-shot, and chain-of-thought settings. Our results show that even the top-performing model, DeepSeek-V3, achieves only 75.8% accuracy, indicating significant room for improvement. Notably, open-source IP and law-oriented models lag behind closed-source general-purpose models. To foster future research, we publicly release IPBench, and will expand it with additional tasks to better reflect real-world complexities and support model advancements in the IP domain. We provide the data and code in the supplementary URLs.

cs.CL↗

arXiv2022

Forecasting foreign exchange rates with regression networks tuned by Bayesian optimization

The article is concerned with the problem of multi-step financial time series forecasting of Foreign Exchange (FX) rates. To address this problem, we introduce a regression network termed RegPred Net. The exchange rate to forecast is treated as a stochastic process. It is assumed to follow a generalization of Brownian motion and the mean-reverting process referred to as the generalized Ornstein-Uhlenbeck (OU) process, with time-dependent coefficients. Using past observed values of the input time series, these coefficients can be regressed online by the cells of the first half of the network (Reg). The regressed coefficients depend only on - but are very sensitive to - a small number of hyperparameters required to be set by a global optimization procedure for which, Bayesian optimization is an adequate heuristic. Thanks to its multi-layered architecture, the second half of the regression network (Pred) can project time-dependent values for the OU process coefficients and generate realistic trajectories of the time series. Predictions can be easily derived in the form of expected values estimated by averaging values obtained by Monte Carlo simulation. The forecasting accuracy on a 100 days horizon is evaluated for several of the most important FX rates such as EUR/USD, EUR/CNY, and EUR/GBP. Our experimental results show that the RegPred Net significantly outperforms ARMA, ARIMA, LSTMs, and Autoencoder-LSTM models in terms of metrics measuring the absolute error (RMSE) and correlation between predicted and actual values (Pearson R, R-squared, MDA). Compared to black-box deep learning models such as LSTM, RegPred Net has better interpretability, simpler structure, and fewer parameters.

q-fin.ST↗

arXiv2022

Towards Semantic Search for Community Question Answering for Mortgage Officers

Community Question Answering (CQA) has gained increasing popularity in many domains. Mortgage is a complex and dynamic industry, and a flexible and efficient CQA platform can potentially enhance the quality of service for mortgage officers significantly. We have built a dynamic CQA platform with a state of the art semantic search engine based on recent Natural Language Processing (NLP) techniques to dynamically and collectively capture and transfer the maturity and tribal knowledge of the more experienced workforce to less experienced ones. The search engine allows for both keyword and natural language queries and is based on a fine-tuned domain-adapted Sentence-BERT encoder linearly composed with a TF-IDF vectorizer, and reciprocal-rank fused with a BM25 vectorizer. Domain adaptation and fine-tuning is based on publicly available mortgage corpora. Evaluation is performed on an internally annotated dataset using standard information retrieval metrics such as normalized discounted cumulative gain (nDCG), precision/recall at n, mean reciprocal rank, and mean average precision (MAP). The results indicate that our hybrid, fine-tuned, domain-adapted search engine is a more effective approach in responding to the information needs of our mortgage officers compared to traditional search techniques. We aim to publish the internally-annotated evaluation and training datasets in the near future.

cs.IR↗

arXiv2021

Cross-document Event Identity via Dense Annotation

In this paper, we study the identity of textual events from different documents. While the complex nature of event identity is previously studied (Hovy et al., 2013), the case of events across documents is unclear. Prior work on cross-document event coreference has two main drawbacks. First, they restrict the annotations to a limited set of event types. Second, they insufficiently tackle the concept of event identity. Such annotation setup reduces the pool of event mentions and prevents one from considering the possibility of quasi-identity relations. We propose a dense annotation approach for cross-document event coreference, comprising a rich source of event mentions and a dense annotation effort between related document pairs. To this end, we design a new annotation workflow with careful quality control and an easy-to-use annotation interface. In addition to the links, we further collect overlapping event contexts, including time, location, and participants, to shed some light on the relation between identity decisions and context. We present an open-access dataset for cross-document event coreference, CDEC-WN, collected from English Wikinews and open-source our annotation toolkit to encourage further research on cross-document tasks.

cs.CL↗

arXiv2021

A Data-Centric Framework for Composable NLP Workflows

Empirical natural language processing (NLP) systems in application domains (e.g., healthcare, finance, education) involve interoperation among multiple components, ranging from data ingestion, human annotation, to text retrieval, analysis, generation, and visualization. We establish a unified open-source framework to support fast development of such sophisticated NLP workflows in a composable manner. The framework introduces a uniform data representation to encode heterogeneous results by a wide range of NLP tasks. It offers a large repository of processors for NLP tasks, visualization, and annotation, which can be easily assembled with full interoperability under the unified representation. The highly extensible framework allows plugging in custom processors from external off-the-shelf NLP and deep learning libraries. The whole framework is delivered through two modularized yet integratable open-source projects, namely Forte (for workflow infrastructure and NLP function processors) and Stave (for user interaction, visualization, and annotation).

cs.CL↗

arXiv2018

Person Identification from Partial Gait Cycle Using Fully Convolutional Neural Network

Gait as a biometric property for person identification plays a key role in video surveillance and security applications. In gait recognition, normally, gait feature such as Gait Energy Image (GEI) is extracted from one full gait cycle. However in many circumstances, such a full gait cycle might not be available due to occlusion. Thus, the GEI is not complete giving rise to a degrading in gait-based person identification rate. In this paper, we address this issue by proposing a novel method to identify individuals from gait feature when a few (or even single) frame(s) is available. To do so, we propose a deep learning-based approach to transform incomplete GEI to the corresponding complete GEI obtained from a full gait cycle. More precisely, this transformation is done gradually by training several auto encoders independently and then combining these as a uniform model. Experimental results on two public gait datasets, namely OULP and Casia-B demonstrate the validity of the proposed method in dealing with very incomplete gait cycles.

cs.CV↗

arXiv2017

YEDDA: A Lightweight Collaborative Text Span Annotation Tool

In this paper, we introduce \textsc{Yedda}, a lightweight but efficient and comprehensive open-source tool for text span annotation. \textsc{Yedda} provides a systematic solution for text span annotation, ranging from collaborative user annotation to administrator evaluation and analysis. It overcomes the low efficiency of traditional text annotation tools by annotating entities through both command line and shortcut keys, which are configurable with custom labels. \textsc{Yedda} also gives intelligent recommendations by learning the up-to-date annotated text. An administrator client is developed to evaluate annotation quality of multiple annotators and generate detailed comparison report for each annotator pair. Experiments show that the proposed system can reduce the annotation time by half compared with existing annotation tools. And the annotation time can be further compressed by 16.47\% through intelligent recommendation.

cs.CL↗

arXiv2017

Rare B Decays at CMS

The flavour changing neutral current decays can be interesting probes for searching for New Physics. Angular distributions of the decay $\mathrm{B}^0 \to \mathrm{K}^{*0} \mu^ +\mu^-$ are studied using a sample of proton-proton collisions at $\sqrt{s} = 8~\mathrm{TeV}$ collected with the CMS detector at the LHC, corresponding to an integrated luminosity of $20.5~\mathrm{fb}^{-1}$. An angular analysis is performed to determine $P_1$ and $P_5'$, where $P_5'$ is of particular interest due to recent measurements that indicate a potential discrepancy with the standard model. Based on a sample of 1397 signal events, $P_1$ and $P_5'$ angular parameters are determined as a function of the dimuon invariant mass squared. The measurements are in agreement with standard model predictions.

hep-ex↗