arXiv subjects

Yimin Du

Publications and source records attributed to Yimin Du.

8 recordsLinked to original sources

arXiv2026

Machine Learning Enhanced Multi-Factor Quantitative Trading: A Cross-Sectional Portfolio Optimization Approach with Bias Correction

Rolling-window factor pipelines for Chinese A-share markets contain a subtle but costly flaw: daily price-move limits (+/-10% main-board, +/-20% STAR/ChiNext) render a fraction of closing prices non-executable, yet standard implementations ingest these values before any row-filtering runs. The contaminated aggregates propagate silently through moving averages, correlations, and ranks--a failure mode we term "upstream contamination". On real A-share data it inflates apparent information coefficient by 18% while reducing realised Sharpe by 0.44 points, because the model learns to predict returns it cannot trade. We resolve this with a mask-first design: a Boolean tradability mask is constructed at data load time and threaded through every operator, so that no window ever reads a non-tradable price. Built on this foundation, the system adds (i) a GPU-vectorised 213-factor engine via PyTorch unfold primitives (51x over pandas); (ii) an Adjusted-MSE loss penalising wrong-sign predictions 11x more heavily than magnitude errors; (iii) block-bootstrap GBM augmentation; and (iv) Markowitz-Ledoit-Wolf portfolio optimisation with cvxpy warm-start caching. On a calibrated 3,000-stock synthetic panel the system achieves annualised Sharpe 2.05; on proprietary real A-share data (2022-2024) it achieves Sharpe 1.63. Ablation shows the mask contract is the single largest contributor (+0.44), exceeding any model or loss choice. The full implementation is released under MIT licence at https://github.com/initial-d/ml-quant-trading.

q-fin.PM↗

arXiv2026

VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models

Large language models frequently exhibit suboptimal performance on low resource languages, primarily due to inefficient subword segmentation and systemic training data imbalances. In this paper, we propose Variable Entropy Policy Optimization (VEPO), which leverages Reinforcement Learning with Verifiable Rewards to incorporate deterministic structural constraints into the policy alignment process. This framework ensures prescribed sequence length, robust format consistency, and rigorous linguistic well formedness, all enforced during training. Central to our approach is a variable entropy mechanism that enables the model to dynamically calibrate the equilibrium between literal fidelity and semantic naturalness by modulating the exploration exploitation manifold. By integrating entropy tempered advantage estimation with asymmetric clipping, VEPO sustains robust exploration while mitigating policy collapse. Empirical evaluations across 90 FLORES-200, COMET-22, chrF directions demonstrate that VEPO yields substantial improvements in both tokenization efficiency and translation quality, bridging the performance gap for underrepresented languages.

cs.CL↗

arXiv2025

Cognitive Load and Information Processing in Financial Markets: Theory and Evidence from Disclosure Complexity

Cognitive-load research in financial markets generally treats disclosure complexity as a property of the document and information acquisition as a direct interaction between an investor and that document. Machine-readable reporting and AI intermediaries make both assumptions incomplete. We develop a reader--task--interface framework in which processing load depends jointly on disclosure content, the representation through which it is accessed, and the transformation technology available to the reader. We evaluate the framework using a historical XBRL-transition diagnostic, a census of 207,684 SEC filings, a paired multi-model interface experiment, and held-out criterion validation. The historical evidence is consistent with interface substitution but has a modest statutory first stage and is interpreted as a measurement diagnostic. Modern filings reveal that human-facing burden and machine accessibility are distinct: large issuers produce longer reports while supplying richer structured coverage. The experiment crosses 432 filing-grounded questions with twelve interfaces and six hosted model implementations, producing 31,104 responses. Grounded accuracy rises from 47.2\% under BM25 HTML to 99.5\% under perfectly localized text; fact-matched oracle XBRL reaches 99.6\%. Most of the observed XBRL--HTML gap in these numerical tasks therefore arises from evidence localization and table reconstruction rather than syntax or taxonomy alone. Cognitive load is consequently not a stable scalar attribute of disclosure: it is local to a reader, task, interface, and processing stage.

q-fin.GN↗

arXiv2025

Deep Learning Enhanced Multi-Day Turnover Quantitative Trading Algorithm for Chinese A-Share Market

This paper presents a sophisticated multi-day turnover quantitative trading algorithm that integrates advanced deep learning techniques with comprehensive cross-sectional stock prediction for the Chinese A-share market. Our framework combines five interconnected modules: initial stock selection through deep cross-sectional prediction networks, opening signal distribution analysis using mixture models for arbitrage identification, market capitalization and liquidity-based dynamic position sizing, grid-search optimized profit-taking and stop-loss mechanisms, and multi-granularity volatility-based market timing models. The algorithm employs a novel approach to balance capital efficiency with risk management through adaptive holding periods and sophisticated entry/exit timing. Trained on comprehensive A-share data from 2010-2020 and rigorously backtested on 2021-2024 data, our method achieves remarkable performance with 15.2\% annualized returns, maximum drawdown constrained below 5\%, and a Sharpe ratio of 1.87. The strategy demonstrates exceptional scalability by maintaining 50-100 daily positions with a 9-day maximum holding period, incorporating dynamic profit-taking and stop-loss mechanisms that enhance capital turnover efficiency while preserving risk-adjusted returns. Our approach exhibits robust performance across various market regimes while maintaining high capital capacity suitable for institutional deployment.

cs.CE↗

arXiv2025

Memory-Efficient FastText: A Comprehensive Approach Using Double-Array Trie Structures and Mark-Compact Memory Management

FastText remains a practical choice for industrial word representation because it can synthesize vectors for out-of-vocabulary words from character n-grams. Its original hash-bucket implementation, however, couples two engineering compromises that become painful at large scale: unrelated n-grams collide into the same row, while increasing the bucket count quickly turns the input matrix into the dominant memory cost. This paper presents a memory-efficient FastText variant based on an exact-then-compress principle: first give every observed word and n-gram an explicit identity, then compress only those rows whose learned vectors and lexical structure justify sharing. Concretely, we replace hash buckets with collision-free double-array trie indexes and compress the resulting n-gram matrix through structurally constrained prefix and suffix merging followed by mark-compact row reorganization. Unlike arbitrary hashing, the proposed method shares rows only after a high cosine-similarity test, preserving interpretable n-gram identities while reducing the number of live rows. We describe the full training and serving pipeline, including UTF-8 aware n-gram enumeration, double-array trie lookup, memory-mapped model loading, and vector reconstruction for words and sentences. On a large Chinese vocabulary benchmark with 30.1M words and 287.4M extracted n-grams, the compressed model reduces memory from 145.2GB to 28.9GB, improves load time from 12.3 minutes to 3.2 minutes, and preserves downstream quality within 0.3 points of a hash-free model. We position the result as a compact lexical memory layer for LLM-era retrieval systems and release the implementation as an extended FastText prototype.

cs.CL↗

arXiv2025

Intuitionistic Fuzzy Sets for Large Language Model Data Annotation: A Novel Approach to Side-by-Side Preference Labeling

The quality of human preference data is crucial for training and evaluating large language models (LLMs), particularly in reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) scenarios. Traditional side-by-side (SBS) annotation approaches often struggle with inherent uncertainty, annotator disagreement, and the complexity of preference judgments. This paper introduces a novel framework based on intuitionistic fuzzy sets (IFS) for modeling and aggregating human preferences in LLM data annotation tasks. Our approach captures not only the degree of preference but also the uncertainty and hesitation inherent in human judgment through membership, non-membership, and hesitation degrees. We propose an IFS-based annotation protocol that enables more nuanced preference modeling, develops aggregation methods for handling annotator disagreement, and introduces quality metrics for preference data assessment. Experimental validation on multiple datasets demonstrates that our IFS-based approach significantly improves annotation consistency, reduces annotator fatigue, and produces higher-quality preference data compared to traditional binary and Likert-scale methods. The resulting preference datasets lead to improved model performance in downstream tasks, with 12.3\% improvement in win-rate against baseline models and 15.7\% reduction in annotation time. Our framework provides a principled approach to handling uncertainty in human preference annotation and offers practical benefits for large-scale LLM training.

cs.CL↗

arXiv2025

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

This paper introduces Light-R1, an open-source suite for training long reasoning models using reproducible and cost-effective methodology. Given the proprietary nature of data used in the DeepSeek-R1 series, we develop an alternative approach leveraging exclusively public data and models. Our curriculum training progressively increases data difficulty, combined with multi-staged post-training. Our Light-R1-32B model, trained from Qwen2.5-32B-Instruct, outperforms DeepSeek-R1-Distill-Qwen-32B in math reasoning. Experimental results show that this curriculum approach becomes more effective when distinct, diverse datasets are available for different training stages: fine-tuning DeepSeek-R1-Distilled models (pre-tuned by DeepSeek team on proprietary data) with 3,000 challenging examples from our curriculum dataset yielded state-of-the-art 7B and 14B models, while the 32B model, Light-R1-32B-DS performed comparably to QwQ-32B and DeepSeek-R1. Furthermore, we extend our work by applying GRPO on long reasoning models. Our final Light-R1-14B-DS achieves SOTA performance among 14B models in math, with AIME24 & 25 scores of 74.0 and 60.2 respectively, surpassing many 32B models and DeepSeek-R1-Distill-Llama-70B. Despite math-focused training, Light-R1-14B-DS demonstrates strong cross-domain generalization. Light-R1 represents a significant advancement in making sophisticated reasoning models more accessible and implementable in real-world applications. Our models, training data and code have been made available at https://github.com/Qihoo360/Light-R1.

cs.CL↗

arXiv2025

BTMTrack: Robust RGB-T Tracking via Dual-template Bridging and Temporal-Modal Candidate Elimination

RGB-T tracking leverages the complementary strengths of RGB and thermal infrared (TIR) modalities to address challenging scenarios such as low illumination and adverse weather. However, existing methods often fail to effectively integrate temporal information and perform efficient cross-modal interactions, which constrain their adaptability to dynamic targets. In this paper, we propose BTMTrack, a novel framework for RGB-T tracking. The core of our approach lies in the dual-template backbone network and the Temporal-Modal Candidate Elimination (TMCE) strategy. The dual-template backbone effectively integrates temporal information, while the TMCE strategy focuses the model on target-relevant tokens by evaluating temporal and modal correlations, reducing computational overhead and avoiding irrelevant background noise. Building upon this foundation, we propose the Temporal Dual Template Bridging (TDTB) module, which facilitates precise cross-modal fusion through dynamically filtered tokens. This approach further strengthens the interaction between templates and the search region. Extensive experiments conducted on three benchmark datasets demonstrate the effectiveness of BTMTrack. Our method achieves state-of-the-art performance, with a 72.3% precision rate on the LasHeR test set and competitive results on RGBT210 and RGBT234 datasets.

cs.CV↗