arXiv subjects

Qi Cheng

Publications and source records attributed to Qi Cheng.

At least 19 recordsLinked to original sources

arXiv2026

MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning

General continual learning (GCL) aims to learn from evolving data streams without task identities, explicit boundaries, or repeated access to previous data, making it a realistic yet challenging setting for continual intelligence. Although pretrained models (PTMs) provide rich prior knowledge for addressing the limited supervision and non-stationary nature of GCL, existing PTM-based methods often directly adapt pretrained representations and overlook two critical gaps: the misalignment between upstream pretraining and downstream continual adaptation, and the unreliability of conventional output alignment under blurry streams. Here we propose MePo++, a unified post-training framework that bridges pretrained knowledge and downstream GCL through representation refinement and reconciliation. MePo++ introduces two complementary components: MetaPrep, which improves representation plasticity for continual adaptation through unsupervised meta-refinement over pseudo continual sequences; and StreamAlign, which reinforces representation stability by reconciling evolving online features with a stable pretrained geometry. By improving representation learnability before adaptation and preserving alignment during continual learning, MePo++ enables PTMs to remain both plastic for new concepts and stable over evolving streams. Experiments across diverse PTMs, datasets, and continual learning baselines demonstrate the consistent effectiveness and generality of MePo++ for PTM-based GCL. Our code is available at https://github.com/SunGL001/MePo_Plus.

cs.AI↗

arXiv2026

No Silver Bullet: Boosting GaussDB Performance on the 30TB TPC-H Workload

GaussDB is Huawei's premier database system, designed for large-scale deployments and the most demanding workloads. It is a distributed shared-nothing system, capable of handling all types of workloads. This paper outlines a series of modifications to GaussDB aimed at improving its performance on large-scale and complex analytical workloads. After these changes, its performance on the TPC-H workload exceeded the best published result by 40% at 30 TB. The key enhancements to achieve this elite performance include adopting a pipeline execution model, a faster and more scalable inter-node data shuffle, exploiting a unified bus and unified remote memory access. We also expanded the support of cost-based Bloom filter placement and implemented several Bloom filter streaming strategies, enabling their use across nodes.

cs.DB↗

arXiv2026

CAP: A Scalable Benchmark for Evaluating Cross-Site Browser Agents with Complex Actions and Perception

Large language models are increasingly deployed as autonomous agents that interact with the web through browsers. While recent progress has been driven by benchmarks that evaluate end-to-end task success, these evaluations largely overlook two fundamental sources of difficulty in real web browsing: complex actions over rich user interfaces and visual perception of dynamically rendered content, especially in workflows that span multiple websites. We introduce CAP, a scalable benchmark for evaluating browser agents on cross-site, human-like web tasks that require non-trivial UI interactions and visual understanding. Specifically, we adopt a decomposition-and-recomposition pipeline that first abstracts each website into a structured site card capturing user-facing functions, complex execution operations, and perceptual requirements, and then recomposes these components into realistic cross-site workflows. Each task is therefore grounded in multiple specific operations on each website, enabling fine-grained diagnosis. Built on this framework, we construct 420 tasks across 108 real-world websites and 24 domains under careful quality control. Experiments on state-of-the-art browser agents using our verifiable agent-as-a-judge evaluation framework show low success rates and reveal that perception-heavy interactions remain a major bottleneck, exposing substantial gaps between current agents and real-world web browsing demands.

cs.AI↗

arXiv2026

Deterministic and Efficient Ideal Arithmetic via Two-Element Representations

Given an ideal in a number field, it is desirable in many situations to find two elements that generate the ideal over the ring of the integers of the field. Existing algorithms are either randomized, or impractical at cryptographic sizes. In the paper, we present a deterministic polynomial time algorithm to find the two-element representation of an ideal. For a monic irreducible integral polynomial $ f(x) $, let $ K=\Q[x]/(f) $ be the number field, and $ O_K $ be the integral closure. Our algorithm works when the norm of the input ideal is co-prime to the index $ [O_K:\Z[x]/f] $. In particular, it handles all ideals for monogenic $ f(x) $, a class that includes the cyclotomic polynomials widely used in lattice based cryptography. A key technical ingredient in our result is a generalized version of Dedekind criterion.

math.NT↗

arXiv2026

PRESTO: Prefix-Aligned Tree Drafting for Diffusion Speculative Decoding

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs, generating tokens in parallel. This makes them effective draft models for speculative decoding (SD), producing an entire block of draft tokens in a single forward pass. Yet existing diffusion-based drafting methods rely on linear drafting, even though dLLMs emit multiple candidate tokens across positions, inducing a large combinatorial space of decoding paths. Consequently, they limit acceptance length and decoding efficiency. To exploit this multi-candidate structure, we apply tree-based drafting to diffusion drafters, enabling exploration of diverse candidate paths. However, we find that naive tree drafting is suboptimal: diffusion marginals are prefix-blind, mismatching the prefix-based AR verification and yielding unreliable path ranking. We propose PRESTO, a principled framework that extends tree-based drafting to diffusion drafters while resolving the fundamental mismatch between diffusion draft confidence and prefix-based AR verification through PREfix-aligned Scoring and priority-based Tree search for diffusion speculative decOding. The key principles behind PRESTO are that (1) candidate ranking should align with the prefix-based nature of AR verification, and (2) tree construction should prioritize candidate paths with high verification potential to maximize acceptance length. Extensive experiments show that PRESTO achieves up to an average of $1.5\times$ end-to-end throughput speedup on the state-of-the-art dedicated diffusion drafter SD and an average of $1.12\times$ on self-speculative diffusion LLMs across diverse benchmarks.

cs.AI↗

arXiv2026

Domain-Informed Representation for Evolutionary Sieving in Integral and Module Lattices

Traditional cryptography, rooted in problems, e.g., integer factorisation or discrete log, is inevitably vulnerable to a fully operational quantum computer. Although it remains an engineering frontier, the looming threat extends to encrypted data stored today, which could be decrypted in the future with quantum capabilities. To safeguard against this eventuality, the backbone of the modern quantum-safe cryptography is the Shortest Vector Problem (SVP). We enhance Laarhoven's treatment of Ajtai et al.'s sieving as a genetic algorithm (GA) for the SVP by incorporating domain-informed SVP representation and crossover while naturally extending application to the module lattices.

cs.CR↗

arXiv2026

Efficient Cost-Based Rewrite in a Bottom-Up Optimizer

The query optimizer in a Database Management Systems (DBMS), translates declarative queries into efficient execution plans. Conventional bottom-up optimization consists of two main stages: Query Rewrite (QRW) and Cost-Based Optimization (CBO). However, applying a rewrite rule during QRW may not always be beneficial; the best choice may depend on the (estimated) execution cost of the original and rewritten expressions. Fully exploiting such cost-dependent rules necessitates interleaving QRW with frequent CBO invocations, thereby incurring substantial overhead and often impractical optimization times. To mitigate this inefficiency, we introduce a novel cost-based rewrite framework for bottom-up optimizers. The core of our approach is a multi-level caching mechanism for intermediate CBO results aimed at eliminating redundant computation. Furthermore, we establish and exploit upper cost bounds to intelligently prune the search space during optimization. We also contribute methodological solutions for caching and reusing intermediate plan results within a bottom-up optimizer architecture. The framework has been implemented in the GaussDB optimizer. Experiments show that it significantly reduces overall optimization time, demonstrating the effectiveness of our approach.

cs.DB↗

arXiv2026

Retrieval-Augmented Multi-scale Framework for County-Level Crop Yield Prediction Across Large Regions

This paper proposes a new method for crop yield prediction, which is essential for developing management strategies, informing insurance assessments, and ensuring long-term food security. Although existing data-driven approaches have shown promise in this domain, their performance often degrades when applied across large geographic regions and long time periods. This limitation arises from two key challenges: (1) difficulty in jointly capturing short-term and long-term temporal patterns, and (2) inability to effectively accommodate spatial data variability in agricultural systems. Ignoring these issues often leads to unreliable predictions for specific regions or years, which ultimately affects policy decisions and resource allocation. In this paper, we propose a new predictive framework to address these challenges. First, we introduce a new backbone model architecture that captures both short-term daily-scale crop growth dynamics and long-term dependencies across years. To further improve generalization across diverse spatial regions, we augment this model with a retrieval-based adaptation strategy. Recognizing the substantial yield variation across years, we design a novel retrieval-and-refinement pipeline that adjusts retrieved samples by removing cross-year bias not explained by input features. Our experiments on real-world county-level corn yield data over 630 counties in the US demonstrate that our method consistently outperforms different types of baselines. The results also verify the effectiveness of the retrieval-based augmentation method in improving model robustness under spatial heterogeneity.

cs.LG↗

arXiv2026

AgroFlux: A Spatial-Temporal Benchmark for Carbon and Nitrogen Flux Prediction in Agricultural Ecosystems

Agroecosystem, which heavily influenced by human actions and accounts for a quarter of global greenhouse gas emissions (GHGs), plays a crucial role in mitigating global climate change and securing environmental sustainability. However, we can't manage what we can't measure. Accurately quantifying the pools and fluxes in the carbon, nutrient, and water nexus of the agroecosystem is therefore essential for understanding the underlying drivers of GHG and developing effective mitigation strategies. Conventional approaches like soil sampling, process-based models, and black-box machine learning models are facing challenges such as data sparsity, high spatiotemporal heterogeneity, and complex subsurface biogeochemical and physical processes. Developing new trustworthy approaches such as AI-empowered models, will require the AI-ready benchmark dataset and outlined protocols, which unfortunately do not exist. In this work, we introduce a first-of-its-kind spatial-temporal agroecosystem GHG benchmark dataset that integrates physics-based model simulations from Ecosys and DayCent with real-world observations from eddy covariance flux towers and controlled-environment facilities. We evaluate the performance of various sequential deep learning models on carbon and nitrogen flux prediction, including LSTM-based models, temporal CNN-based model, and Transformer-based models. Furthermore, we explored transfer learning to leverage simulated data to improve the generalization of deep learning models on real-world observations. Our benchmark dataset and evaluation framework contribute to the development of more accurate and scalable AI-driven agroecosystem models, advancing our understanding of ecosystem-climate interactions.

cs.LG↗

arXiv2025

Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning

Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs). Yet on-policy algorithms such as Group Relative Policy Optimization (GRPO) often suffer in early training: noisy gradients from low-quality rollouts lead to unstable updates and inefficient exploration. We introduce Slow-Fast Policy Optimization (SFPO), a simple yet efficient framework to address the above limitations via decomposing each step into three stages: a short fast trajectory of inner steps on the same batch, a reposition mechanism to control off-policy drift, and a final slow correction. This reposition-before-update design preserves the objective and rollout process unchanged, making SFPO plug-compatible with existing policy-gradient pipelines. Extensive experiments demonstrate that SFPO consistently improves stability, reduces number of rollouts, and accelerates convergence of reasoning RL training. Specifically, it outperforms GRPO by up to 2.80 points in average on math reasoning benchmarks. It also achieves up to 4.93\texttimes{} fewer rollouts and an up to 4.19\texttimes{} reduction in wall-clock time to match GRPO's best accuracy. Project website is available at https://slow-fast-po.github.io/.

cs.LG↗

arXiv2025

Solving the Decision Principal Ideal Problem with Pre-processing

The principal ideal problem constitutes a fundamental problem in algebraic number theory and has attracted significant attention due to its applications in ideal lattice based cryptosystems. Efficient quantum algorithm has been found to address this problem. The situation is different in the classical computational setting. In this work, we delve into the relationship between the principal ideal problem and the class field computation. We show that the decision version of the problem can be solved efficiently if the class group is smooth, after pre-computation has been completed to collect information about the Hilbert class field.

math.NT↗

arXiv2025

LLM-based Evaluation Policy Extraction for Ecological Modeling

Evaluating ecological time series is critical for benchmarking model performance in many important applications, including predicting greenhouse gas fluxes, capturing carbon-nitrogen dynamics, and monitoring hydrological cycles. Traditional numerical metrics (e.g., R-squared, root mean square error) have been widely used to quantify the similarity between modeled and observed ecosystem variables, but they often fail to capture domain-specific temporal patterns critical to ecological processes. As a result, these methods are often accompanied by expert visual inspection, which requires substantial human labor and limits the applicability to large-scale evaluation. To address these challenges, we propose a novel framework that integrates metric learning with large language model (LLM)-based natural language policy extraction to develop interpretable evaluation criteria. The proposed method processes pairwise annotations and implements a policy optimization mechanism to generate and combine different assessment metrics. The results obtained on multiple datasets for evaluating the predictions of crop gross primary production and carbon dioxide flux have confirmed the effectiveness of the proposed method in capturing target assessment preferences, including both synthetically generated and expert-annotated model comparisons. The proposed framework bridges the gap between numerical metrics and expert knowledge while providing interpretable evaluation policies that accommodate the diverse needs of different ecosystem modeling studies.

cs.AI↗

arXiv2025

Knowledge Guided Encoder-Decoder Framework: Integrating Multiple Physical Models for Agricultural Ecosystem Modeling

Agricultural monitoring is critical for ensuring food security, maintaining sustainable farming practices, informing policies on mitigating food shortage, and managing greenhouse gas emissions. Traditional process-based physical models are often designed and implemented for specific situations, and their parameters could also be highly uncertain. In contrast, data-driven models often use black-box structures and does not explicitly model the inter-dependence between different ecological variables. As a result, they require extensive training data and lack generalizability to different tasks with data distribution shifts and inconsistent observed variables. To address the need for more universal models, we propose a knowledge-guided encoder-decoder model, which can predict key crop variables by leveraging knowledge of underlying processes from multiple physical models. The proposed method also integrates a language model to process complex and inconsistent inputs and also utilizes it to implement a model selection mechanism for selectively combining the knowledge from different physical models. Our evaluations on predicting carbon and nitrogen fluxes for multiple sites demonstrate the effectiveness and robustness of the proposed model under various scenarios.

cs.LG↗

arXiv2025

Including Bloom Filters in Bottom-up Optimization

Bloom filters are used in query processing to perform early data reduction and improve query performance. The optimal query plan may be different when Bloom filters are used, indicating the need for Bloom filter-aware query optimization. To date, Bloom filter-aware query optimization has only been incorporated in a top-down query optimizer and limited to snowflake queries. In this paper, we show how Bloom filters can be incorporated in a bottom-up cost-based query optimizer. We highlight the challenges in limiting optimizer search space expansion, and offer an efficient solution. We show that including Bloom filters in cost-based optimization can lead to better join orders with effective predicate transfer between operators. On a 100 GB instance of the TPC-H database, our approach achieved a 32.8% further reduction in latency for queries involving Bloom filters, compared to the traditional approach of adding Bloom filters in a separate post-optimization step. Our method applies to all query types, and we provide several heuristics to balance limited increases in optimization time against improved query latency.

cs.DB↗

arXiv2024

A Construction of Evolving $3$-threshold Secret Sharing Scheme with Perfect Security and Smaller Share Size

The evolving $k$-threshold secret sharing scheme allows the dealer to distribute the secret to many participants such that only no less than $k$ shares together can restore the secret. In contrast to the conventional secret sharing scheme, the evolving scheme allows the number of participants to be uncertain and even ever-growing. In this paper, we consider the evolving secret sharing scheme with $k=3$. First, we point out that the prior approach has risks in the security. To solve this issue, we then propose a new evolving $3$-threshold scheme with perfect security. Given a $\ell$-bit secret, the $t$-th share of the proposed scheme has $\lceil\log_2 t\rceil +O({\lceil \log_4 \log_2 t\rceil}^2)+\log_2 p(2\lceil \log_4 \log_2 t\rceil-1)$ bits, where $p$ is a prime. Compared with the prior result $2 \lfloor\log_2 t\rfloor+O(\lfloor\log_2 t\rfloor)+\ell$, the proposed scheme reduces the leading constant from $2$ to $1$. Finally, we propose a conventional $3$-threshold secret sharing scheme over a finite field. Based on this model of the revised scheme and the proposed conventional $3$-threshold scheme, we present a brand-new and more concise evolving $3$-threshold secret sharing scheme.

cs.CR↗

arXiv2024

Learning Multimodal Cues of Children's Uncertainty

Understanding uncertainty plays a critical role in achieving common ground (Clark et al.,1983). This is especially important for multimodal AI systems that collaborate with users to solve a problem or guide the user through a challenging concept. In this work, for the first time, we present a dataset annotated in collaboration with developmental and cognitive psychologists for the purpose of studying nonverbal cues of uncertainty. We then present an analysis of the data, studying different roles of uncertainty and its relationship with task difficulty and performance. Lastly, we present a multimodal machine learning model that can predict uncertainty given a real-time video clip of a participant, which we find improves upon a baseline multimodal transformer model. This work informs research on cognitive coordination between human-human and human-AI and has broad implications for gesture understanding and generation. The anonymized version of our data and code will be publicly available upon the completion of the required consent forms and data sheets.

cs.CL↗

arXiv2024

Every Answer Matters: Evaluating Commonsense with Probabilistic Measures

Large language models have demonstrated impressive performance on commonsense tasks; however, these tasks are often posed as multiple-choice questions, allowing models to exploit systematic biases. Commonsense is also inherently probabilistic with multiple correct answers. The purpose of "boiling water" could be making tea and cooking, but it also could be killing germs. Existing tasks do not capture the probabilistic nature of common sense. To this end, we present commonsense frame completion (CFC), a new generative task that evaluates common sense via multiple open-ended generations. We also propose a method of probabilistic evaluation that strongly correlates with human judgments. Humans drastically outperform strong language model baselines on our dataset, indicating this approach is both a challenging and useful evaluation of machine common sense.

cs.CL↗

arXiv2024

A Construction of Evolving $k$-threshold Secret Sharing Scheme over A Polynomial Ring

The threshold secret sharing scheme allows the dealer to distribute the share to every participant such that the secret is correctly recovered from a certain amount of shares. The traditional $(k, n)$-threshold secret sharing scheme requests that the number of participants $n$ is known in advance. In contrast, the evolving secret sharing scheme allows that $n$ can be uncertain and even ever-growing. In this paper, we consider the evolving secret sharing scenario. Using the prefix codes and the properties of the polynomial ring, we propose a brand-new construction of evolving $k$-threshold secret sharing scheme for an $\ell$-bit secret over a polynomial ring, with correctness and perfect security. The proposed schemes establish the connection between prefix codes and the evolving schemes for $k\geq2$, and are also first evolving $k$-threshold secret sharing schemes by generalizing Shamir's scheme onto a polynomial ring. Specifically, the proposal also provides an unified mathematical decryption for prior evolving $2$-threshold secret sharing schemes. Besides, the analysis of the proposed schemes show that the size of the $t$-th share is $(k-1)(\ell_t-1)+\ell$ bits, where $\ell_t$ denotes the length of a binary prefix code of encoding integer $t$. In particular, when $\delta$ code is chosen as the prefix code, the share size achieves $(k-1)\lfloor\lg t\rfloor+2(k-1)\lfloor\lg ({\lfloor\lg t\rfloor+1}) \rfloor+\ell$, which improves the prior best result $(k-1)\lg t+6k^4\ell\lg{\lg t}\cdot\lg{\lg {\lg t}}+ 7k^4\ell\lg k$, where $\lg$ denotes the binary logarithm. When $k=2$, the proposed scheme also achieves the minimal share size for single-bit secret, which is the same as the best known scheme.

cs.IT↗