arXiv subjects

Jiahui Liang

Publications and source records attributed to Jiahui Liang.

At least 19 recordsLinked to original sources

arXiv2026

Mind the Gap: Exposing LLM Translation Blind Spots Using the AlphaMWE Multilingual Parallel Corpus

LLMs' performance on machine translation (MT) tasks is often dependent on the data availability in the specific domains and language pairs that they are trained upon. To examine if Multiword Expressions (MWEs) still set a bottleneck for LLMs regarding language understanding and translation, we report the system performances from the WMT2026 Test Suites shared task, for which we used the publicly available multilingual parallel corpus AlphaMWE as the test suites. We received 31 MT systems' outputs covering English to Chinese (zh), Polish (pl), German (de), Arabic (ar) including Modern Standard Arabic (MSA) and two dialectal ones (Egyptian and Tunisian Arabic). We carried out automatic evaluations using BLEU, ChrF, BERT-score to select the Top3 systems per language pair, followed up with human evaluations on the selected systems. Our findings show that: figurative/MWE phenomena remain challenging; automatic metrics sometimes disagree; human evaluation uncovers language-specific errors hidden by aggregate scores.

cs.CL↗

arXiv2026

Towards End-to-End Multilingual Metaphor Processing: Integrating Detection, Translation, and Evaluation

Metaphorical language remains a major challenge for multilingual natural language processing because successful interpretation and translation require reasoning beyond literal lexical meaning. Existing research has largely investigated metaphor detection, machine translation, and translation evaluation as separate tasks, while little work has explored how these components can be integrated into a unified computational framework. This PhD proposal aims to develop an end-to-end framework for multilingual metaphor processing consisting of three complementary research directions: (1) robust metaphor detection across languages, (2) metaphor-oriented translation evaluation for both human assessment and automatic quality estimation, and (3) joint modelling that connects metaphor detection with translation evaluation. The proposed research will combine linguistic theory with recent advances in large language models to develop new datasets, annotation methodologies, evaluation benchmarks, and automatic evaluation approaches for metaphor-aware machine translation. The expected outcome is a unified framework that improves both the development and evaluation of multilingual NLP systems when processing figurative language.

cs.CL↗

arXiv2026

MetaHOPE: A Metaphor-Oriented Evaluation Framework for Analysing MT and LLM Translation Errors

In this opinion paper, we propose MetaHOPE, an error severity-aware annotation framework for evaluating metaphor translations. Metaphors present challenges for machine translation (MT) and natural language understanding and processing (NLU, NLP), because it presents the features of semantic complexity, contextual dependency, and cultural embeddings that can lead to ambiguity issues for NLP models. To investigate how state-of-the-art NLP models perform on translating metaphors, we select three representative systems, i.e., GoogleMT, GPT5.4, and Hunyuan-7b as Neural MT (NMT) models and LLMs. We used two human-annotated metaphor corpora, including VUAMC and PSUCMC for English-to-Chinese and Chinese-to-English translation purposes. The original corpora we used are monolingual, where we carried out error annotation using the MetaHOPE framework, and also produced the human post-edited gold reference for bilingual use as a new resource. We believe the MetaHOPE evaluation framework for metaphor translation annotation, the parallel corpora resources, and the error analysis on SOTA automatic translation models can be useful and shed some light for the field of metaphor translation study. We share our resources publicly at github.com/Jiahui84/MetaHOPE

cs.CL↗

arXiv2026

Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong Models

Large language models often fail on reasoning tasks despite possessing the capability to solve them. We argue that many such failures arise from localized reasoning bugs in intermediate steps rather than from global incompetence. We show that these bugs are frequently repairable: inserting a short patch generated by a weak probe model after the same strong-model reasoning prefix can redirect the trajectory toward a correct solution. However, this corrective effect is not reliably internalized by directly fine-tuning on weak patches or repaired trajectories, suggesting that the useful signal lies not in the intervention text itself, but in how it reshapes the model's future reasoning distribution. We therefore propose Woodpecker Distillation, a weak-to-strong training framework that learns from contrastive local interventions. Our method contrasts successful and unsuccessful weak-model patches at the same prefix, constructs a corrective teacher distribution from their induced future token predictions, and distills this signal into the strong model. Experiments on mathematical reasoning benchmarks show that Woodpecker Distillation consistently improves strong-model performance and outperforms direct imitation baselines.

cs.AI↗

arXiv2026

RepoZero: Can LLMs Generate a Code Repository from Scratch?

Large Language Models (LLMs) have recently shown remarkable progress in code generation, yet their ability to construct complete software repositories from scratch remains poorly understood. A fundamental bottleneck is the lack of verifiable and scalable evaluation: existing benchmarks either focus on patch-based editing or rely on human or LLM-based judgments, which introduce bias and limit reproducibility. In this work, we present RepoZero, the first benchmark that enables fully automated, execution-based verification of repository-level generation from scratch. Our key idea is to reformulate generation as repository reproduction: given only API specifications, an agent must re-implement an entire repository such that its behavior matches the original implementation. This design allows for strict black-box validation via output equivalence, while naturally supporting large-scale construction by reusing existing open-source repositories. To further mitigate data leakage and shortcut solutions, we introduce cross-language constraints and a sandboxed evaluation protocol. Building on this benchmark, we propose an Agentic Code-Test Evolution (ACE) framework that performs iterative test generation and error-driven refinement, enabling effective test-time scaling for repository-level synthesis. Extensive experiments across multiple state-of-the-art LLMs and agent frameworks reveal that even the strongest LLM agents achieve only limited pass rates (30\% - 55\%), exposing a substantial gap between current capabilities and real-world software development requirements. Our results establish RepoZero as a challenging, scalable, and reliable testbed for end-to-end code generation, and highlight self-verification via test generation as a critical direction for advancing LLM-based coding agents.

cs.SE↗

arXiv2026

It Takes 8 Tokens: Weak-to-Strong Off-Policy RL via Auxiliary Branches

Reinforcement learning with verifiable rewards has emerged as a standard approach for enhancing reasoning in large language models, which typically optimizes the policy by contrasting multiple self generated rollouts. However, we identify a critical support limited bottleneck in this paradigm: on challenging reasoning tasks, the target model's samples often exhibit semantic redundancy, converging into the same erroneous "reasoning basins" that offer negligible reward contrast for policy updates. In this paper, we propose to overcome this limitation through a weak to strong learning paradigm, where a policy's exploration is informed by a weaker but computationally efficient auxiliary model. We introduce W2SPO, an off policy RL method that injects short auxiliary segments often as brief as 8 tokens into intermediate target model trajectories and the target model then completes the reasoning path from these diverted states. Policy updates are restricted to these short inserted segments based on final verifiable rewards. Empirically, W2SPO achieves superior performance among evaluated 4B scale models on mathematical reasoning benchmarks, outperforming evaluated post trained baselines. Compared with vanilla GRPO under the same sampling budget, W2SPO improves Pass@1 from 62.3% to 64.2% while achieving a 3.55 times training speedup. These results suggest that weak auxiliary branches can induce stronger target reasoning policies by expanding local exploration support.

cs.AI↗

arXiv2026

Scalable Multimodal Beam Alignment in V2X: An Anti-Imbalance Graph Learning Approach

Efficient beam alignment is fundamental to high-throughput and reliable connectivity in Vehicle-to-Everything (V2X) systems. However, conventional beam management in dynamic vehicular topologies incurs prohibitive alignment overhead and struggles to maintain robust links under rapid mobility. To overcome these challenges, this paper proposes a distributed multimodal graph beam alignment (GBA) framework. The core innovation lies in leveraging onboard multimodal sensing data to predict implicit feedback while employing graph neural networks to coordinate multi-user alignment, thereby jointly enhancing scalability and drastically reducing overhead. The architecture adopts a dual-network design with GBA-RSU and GBA-Vehicle units, optimized through a hybrid strategy of centralized learning and federated learning (FL) to balance global performance with local privacy. Furthermore, a dedicated data augmentation (DA) scheme is introduced to address multimodal data imbalance issues in vehicular networks. Negative augmentation applies dominant modality dropout to bolster robustness, while positive augmentation generates underrepresented samples to mitigate label imbalance. Numerical results demonstrate that GBA maintains a competitive sum rate on par with high-resolution codebook-based feedback yet reduces beam alignment overhead by over 90\% and scales efficiently in mobile scenarios. Notably, integrating DA enables GBA to consistently outperform state-of-the-art FL-based alignment benchmarks, with particularly pronounced gains under severe label and modality imbalance, establishing a practical solution for V2X beam management.

eess.SP↗

arXiv2026

FARM: Foundational Aerial Radio Map for Intelligent Low-Altitude Networking

Precise aerial radio environment characterization is vital for low-altitude airspace planning. However, existing datasets and construction methods lack the high-resolution granularity required for complex aerial spaces, particularly failing to capture spatial variations across both horizontal and vertical dimensions. To address these gaps, this paper introduces FARM, a pioneering foundation model for unified aerial radio map (ARM) construction. FARM is supported by our newly curated, high-granularity full-domain ARM dataset, which features multi-band and multi-antenna configurations, effectively filling a critical void in comprehensive low-altitude radio data. Structurally, FARM leverages a masked autoencoder to extract deep latent representations of the aerial radio environment, which subsequently guide a diffusion-based decoder to synthesize high-fidelity signal distributions through only a few iterative refinement steps. Benefiting from this design, the architecture seamlessly accommodates both condition-based and condition-free ARM construction, providing robust support for diverse signal and environmental priors. Extensive experiments demonstrate that FARM significantly outperforms state-of-the-art benchmarks while exhibiting strong cross-scenario generalization. Crucially, we validate the transferability of FARM on a real-world dataset collected from field tests, proving its robust deployment capability. Ultimately, FARM serves as a foundational infrastructure for the low-altitude economy by enabling autonomous aerial logistics and intelligent urban networking.

eess.SP↗

arXiv2026

InjectFlow: Weak Guides Strong via Orthogonal Injection for Flow Matching

Flow Matching (FM) has recently emerged as a leading approach for high-fidelity visual generation, offering a robust continuous-time alternative to ordinary differential equation (ODE) based models. However, despite their success, FM models are highly sensitive to dataset biases, which cause severe semantic degradation when generating out-of-distribution or minority-class samples. In this paper, we provide a rigorous mathematical formalization of the ``Bias Manifold'' within the FM framework. We identify that this performance drop is driven by conditional expectation smoothing, a mechanism that inevitably leads to trajectory lock-in during inference. To resolve this, we introduce InjectFlow, a novel, training-free method by injecting orthogonal semantics during the initial velocity field computation, without requiring any changes to the random seeds. This design effectively prevents the latent drift toward majority modes while maintaining high generative quality. Extensive experiments demonstrate the effectiveness of our approach. Notably, on the GenEval dataset, InjectFlow successfully fixes 75% of the prompts that standard flow matching models fail to generate correctly. Ultimately, our theoretical analysis and algorithm provide a ready-to-use solution for building more fair and robust visual foundation models.

cs.CV↗

arXiv2026

DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolution

Immersive conversational systems in production face a persistent trade-off between responsiveness and long-horizon task capability. Real-time interaction is achievable for lightweight turns, but requests involving planning and tool invocation (e.g., search and media generation) produce heavy-tail execution latency that degrades turn-taking, persona consistency, and user trust. To address this challenge, we propose DuCCAE (Conversation while Collaboration with Augmentation and Evolution), a hybrid engine for immersive conversation deployed within Baidu Search, serving millions of users. DuCCAE decouples real-time response generation from asynchronous agentic execution and synchronizes them via a shared state that maintains session context and execution traces, enabling asynchronous results to be integrated back into the ongoing dialogue. The system orchestrates five subsystems-Info, Conversation, Collaboration, Augmentation, and Evolution-to support multi-agent collaboration and continuous improvement. We evaluate DuCCAE through a comprehensive framework that combines offline benchmarking on the Du-Interact dataset and large-scale production evaluation within Baidu Search. Experimental results demonstrate that DuCCAE outperforms strong baselines in agentic execution reliability and dialogue quality while reducing latency to fit strict real-time budgets. Crucially, deployment metrics since June 2025 confirm substantial real-world effectiveness, evidenced by a tripling of Day-7 user retention to 34.2% and a surge in the complex task completion rate to 65.2%. Our hybrid architecture successfully preserves conversational continuity while enabling reliable agentic execution, offering practical guidelines for deploying scalable agentic systems in industrial settings.

cs.CL↗

arXiv2026

LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts

We introduce LM-Lexicon, an innovative definition modeling approach that incorporates data clustering, semantic expert learning, and model merging using a sparse mixture-of-experts architecture. By decomposing the definition modeling task into specialized semantic domains, where small language models are trained as domain experts, LM-Lexicon achieves substantial improvements (+7% BLEU score compared with the prior state-of-the-art model) over existing methods on five widely used benchmarks. Empirically, we demonstrate that 1) the clustering strategy enables fine-grained expert specialization with nearly 10% improvement in definition quality; 2) the semantic-aware domain-level routing mechanism achieves higher expert efficacy (+1%) than conventional token-level routing; and 3) further performance gains can be obtained through test-time compute and semantic expert scaling. Our work advances definition modeling while providing insights into the development of efficient language models for semantic-intensive applications.

cs.CL↗

arXiv2026

Beyond Alignment: Expanding Reasoning Capacity via Manifold-Reshaping Policy Optimization

Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). However, recent studies question whether RL genuinely expands reasoning capacity or merely aligns existing latent capabilities, arguing that exploration remains confined within the pre-trained model's low-rank bias manifold. In this work, we challenge this accessibility boundary hypothesis by demonstrating that the latent reasoning space can be fundamentally expanded through targeted geometric interventions. We propose Manifold-Reshaping Policy Optimization (MRPO), a geometric framework designed to fundamentally restructure the inference space of LLMs. MRPO operates in two stages: first, we employ Spectral Orthogonal Exploration (SOE) to eject the policy initialization into the null space of the bias manifold; second, we integrate an Effective Rank regularization term into the policy optimization objective. This approach incentivizes the discovery and maintenance of high-dimensional reasoning trajectories against the entropy-reducing tendency of standard RL. Empirically, our 4B-parameter method achieves state-of-the-art performance on mathematical tasks, significantly outperforming larger models (e.g., Qwen3-32B) and expanding the capability boundary beyond standard GRPO. Our code is available at https://anonymous.4open.science/r/MRPO-D57B/

cs.LG↗

arXiv2026

Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration

Large Language Models (LLMs) often suffer from ''Reasoning Collapse'' on challenging mathematical reasoning tasks, where stochastic sampling produces lexical variations of the same erroneous logic rather than genuine semantic exploration. We observe that failed reasoning traces are often associated with a low-rank bias manifold in the model's hidden-state geometry, which reduces exploration toward corrective solution directions. To address this, we propose Spectral Orthogonal Exploration (SOE), a geometric inference framework under a ''Student Guides Teacher'' paradigm. Instead of using a weak auxiliary agent for imitation, SOE uses it as an orthogonal probe to introduce semantically heterogeneous reasoning signals into the teacher's orthogonal complement of its dominant subspace. This intervention steers the teacher toward more diverse reasoning trajectories and improves exploration beyond standard sampling. Experiments on mathematical benchmarks show that SOE improves average accuracy by 62.4\% and average sampling efficiency by 113.7\% over baseline methods, suggesting that geometric interventions can be effective for mitigating reasoning collapse in mathematical reasoning. We further provide preliminary evidence that SOE is also effective on logic and code generation benchmarks.

cs.AI↗

arXiv2025

One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents

Locating files and functions requiring modification in large software repositories is challenging due to their scale and structural complexity. Existing LLM-based methods typically treat this as a repository-level retrieval task and rely on multiple auxiliary tools, which often overlook code execution logic and complicate model control. We propose RepoNavigator, an LLM agent equipped with a single execution-aware tool: jumping to the definition of an invoked symbol. This unified design reflects the actual flow of code execution while simplifying tool manipulation. RepoNavigator is trained end-to-end via Reinforcement Learning (RL) directly from a base pretrained model, without relying on closed-source distillation. Experiments demonstrate that RL-trained RepoNavigator achieves state-of-the-art performance, with the 7B model outperforming 14B baselines, the 14B model surpassing 32B competitors, and the 32B model exceeding closed-source models such as GPT-5 on most metrics. These results confirm that integrating a single, structurally grounded tool with RL training provides an efficient and scalable solution for repository-level issue localization.

cs.SE↗

arXiv2025

Relaying Signal When Monitoring Traffic: Double Use of Aerial Vehicles Towards Intelligent Low-Altitude Networking

In intelligent low-altitude networks, integrating monitoring tasks into communication unmanned aerial vehicles (UAVs) can consume resources and increase handoff latency for communication links. To address this challenge, we propose a strategy that enables a "double use" of UAVs, unifying the monitoring and relay handoff functions into a single, efficient process. Our scheme, guided by an integrated sensing and communication framework, coordinates these multi-role UAVs through a proactive handoff network that fuses multi-view sensory data from aerial and ground vehicles. A lightweight vehicle inspection module and a two-stage training procedure are developed to ensure monitoring accuracy and collaborative efficiency. Simulation results demonstrate the effectiveness of this integrated approach: it reduces communication outage probability by nearly 10% at a 200 Mbps requirement without compromising monitoring performance and maintains high resilience (86% achievable rate) even in the absence of multiple UAVs, outperforming traditional ground-based handoff schemes. Our code is available at the https://github.com/Jiahui-L/UAP.

eess.SP↗

arXiv2025

Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning

Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-integrated reasoning systems, however, often follow a single-agent paradigm in which one large model interleaves long-horizon reasoning with precise tool operations, leading to cognitive-load interference and unstable coordination. We present MSARL, a Multi-Small-Agent Reinforcement Learning framework that explicitly decouples reasoning from tool use. In MSARL, a Reasoning Agent decomposes problems and plans tool invocations, while multiple Tool Agents specialize in specific external tools, each trained via a combination of imitation learning and reinforcement learning with role-specific rewards. On mathematical problem solving with code execution, MSARL significantly improves reasoning stability and final-answer accuracy over single-agent baselines. Moreover, the architecture generalizes to diverse tool-use tasks, demonstrating that cognitive-role decoupling with small agents is a scalable blueprint for multi-agent AI design.

cs.AI↗

arXiv2025

Aligning Beam with Imbalanced Multi-modality: A Generative Federated Learning Approach

As vehicle intelligence advances, multi-modal sensing-aided communication emerges as a key enabler for reliable Vehicle-to-Everything (V2X) connectivity through precise environmental characterization. As centralized learning may suffer from data privacy, model heterogeneity and communication overhead issues, federated learning (FL) has been introduced to support V2X. However, the practical deployment of FL faces critical challenges: model performance degradation from label imbalance across vehicles and training instability induced by modality disparities in sensor-equipped agents. To overcome these limitations, we propose a generative FL approach for beam selection (GFL4BS). Our solution features two core innovations: 1) An adaptive zero-shot multi-modal generator coupled with spectral-regularized loss functions to enhance the expressiveness of synthetic data compensating for both label scarcity and missing modalities; 2) A hybrid training paradigm integrating feature fusion with decentralized optimization to ensure training resilience while minimizing communication costs. Experimental evaluations demonstrate significant improvements over baselines achieving 16.2% higher accuracy than the current state-of-the-art under severe label imbalance conditions while maintaining over 70% successful rate even when two agents lack both LiDAR and RGB camera inputs.

eess.SP↗

arXiv2022

OPERA:Operation-Pivoted Discrete Reasoning over Text

Machine reading comprehension (MRC) that requires discrete reasoning involving symbolic operations, e.g., addition, sorting, and counting, is a challenging task. According to this nature, semantic parsing-based methods predict interpretable but complex logical forms. However, logical form generation is nontrivial and even a little perturbation in a logical form will lead to wrong answers. To alleviate this issue, multi-predictor -based methods are proposed to directly predict different types of answers and achieve improvements. However, they ignore the utilization of symbolic operations and encounter a lack of reasoning ability and interpretability. To inherit the advantages of these two types of methods, we propose OPERA, an operation-pivoted discrete reasoning framework, where lightweight symbolic operations (compared with logical forms) as neural modules are utilized to facilitate the reasoning ability and interpretability. Specifically, operations are first selected and then softly executed to simulate the answer reasoning procedure. Extensive experiments on both DROP and RACENum datasets show the reasoning ability of OPERA. Moreover, further analysis verifies its interpretability.

cs.CL↗