arXiv subjects

Shuhan Liu

Publications and source records attributed to Shuhan Liu.

At least 19 recordsLinked to original sources

arXiv2026

AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis

Large language models are pushing data science toward increasingly autonomous and agentic workflows, with recent systems already supporting multi-step and long-running analyses. As these workflows become more autonomous, conventional interfaces no longer provide adequate support for two critical requirements: observability for understanding an agent's evolving reasoning and evidence, and steerability for redirecting low-value directions or deepening promising ones during execution. Existing interactive approaches improve process visibility and open intervention points, but they remain largely designed for discrete, turn-by-turn exchanges rather than the parallel branches and evolving decision structures of long-running agentic analysis. We study this need as interactive oversight in long-running agentic data analysis and present AdaLens, an interactive system for monitoring and steering ongoing runs. AdaLens combines a storyline-based representation that unifies analytical plans, execution progress, intermediate findings, and data-column involvement with steering interactions grounded in these analytical elements for directional guidance and execution control. We evaluate AdaLens through two case studies and a user study, examining how it supports analysts in monitoring and steering long-running agentic data analysis.

cs.HC↗

arXiv2026

Layer-Number-Controlled Symmetry Breaking and Surface-State Transport in Rhombohedral Graphene Multilayers

Rhombohedral multilayer graphene hosts layer-polarized flat bands, providing an intriguing platform for correlated and topological electronic states; however, the role of layer number in governing symmetry breaking and surface screening remains elusive. Here we prepare rhombohedral graphene multilayers and systematically conduct electrical transport measurements. We uncover an unconventional layer dependence of phase transitions: the critical displacement field (D$_{c}$) for the layer-antiferromagnetic (LAF)-to-semimetal transitions remains constant across tetralayer to hexalayer graphene, whereas the D$_{c}$ for semimetal-to-layer-polarized-insulator (LPI) transition increases with layer number, defying unscreened Coulomb interaction models. In hexalayer graphene, surface-state-dominated transport emerges, with Landau levels (LLs) and resistive peaks selectively controlled by adjacent gates, a signature of strong interlayer screening absent in thinner stacks. High magnetic fields reveal valley-layer-locked LLs and dissipative states possibly from interlayer backscattering, highlighting the presence of decoupled surface states. Our findings establish layer number as a key tuning knob for engineering correlated and topological phases in rhombohedral graphene multilayers.

cond-mat.mes-hall↗

arXiv2026

POEM: Phase-Aware $\mathrm{SO}(2)$ Feature Rotation for Time Series Forecasting Under Periodicity Drift

Deep learning has advanced time series forecasting, but periodicity drift, in which cycle timing and phase vary over time, remains a challenging problem. Existing methods predominantly model these sequences on fixed time grids, suffering from a limited ability to accommodate phase-related variation. To address this limitation, we propose \textbf{POEM}, a phase-aware forecasting framework based on latent feature rotation using the special orthogonal group in two dimensions, denoted by $\mathrm{SO}(2)$. POEM aims to reduce the phase-related variability by learning a phase-correction coordinate and applying an invertible $\mathrm{SO}(2)$-based rotation to paired latent features. To extrapolate this correction coordinate, Directional Phase Increment Attention (DPIA) retrieves historical phase increments from similar temporal contexts and integrates them into future phase corrections. Experiments demonstrate that POEM achieves competitive performance, while qualitative visualizations suggest that the learned phase-aware transformation makes latent trajectories more regular.

cs.LG↗

arXiv2026

Mitigating Package Hallucinations in Large Language Models via Model Editing

Large language models (LLMs) have demonstrated strong capabilities in software engineering tasks, such as code generation, library recommendation, and dependency configuration. However, recent studies show that LLMs may suffer from package hallucination, where they generate non-existent or invalid package names. These hallucinations can be exploited in software supply chain attacks, as attackers may register malicious packages under hallucinated names. Therefore, mitigating package hallucination is important for improving the reliability and security of LLM-assisted software development. In this paper, we introduce BOUND, a lightweight localized model editing framework for mitigating package hallucinations in LLMs. BOUND formulates package hallucination mitigation as a package-validity boundary editing problem, where the boundary refers to the model's ability to distinguish valid packages from hallucinated package names under a given task context. It first locates modules related to package hallucination through a risk-aware localization strategy, and then edits these modules with lightweight LoRA adapters using a boundary-aware objective that reinforces valid packages, suppresses hallucinated packages, and preserves locality behavior. Experimental results show that BOUND effectively reduces package hallucinations while preserving valid package recommendations. In the package recommendation task, BOUND reduces package-level hallucination rate (Package-HR) by 79.9% on edit prompts and by 65.4% on unseen prompts. The learned package-validity boundary further generalizes to other package-related tasks, reducing Package-HR by 12.8% in code generation and by 34.0% in pip install recommendation. These results show that BOUND refines the package-validity boundary of LLMs and improves the reliability of package-related outputs.

cs.SE↗

arXiv2026

Towards CSI-Native Foundation Models: A Channel-Adaptive Roadmap for 6G

Wireless foundation models offer a path toward reusable channel state information (CSI) intelligence for sixth-generation (6G) systems. However, existing generic-backbone adaptation and CSI pretraining methods often treat CSI as task tensors rather than propagation-conditioned channel responses, thereby failing to capture the intrinsic time-frequency-spatial geometry of wireless environments. This paper presents a channel-adaptive roadmap toward CSI-native foundation models, proposing a unified framework that aligns pretraining, positional modeling, and attention control with three channel requirements: scale-aware heterogeneous exposure, physical time-frequency-antenna coordinates, and correlation-bounded token interaction. Extensive experiments demonstrate the superiority of the proposed framework across three dimensions: zero-shot generalization, reducing NMSE by more than 4 dB across spatial-temporal-frequency tasks; scale extrapolation, yielding up to a 5.4 dB gain under 8 times unseen antenna scaling; and inference efficiency, accelerating mobility-aware processing by up to 18.8%. A system-level evaluation with Sionna SYS further shows that the proposed framework uses only 7.01% of dense-pilot overhead, reaches -18.64 dB average NMSE, and improves average net spectral efficiency by 36.6% over dense LMMSE and 15.5% over WiFo, indicating that CSI-native representation learning can support pilot-efficient radio access.

cs.LG↗

arXiv2026

Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting

Non-stationary time series forecasting is challenged by evolving distribution shifts that static models struggle to capture. While Mixture-of-Experts (MoE) architectures offer a promising paradigm for decoupling complex drift patterns, existing approaches are limited by fixed expert pools and memoryless routing, hampering their ability to adapt to abrupt regime shifts. To address this, we propose Dynamic TMoE, a framework that unifies architectural evolution with temporal continuity during learning phase. By detecting distribution shifts via Maximum Mean Discrepancy (MMD), we dynamically instantiate heterogeneous experts and prune redundant ones to optimize capacity. Additionally, a temporal memory router leverages recurrent states and an anomaly repository to ensure stable, context-aware expert selection without requiring test-time updates. Experiments on nine benchmarks demonstrate state-of-the-art performance, reducing MSE by 10.4% and MAE by 7.8%. Code is available at https://github.com/andone-07/Dynamic-TMoE.

cs.LG↗

arXiv2026

Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Models

Positional encoding plays a pivotal role in determin?ing the extrapolation and generalization performance of wireless foundation models for channel state information (CSI) modeling, latent characterization, and task-specific prediction. However, existing CSI models inherit static or one-dimensional positional priors from natural language and vision architectures, which fundamentally misalign with the intrinsic physics of wireless channels by lacking explicit relative decay, collapsing the 3D spatio-temporal-frequency structure, and remaining scenario?rigid. This paper proposes Adaptive 3D-RoPE, a physics-aligned rotary positional encoding that establishes the structural corner?stone for wireless foundation models. The framework integrates a learnable, axis-decoupled 3D frequency bank to explicitly disentangle multi-dimensional phase dependencies, coupled with a lightweight channel-conditioned controller that dynamically modulates the prior via compact global CSI descriptors. This sample-adaptive mechanism transforms positional encoding from a static transformer component into a dynamic, coherence-aware inductive bias to resolve heterogeneous channel physics. Extensive experiments across 100 datasets demonstrate the superiority of the proposed scheme in both scale extrapolation and zero-shot generalization. Compared to the state-of-the-art, our method achieves up to a 10.7 dB reduction in normalized mean square error (NMSE) under 8 times antenna scale extrapolation. Given the same CSI input scales, our method can also improve zero-shot NMSE by 1.07 dB across unseen mobility scenarios and 0.90 dB in low-frequency-to-millimeter-wave tasks.

eess.SP↗

arXiv2026

RACE-Bench: A Reasoning-Augmented Benchmark for Repository-Level Code Agents on Feature Addition

Repository-level code agents have shown strong promise in real-world feature addition tasks, making reliable evaluation of their capabilities increasingly important. However, existing benchmarks primarily evaluate these agents as black boxes based on final test correctness, providing limited insight into how they reason and where failures arise. To address this limitation, we introduce RACE-bench, a reasoning-augmented benchmark for evaluating code agents on repository-level feature addition tasks. RACE-bench contains 528 real-world feature addition instances from 12 open-source repositories. Each instance is paired with executable patch verification and structured intermediate reference reasoning covering issue understanding, file localization, implementation tasks, and step decomposition. Based on this design, we introduce a dual-track evaluation framework that jointly measures patch correctness and intermediate reasoning alignment with developer-accepted reference trajectories. We evaluate three representative repository-level code agents on RACE-bench. On the full benchmark, Resolved Rate ranges from 29% to 70% across different agents. Our reasoning-level analysis further shows that while current agents perform well at understanding high-level intent, their performance degrades substantially when translating intent into concrete implementation steps. We also find patches that can be applied but still fail the tests cover fewer reference-reasoning elements (35.7% lower recall) and contain more unsupported reasoning elements (94.1% higher over-prediction) than successful patches. These findings highlight the importance of evaluating repository-level code agents beyond final patch correctness by examining the quality of their reasoning processes.

cs.SE↗

arXiv2026

Heterogeneous Memory Design Exploration for AI Accelerators with a Gain Cell Memory Compiler

As memory increasingly dominates system cost and energy, heterogeneous on-chip memory systems that combine technologies with complementary characteristics are becoming essential. Gain Cell RAM (GCRAM) offers higher density, lower power, and tunable retention, expanding the design space beyond conventional SRAM. To this end, we create an OpenGCRAM compiler supporting both SRAM and GCRAM. It generates macro-level designs and layouts for commercial CMOS processes and characterizes area, delay, and power across user-defined configurations. The tool enables systematic identification of optimal heterogeneous memory configurations for AI tasks under specified performance metrics.

cs.AR↗

arXiv2026

HeterCSI: Channel-Adaptive Heterogeneous CSI Pretraining Framework for Generalized Wireless Foundation Models

Wireless foundation models promise transformative capabilities for channel state information (CSI) processing across diverse 6G network applications, yet face fundamental challenges due to the inherent dual heterogeneity of CSI across both scale and scenario dimensions. However, current pretraining approaches either constrain inputs to fixed dimensions or isolate training by scale, limiting the generalization and scalability of wireless foundation models. In this paper, we propose HeterCSI, a channel-adaptive pretraining framework that reconciles training efficiency with robust cross-scenario generalization via a new understanding of gradient dynamics in heterogeneous CSI pretraining. Our key insight reveals that CSI scale heterogeneity primarily causes destructive gradient interference, while scenario diversity actually promotes constructive gradient alignment when properly managed. Specifically, we formulate heterogeneous CSI batch construction as a partitioning optimization problem that minimizes zero-padding overhead while preserving scenario diversity. To solve this, we develop a scale-aware adaptive batching strategy that aligns CSI samples of similar scales, and design a double-masking mechanism to isolate valid signals from padding artifacts. Extensive experiments on 12 datasets demonstrate that HeterCSI establishes a generalized foundation model without scenario-specific finetuning, achieving superior average performance over full-shot baselines. Compared to the state-of-the-art zero-shot benchmark WiFo, it reduces NMSE by 7.19 dB, 4.08 dB, and 5.27 dB for CSI reconstruction, time-domain, and frequency-domain prediction, respectively. The proposed HeterCSI framework also reduces training latency by 53% compared to existing approaches while improving generalization performance by 1.53 dB on average.

cs.LG↗

arXiv2025

Gate Dielectric Engineering with an Ultrathin Silicon-oxide Interfacial Dipole Layer for Low-Leakage Oxide-Semiconductor Memories

We demonstrate a gate dielectric engineering approach leveraging an ultrathin, atomic layer deposited (ALD) silicon oxide interfacial layer (SiL) between the amorphous oxide semiconductor (AOS) channel and the high-k gate dielectric. SiL positively shifts the threshold voltage (V$_T$) of AOS transistors, providing at least four distinct $V_T$ levels with a maximum increase of 500 mV. It achieves stable $V_T$ control without significantly degrading critical device parameters such as mobility, on-state current, all while keeping the process temperature below 225 $^{\circ}$C and requiring no additional heat treatment to activate the dipole. Positive-bias temperature instability tests at 85 $^{\circ}$C indicate a significant reduction in negative $V_{T}$ shifts for SiL-integrated devices, highlighting enhanced reliability. Incorporating this SiL gate stack into two-transistor gain-cell (GC) memory maintains a more stable storage node voltage ($V_{SN}$) (reduces $V_{SN}$ drop by 67\%), by limiting unwanted charge losses. SiL-engineered GCs also reach retention times up to 10,000 s at room temperature and reduce standby leakage current by three orders of magnitude relative to baseline device, substantially lowering refresh energy consumption.

cond-mat.mtrl-sci↗

arXiv2025

Reasoning Efficiently Through Adaptive Chain-of-Thought Compression: A Self-Optimizing Framework

Chain-of-Thought (CoT) reasoning enhances Large Language Models (LLMs) by prompting intermediate steps, improving accuracy and robustness in arithmetic, logic, and commonsense tasks. However, this benefit comes with high computational costs: longer outputs increase latency, memory usage, and KV-cache demands. These issues are especially critical in software engineering tasks where concise and deterministic outputs are required. To investigate these trade-offs, we conduct an empirical study based on code generation benchmarks. The results reveal that longer CoT does not always help. Excessive reasoning often causes truncation, accuracy drops, and latency up to five times higher, with failed outputs consistently longer than successful ones. These findings challenge the assumption that longer reasoning is inherently better and highlight the need for adaptive CoT control. Motivated by this, we propose SEER (Self-Enhancing Efficient Reasoning), an adaptive framework that compresses CoT while preserving accuracy. SEER combines Best-of-N sampling with task-aware adaptive filtering, dynamically adjusting thresholds based on pre-inference outputs to reduce verbosity and computational overhead. We then evaluate SEER on three software engineering tasks and one math task. On average, SEER shortens CoT by 42.1%, improves accuracy by reducing truncation, and eliminates most infinite loops. These results demonstrate SEER as a practical method to make CoT-enhanced LLMs more efficient and robust, even under resource constraints.

cs.SE↗

arXiv2025

Stage-Diff: Stage-wise Long-Term Time Series Generation Based on Diffusion Models

Generative models have been successfully used in the field of time series generation. However, when dealing with long-term time series, which span over extended periods and exhibit more complex long-term temporal patterns, the task of generation becomes significantly more challenging. Long-term time series exhibit long-range temporal dependencies, but their data distribution also undergoes gradual changes over time. Finding a balance between these long-term dependencies and the drift in data distribution is a key challenge. On the other hand, long-term time series contain more complex interrelationships between different feature sequences, making the task of effectively capturing both intra-sequence and inter-sequence dependencies another important challenge. To address these issues, we propose Stage-Diff, a staged generative model for long-term time series based on diffusion models. First, through stage-wise sequence generation and inter-stage information transfer, the model preserves long-term sequence dependencies while enabling the modeling of data distribution shifts. Second, within each stage, progressive sequence decomposition is applied to perform channel-independent modeling at different time scales, while inter-stage information transfer utilizes multi-channel fusion modeling. This approach combines the robustness of channel-independent modeling with the information fusion advantages of multi-channel modeling, effectively balancing the intra-sequence and inter-sequence dependencies of long-term time series. Extensive experiments on multiple real-world datasets validate the effectiveness of Stage-Diff in long-term time series generation tasks.

cs.LG↗

arXiv2025

DLGAN : Time Series Synthesis Based on Dual-Layer Generative Adversarial Networks

Time series synthesis is an effective approach to ensuring the secure circulation of time series data. Existing time series synthesis methods typically perform temporal modeling based on random sequences to generate target sequences, which often struggle to ensure the temporal dependencies in the generated time series. Additionally, directly modeling temporal features on random sequences makes it challenging to accurately capture the feature information of the original time series. To address the above issues, we propose a simple but effective generative model \textbf{D}ual-\textbf{L}ayer \textbf{G}enerative \textbf{A}dversarial \textbf{N}etworks, named \textbf{DLGAN}. The model decomposes the time series generation process into two stages: sequence feature extraction and sequence reconstruction. First, these two stages form a complete time series autoencoder, enabling supervised learning on the original time series to ensure that the reconstruction process can restore the temporal dependencies of the sequence. Second, a Generative Adversarial Network (GAN) is used to generate synthetic feature vectors that align with the real-time sequence feature vectors, ensuring that the generator can capture the temporal features from real time series. Extensive experiments on four public datasets demonstrate the superiority of this model across various evaluation metrics.

cs.LG↗

arXiv2025

An Empirical Study of Vulnerable Package Dependencies in LLM Repositories

Large language models (LLMs) have developed rapidly in recent years, revolutionizing various fields. Despite their widespread success, LLMs heavily rely on external code dependencies from package management systems, creating a complex and interconnected LLM dependency supply chain. Vulnerabilities in dependencies can expose LLMs to security risks. While existing research predominantly focuses on model-level security threats, vulnerabilities within the LLM dependency supply chain have been overlooked. To fill this gap, we conducted an empirical analysis of 52 open-source LLMs, examining their third-party dependencies and associated vulnerabilities. We then explored activities within the LLM repositories to understand how maintainers manage third-party vulnerabilities in practice. Finally, we compared third-party dependency vulnerabilities in the LLM ecosystem to those in the Python ecosystem. Our results show that half of the vulnerabilities in the LLM ecosystem remain undisclosed for more than 56.2 months, significantly longer than those in the Python ecosystem. Additionally, 75.8% of LLMs include vulnerable dependencies in their configuration files. This study advances the understanding of LLM supply chain risks, provides insights for practitioners, and highlights potential directions for improving the security of the LLM supply chain.

cs.CR↗

arXiv2025

The Future of Memory: Limits and Opportunities

Memory latency, bandwidth, capacity, and energy increasingly limit performance. In this paper, we reconsider proposed system architectures that consist of huge (many-terabyte to petabyte scale) memories shared among large numbers of CPUs. We argue two practical engineering challenges, scaling and signaling, limit such designs. We propose the opposite approach. Rather than create large, shared, homogenous memories, systems explicitly break memory up into smaller slices more tightly coupled with compute elements. Leveraging advances in 2.5D/3D integration, this compute-memory node provisions private local memory, enabling accesses of node-exclusive data through micrometer-scale distances, and dramatically reduced access cost. In-package memory elements support shared state within a processor, providing far better bandwidth and energy-efficiency than DRAM, which is used as main memory for large working sets and cold data. Hardware making memory capacities and distances explicit allows software to efficiently compose this hierarchy, managing data placement and movement.

cs.AR↗

arXiv2025

Cascade of Even-Denominator Fractional Quantum Hall States in Mixed-Stacked Multilayer Graphene

The fractional quantum Hall effect (FQHE), particularly at half-filling of Landau levels, provides a unique window into topological phases hosting non-Abelian excitations. However, experimental platforms simultaneously offering large energy gaps, delicate tunability, and robust non-Abelian signatures remain scarce. Here, we report the observation of a cascade of even-denominator FQH states at filling factors ${\nu}$ = ${-5/2}$, ${-7/2}$, ${-9/2}$, ${-11/2}$, and ${-13/2}$, alongside numerous odd-denominator states in mixed-stacked pentalayer graphene, a previously unexplored system characterized by intertwined quadratic and cubic band dispersions. These even-denominator states, representing the highest filling half-filled states reported so far in the zeroth Landau level (ZLL), emerge from two distinct intra-ZLL and exhibit unprecedented displacement field tunability driven by LL crossings in the hybridized multiband structure. At half fillings, continuous quasiparticle phase transitions between paired FQH states, magnetic Bloch states, and composite Fermi liquids are clearly identified upon tuning external fields. Numerical calculations, revealing characteristic sixfold ground-state degeneracy and chiral graviton spectral analysis, suggest the observed even-denominator FQH states belong to the non-Abelian Moore-Read type. These results establish mixed-stacked multilayer graphene as a rich and versatile crystalline platform for exploring tunable correlated topological phases.

cond-mat.mes-hall↗

arXiv2025

CREME: Robustness Enhancement of Code LLMs via Layer-Aware Model Editing

Large language models (LLMs) have demonstrated impressive capabilities in code generation, where the natural language prompt plays a crucial role in conveying user intent to the model. However, prior studies have shown that LLMs are highly sensitive to prompt perturbations. Minor modifications in wording, syntax, or formatting can significantly reduce the functional correctness of generated code. As perturbations frequently occur in real-world scenarios, improving the robustness of LLMs to prompt perturbations is essential for ensuring reliable performance in practical code generation. In this paper, we introduce CREME (Code Robustness Enhancement via Model Editing), a novel approach that enhances LLM robustness through targeted parameter updates. CREME first identifies robustness-sensitive layers by comparing hidden states between an original prompt and its perturbed variant. Then, it performs lightweight parameter editing at the identified layer to reduce performance degradation. We evaluate CREME on two widely used code generation benchmarks (HumanEval and MBPP) along with their perturbed counterparts. Experimental results show that CREME improves Pass@1 accuracy by 63% on perturbed prompts while maintaining stable performance on clean inputs, with accuracy deviations within 1%. Further analysis reveals that robustness-sensitive layers are primarily concentrated in the middle and deeper layers of the network, and their locations vary across different model architectures. These insights provide a valuable foundation for developing future robustness-oriented editing strategies.

cs.SE↗