Searcharxiv⌕ Search

arXiv subjects

Zihao Chen

Publications and source records attributed to Zihao Chen.

At least 19 recordsLinked to original sources
arXiv2026

CoMerge: Conflict-Driven Preference Optimization for Multi-Task Model Merging

Model merging provides an efficient paradigm for constructing multi-task large language models (LLMs) without full model retraining, yet it remains challenged by parameter interference. While existing methods aim to preserve the capabilities of individual expert models and mitigate interference, they generally do not directly learn from the potentially degraded behaviors exposed by naive merging. In this paper, we propose a conflict-driven preference optimization framework for model merging (CoMerge), which reformulates model merging as a preference optimization problem. The approach utilizes a self-supervised, conflict-driven strategy that leverages the defects of naive merging methods (e.g., task arithmetic) as hard negative samples to construct preference pairs without external annotations. By applying preference optimization to refine lightweight, tensor-wise merging coefficients, CoMerge enables the model to mitigate parameter-space conflicts while preserving task-specific capabilities. Extensive experiments show that CoMerge achieves an average normalized performance of 0.9968 on MergeBench, outperforming all evaluated data-free and data-driven model-merging baselines. Furthermore, on Llama-3.1-8B-Instruct, CoMerge yields marked improvements on conflict-sensitive tasks such as instruction following and safety, while remaining highly competitive with full-parameter fine-tuning despite optimizing only 1,445 scalar coefficients.

cs.AI↗
arXiv2026

AutoDRI: Bridging the Semantic Gap for Automated Design Rule Integration in CP-SAT-Based Cell Synthesis under Multi-Patterning

Design-rule integration (DRI) remains a major bottleneck for scalable (Constraint Programming with SAT) CP-SAT-based standard cell synthesis and rapid technology enablement at advanced nodes. It still depends heavily on manual effort and domain expertise. Moreover, existing low-level rule encodings are not expressive enough for emerging constraints such as cut-based rules under multi-patterning technology. This paper presents \textbf{AutoDRI}, a multi-agent framework for automated design-rule integration in standard cell synthesis. AutoDRI combines a geometric semantic library, a standardized conflict-set encoding, a constructive multicolor-cut modeling method, and a feedback-driven multi-agent flow to bridge the semantic gap between natural-language design rules and executable CP-SAT constraints. In the reported experiments, AutoDRI achieves near-perfect rule-integration correctness across 41 cell benchmarks under 10+ complex rules, including colored cut-mask spacing rules, reaching 33/33 correct integrations with Gemini-3-pro and 32/33 with GPT-5.4, while maintaining runtime comparable to manual hard-coding and passing KLayout DRC and Cadence LVS.

eess.SY↗
arXiv2026

IF:CARGO: LLM-Based Semantic Compilation for Al-Native Rule Programming Games

This case study presents IF: CARGO, an experimental puzzle game that uses a large language model as a semantic compiler rather than an autonomous game-playing agent. Players author IF/THEN rules in natural language, which the model translates into a constrained command schema for deterministic validation and execution by the game engine. This architecture creates a playable loop of expression, execution, observation, and revision, framing AI interaction as semantic debugging. A mixed-methods playtest with 24 participants across eight levels examined player attempts, thinking time, perceived controllability, adjustability, and interpretations of the AI's role. Results suggest that players generally understood the model as a translation intermediary and could revise their strategies through feedback, while periodic commands, multi-robot coordination, and rule-priority mechanics created greater cognitive and diagnostic demands. The study proposes a practical pattern for AI-native gameplay: constrain natural-language input, preserve player authorship, and ensure deterministic execution.

cs.HC↗
arXiv2026

PinEqualizer: Full Funnel Content Exploration and Debiasing System at Pinterest

In this paper, we propose a new solution for addressing the content cold-start problem in industry-scale search and recommender systems. Compared to prior approaches, we have made the following new contributions: 1) our solution spans the entire multi-stage funnel and generalizes well for both search and recommendation surfaces, 2) our solution reduces bias favoring existing content, allowing more accurate model prediction across content types and reducing short-term tradeoffs associated with high volumes of explicit content exploration, 3) our solution is evaluated with a scalable measurement framework that enables fast short-term experimentation while validating long-term impact. We have iteratively built and successfully deployed this new system at Pinterest in the past two years and observed significant improvements in fresh content exploration, overall user engagement, and content ecosystem health.

cs.IR↗
arXiv2026

PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution

Vision-language-action models, world models, and agentic planners each advance physical intelligence, yet their composition lacks a common execution abstraction, shared state, semantic verification, and persistent experience across heterogeneous embodiments. We present PhyAgentOS, a runtime foundation delivering scheduling, verification, memory, benchmarking, and safety as system-level services. Its Session-Centered Runtime treats a session, not an action, as the minimum unit of scheduling, compatibility preflight, supervised execution, evidence collection, and acceptance. To decouple cognition from physical execution, the cognition-physics boundary is a file system: the State-as-a-File protocol materializes cross-layer state as Markdown with YAML, yielding inspectable, versionable records without code dependencies between Agent and Runtime layers. These views form a unified cognitive state space aligning intent, capabilities, environment, execution, and experience. The SessionVerifier distinguishes execution termination from semantic task completion via evidence-grounded verdicts of success, failure, or replan. Verified outcomes are consolidated through epistemic memory into reusable knowledge and corrective lessons, closing a trial-and-error loop without retraining. Benchmarking reuses the deployment session and verification path, so results trace to real execution. Layered safety constrains both policy-driven and agent-driven execution: preflight, action bridges, SafetyGuard, heartbeat monitoring, and target-local constraints. Validation is progressive: games test cognitive planning, simulation adds dynamics and control, real robots add hardware noise, with the cognitive layer held constant. PhyAgentOS is benchmarked on Optimus-67, StarDojo, and DST-Dojo, validated on 19+ simulated and physical embodiments, and gains on LIBERO, Calvin, and RoboCasa365 across multiple VLA models.

cs.RO↗
arXiv2026

UniVoice: A Unified Model for Speech and Singing Voice Generation

Text-to-speech (TTS) and singing voice synthesis (SVS) both aim to generate human vocal audio from symbolic inputs, but they impose different requirements on the generation process. Speech generation relies on flexible, language-driven prosody, whereas singing generation requires explicit melody control and accurate rhythmic alignment. This mismatch makes it challenging to train a single model that can generate both natural speech and controllable singing, since melody-related conditions should strongly constrain singing but should not restrict speech prosody. We present UniVoice, a unified speech and singing voice generation framework based on conditional flow matching. Instead of using a single undifferentiated conditioning representation, UniVoice factorizes the condition into content, melody, and timbre, which are encoded by modality-appropriate encoders and consumed by a shared Diffusion Transformer (DiT) backbone. For singing, the melody condition is represented by MIDI note sequences; for speech, it is replaced with a learned null melody token, allowing the model to infer prosody from linguistic and acoustic context. This design preserves explicit melody control for singing while avoiding the need to impose melody constraints on speech. We further analyze the null melody token as an approximation to melody marginalization in the conditional flow. Trained on 30k hours of speech and 35k hours of singing data, UniVoice achieves a speech PER of 5.26\%, comparable to dedicated TTS systems such as F5-TTS (5.21\%) and CosyVoice3 (5.30\%). On singing generation, UniVoice achieves a PER of 16.22\%, outperforming the unified baseline Vevo1.5 (24.72\%).

cs.SD↗
arXiv2026

A Unifying View of Anchoring via Operator-Side Tikhonov Regularization

Anchored fixed point and monotone equation methods, including Halpern iteration, extra anchored gradient, and their relatives, add a vanishing pull toward a reference point to obtain last-iterate guarantees. Existing anchored variants often achieve sharp last-iterate guarantees, but from the update-level perspective the placement of the anchor can be algorithm-specific and conceptually opaque. We show that anchoring admits a single operator-side construction: regularize the operator queried by the base method with a vanishing Tikhonov term, then run the unmodified base method. Applied to the Picard iteration, this recipe reproduces the Halpern iteration; applied to the forward step, extragradient (EG), and past extragradient (PEG, also known as Popov's method), it yields three variants whose anchor placements inherit the base method's query pattern. The forward-step instantiation gives a new residual convergence guarantee, while the EG and PEG instantiations give new regularized variants. The four analyses share a residual recurrence, recovering the $O(1/k)$ Halpern residual-norm convergence rate, giving $O(1/\sqrt{k})$ for the regularized forward step, and giving $O(1/k)$ for the regularized EG and PEG variants in the unconstrained monotone Lipschitz setting.

math.OC↗
arXiv2026

Reinforcement Learning with Robust Rubric Rewards

While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi-criteria supervision (e.g., perceptual details, reasoning steps, and constraints). Rubrics provide a natural interface for this fine-grained supervision, but their effectiveness depends on the execution accuracy during online RL. We propose Reinforcement Learning with Robust Rubric Rewards ($\text{RLR}^3$), extending RLVR from task-level verification to criterion-level verification. $\text{RLR}^3$ routes instance-specific rubrics through two execution paths: an LLM-as-an-extractor paired with a deterministic verifier, or an LLM-as-a-Judge for non-verifiable criteria. To ensure faithful scoring, $\text{RLR}^3$ introduce a minimal exposure strategy that masks ground truths from extractors and images from judges. Furthermore, $\text{RLR}^3$ employs hierarchical aggregation to prioritize essential criteria over additional criteria, and mitigates score saturation within rollout groups. Evaluated on Qwen3-VL-30B-A3B across 15 benchmarks, $\text{RLR}^3$ consistently outperforms RLVR, yielding a 4.7-point improvement over the base model and exceeding the official instruct-to-thinking model gap. Controlled audits confirm our deterministic verification and minimal exposure significantly reduce exploitable false positives.

cs.CV↗
arXiv2026

GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation

With the rapid emergence of multi-behavior learning in recommender systems, leveraging auxiliary user behaviors has proven effective for mitigating target-behavior data sparsity. Yet auxiliary behavior graphs frequently contain noisy or irrelevant interactions that do not align with the target task, impeding the learning of accurate user and item embeddings. Moreover, the scarcity of direct supervision from the target behavior complicates the extraction of informative collaborative signals. In this paper, we introduce GCIB (Graph Contrastive Information Bottleneck), a novel framework that denoises auxiliary behavior information and enriches target behavior representations at both the structural and feature levels. At the structural level, GCIB employs a Graph Information Bottleneck (GIB) objective to maximize mutual information between the denoised auxiliary graph and the target-behavior graph while minimizing mutual information with the original auxiliary graph. This formulation preserves task-relevant structural patterns and suppresses spurious interactions. At the feature level, we propose a cross-behavior Graph Contrastive Learning (GCL) scheme in which denoised auxiliary features and target-behavior features serve as complementary views for both users and items. By contrasting these views, GCIB enriches sparse target-behavior representations with semantics distilled from auxiliary behaviors. Extensive experiments demonstrate that GCIB outperforms state-of-the-art baselines, highlighting its ability to learn noise-resilient and target-aware representations for multi-behavior recommendation.

cs.IR↗
arXiv2026

GRID: Graph Representation of Intelligence Data for Security Text Knowledge Graph Construction

Security knowledge graphs can provide computable external memory for security agents, but constructing them from long-form cyber threat intelligence (CTI) remains difficult: LLMs often lack grounded security-domain knowledge, and end-to-end document-to-graph training is hard to supervise with cheap, stable rewards. We present GRID (Graph Representation of Intelligence Data), an end-to-end framework for security text knowledge graph construction. GRID first builds security-domain supervision from CTI articles by creating traceable article-graph alignments through graph extraction and knowledge-graph-conditioned text revision. It then turns document-to-graph learning into a scripted task bank combining four-option multi-select questions with triple-level regex matching targets, yielding more stable task-specific rewards than repeatedly scoring full graph outputs with an LLM judge. Using this supervision pipeline, we train two Qwen3-4B-Instruct-2507-based 4B extractors: a primary Task-bank Reward model and a secondary End2End Reward model with LLM-as-judge precision/recall rewards. On 249 CTI articles from GRID, CASIE, CTINexus, MalKG, and SecureNLP, the Task-bank Reward model with the ontology-guided GRID extraction pipeline reaches 84.62% source-averaged precision, 64.91% source-averaged recall, and 68.53% Avg F1, achieving the best source-averaged recall and near-top Avg F1 with lower token usage and deployment cost. The End2End Reward model reaches 76.91% precision, 53.85% recall, and 58.06% Avg F1. Further analyses show that task-bank rewards can be built once offline and reused across later post-training runs, outperforming online End2End LLM-as-judge reward and weaker alternatives such as Choice-only Reward and End2End SFT without RL.

cs.AI↗
arXiv2026

Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies

Data selection is a key component of efficient instruction tuning for large language models, as recent work has shown that data quality often matters more than data quantity. Accordingly, prior studies have introduced various multi-dimensional heuristics to evaluate and filter instruction data. However, most existing methods rely on static task-agnostic and model-agnostic weighting schemes, which overlook the varying requirements of specific downstream tasks and the differing pre-existing capabilities of models. In this paper, we propose a framework for learning multi-indicator weights that jointly adapts data selection to both the downstream task and the specific model. Our method identifies optimal weight configurations without full-scale fine-tuning by utilizing in-context learning (ICL) signals on compact tiny-validation sets. These signals serve as efficient performance proxies that ensure high-fidelity evaluation at minimal computational cost. Experiments across multiple benchmarks and model families, including Mistral, Qwen, and Llama, show that the approach achieves performance comparable to or exceeding full-dataset tuning while using only 30\% of the training samples on GSM8K. Furthermore, our analysis reveals a trade-off between semantic diversity and logical complexity in reasoning tasks, highlighting the necessity of joint task-model adaptation.

cs.LG↗
arXiv2026

Visual Preference Optimization with Rubric Rewards

The effectiveness of Direct Preference Optimization (DPO) depends on preference data that reflect the quality differences that matter in multimodal tasks. Existing pipelines often rely on off-policy perturbations or coarse outcome-based signals, which are not well suited to fine-grained visual reasoning. We propose rDPO, a preference optimization framework based on instance-specific rubrics. For each image-instruction pair, we create a checklist-style rubric of essential and additional criteria to score responses from any possible policies. The instruction-rubric pool is built offline and reused during the construction of on-policy data. On public reward modeling benchmarks, rubric-based prompting massively improves a 30B-A3B judge and brings it close to GPT-5.4. On public downstream benchmarks, rubric-based filtering raises the macro average to 82.69, whereas outcome-based filtering drops it to 75.82 from 81.14. When evaluating scalability on a comprehensive benchmark, rDPO achieves 61.01, markedly outperforming the style-constrained baseline (52.36) and surpassing the 59.48 base model. Together, these results show that visual preference optimization benefits from combining on-policy data construction with instance-specific criterion-level feedback.

cs.CV↗
arXiv2026

YingMusic-Singer: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance

Regenerating singing voices with altered lyrics while preserving melody consistency remains challenging, as existing methods either offer limited controllability or require laborious manual alignment. We propose YingMusic-Singer, a fully diffusion-based model enabling melody-controllable singing voice synthesis with flexible lyric manipulation. The model takes three inputs: an optional timbre reference, a melody-providing singing clip, and modified lyrics, without manual alignment. Trained with curriculum learning and Group Relative Policy Optimization, YingMusic-Singer achieves stronger melody preservation and lyric adherence than Vevo2, the most comparable baseline supporting melody control without manual alignment. We also introduce LyricEditBench, the first benchmark for melody-preserving lyric modification evaluation. The code, weights, benchmark, and demos are publicly available at https://github.com/ASLP-lab/YingMusic-Singer-Plus.

eess.AS↗
arXiv2026

rt2gtfs: A scalable framework for correcting public transport timetables using real-time data for accessibility analysis

Travel time is a fundamental component of accessibility measurement, yet most accessibility analyses rely on static timetable data that assume public transport services operate exactly as scheduled. Such representations overlook the substantial variability in travel times arising from operational conditions and service disruptions. In this paper, we present rt2gtfs, an open-source Python package for reconstructing empirical public transport timetables from high-frequency vehicle location data. The package provides a configurable and scalable workflow for collecting GTFS-Realtime vehicle position feeds from the UK Bus Open Data Service (BODS), matching observed vehicle locations to scheduled GTFS trips and stops, inferring stop-level arrival and departure times, and exporting corrected GTFS format timetable bundles. Using national-scale real-time bus data feeds from BODS, we demonstrate how rt2gtfs can be used to generate observed timetables suitable for routing and origin-destination travel time calculation, as well as accessibility analysis. By packaging the framework as reusable software, this work supports more reproducible and realistic accessibility analysis and provides a practical tool for researchers and practitioners seeking to incorporate observed public transport performance into transport planning.

cs.CY↗
arXiv2026

Distribution-free screening of spatially variable genes in spatial transcriptomics

Spatial transcriptomics (ST) technologies enable transcriptome-wide gene expression profiling while preserving spatial resolution, offering unprecedented opportunities to uncover complex spatial structures. Due to the ultra-high dimensionality of ST data, identifying spatially variable genes (SVGs) associated with unknown spatial clusters has become a central task in ST data analysis. Here, we develop a distribution-free SVG screening method based on a novel quasi-likelihood ratio statistic, the MM-test, combined with a knockoff procedure to control the false discovery rate (FDR). MM-test leverages auxiliary information, such as spatial distances, about the unknown spatial domains for SVG screening. Notably, in addition to two-dimensional ST datasets, MM-test is well-suited for increasingly common three-dimensional (3D), multi-slice ST datasets. Extensive benchmarking using simulations and 34 real ST datasets demonstrates that MM-test consistently outperforms existing SVG detection methods. In a 3D mouse brain dataset, MM-test accurately delineates fine-scale structures that are challenging for other methods, such as the 3D architecture of the pyramidal layer of the hippocampal cornu ammonis and the dentate gyrus. Theoretical guarantees-including selection consistency, FDR control, and an error bound for post-selection clustering-are also established.

stat.AP↗
arXiv2026

LLM-Assisted Op-Amp Behavioral-Level Design via Agentic Human-Mimicking Reasoning

This paper proposes White-Op, an operational amplifier (op-amp) behavioral-level parameter design framework assisted by the human-mimicking reasoning of large language model agents. A symbolic reasoning-numerical solving decoupled paradigm is adopted: the agent performs step-by-step symbolic reasoning and formulates the design as a white-box optimization problem, which is then solved programmatically, verified via simulation, and refined iteratively. To guide this symbolic design process, implicit human reasoning mechanisms are formalized into explicit steps of introducing hypothetical constraints during transfer function simplification, pole-zero extraction and position regulation, converting design heuristics into mathematical formulations. A programming mapping protocol then standardizes the translation from symbolic designs to executable programs. Finally, a causality-driven refinement loop enables the agent to trace simulation-theory mismatches back to specific symbolic reasoning steps and make targeted corrections iteratively until convergence. Experiments on 9 op-amp topologies demonstrate that White-Op achieves interpretable behavioral-level designs with an average of 8.52\% theoretical prediction error and retains circuit functionality after transistor-level mapping for all topologies, whereas black-box baselines fail in 5 to 7 topologies. White-Op is open-sourced at https://github.com/zhchenfdu/whiteop.

cs.AI↗
arXiv2025

PRISM: A hierarchical multiscale approach for time series forecasting

Forecasting is critical in areas such as finance, biology, and healthcare. Despite the progress in the field, making accurate forecasts remains challenging because real-world time series contain both global trends, local fine-grained structure, and features on multiple scales in between. Here, we present a new forecasting method, PRISM (Partitioned Representation for Iterative Sequence Modeling), that addresses this challenge through a learnable tree-based partitioning of the signal. At the root of the tree, a global representation captures coarse trends in the signal, while recursive splits reveal increasingly localized views of the signal. At each level of the tree, data are projected onto a time-frequency basis (e.g., wavelets or exponential moving averages) to extract scale-specific features, which are then aggregated across the hierarchy. This design allows the model to jointly capture global structure and local dynamics of the signal, enabling accurate forecasting. Experiments across benchmark datasets show that our method outperforms state-of-the-art methods for forecasting. Overall, these results demonstrate that our hierarchical approach provides a lightweight and flexible framework for forecasting multivariate time series. The code is available at https://github.com/nerdslab/prism.

cs.LG↗
arXiv2025

From Optimization to Learning: Dual-Approach Resource Allocation for Over-the-Air Edge Computing Under Execution Uncertainty

The exponential proliferation of mobile devices and data-intensive applications in future wireless networks imposes substantial computational burdens on resource-constrained devices, thereby fostering the emergence of over-the-air computation (AirComp) as a transformative paradigm for edge intelligence.} To enhance the efficiency and scalability of AirComp systems, this paper proposes a comprehensive dual-approach framework that systematically transitions from traditional mathematical optimization to deep reinforcement learning (DRL) for resource allocation under execution uncertainty. Specifically, we establish a rigorous system model capturing execution uncertainty via Gamma-distributed computational workloads, resulting in challenging nonlinear optimization problems involving complex Gamma functions. For single-user scenarios, we design advanced block coordinate descent (BCD) and majorization-maximization (MM) algorithms, which yield semi-closed-form solutions with provable performance guarantees. However, conventional optimization approaches become computationally intractable in dynamic multi-user environments due to inter-user interference and resource contention. To this end, we introduce a Deep Q-Network (DQN)-based DRL framework capable of adaptively learning optimal policies through environment interaction. Our dual methodology effectively bridges analytical tractability with adaptive intelligence, leveraging optimization for foundational insight and learning for real-time adaptability. Extensive numerical results corroborate the performance gains achieved via increased edge server density and validate the superiority of our optimization-to-learning paradigm in next-generation AirComp systems.

eess.SP↗