Search arXiv⌕ Search

arXiv subjects

Miao Zhang

Publications and source records attributed to Miao Zhang.

At least 19 recordsLinked to original sources
arXiv2026

Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings

Accurate prediction in ungauged basins (PUB) requires effective transfer across hydrologically diverse regions. While deep learning has advanced large-sample hydrological modeling, its cross-regional generalization depends in part on the static basin descriptors used to guide model behavior. Earth Foundation Models (EFMs) provide a promising alternative by learning environmental representations from multi-modal satellite data. In this study, we evaluate the 64-dimensional AlphaEarth Foundations (AEF) embeddings as a new form of static basin representation and assess their value for streamflow prediction under both in-sample (IS) and out-of-sample (OOS) settings using the CAMELS dataset. Results show that AEF embeddings offer higher OOS robustness than CAMELS attributes, despite nearly identical IS performance. Mutual-information analysis reveals statistical associations between AEF embeddings and conventional catchment attributes related to terrain, vegetation, and rooting characteristics. We further investigate similarity-based donor-basin selection for PUB using CAMELS attributes and AEF embeddings. Across 100 target basins, AEF static inputs generally improved PUB performance. With AEF inputs, similarity-based donor selection outperformed random selection for smaller donor pools, but its advantage diminished as pool size increased. Adding more donor basins did not consistently improve performance. Leave-one-cluster-out experiments showed AEF input benefits depended on basin partitioning, suggesting that transferability remains sensitive to the catchment conditions represented during training. Overall, this study demonstrates that Earth Foundation Model embeddings provide a transferable representation for PUB prediction and underscores the importance of basin representation quality and donor pool design, motivating future research toward unified hydrological foundation models.

cs.LG↗
arXiv2026

Trace2Eval: Contextualized Evaluation of Coding Agents from Real-World Traces

Coding agents are increasingly used in real-world workflows across diverse domains, motivating evaluation grounded in real user tasks. Existing benchmarks, however, largely rely on static public tasks with reference patches or hidden tests. Next-generation coding-agent benchmarks should therefore move beyond correctness on fixed tasks toward continually renewed evaluation of overall artifact quality in real user workflows. We propose Trace2Eval, a dynamically updatable pipeline that constructs benchmarks from real-world interaction trajectories. Trace2Eval employs a multi-agent reconstruction system to analyze the filtered trajectory, recover the original user query, restore the workspace files to their pre-interaction state, and rebuild a trajectory-equivalent execution environment. A candidate agent then executes the reconstructed query to produce an initial artifact. To evaluate these artifacts, the pipeline iteratively refines human rubrics through inter-annotator alignment, and calibrates judge agents against human assessments using source-code and runtime evidence. Guided by feedback from the Trace2Eval pipeline, models revise their initial artifacts, yielding a mean score gain of 10.05 percentage points across 19 model-harness configurations and a maximum of 19.28 percentage points for DeepSeek-V4-Pro with Claude Code, which supports rubric feedback as actionable guidance for artifact improvement.

cs.SE↗
arXiv2026

Guess and Send: World-Model-Guided Semantic Packet Transmission for Robust Video Perception

Reliable video perception over bandwidth-constrained wireless links requires transmitting information that the receiver cannot already recover from its evolving scene representation. This paper introduces Guess and Send, a world-model-guided semantic packet transmission framework that prioritizes information according to its contribution to the receiver's perception. A shared feature-space world model predicts the receiver's scene state through affine motion compensation and learned residual displacement, while sender-side verification identifies reusable predictions. An acknowledgment-synchronized receiver twin estimates task-impact scores through two counterfactual evaluations, guiding packet selection and unequal error protection over LDPC-coded wireless channels. A compact 3-bit feature representation increases spatial coverage under stringent bandwidth constraints, while predictive fallback sustains perception during packet outages. Experiments on KITTI-MOTS (KITTI) and VisDrone2019-MOT (VisDrone) under Rayleigh fading and AWGN demonstrate substantial gains in low-SNR conditions. On KITTI at a 4.13% reference bandwidth budget, Guess and Send achieves 47.5% J&F at 0 dB Rayleigh SNR, outperforming H.264 by 11.3 percentage points. Controlled ablations show that world-model prediction contributes up to 8.7 points under Rayleigh fading. Object-detection experiments further demonstrate the transferability of receiver-relative predictive transmission across visual perception tasks. These results establish world-model-guided, receiver-state-aware transmission as an effective approach to robust video perception under severe communication constraints.

cs.MM↗
arXiv2026

Recursive Code Evolution for Task-Oriented Semantic Communications

Semantic communication jointly optimizes inference accuracy, channel use, and computation, yet the underlying communication program is typically specified before training. This paper presents ComRSI (Communications-Oriented Recursive Self-Improvement), a framework for recursively evolving that program through large-language-model-assisted code edits. An agent modifies the encoder, channel adapters, decoder, loss, and training policy; a protected evaluator screens candidates under prescribed budgets and resource constraints. Accepted code and textual feedback inform subsequent proposals, while candidate weights are trained from scratch. In the original ten-generation CIFAR-100 lineage, eight accepted revisions produce an attention-pooled code achieving 74.3% test accuracy over an Additive White Gaussian Noise (AWGN) channel at 32 complex symbols per image, compared with 67.2% at 256 symbols for the initial design. The program also improves fading-channel accuracy and transfers to Tiny-ImageNet after retraining, where a separate ComRSI search demonstrates further recursive improvements. A repeat study with ten searches per method compares ComRSI against non-recursive agents with and without textual history. Mean final search scores balancing accuracy, transmission rate, and computational cost are 0.7587, 0.7376, and 0.7089, respectively; the mean numbers of accepted revisions per search are 6.0, 5.0, and 2.1. The advantage over the memoryless agent is supported by a two-sided rank test, whereas the difference from the history-equipped agent remains statistically inconclusive at this sample size. Archived proposals show that pooling can yield a large improvement, while retained history supports subsequent refinement. These results support recursive program optimization within the evaluated setting and expose its remaining rate-robustness and compute-placement trade-offs.

cs.IT↗
arXiv2026

Frequency-Domain Decomposition and Recomposition for Robust Audio-Visual Segmentation

Audio-visual segmentation (AVS) plays a critical role in multimodal machine learning by effectively integrating audio and visual cues to precisely segment objects or regions within visual scenes. Recent AVS methods have demonstrated significant improvements. However, they overlook the inherent frequency-domain contradictions between audio and visual modalities--the substantial noise often present in audio high-frequency signals vs. the structurally rich details in visual high-frequency signals. Ignoring these differences can result in suboptimal performance. In this paper, we rethink the AVS task from a deeper perspective by reformulating AVS task as a frequency-domain decomposition and recomposition problem. To this end, we introduce a novel Frequency-Aware Audio-Visual Segmentation (FAVS) framework consisting of two key modules: Frequency-Domain Enhanced Decomposer (FDED) module and Synergistic Cross-Modal Consistency (SCMC) module. FDED module employs a residual-based iterative frequency decomposition to discriminate modality-specific semantics and structural features, and SCMC module leverages a mixture-of-experts architecture to reinforce semantic consistency and modality-specific feature preservation through dynamic expert routing. Extensive experiments demonstrate that our FAVS framework achieves state-of-the-art performance on three benchmark datasets, and abundant qualitative visualizations further verify the effectiveness of the proposed FDED and SCMC modules. The project repository is available at https://github.com/happylife-pk/FAVS.

cs.CV↗
arXiv2026

ATLAS: Expert-Guided Sustainable Satellite Backhaul for Off-Grid Wildlife Monitoring

Remote wildlife monitoring increasingly depends on high-fidelity cameras and sensors deployed far from grid power and terrestrial networks. Low Earth orbit satellite links can provide connectivity in these settings, but their high power draw and variable bandwidth, combined with intermittent on-site solar harvesting, make continuous backhaul infeasible. Current systems therefore filter at the edge, with motion triggers that waste limited energy and bandwidth on environmental artifacts, or fixed vision models that cannot follow evolving expert objectives. We present \textsc{ATLAS}, an expert-guided edge-to-cloud system that treats satellite backhaul as a scarce resource for off-grid wildlife monitoring. \textsc{ATLAS} uses foundation models to compile natural-language expert intent into semantic scoring logic, combines semantic relevance with environmental and energy state, and uses a constrained reinforcement-learning scheduler to decide which clips to upload and when. As a representative case study, we deployed \textsc{ATLAS} for over six months across 18 off-grid salmon-monitoring river sites. \textsc{ATLAS} achieves a mean clip-selection accuracy of $87.4\%$, exceeding mean baseline accuracy by $26.4$ percentage points, while maintaining near-continuous operation through low-solar periods in which baselines incur 16.0\% downtime.

eess.SY↗
arXiv2026

ChronoScribe: Semantic-Numerical Specialization for Instruction-Driven Time Series Forecasting

Recent advances in instruction-driven time series forecasting highlight a fundamental tension: systems must simultaneously master natural-language instruction following and precise numerical prediction. Current approaches often force a compromise. Large language models (LLMs) can interpret unstructured requests but may be inaccurate when asked to produce forecast values directly, whereas time series foundation models (TSFMs) provide numerical forecasts but typically require structured inputs specifying the target series, context window, and horizon. We present ChronoScribe, which applies semantic-numerical specialization to this workflow. A LoRA-adapted LLM proposes an execution path and context length; deterministic rules resolve the executable configuration. On the specialist path, a frozen TSFM produces quantile trajectories for the task-specified horizon. Deterministic trajectory summaries condition the response, while the LLM neither generates nor revises predicted values. We evaluate a Qwen3.5-9B--Chronos-2 implementation across 23 evaluation dimensions and 30 public datasets against eleven proprietary direct LLMs and three open TSFMs. ChronoScribe has the lowest error on sMAPE, MASE, WAPE, RMSE, and MAE among all evaluated systems, including fixed-context controls. Across these metrics, even the lowest direct-LLM error remains 2.0--2.7 times the corresponding ChronoScribe error. At the system level, ChronoScribe achieves a Task-Level Score (TLS) of 65.5, 10.6 points above the strongest direct-LLM baseline. The results support ChronoScribe's division of labor, in which the LLM handles interpretation, configuration, and communication while the TSFM handles numerical forecasting.

cs.AI↗
arXiv2026

OpenDGO: Benchmarking Multi-Agent Organizations Across Diverse Application Domains

Large language model (LLM)-based multi-agent systems are increasingly applied across diverse domains, yet different applications require different forms of agent organization. Existing studies typically adopt predefined organizations, such as Star, Chain, and Tree, or learn communication graphs to improve performance on specific tasks. However, these methods are largely designed and evaluated within a limited set of application domains, providing little understanding of whether an organization effective in one domain remains suitable for others with different collaboration requirements. We present \textbf{OpenDGO}, a controlled benchmark and analysis framework covering six real-world domains and three collaboration settings: Sequential Dependency, Parallel Decomposition, and Information Integration. Under matched tasks, agents, tools, and resource limits, OpenDGO compares fixed and learned organizations while separately examining communication graphs, role assignments, input assignments, resource budgets, and component failures. Our results show that there is no ``one-organization-for-all'' solution: preferred organizations vary across applications, and even the same communication graph can yield different outcomes under different role and input assignments. These findings highlight the need for application-dependent organization design, aiming to understand \emph{which organization is suitable for a given application, under what conditions, and why}.

cs.LG↗
arXiv2026

When Skills Remain But Access Fails: Factorized Skill Memory for Continual Skill Internalization

Skill internalization aims to convert externally specified procedural skills into persistent model capabilities, allowing language-model agents to execute them without retrieving or reinjecting skill descriptions at inference time. Yet when new skills are learned continually, whether previously internalized skills remain usable is still poorly understood. We study forgetting in continual skill internalization and uncover a clear hierarchical structure. Early in subsequent training, a model may lose the ability to invoke an old skill from the raw request, while supplying only the correct canonical skill name substantially restores the learned behavior; with further optimization, this conditional execution also degrades. We call these two stages skill-addressing forgetting and skill-execution forgetting. Guided by this finding, we introduce Factorized Skill Memory (FSM), which separates continual skill memory into a plastic Address Memory and a stable Execution Memory. At each stage, FSM trains a new LoRA executor using only current-stage data, freezes it after acquisition, and appends it to Execution Memory; in parallel, Address Memory incrementally learns to map current requests to executors without replaying historical requests or execution trajectories. At inference time, Address Memory selects one executor from the raw request, and only that frozen executor performs a single language-model generation. On a five-stage benchmark built from 100 TaskBench skills, FSM achieves 65.95% mean exact match and 93.38% addressing accuracy across two task orders, improving over the strongest replay-free parameter-isolation baseline by 14.3 percentage points while remaining within 1.9 points of Replay, which retains historical training examples.

cs.AI↗
arXiv2026

CacheLink: Functional KV Transport for Zero-Prefill Cross-Model Context Handoff

KV caches make long-context serving efficient by reusing past computation, but model switching breaks this reuse and forces the receiver to prefill the context again. We study \emph{zero-prefill cross-model context handoff}: translating a sender cache into a receiver-compatible state so that the receiver can continue directly without prefilling same context. Existing affine transport methods show that receiver KV states can be substantially reconstructed from sender caches. However, through extensive analyses, we find that reconstruction fidelity is a poor proxy for receiver utility. Similar K/V reconstruction errors can lead to substantially different attention patterns, predictive distributions, and downstream accuracy, because conventional reconstruction objectives overlook the query-dependent functional importance of K and V in receiver attention. We thus introduce CACHELINK, which learns a coupled K/V correction through the receiver behavior directly. Across four independently trained sender--receiver pairs and seven evaluation panels, CACHELINK improves the equal-weight mean over all methods for every pair. In matched diagnostics, CACHELINK changes K/V squared error by less than 0.4% while substantially changing receiver attention and next-token behavior. At 32K context, it reduces handoff latency by up to $7.27\times$ relative to receiver re-prefill. Our findings verify that reconstruction fidelity alone is insufficient and that preserving the receiver computation induced by the transported cache is important for effective cross-model KV transport.

cs.LG↗
arXiv2026

VisualErase: Dual-Branch Visual Trajectory Redirection for Robust Concept Erasure in Text-to-Image Diffusion Models

Concept erasure is essential for the safe deployment of text-to-image diffusion models, as they may reproduce harmful, copyrighted, or privacy-sensitive content learned from unconstrained large-scale data. Existing methods typically erase unwanted concepts while preserving general generation capability by redirecting target-related text-to-image mappings. However, recent studies show that erased models may still retain visual generative trajectories of target concepts, leaving them vulnerable to adversarial recovery attacks and revealing a fundamental gap between redirecting text-to-image mappings and truly removing visual knowledge. To bridge this gap, we propose VisualErase, a new paradigm that redirects concept-bearing visual generative trajectories toward explicitly defined concept-removed outcomes. To enable this redirection, we use structure-preserving image editing to construct content-aligned, concept-removed counterparts for source images, providing explicit visual endpoints that retain non-target content. We then derive a denoising target from each source-to-counterpart pair and use a dual-branch redirection loss to align both text-conditioned and unconditional predictions with this target, since conditional supervision alone does not explicitly constrain generation without textual guidance. To mitigate the adverse effects of concept erasure on non-target generation, we jointly optimize the redirection loss with a counterpart retention loss that matches denoising predictions from the frozen pretrained model. Across style, celebrity, and nudity erasure, VisualErase limits the maximum attack success rate over seven attacks to 0%, 8%, and 0.1%, respectively, while retaining general generation quality. These results highlight the importance of visual trajectory redirection for robust concept erasure beyond text-to-image mappings alone.

cs.CV↗
arXiv2026

ATI-VLA: Action-Centric Predictive Vision-Language-Action Models via Actionable Alignment Then Adaptive Injection

Predictive Vision-Language-Action (VLA) models aim to improve robotic manipulation via future observation or world dynamics forecasting. However, existing approaches often fail to realize this potential and underperform direct action prediction models. We argue that these limitations stem from modality misalignment between observations and actions, together with joint optimization conflicts that drive learning away from an action-centric objective. To this end, we introduce ATI-VLA, an Action-Centric Predictive Vision-Language-Action framework via Actionable Alignment Then Adaptive Injection. Specifically, it follows a two-step design: 1) Actionable Representation Alignment via a Shared Codebook. It aligns predictive observation and action representations by mapping both modalities into a shared discrete latent space via a unified codebook, making predictive observation latents readily usable for action generation and mitigating modality misalignment. 2) Action-Centric Adaptive Injection of Predictive Latents. Building upon this, it then injects predictive observation latents into action decoding as explicit predictive priors via a lightweight adaptive side-path, enabling adaptive predictive guidance under a single action-centric objective. Extensive experiments on both simulation and real-world robotic tasks demonstrate that ATI-VLA achieves state-of-the-art performance with faster convergence.

cs.CV↗
arXiv2026

HELIX: Purified and Unified - Rethinking Feature Interaction and Sequence Modeling for Large-Scale Recommendation

Industrial recommendation ranking models typically scale along two modeling axes: feature interaction over heterogeneous user, item, context, and cross features, and sequence modeling over long, informative, and multi-type user behavior histories. We find that scaling either capability in isolation is insufficient, as each exhibits a limited scaling ceiling and a suboptimal scaling-law slope. We conjecture that achieving a more favorable scaling-law slope requires jointly scaling both axes. To support this, we present HELIX, a purified and unified architecture for large-scale recommendation. HELIX interleaves sequence retrieval and feature interaction while enforcing one-way information flow from reusable sequence states to candidate-conditioned mix-tokens. This design preserves cross-depth communication between the two modeling axes while keeping user-side sequence computation amortizable, enabling flexible and asymmetric scaling of sequence modeling and feature interaction. Deployed in TikTok's e-commerce recommendation system, HELIX consistently improves offline CTR AUC, CVR AUC, and other ranking metrics. In online A/B tests, it achieves an approximately 6% increase in e-commerce video GMV per user.

cs.IR↗
arXiv2026

MASRubric: Auditing Information Flow in Multi-Agent Systems with Failure-Distilled Pitfall Rubrics

While multi-agent systems (MAS) excel at complex reasoning, they are vulnerable to errors that intermediate agents introduce and downstream agents build upon. Auditing intermediate messages before they propagate requires an explicit standard, yet evaluation rubrics are typically authored by domain experts or written against a reference answer, neither of which is available for an unseen message at test time. We present MASRubric, a MAS information flow auditing framework with failure-distilled pitfall rubrics. Offline, trajectories on which the MAS has failed are automatically distilled into a reusable bank of pitfall criteria, each describing a recurrent error by its underlying misconception, the reasoning situations in which it arises, and the check that would expose it. Online, the criteria applicable to each intermediate message are retrieved from this off-the-shelf bank and checked one by one, and the resulting satisfaction rate decides whether the message is broadcast, returned to its author with diagnostic feedback for revision, or withheld. Empirical results demonstrate that MASRubric enhances MAS performance on both fixed and dynamic frameworks, achieving average accuracy gains of up to 2.83 points on math reasoning benchmarks and 1.74 points on code generation benchmarks. Further analysis shows that the retrieved criteria vary systematically with task types, and that the audit effort tracks task difficulty. Moreover, the bank transfers without re-mining to a system with a stronger backbone, which makes more adaptive and more efficient use of it. Our code and dataset are released at https://github.com/TonySY2/MASRubric.

cs.AI↗
arXiv2026

QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models

Video world models achieve long-range temporal consistency by storing KV cache during generation, but the growing cache makes KV cache memory a major deployment bottleneck, which motivates low-bit quantization study for efficiency. Existing 2-bit KV cache quantization methods can achieve nearly lossless performance on VBench, however, when applied to video world models, we find they still cause severe temporal flickering and visual degradation. Meanwhile, deeper investigates show that Key quantization produces smaller reconstruction errors than Value, but surprisingly leads to larger output degradation. We trace this discrepancy to attention in video world models: Key perturbations can change the attention logits, and shift the temporal-spatial tokens selected by Queries. These observations motivate us to preserve attention logits and temporal-spatial token selection during KV cache quantization. To address this issue, we present QuantWM, a training-free 2-bit KV cache quantization framework for video world models. QuantWM introduces two complementary techniques to mitigate the attention shifts. Firstly, quantization-sensitivity-aware clustering (QSAC) jointly considers historical Query sensitivity and residual ranges to select INT2-friendly Key centroids, which reduces quantization errors in channels that are more critical to attention. In addition, principal-subspace attention compensation (PSAC) restores the remaining Key errors along the dominant Query subspace using low-rank projections, which provides a direct and efficient correction to stabilize attention logits. Experiments on LingBot-World-v2, HY-World 1.5, Matrix-Game-2, Longcat-Video and Causal-Forcing demonstrate that QuantWM significantly improves visual quality and temporal consistency, while outperforming existing methods across benchmarks with up to 6.20 KV cache memory compression and limited additional overhead.

cs.CV↗
arXiv2026

MOVE: Multimodal Open-world Verification and Expansion for Graph Learning

Multimodal graph learning faces a fundamental challenge: new classes may emerge after deployment, while models are trained with a fixed label space. Existing approaches typically detect unknown nodes and use LLMs to generate candidate class descriptions, but they do not determine whether existing classes are insufficient to cover these nodes or whether a generated class is reliable enough to expand the class space. Our empirical study reveals three challenges: multimodal information beyond individual modalities is required for unknown-node identification, LLM-generated class descriptions may not fully capture multimodal class characteristics, and directly adding candidate classes can introduce redundant categories. Based on these observations, we propose MOVE, a multimodal open-world class verification and expansion framework. MOVE identifies nodes that cannot be assigned to existing classes by jointly considering visual tokens, textual attributes, and graph context, leverages a multimodal LLM to generate candidate classes, and selectively expands the class space only when candidates are consistently supported by multimodal evidence without introducing unnecessary categories. Experiments demonstrate that MOVE achieves an average improvement of 11.87\% across unknown recognition, open-domain annotation, and downstream graph learning tasks.

cs.LG↗
arXiv2026

M-SQE: Multilingual Skill Quality Estimation for Enhancing Language Equality in Agentic Skill Use

Agent skills, reusable procedural documents that extend LLM agents beyond their parametric memory, have become an important interface for deploying agents on real-world tasks. Community-maintained skill libraries built around this interface are growing rapidly. However, this ecosystem remains deeply English-centric: our audit finds that low-resource languages such as Swahili and Hindi have no in-language skill content, so retrieval often returns a skill written in a different language than the query, degrading accuracy and recall. A practical solution is to synthesize in-language skills for retrieval but the quality can be unreliable, so relevance in this setting alone often surfaces a related but unusable candidate. To address this, we propose M-SQE, a post-retrieval Multilingual Skill Quality Estimation framework that scores candidates via a Theory view for intrinsic quality and an Action view for task-grounded utility, unified into a domain-conditioned final score. We evaluate M-SQE across three skill-use domains: general, tool-use, and cultural tasks. Empirically, we build three-layer candidate skill pools mirroring today's ecosystem, where M-SQE's task success exceeds existing baseline's average by at least +3.5 points across three different retrievers. Particularly, M-SQE lifts the lowest-resource languages most (+12.9pp on Hindi and +5.6pp on Swahili) and achieves strong performance across all six culture regions, thereby moving agentic skill use toward linguistic and cultural equality.

cs.CL↗
arXiv2026

LLM-Based Semantic Modeling and Cooperative Evolutionary Fuzzing for Traffic Violation Scenario Generation

Ensuring the safety of autonomous driving systems (ADS) in a cost-effective and efficient manner remains a critical challenge. Existing law-guided scenario generation approaches are typically limited to a narrow subset of legal rules, resulting in insufficient scenario diversity, and search-based methods often struggle with large and sparse search spaces. To address these limitations, we propose SLaFE (Semantic Law Modeling and Fuzzing based on Cooperative Evolution), a novel traffic violation scenario generation framework designed to systematically evaluate the safety of ADS. SLaFE harnesses the reasoning capabilities of large language models (LLMs) to convert traffic laws into structured scenario constraints. These scenarios are then optimized via a cooperative evolutionary fuzzing algorithm that explores the parameter space to identify boundary cases likely to trigger abnormal ADS behaviors. We evaluate SLaFE on the Apollo platform within the LGSVL simulator using ten real-world traffic regulations. Experimental results show that SLaFE successfully triggered all 10 types of traffic law violations (10/10), outperforming the best existing method, VioHawk (9/10), while others detected no more than 3. Moreover, SLaFE achieved an average triggering time of 5.1 minutes per law type, significantly faster than VioHawk (9.0 minutes) and other baselines. These results highlight SLaFE's effectiveness in discovering diverse and critical law-violating scenarios for ADS testing.

cs.CE↗