Search arXiv⌕ Search

arXiv subjects

Peng Cheng

Publications and source records attributed to Peng Cheng.

At least 55 records · Page 3Linked to original sources
arXiv2026

Ghosts Beneath Textures: Texture-Relation Cues for Cross-Paradigm AI-Generated Image Detection

AI-generated images have proliferated rapidly, motivating extensive research. Most existing AI-generated image detectors are developed and evaluated under image-free generation paradigms, such as noise-based or text-guided generation. However, image-conditioned generation has become increasingly important in practical applications, as it enables more fine-grained control over generated content. Detecting AI-generated images across these two paradigms creates a critical cross-paradigm detection problem that has long been overlooked. To study this problem, we construct ConImageGen, a benchmark for cross-paradigm AI-generated image detection. Evaluations on ConImageGen show that existing detectors fail to generalize reliably across image-free and image-conditioned generation. To address this failure, this paper identifies a cross-paradigm forensic cue and provides a new perspective for generalized AI-generated image detection. Specifically, by suppressing semantic interference, we visualize, for the first time, semantics-irrelevant texture patterns across generation paradigms. These patterns exhibit structured local-global texture relations, indicating a generalizable form of forensic evidence. Motivated by this finding, we shift the focus from directly exploiting explicit artifacts to modeling texture relations and propose DTS-Det, a detection framework that captures and leverages such relations for generalized AI-generated image detection. Extensive experiments validate the effectiveness of our method. DTS-Det achieves state-of-the-art performance across diverse evaluation settings, reaching 99.6% ACC on ConImageGen with a 10.5% gain over the best baseline. It also achieves 93.2%/94.1% ACC in cross-dataset evaluation on PicoBanana/RAID and maintains detection rates of 95.2%/88.1% under reconstruction attacks and black-box adversarial attacks, respectively.

cs.CV↗
arXiv2026

ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving

In prefill-decode (PD) disaggregated LLM serving, each request is assigned to a decode worker after prefill. Existing decode routers balance only load; for mixture-of-experts (MoE) models this is incomplete: equally loaded workers can differ in latency, since each decode step loads the weights of every distinct expert its batch activates. We present ELDR, an expert-locality-aware decode router for PD-disaggregated MoE serving. From a request's prefill expert activations, ELDR builds an expert signature predicting the experts it will activate during generation. Offline, balanced K-means partitions signature space across decode workers; online, locality-band routing sends each request to the least-loaded worker among those best matching its signature. A signature cache, co-indexed with the KV cache at KV-block granularity, keeps signatures exact under prefix caching. Implemented in vLLM and evaluated on deployments of up to 40 GPUs, ELDR reduces median TPOT by 5.9-13.9% over the strongest of four load-balancing baselines across three MoE models and two workloads, with model outputs unchanged.

cs.DC↗
arXiv2026

SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills

Agents often repeatedly solve similar task instances from scratch, leading to unnecessary reasoning cost and long execution traces. Prior work has explored workflow reuse and executable skill induction, but it remains unclear which task scenarios admit procedural skills and how the shared procedural structure should be represented across successful traces. We study this problem in FSM-defined scenarios, where successful traces can be viewed as paths in an unknown transition graph, and formulate procedural skills as reusable parameterized control-flow subgraphs. Based on this view, we introduce SkillDisCo, a distillation-and-compilation framework that distills reusable PFSM subgraphs from successful traces and compiles them into callable, executable, and verifiable procedural skills. Experiments on ALFWorld and WebArena show that SkillDisCo improves success rates and reduces agent turns across benchmarks and model scales, demonstrating the benefits of representing shared experience as reusable execution structures.

cs.AI↗
arXiv2026

On the Universal Cuspy Behavior in Black Hole Shadows

This work investigates the universality of cusp formation in the shadows of compact objects. The emergence of cusps is accompanied by three interrelated phenomena: a topological charge transition, an equal-area law governing the self-intersecting structure, and universal critical scaling behavior. We demonstrate that, because these phenomena originate from the global morphology of the shadow, they are fundamentally independent of specific spacetime metric details and apply across diverse models. These features are systematically analyzed for the Kerr black hole endowed with a running Newton coupling. By extending our framework to rotating traversable wormholes, we confirm that the same universal behavior persists in more general compact objects. Our study uncovers the universality underlying cusp formation, offering a model-independent framework for characterizing possible non-Kerr shadow morphologies.

gr-qc↗
arXiv2026

HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detection

Advances in AIGC technologies have enabled the synthesis of highly realistic audio deepfakes capable of deceiving human auditory perception. Although numerous audio deepfake detection (ADD) methods have been developed, most rely on local temporal/spectral features or pairwise relations, overlooking high-order interactions (HOIs). HOIs capture discriminative patterns that emerge from multiple feature components beyond their individual contributions. We propose HyperPotter, a hypergraph-based framework designed to capture high-order relations associated with synergistic patterns through clustering-based hyperedges with class-aware prototype initialization. Extensive experiments on 13 test sets show that HyperPotter improves over the baseline on 11 sets, yielding an average relative EER reduction of 12.68\% across all test sets and 22.15\% on the improved sets. These results demonstrate strong cross-scenario generalization, while also revealing robustness limits under severe codec or channel distortion.

cs.SD↗
arXiv2026

Quantum-corrected black hole thermodynamics from the gravitational path integral

Exploring quantum effects from black hole thermodynamics has always been a pivotal topic. In recent years, the free energy landscape and ensemble-averaged theory based on the Euclidean path integral approach have provided further understanding of the statistical aspects of the black hole system. We investigate the quantum-corrected thermodynamics of the Reissner-Nordstrom AdS black hole by including off-shell geometries in a reduced gravitational path integral. Within this collective-variable approximation, we derive an effective action by considering the subleading-order terms in the ensemble-averaged theory and show that the corresponding thermodynamic quantities define a consistent thermodynamics. Furthermore, the phase diagram was modified by the off-shell effects, resulting in a more abundant phase structure. We show that the traditional black hole thermodynamics can be recovered in the semi-classical limit. The region of first-order phase transitions shrinks and zero-order phase transitions emerge when off-shell effects are included. These results provide a tractable framework for understanding how off-shell black hole geometries generate quantum corrections to black hole phase structures.

hep-th↗
arXiv2026

Complex Temperature-dependent Thermal Conductivity in a Sawtooth Chain Magnet Fe$_\mathrm{2}$SiSe$_\mathrm{4}$

Geometrically frustrated magnets provide an ideal platform for exploring the interplay between lattice geometry and spin degrees of freedom. Here, we investigate the interactions between lattice and spin via thermal-transport measurements on the triangular sawtooth-lattice olivine magnet Fe$_\mathrm{2}$SiSe$_\mathrm{4}$, which exhibits successive magnetic transitions at $T_1 = 110$ K (antiferromagnetic) and $T_2 = 50$ K (ferrimagnetic). Although phonons dominate the thermal conductivity, its temperature dependence displays a pronounced double-peak structure arising from spin-phonon coupling. In the intermediate temperature range between $T_1$ and $T_2$ , resonant scattering of phonons by magnetic excitations around 5 meV produces a broad maximum around 60 K. Below $T_2$, the resonant spin-phonon scattering is strongly suppressed, leading to a rapid increase in thermal conductivity upon cooling and a pronounced low-temperature peak near 11 K, characteristic of heat transport governed by conventional phonon scattering mechanisms. Notably, this low-temperature peak is enhanced by a factor of $\sim 5$ compared to the broad maximum at higher temperatures. These results demonstrate the strong sensitivity of thermal transport to spin-lattice interactions and highlight spin-phonon scattering as an effective mechanism for tailoring thermal conductivity in geometrically frustrated magnets.

cond-mat.str-el↗
arXiv2026

QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving

Retrieval-augmented generation (RAG) improves large language model (LLM) answer quality by grounding generation in external evidence, but processing retrieved contexts makes the prefill stage a dominant serving cost. RAG cache fusion reduces this cost by reusing precomputed key-value (KV) caches for retrieved chunks and selectively recomputing tokens under the current prompt. Existing selectors, however, face a dilemma between quality and efficiency: fast query-agnostic or final-layer query-to-context selectors can miss request-relevant evidence, whereas full-view query-aware selectors require broad context and layer visibility before recomputation and therefore stall the layer-wise cache-fusion pipeline. We present QCFuse, a compressed-view query-aware selector for RAG cache fusion. QCFuse uses chunk-anchor query probing to condition user-query states on compact per-chunk anchors and critical-layer profiling to identify recomputation tokens without all-layer inspection. We implement QCFuse in SGLang and evaluate it on four open-weight LLMs across six datasets. QCFuse reaches full-prefill-level quality. At matched quality, QCFuse achieves an average prefill-time speedup of 1.7x over full prefill and 1.5x over ProphetKV, the strongest quality-preserving baseline.

cs.AI↗
arXiv2026

Potential-Guided Flow Matching for Vision-Language-Action Policy Improvement

Large vision-language-action (VLA) policies are increasingly trained as conditional generative models over action chunks. Yet deployment produces mixed-quality experience-successful demonstrations, partial completions, recoverable mistakes, and failures-that is difficult to use with standard imitation. Full behavior cloning (BC) imitates failures, filtered BC discards useful sub-trajectories, and offline reinforcement learning adds a large critic. We introduce ForesightFlow, a self-guided flow-matching policy that augments each generated action chunk with a learned success-potential trajectory. The same flow proposes and scores candidate actions, enabling best-of-$K$ inference without an external critic. The key issue is that policy improvement and value calibration require different supervision: advantage weighting should emphasize high-quality actions, but applying the same weights to potential coordinates suppresses failure gradients and creates overconfident scores. We address this with decoupled advantage-weighted flow matching, applying exponentiated advantage weights only to action velocities while training potential velocities uniformly. We further derive a one-step boundary estimator for conditional flow matching, allowing advantage computation with a single stop-gradient forward pass. Across five BEHAVIOR-1K simulation tasks and five real-world bimanual tasks, ForesightFlow improves over imitation baselines, matches the strongest separate-critic baseline in simulation success, improves real-world success, and reduces training compute by $38\%$. Ablations show that decoupling prevents value hallucination, the one-step estimator preserves candidate-ranking fidelity, and self-guided sampling improves long-horizon execution.

cs.RO↗
arXiv2026

From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents

Supervised fine-tuning (SFT) on long teacher trajectories is the dominant way to instill investigation and reasoning in open software-engineering (SWE) agents. Since every retained response becomes an imitation target, the student inherits the final outcome and intermediate flaws, including ungrounded leaps and redundant loops. High-quality training data must be effective(each step is grounded and narrows the agent's epistemic gap to the correct fix) and efficient(each step is information-bearing rather than redundant or looping). Existing recipes filter or relabel teacher rollouts using only a binary terminal verifier, which does not directly target these axes and provides no supervision on instances where the teacher fails. Most real issue includes a developer-authored reference patch, $p^\star$, revealing the file paths, runtime behaviors, and coding conventions presupposed by the correct fix, yet standard pipelines discard it. We propose Patches-to-Trajectories (P2T), which uses $p^\star$ as privileged information during curation and formulates trajectory construction as bi-objective optimization over per-step effectiveness and trajectory length. A reverse phase distills $p^\star$ into a latent process graph, $G^\star$, of contextual facts and solution milestones. A forward phase curates trajectories from blinded teacher continuations by scoring per-step progress against $G^\star$ under a leakage-blocking groundedness check and retaining the shortest effective segments. Using only 1.8k curated SWE-Gym instances, P2T improves effectiveness and efficiency over outcome-filtered SFT and its tool-error-masking variant. On SWE-bench Verified, it raises Pass@1 by up to 10.8 points while reducing per-instance inference cost by ~15%, with consistent gains on SWE-bench Lite. Size-matched ablations and qualitative analysis further isolate trajectory quality from data scale.

cs.SE↗
arXiv2026

Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts

As the computational demands for pre-training Large Language Models (LLMs) continue to surge, the need for efficient training paradigms becomes critical. Despite the vast resources already invested in existing pre-trained checkpoints, these assets often remain under-leveraged due to architectural limitations. We introduce an "orthogonal growth" strategy designed to "recycle" these checkpoints by strategically expanding their parameters prior to continued training. Our method focuses on optimizing converged Mixture-of-Experts (MoE) models through two dimensions: interpositional layer copying for increased depth and noisy expert duplication for expanded width. Through extensive scaling laws analysis, we demonstrate a strong positive correlation between the "sunk cost" (prior investment) and the final model accuracy. Empirical results on models up to 70B parameters and 1T tokens show that our recycling approach yields a 10.6% accuracy improvement compared to training from scratch under identical extra compute budgets. This work provides a cost-effective blueprint for sustainable large-scale LLM development.

cs.LG↗
arXiv2026

Structure-BiEval: A Self-Supervised, Dual-Track Framework for Decoupling Structure and Content in LLM Evaluation for Web Information Systems

As Large Language Models (LLMs) evolve into the core of Web-based autonomous agents and complex Web Information Systems, their ability to faithfully translate natural language into rigorous structured formats has become paramount, as this capability is critical for Web API invocation and data exchange. However, evaluating this structural fidelity in Web-native payloads remains a challenge: traditional text metrics fail to capture topological consistency in semi-structured Web data, while manual evaluation is prohibitively costly. To address this, we propose Structure-BiEval, a novel self-supervised framework for quantitative, annotation-free assessment tailored for Web data engineering. By leveraging deterministic Intermediate Representations, our framework effectively decouples structure from content, utilizing Content Semantic Accuracy and Normalized Tree Edit Distance as precise metrics. We empirically benchmark 15 state-of-the-art LLMs across dual Web structural topologies, namely Hierarchical Data (Web backend payloads) and Tabular Data (Web frontend presentation). The results reveal substantial variability in structural performance, including cases where mid-sized models unexpectedly outperform larger counterparts in Web data formatting. Furthermore, our findings show that deep recursive nesting poses a consistent challenge for Web agents across varying parameter scales.

cs.CL↗
arXiv2026

Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues

Toxic speech detection has become a crucial challenge in maintaining safe online communication environments. However, existing approaches to toxic speech detection often neglect the contribution of paralinguistic cues, such as emotion, intonation, and speech rate, which are key to detecting speech toxicity. Moreover, current toxic speech datasets are predominantly text-based, limiting the development of models that can capture paralinguistic cues.To address these challenges, we present ToxiAlert-Bench, a large-scale audio dataset comprising over 30,000 audio clips annotated with seven major toxic categories and twenty fine-grained toxic labels. Uniquely, our dataset annotates toxicity sources -- distinguishing between textual content and paralinguistic origins -- for comprehensive toxic speech analysis.Furthermore, we propose a dual-head neural network with a multi-stage training strategy tailored for toxic speech detection. This architecture features two task-specific classification headers: one for identifying the source of sensitivity (textual or paralinguistic), and the other for categorizing the specific toxic type. The training process involves independent head training followed by joint fine-tuning to reduce task interference. To mitigate data class imbalance, we incorporate class-balanced sampling and weighted loss functions.Our experimental results show that leveraging paralinguistic features significantly improves detection performance. Our method consistently outperforms existing baselines across multiple evaluation metrics, with a 21.1% relative improvement in Macro-F1 score and a 13.0% relative gain in accuracy over the strongest baseline, highlighting its enhanced effectiveness and practical applicability.

cs.SD↗
arXiv2026

Reducing the Costs of Proof Synthesis on Rust Systems by Scaling Up a Seed Training Set

Large Language Models (LLMs) are widely used for code generation. However, the correctness of code generated by LLMs remains a concern. A potential remedy to this concern is to have LLMs generate formal correctness proofs along with such code. However, compared with code generation, code-proof generation requires much higher reasoning capability and has much less existing data to learn from. In this paper, we present VeruSyn, a data synthesis pipeline for Verus, a state-of-the-art verification tool for system software written in Rust. Through self-synthesis and tutorial-based synthesis, VeruSyn achieves much larger scale and Verus-feature coverage than previous data-synthesis techniques designed for Verus; VeruSyn also supplements its dataset with long-chain-of-thought (CoT) data through agent trajectory synthesis. With VeruSyn, we synthesize the largest set of Verus verified programs: 6.9 million Rust programs, each with a formal specification and a proof that it meets that specification. This dataset lets us create a fine-tuned Qwen2.5-Coder-32B-Instruct model with appealing cost-proof tradeoff compared with state-of-the-art commercial models like Claude Sonnet 4.5. It also significantly outperforms models like o4-mini and previously proposed research models.

cs.SE↗
arXiv2026

Noncollinear antiferromagnetic structure and physical properties of CrRhAs with distorted kagome lattice

CrRhAs was theoretically proposed to be a kagome metal with unusual magnetic ground states; however, little is known about its magnetic structure and physical properties experimentally. Here, we present an experimental investigation of CrRhAs with ZrNiAl-type structure and a distorted Cr kagome lattice. CrRhAs is an antiferromagnet with TN = 149 K. Powder neutron diffraction analysis reveals a noncollinear antiferromagnetic structure with propagation vector k = (1/3, 1/3, 1/2), which features a ferromagnetic second nearest neighbor coupling in the kagome plane that is different from the prediction in previous density functional theory calculations. Furthermore, CrRhAs exhibits anomalous electrical transport properties which are possibly related to multiband effects and strong spin fluctuations. For the temperature-dependent longitudinal resistivity \r{ho}xx, it is semiconductinglike above TN and becomes metallic below TN . The Hall coefficients exhibit two sign changes near 70 and 300 K. Combined with the results of heat capacity measurements, a large Kadowaki-Woods ratio α = 33.9 μΩ cm mol2 K2/J2 is obtained. The above results suggest CrRhAs is a strongly correlated kagome metal with multiband and noncollinear magnetic structure features.

cond-mat.str-el↗
arXiv2026

TSGuard: Automated User-Centric Incident Diagnosis for AI Workloads in the Cloud

AI workloads incur frequent failures and incidents from the underlying infrastructure. The current incident management workflow follows a provider-centric paradigm, where users report incidents to the infrastructure provider who then conducts troubleshooting. Due to the large number of incidents and the manual nature of the troubleshooting process, the provider often takes several days to resolve an incident, resulting in operational delays and productivity loss. To address these challenges, we present TSGuard, a user-centric multi-agent system that delivers immediate incident diagnosis to users who deploy the workloads. The core innovation of TSGuard is twofold: (1) constructing domain-specific knowledge bases by mining historical on-call experiences in the offline phase, and (2) mimicking human expert diagnosis via structured reasoning and iterative trial-and-error in the online phase. Evaluation using production incident records from Microsoft Azure demonstrates that TSGuard significantly outperforms state-of-the-art baselines, improving diagnostic accuracy by 19.8%. Furthermore, TSGuard reduces the average verification time by 63.4% compared to the sequential execution baseline.

cs.SE↗
arXiv2026

Evidence for monopole-like topological magnetoelectric effect in image potential states

Magnetic monopoles, hypothetical particles behaving as isolated magnetic charges, have long been predicted by theories beyond the standard model but remain elusive in experimental detection. Subsequently, Xiaoliang Qi et al. proposed that magnetic monopoles can be constructed in real space by introducing an active electric field at the interface between a topological insulator and vacuum [Science 323, 1184 (2009)]. Here we use scanning tunneling microscopy in the field-emission regime to realize an active electric-field geometry at the surface of the higher-order topological insulator Bi(111), and observe an anomalous splitting of the image potential states (IPSs). By tuning the dielectric properties of the substrate and film thickness, we considered that the peak-splitting of IPSs is related to the radially active electric field and topological surface states. Combined with phenomenological analysis, this peaksplitting can be attributed to the equivalent magnetic field of monopole-like topological magnetoelectric response. This work establishes field-emission IPS spectroscopy as a sensitive platform for generating active electric fields and probing the resulting image magnetic monopoles at topological surfaces.

cond-mat.mtrl-sci↗
arXiv2026

Dai-Freed anomalies and level matching in heterotic asymmetric orbifolds

We study asymmetric orbifolds of the $E_8\times E_8$ heterotic string from the perspective of worldsheet Dai-Freed anomalies. Focusing on cyclic symmetries $G = \mathbb{Z}_m$ that act chirally on the fermions and symmetrically on the bosons, we compute the corresponding spin-bordism invariants and derive the conditions for the vanishing of global anomalies from this perspective. In the fermionic description, these conditions are exactly the familiar level-matching constraints, together with the additional mod-2 conditions that appear for even $m$. We then discuss the same conditions from the transformation properties of higher-genus fermion partition functions and explain how the anomaly is matched under bosonization for a large class of inner automorphisms of the $E_8\times E_8$ lattice theory. This gives an interpretation of the standard consistency conditions for asymmetric heterotic orbifolds from the Dai-Freed anomaly perspective.

hep-th↗