arXiv subjects

Ke Yang

Publications and source records attributed to Ke Yang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Boson Stars in Teleparallel Gravity with a Nonminimally Coupled Field: The Violation of Energy Conditions and Gravitational Waveforms from EMRIs

In this work, we investigate boson star models within the framework of teleparallel gravity with non-minimal coupling, and obtain static, spherically symmetric solutions for both the ground state and excited states. The results indicate that the energy density of the excited-state solutions can become negative. For these solutions, the four commonly used energy conditions are no longer satisfied. In contrast, for all the ground-state solutions we have studied, the energy density remains positive and all four energy conditions are consistently satisfied. Moreover, considering the importance of astrophysical observations, the gravitational-wave signals from Extreme-Mass-Ratio Inspirals (EMRIs) composed of these boson stars are investigated. Our results reveal that the frequency-domain characteristic strain of these waveforms falls within the detectability range of LISA, which can provide potential evidence for distinguishing compact astrophysical objects.

gr-qc↗

arXiv2026

Hermes: A General-Purpose Proxy-Enabled Networking Architecture

We introduce Hermes, a general-purpose networking architecture that aims to improve service delivery over the Internet. Hermes delegates networking responsibilities from applications and services to proxies and is designed as a portable, adaptable solution to four fundamental challenges of efficient service delivery over the Internet: end-to-end traffic management, backward compatibility, data-plane security and privacy models, and adaptable communication layers. The design centers on an overlay of reconfigurable proxies and HTTP tunneling and proxying techniques, utilizing assisting components to extend proxy functionality when needed. Through prototyping and emulation, we demonstrate that Hermes improves key performance metrics across multiple use cases: it provides backward compatibility through protocol translation and tunneling, improves reliability by delegating retry logic to proxies, enables unified policy-based Layer 3 routing across network segments, and serves as an efficient substrate for future architectures like NDN, facilitating their operation over the Internet. Beyond evaluating Hermes across various use cases, we measured the overhead of Hermes' HTTP tunneling and proxying mechanisms and found it to be modest, typically under 2 ms per proxy pair traversal in an isolated collocated setup. Although the HTTP proxying and tunneling techniques used by Hermes increase single-connection processing overhead, we also show that, with up to 1,000 concurrent requests, proxies can amortize connection setup time and reduce end-to-end latency by utilizing connection pooling and multiplexing.

cs.NI↗

arXiv2026

Boson Stars in Bumblebee Gravity and Their Gravitational Waveforms from Extreme-Mass-Ratio Inspirals

We investigate the impact of Lorentz violation on the compactness of mini-boson stars and the resulting gravitational-wave signals from extreme-mass-ratio inspirals (EMRIs) within the framework of bumblebee gravity. Numerical solutions for static, spherically symmetric configurations reveal that a positive Lorentz-violating parameter $\ell$ suppresses repulsive pressure, thereby enhancing gravitational binding and yielding more compact boson stars. Conversely, a negative $\ell$ amplifies repulsive pressure and weakens gravitational binding, such that no static solutions exist beyond a critical negative value. These structural modifications imprint distinct features on EMRI dynamics, characterized by a monotonic decrease in both orbital eccentricity and radial range as $\ell$ gradually increases from negative to positive values. Unlike the intermittent bursts from grazing orbits that resemble black-hole signals, penetrating orbits that enter the boson-star core exhibit sustained, amplitude-modulated gravitational-wave signatures without quiet intervals. Their characteristic strain falls within the detectability range of LISA, providing a potential observable for constraining Lorentz violation.

gr-qc↗

arXiv2026

Topology-Aware Skeleton Detection via Lighthouse-Guided Structured Inference

In natural images, object skeletons are used to represent geometric shapes. However, even slight variations in pose or movement can cause noticeable changes in skeleton structure, increasing the difficulty of detecting the skeleton and often resulting in discontinuous skeletons. Existing methods primarily focus on point-level skeleton point detection and overlook the importance of structural continuity in recovering complete skeletons. To address this issue, we propose Lighthouse-Skel, a topology-aware skeleton detection method via lighthouse-guided structured inference. Specifically, we introduce a dual-branch collaborative detection framework that jointly learns skeleton confidence field and structural anchors, including endpoints and junction points. The spatial distributions learned by the point branch guide the network to focus on topologically vulnerable regions, which improves the accuracy of skeleton detection. Based on the learned skeleton confidence field, we further propose a lighthouse-guided topology completion strategy, which uses detected junction points and breakpoints as lighthouses to reconnect discontinuous skeleton segments along low-cost paths, thereby improving skeleton continuity and structural integrity. Experimental results on four public datasets demonstrate that the proposed method achieves competitive detection accuracy while substantially improving skeleton connectivity and structural integrity.

cs.CV↗

arXiv2026

BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization

Mitigating social bias in Large Language Models (LLMs) presents a distinct alignment challenge: unlike verifiable tasks, bias lacks a single ground truth, creating a high-variance, subjective reward landscape. Previous preference-based fine-tuning methods have major trade-offs: Direct Preference Optimization (DPO) is limited by the lack of exploration inherent in offline training, while Proximal Policy Optimization (PPO) can lead to training instability due to potentially unreliable critic estimates. In this paper, we propose BiasGRPO, a framework using Group Relative Policy Optimization (GRPO) to stabilize alignment by normalizing rewards across a group of sampled completions. By substituting the value function with a group-relative baseline, our approach reduces instability while maintaining the exploration benefits of online training. We find that BiasGRPO outperforms DPO and PPO across multiple benchmarks, indicating its effectiveness. To adapt GRPO, we synthetically extend a dataset spanning multiple domains and contexts. We also create and release a custom bias reward model that effectively guides generation while being highly compute-efficient and avoiding knowledge degradation, providing a valuable resource that can be seamlessly integrated into multi-objective RLHF pipelines.

cs.AI↗

arXiv2026

When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG

Medical question answering is a high-stakes setting where factual errors can have serious consequences. Retrieval-augmented generation (RAG) is widely viewed as a promising solution, and prior work has reported substantial gains for large medical QA models. We revisit this assumption across a broad range of open-weight instruction-tuned models spanning 7B to 72B parameters. Across five models, ten biomedical QA datasets, four retrieval methods, and four retrieval corpora, we find that retrieval yields only small and inconsistent improvements over a no-retrieval baseline, typically within 1-2 points. In contrast, the choice of backbone model has a much larger effect than the choice of retriever or corpus, and expert and layman retrieval sources perform similarly in most settings. These results suggest that the main bottleneck is not retrieval quality alone, but the model's limited ability to use retrieved evidence effectively.

cs.CL↗

arXiv2026

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a shortage of high-quality, action-aligned reasoning data, and the direct adoption of generic post-training pipelines that overlook the unique challenges of GUI agents. We identify two fundamental issues in these pipelines: (i) standard SFT with CoT reasoning often hurts grounding, and (ii) step-wise RLVR-tyle training faces partial verifiability, where multiple actions can be correct but only a single demonstrated action is used for verification. This makes offline step-wise metrics weak predictors of online task success. In this work, we present GUI-Libra, a tailored training recipe that addresses these challenges. First, to mitigate the scarcity of action-aligned reasoning data, we introduce a data construction and filtering pipeline and release a curated 81K GUI reasoning dataset. Second, to reconcile reasoning with grounding, we propose action-aware SFT that mixes reasoning-then-action and direct-action data and reweights tokens to emphasize action and grounding. Third, to stabilize RL under partial verifiability, we identify the overlooked importance of KL regularization in RLVR and show that a KL trust region is critical for improving offline-to-online predictability; we further introduce success-adaptive scaling to downweight unreliable negative gradients. Across diverse web and mobile benchmarks, GUI-Libra consistently improves both step-wise accuracy and end-to-end task completion. Our results suggest that carefully designed post-training and data curation can unlock significantly stronger task-solving capabilities without costly online data collection. We release our dataset, code, and models to facilitate further research on data-efficient post-training for reasoning-capable GUI agents.

cs.LG↗

arXiv2026

DART: Semantic Recoverability for Structured Tool Agents

When a structured tool agent fails mid-execution, the runtime faces a dilemma: replaying the entire task is safe but wasteful, while restoring from a local checkpoint is efficient but can leave committed downstream work tied to an upstream history that no longer exists. This tension is acute in commitment-sensitive settings, where rollback targets a single failed instance yet downstream consumers have already acted on its output. Existing recovery approaches provide mechanical rollback but no criterion for whether a local restore remains semantically valid after downstream commitment. We formalize this gap as semantic recoverability and address it in DART, a modular runtime that localizes the failed instance, certifies semantically recoverable boundaries of that instance, aligns checkpoints to those boundaries, and selects an admissible restore point that preserves committed downstream work under dependency and effect constraints-or blocks otherwise. Across three LLM-driven domains and external validation on a LangGraph-based substrate, DART correctly recovers all evaluated commitment-sensitive cases where baseline local recovery fails, and a five-domain safety audit finds no unsafe admitted rollbacks. These results show that controller legality does not imply semantic validity, and that sound local recovery requires an explicit admissibility check.

cs.AI↗

arXiv2026

Code as Agent Harness

Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification. We frame this shift through the lens of agent harnesses and introduce code as agent harness: a unified view that centers code as the basis for agent infrastructure. To systematically study this perspective, we organize the survey around three connected layers. First, we study the harness interface, where code connects agents to reasoning, action, and environment modeling. Second, we examine harness mechanisms: planning, memory, and tool use for long-horizon execution, together with feedback-driven control and optimization that make harness reliable and adaptive. Third, we discuss scaling the harness from single-agent systems to multi-agent settings, where shared code artifacts support multi-agent coordination, review, and verification. Across these layers, we summarize representative methods and practical applications of code as agent harness, spanning coding assistants, GUI/OS automation, embodied agents, scientific discovery, personalization and recommendation, DevOps, and enterprise workflows. We further outline open challenges for harness engineering, including evaluation beyond final task success, verification under incomplete feedback, regression-free harness improvement, consistent shared state across multiple agents, human oversight for safety-critical actions, and extensions to multimodal environments. By centering code as the harness of agentic AI, this survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.

cs.CL↗

arXiv2026

DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion

Achieving versatile humanoid locomotion with a single policy presents a critical scalability challenge. Prevailing methods often rely on distilling multiple terrain-specific teacher policies into a unified student policy. However, while such distillation captures basic locomotion primitives, it struggles to organically compose these skills to adapt to complex environments, resulting in poor generalization to novel composite terrains unseen during training. To overcome this, we present DreamPolicy, a unified framework that integrates offline data with a diffusion-based world model, enabling a single policy to master both known and unseen terrains. Central to our approach is a terrain-aware world model, driven by an autoregressive diffusion world model trained on aggregated rollouts from specialized policies. This model synthesizes physically plausible future trajectories, which serve as dynamic objectives for a conditioned policy, thereby bypassing manual reward engineering. Unlike distillation, our world model captures generalizable locomotion skills, allowing for robust zero-shot transfer to unseen composite terrains. DreamPolicy naturally scales with data availability. As the offline dataset expands, the diffusion world model continuously acquires richer skills. Experiments demonstrate that DreamPolicy outperforms the strongest baseline by up to 27\% on unseen terrains and 38\% on combined terrains. By unifying world model-based planning and policy learning, DreamPolicy breaks the "one task, one policy" bottleneck and establishes a scalable, data-driven paradigm for generalist humanoid control.

cs.RO↗

arXiv2026

Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary

Enabling humanoid robots to follow free-form natural language commands is a critical step toward seamless human-robot interaction and general-purpose embodied AI. However, existing methods remain limited, often constrained to simple instructions or forced to sacrifice motion diversity for physical plausibility. To address this gap, we present Humanoid-LLA, a Large Language Action model that translates unconstrained natural language directly into executable whole-body motions for humanoid robots. Our approach tackles two core challenges: paired language-humanoid motion data scarcity and physical instability. First, we bridge high-level language semantics with physically-grounded control by learning a unified human-humanoid motion vocabulary. Second, we introduce a novel two-stage fine-tuning framework that begins with supervised motion Chain-of-Thought learning, followed by reinforcement learning refined with physical feedback to ensure robustness and stability. Extensive evaluation in simulation and real-world cross-embodiment experiments demonstrates that Humanoid-LLA achieves superior generalization to novel language commands and diverse motion generation while maintaining high physical fidelity.

cs.RO↗

arXiv2026

Surviving Partial Rank Failures in Wide Expert-Parallel MoE Inference

Mixture-of-Experts (MoE) serving relies on wide expert parallelism (EP) to aggregate the memory capacity and bandwidth of many GPUs within one inference instance. This efficiency comes with a systems cost: every decoding step depends on token dispatch and combination across all active EP ranks, so even one rank failure can disrupt the entire service. Existing EP stacks handle such failures poorly because they treat membership as a fixed configuration established at initialization. The same rank set determines communicator state, expert placement, and the routing metadata baked into CUDA execution graphs, leaving the system with no way to shrink around a failure while keeping the instance valid. This paper argues that partial-failure tolerance should instead be formulated as a live EP validity problem. We present EEP, a communication and runtime substrate that represents membership as explicit, mutable runtime state. EEP repairs the specific state invalidated by a fault: it restores peer reachability without rebuilding the communication substrate, repairs lost expert coverage through a bandwidth-aware hierarchy, and reintegrates repaired ranks without forcing healthy ranks to recapture their CUDA graphs. We implement EEP in an EP serving stack integrated with SGLang and evaluate it under steady-state serving, failure recovery, and rank reintegration. The results show that explicit mutable membership preserves the steady-state fast path, staying within 4.4% of a fixed-membership DeepEP baseline under static serving, while turning a local rank fault from whole-instance downtime into two bounded interruptions. On a single-rank failure workload, EEP incurs an 11s recovery pause and an 8s reintegration pause, and restores throughput to within 95% of the pre-fault level within 52s, whereas a fixed-membership full-restart baseline remains unavailable until 348s.

cs.DC↗

arXiv2026

Entanglement probes of gravitational Kaluza-Klein spectra: signal hierarchy and model discrimination

Quantum-gravity-induced entanglement of masses (QGEM) provides a phase-sensitive probe of extra-dimensional corrections to the Newtonian potential at submillimeter separations. We compare three representative Kaluza-Klein spectral scenarios: the Randall-Sundrum II (RSII) and Arkani-Hamed-Dimopoulos-Dvali (ADD) models, and the case of a gapped continuum modeled by a Pöschl-Teller potential. We evaluate the entangling phase, concurrence, and normalized phase-response profiles over $d=40$-$80\,μ\mathrm{m}$ using representative benchmark parameters guided by current short-range gravity tests. In this range, the signal exhibits a stable hierarchy: ADD $>$ gapped $>$ RSII. For conservative experimental parameters, the ADD signal surpasses the nominal entanglement threshold at smaller separations, whereas the gapped benchmark is resolvable only at the lower end of the window, and RSII remains below resolution. In a more optimistic near-term scenario, all three spectral signatures comfortably exceed the threshold. We further show that normalized distance scans of the phase response clearly separate the RSII benchmark from the ADD and gapped cases, whereas ADD and the gapped continuum remain nearly indistinguishable in normalized profile. QGEM phase observables therefore provide a complementary discriminator of Kaluza-Klein spectral structure at submillimeter scales.

gr-qc↗

arXiv2026

RRAT J1541+4703: A Rotating Radio Transient Exhibiting Normal Pulsar States

Rotating Radio Transients (RRATs) are a class of pulsar-like objects characterized by intermittent radio emissions. Among them, RRATs that exhibit both RRAT and normal pulsar (NP) states may represent a key evolutionary stage from nulling pulsars to RRATs. We performed a detailed analysis of RRAT J1574+4703 using the Five-hundred-meter Aperture Spherical Radio Telescope (FAST) at a frequency of 1250 MHz. Our findings indicate that this RRAT spends approximately 98% of its time in the RRAT state, with the remainder spent in an NP state exhibiting nulling behavior. Additionally, we observed distinct integral pulse profiles and polarization properties between the two states, suggesting that they originate from different emission heights and magnetospheric structures. Furthermore, it was observed that the NP states of this RRAT exhibit mode switching, with ~44% of the time spent in the normal mode and ~39% in the abnormal mode. Notably, abnormal modes are predominantly detected at the onset and termination of the NP states. This discrepancy between the modes indicates potential instability in the magnetospheric processes that govern the NP states.

astro-ph.HE↗

arXiv2026

The annular gap model under a rotating dipole field approximation: simulating gamma-ray light curve

A more realistic description of the magnetosphere is crucial for understanding the radiation emitted by pulsars. In this paper, we revisit the annular gap model by employing a rotating dipole field, which is more realistic than the static dipole field, as an approximation of the magnetic structure of the pulsar magnetosphere. Compared with the static dipole field approximation, the open field-line region, including both the core and annular gaps, is significantly enlarged, and the two regions become asymmetric with respect to the fiducial plane. We apply this model to three young gamma-ray pulsars with distinct light-curve morphologies, PSRs J0631$+$1036 (single peak), J1709$-$4429 (double peaks), and J1048$-$5832 (three peaks). Using viewing geometries constrained by radio polarization measurements, the annular gap model within the rotating dipole field successfully reproduces the main morphological features of their gamma-ray light curves above 0.1 GeV. Our model provides a framework for interpreting pulsar high-energy emission, which can be used to analyze the emission properties of high-energy pulsars.

astro-ph.HE↗

arXiv2026

Attention-guided Evidence Grounding for Spoken Question Answering

Spoken Question Answering (Spoken QA) presents a challenging cross-modal problem: effectively aligning acoustic queries with textual knowledge while avoiding the latency and error propagation inherent in cascaded ASR-based systems. In this paper, we introduce Attention-guided Evidence Grounding (AEG), a novel end-to-end framework that leverages the internal cross-modal attention of Speech Large Language Models (SpeechLLMs) to explicitly locate and ground key evidence in the model's latent space. To address the diffuse attention distribution in pre-trained models, we propose Learning to Focus on Evidence (LFE), a supervised fine-tuning paradigm that calibrates the model's attention mechanism to distinguish query-relevant segments from irrelevant context. Experiments on SQuAD, HotpotQA, and MuSiQue demonstrate that AEG reduces hallucinations and achieves strong efficiency gains, outperforming large-scale cascaded baselines (Whisper-Large-v3 + Reranker) while reducing inference latency by approximately 62%.

cs.CL↗

arXiv2026

PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents

Long-term memory is essential for large language model (LLM) agents operating in complex environments, yet existing memory designs are either task-specific and non-transferable, or task-agnostic but less effective due to low task-relevance and context explosion from raw memory retrieval. We propose PlugMem, a task-agnostic plugin memory module that can be attached to arbitrary LLM agents without task-specific redesign. Motivated by the fact that decision-relevant information is concentrated as abstract knowledge rather than raw experience, we draw on cognitive science to structure episodic memories into a compact, extensible knowledge-centric memory graph that explicitly represents propositional and prescriptive knowledge. This representation enables efficient memory retrieval and reasoning over task-relevant knowledge, rather than verbose raw trajectories, and departs from other graph-based methods like GraphRAG by treating knowledge as the unit of memory access and organization instead of entities or text chunks. We evaluate PlugMem unchanged across three heterogeneous benchmarks (long-horizon conversational question answering, multi-hop knowledge retrieval, and web agent tasks). The results show that PlugMem consistently outperforms task-agnostic baselines and exceeds task-specific memory designs, while also achieving the highest information density under a unified information-theoretic analysis. Code and data are available at https://github.com/TIMAN-group/PlugMem.

cs.CL↗

arXiv2026

Geometric-disentangelment Unlearning

Large language models (LLMs) can internalize private or harmful content, motivating unlearning that removes a forget set while preserving retaining knowledge. However, forgetting updates often cause collateral degradation on retaining knowledge, creating a persistent trade-off. Existing LLM unlearning methods are often heuristic, and other theoretical approaches rely on offline feature constructions that do not capture update-time forget-retain interaction in LLMs. To address this limitation, we aim to develop an LLM unlearning method that reduces the forget-retain trade-off with theoretical guarantees. We take a first-principles view by formalizing "no side effects" as local retain invariance under small parameter updates, and prove an equivalence under optimizer-induced geometry: the retain loss is locally invariant if and only if the update direction is orthogonal to the subspace spanned by retain gradients. Based on the insight, we propose Geometric-disentanglement Unlearning (GU), a lightweight and theoretically grounded projection that can be plug-and-play to existing gradient-based unlearning methods to mitigate forget-retain side effects. Experiments on TOFU, MUSE, and WMDP-cyber show that GU strengthens forgetting while reducing retain drift. When added to SimNPO, it achieves up to 62\% improved forgetting Extraction Strength (ES) and 31\% higher retain ES. We open-sourced our code in https://github.com/Lemutisme/Geometric-Unlearning.

cs.LG↗