arXiv subjects

Hao Li

Publications and source records attributed to Hao Li.

At least 73 records · Page 4Linked to original sources

arXiv2026

Generation of TeV Photons by PeV Neutrinos in Dense Astrophysical Environments

Recent observations by IceCube and KM3Net of PeV-scale ultra-high-energy (UHE) neutrinos, together with detections of TeV-PeV photons from various sources such as the Crab Nebula, the Galactic Center, and gamma-ray burst by ground-based observatories including Tibet AS$γ$, MAGIC, Carpet-3, and LHAASO, point to the existence of extreme astrophysical environments capable of accelerating particles to ultra-high energies. These findings motivate investigations of possible connections between UHE neutrinos and photons in such environments. Theoretically, dense regions surrounding compact objects can efficiently produce UHE neutrinos. In this work, we calculate the production of UHE photons from neutrino-nucleon interactions, and note that if these interactions occur in the outer, optically thin regions of dense environments, the resulting photons could potentially be observed. In our model, an incident neutrino scatters off a nucleon, generating secondary partons that hadronize into pions and subsequently decay into UHE photons. We calculate the resulting photon energy spectra and find that for incident (anti)neutrinos with energies above 1 PeV, the probability of producing photons with energies exceeding 1 TeV is greater than 13%. As a concrete application, we show that this mechanism can quantitatively account for the preburst TeV photons observed in GRB 221009A, providing a natural explanation for both their energies and lead times. These findings establish a plausible mechanism linking UHE neutrino events to gamma-ray observations, providing new insights into hadronic processes in extreme astrophysical environments and supporting multi-messenger astronomy studies.

astro-ph.HE↗

arXiv2026

EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies

We present EBench, a simulation benchmark that diagnoses generalist mobile manipulation policies beyond a single success-rate scalar. EBench comprises 26 diverse and challenging manipulation tasks annotated along 5 capability dimensions and 4 generalization dimensions. We evaluate state-of-the-art generalist manipulation models including $π_0$, $π_{0.5}$, XVLA, and InternVLA-A1, and reveal that the models exhibit strikingly different capability profiles: $π_{0.5}$ achieves the highest test success rate, the best train--test retention, and the strongest mobile manipulation performance; $π_0$ leads on dexterous fixed-base and high-precision tasks; XVLA and InternVLA-A1 exhibit complementary strengths across atomic skills and operating regimes. Beyond capability profiling, EBench analyzes the generalization ability from 4 representative perspectives, identifying the impact of different distribution shift factors. The results reveal strengths and weaknesses of models behind an overall score. We hope this benchmark offers a broad set of diagnostic signals to guide iteration on generalist manipulation models.

cs.RO↗

arXiv2026

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing complete blocks perturbs the embeddings consumed by the decoder and can cause deletion and premature end-of-sequence errors. We introduce X-AuT, a progressive framework that selects layer combinations through short behavioral probes and restores the pruned model through representation alignment, cross-scale distillation, scheduled student-policy supervision, and LoRA finetuning. The language-model backbone remains frozen, while attention LoRA adapters and the tied output embedding adapt during distillation. Training uses the highest-agreement tier from a transcript-consistency pipeline, followed by source reweighting during finetuning. On ten public Chinese--English benchmarks, compressing Qwen3-ASR-0.6B from 18 to 16 audio-encoder layers reduces macro-average error from 5.61% to 5.27%. The 14-layer model reaches 5.75% with 20.7% fewer audio-tower parameters. Under the matched recipe, the 1.7B teacher yields 5.55% mean error, compared with 8.45% for self-distillation, and progressive 18$\rightarrow$14 pruning outperforms direct pruning (5.75% vs. 6.73%). These single-run results establish two practical operating points and show that the accuracy effects vary across benchmarks. Project website: https://xpeng-ai.github.io/x-aut

cs.SD↗

arXiv2026

Stabilizing Instruction Supervision for Instruct-TTS via Controllable Diversification and Drift Filtering

Instruct-TTS systems expand structured style labels into natural-language training instructions through LLM rewriting, yet we find that over 40% of unconstrained rewrites contain semantic drift that corrupts supervision and weakens generalization. We formalize this problem as instruction supervision instability and propose a data-centric stabilization recipe that jointly improves coverage and fidelity through three mechanisms: controllable instruction diversification for systematic expansion, LLM-based drift filtering for quality control, and attribute-aligned supervision that grounds prosody control in acoustic perturbations. On the Chinese split of InstructTTSEval, our recipe raises instruction-following from 34.5% without fine-tuning and 51.0% with naive fine-tuning to 56.4%, while constrained rewriting reduces drift from 40.4% to 15.4%. Ablations confirm the three mechanisms are complementary, and the drift taxonomy may generalize to instruction-driven generation beyond TTS.

cs.SD↗

arXiv2026

TacClip: a clip-on sensor measures dynamic contact forces without covering the fingerpads

TacClip is a minimally encumbering wearable device for recording fingertip deformation caused by contact forces and vibrations. It can be combined with vision- or glove-based hand tracking systems that leave the fingertips uncovered and provides a measure of dynamic contact interactions, while leaving the finger pads exposed so that the user retains natural sensitivity to texture, friction, temperature, and fine surface features. The signal is produced by a Fiber Bragg Grating (FBG) embedded on a small plastic clip mounted over the fingernail. Optionally, for use with vision-based tracking, additional FBGs on polyimide strips can complement camera-based pose estimation. In finger pressing tests, TacClip estimates the force magnitude with typical errors below $0.5~\mathrm{N}$ over a $0$--$8~\mathrm{N}$ range. In tests of cloth handling and tape edge finding, we show that it captures the vibrations and dynamic events generated during exploratory sliding. With no electronics, TacClip can also be used submerged in water, while preserving bare finger contact.

cs.RO↗

arXiv2026

Edge-Dominated Twist Mechanics at van der Waals Interfaces

Despite the pivotal role of twist in modulating physical properties at van der Waals (vdW) interfaces, the mechanics governing torsional response remain poorly understood. Here, we probe twist mechanics at homo- and heterogeneous vdW interfaces, together with their sliding behaviors within a unified experimental framework. For both systems, the peak torque scales nearly linearly with contact area, in contrast to predictions from linear elastic and rigid models. Remarkably, while the sliding friction of the two interfaces diverges by over three orders of magnitude owing to different scaling laws, the corresponding torque follows the same linear scaling and differs by only about twenty-fold. Large-scale atomistic simulations reveal an edge-dominated yielding mechanism for torsional motion, wherein elastic reconstruction shifts the effective load-bearing region toward the edges, eliminating torque from the contact interior. This mechanism contrasts with the bulk-mediated stress transmission governing translational sliding, a distinction rooted in the different loading geometries inherent to the two motion modes, where torsional loading necessitates perimeter actuation, whereas sliding enables center-driven loading. This symmetry-imposed divergence demonstrates that translational and torsional properties cannot be predicted from one another at vdW interfaces, providing critical insights for the design of dynamically reconfigurable micro- and nanoelectromechanical devices.

cond-mat.mtrl-sci↗

arXiv2026

Collective Excitonic Structure Governs Anomalously Weak Thermal Optical Dephasing in Conjugated Polymers

Conjugated polymer aggregates exhibit optical decoherence in the presence of strong vibronic coupling and substantial diversity in chemical structure, solid-state organization, and excitonic character. Here, we use coherence-detected and population-detected two-dimensional electronic spectroscopies to examine the temperature dependence of the homogeneous optical linewidth across a series of semiconducting polymers. Despite substantial differences in molecular architecture and solid-state organization, all polymers studied exhibit remarkably weak thermal linewidth scaling over the measured temperature range. Comparison between complementary detection modalities further shows that, while this weak temperature dependence is obust, the absolute homogeneous linewidth depends on the measured observable. This behavior reflects the different ways in which coherence- and population-detected measurements project population relaxation and pure dephasing onto the spectroscopic response. These results establish the weak thermal scaling of optical decoherence across a diverse series of conjugated polymers and show that its experimental manifestation must be interpreted in the context of the detection observable.

cond-mat.mtrl-sci↗

arXiv2026

Geometry Conditioning in an Embodied SLM: Training Controls and Robustness Diagnostics in a 0.8B Hybrid Model

We study how physical-state inputs affect a 0.8B hybrid language model adapted for manipulation with 6.2M trainable parameters. Six conditions are trained on three LIBERO-Spatial tasks and evaluated over three seeds and 540 held-out rollouts. Conditioning recurrent decay gates on geometric increments yields 28.9% success, compared with 36.7% when those increments are shuffled during training and 24.4% without explicit object/goal geometry. Both geometry policies receive correct inputs at evaluation. A token adapter using the same increments scores 27.8%; differences vary across seeds and remain inconclusive. Token-clock conditioning scores 11.1%, including one seed that fails to converge. In separate robustness tests, a state-only relative-coordinate policy retains 7/10 success under frame relabeling, whereas all four tested visual policies fall to at most 3/20 after a 5 cm object displacement. These results show no reliable advantage from training-time geometric alignment under this recipe and illustrate the gap between coordinate invariance and physical-layout generalization. Episode records, seed-level analyses, and figure-generation code accompany the paper.

cs.RO↗

arXiv2026

Detection Defines Dephasing in Two-Dimensional Electronic Spectroscopy of Materials: Coherent Field Emission versus Incoherent Population Observables

The homogeneous spectral linewidth associated with light-matter interactions is a fundamental descriptor of the optical properties of materials, governed by the quantum dynamics of the condensed-matter system. We discuss here that the homogeneous linewidth measured by means of two-dimensional electronic spectroscopy depends not only on the intrinsic microscopic dynamics of the material, but also on the observable through which those dynamics are projected onto the measurement. In this Perspective, we develop a unified framework showing that identical microscopic dynamics can yield different experimentally inferred dephasing times because different detection operators project different sectors of the nonequilibrium dynamics. For coherent emitted-field measurements, the observed linewidth largely retains its conventional connection to the optical coherence time $T_2$. By contrast, in population-detected modalities such as photoluminescence, photocurrent, and other action-detected two-dimensional spectroscopies, the apparent linewidth can additionally encode excited-state population redistribution dynamics, leading naturally to an effective coherence time $T_{2,\mathrm{eff}}$. Using a coupled-mode model propagated under a common Liouvillian, we show that identical microscopic dynamics yield distinct apparent dephasing times when projected onto coherent-emission and population-derived observables. The detection observable is therefore not merely part of the experimental implementation, but determines what dynamical information remains experimentally observable and how homogeneous linewidths should be interpreted as materials descriptors.

physics.chem-ph↗

arXiv2026

Twin-photon generation in a silicon nitride microresonator

Photonic chips with silicon nitride ($\mathrm{Si_3N_4}$) microring resonators are well established as heralded single-photon sources, but their operation as frequency-degenerate twin-photon sources has not previously been demonstrated. Here, we realise a twin-photon source at telecommunication wavelengths in a $\mathrm{Si_3N_4}$ ring microresonator via an inverse four-wave mixing (FWM) process, in which two photons from spectrally distinct pumps are converted into a pair of identical twin photons. The measurements show a maximum coincidence-to-accidental ratio (CAR) of $5.4\pm0.6$. In addition, the microresonator functions as a heralded single-photon source through pump-degenerate spontaneous four-wave mixing (SFWM), exhibiting a spectral purity of $P=0.67\pm0.05$ and a heralded anti-bunching of $g^{(2)}_h(0)=0.0042\pm0.0015$. Together, these results demonstrate both photon-generation schemes on a single integrated $\mathrm{Si_3N_4}$ platform, highlighting its potential for scalable, tailored quantum light generation.

physics.optics↗

arXiv2026

SchedBlame: Who Ran While You Waited? Culprit-Attributed CPU Contention for Containers on Stock Kernels

Containers that share a machine compete for CPU. When one slows down, the operator needs to know which co-tenant is responsible, and no deployed signal can say. Pressure stall information, per-cgroup wait counters, and run-queue latency histograms are all victim-side: they report that a container waited, never who it waited for. Recovering the culprit means a kernel patch, full scheduler tracing, or statistical inference: unportable, too costly to leave on, or unreliable when victims coexist. SchedBlame is an eBPF tracer that attributes CPU contention to the cgroups that caused it, on stock kernels, continuously. It inverts the accounting: instead of measuring how long a victim waited, it measures the CPU time every other cgroup consumed while that victim was runnable but not running on the same CPU. The mechanism is a per-CPU bitmap of which measured cgroups are waiting, maintained from the kernel's own runnable counts at four scheduler hooks. Every run slice carries that bitmap, so one 16-byte record charges CPU time to a full row of a competitor x victim blame matrix; the kernel stores no per-pair state. Three properties follow. Slices are self-describing, so userspace holds no waiting state and a lost record costs measurements, not correctness. The measured set is reconfigured by publishing an epoch, invalidating every cache and per-CPU bitmap in constant time while the hooks keep running. Sampling never touches waiting state, so rescaling by the inverse keep probability keeps the estimator unbiased. SchedBlame splits each container's per-second CPU demand into runtime, internal contention, external contention, and throttling, flags anomalies against a rolling 99th-percentile baseline, and names the competitors responsible. In production on unmodified 4.18 and 5.10 kernels, tracking 84 containers on a 96-core host, it costs about 1% of Redis throughput and 6% of one core.

cs.OS↗

arXiv2026

Observation of Hong-Ou-Mandel interference between photon and polariton

Light-matter interactions underlie many quantum technologies, yet whether quasiparticles formed from such interactions preserve the full quantum state of light remains unresolved. Surface plasmon polaritons (SPPs), a class of polaritons formed by interacting photons with free-electron oscillations at metal-dielectric interfaces, are prime candidates to explore this question. Here we demonstrate quantum interference between single photons and SPPs using an Au-SiN$_{\mathrm{x}}$ integrated photonic-plasmonic device. Our results reveal that SPPs retain the indistinguishability of their excitation photons, establishing SPP as a viable quantum information carrier and opening a potential route toward photonic-plasmonic quantum circuitry.

quant-ph↗

arXiv2026

Homological Description of Equivariant Geometric Bordism

Using the evenness criterion in \cite{LCLS} and duality principle in \cite{CLT}, we construct a finite chain complex $\mathfrak{B}_{\bullet}((\mathbb{Z}_2)^k)$ built from the universal complex $X((\mathbb{Z}_2)^k)$ and its links. We then show that the equivariant unoriented bordism group $\mathcal{Z}_{k+1}((\mathbb{Z}_2)^k)$ of all $(k+1)$-dimensional smooth closed connected manifolds with effective $(\mathbb{Z}_2)^k$-actions fixing isolated points, is naturally isomorphic to $H_{k-2}(\mathfrak{B}_{\bullet}((\mathbb{Z}_2)^k);\mathbb{Z}_2)$. The vertical spectral sequence associated with the natural double-complex structure on $\mathfrak{B}_\bullet((\mathbb{Z}_2)^k)$ collapses at $E^3$, yielding an explicit formula for $\dim_{\mathbb{Z}_2}\mathcal{Z}_{k+1}((\mathbb{Z}_2)^k)$ for every $k$.

math.AT↗

arXiv2026

TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models

Large Reasoning Models (LRMs) introduce a reasoning-level attack surface: adversaries can corrupt intermediate inferences while preserving a plausible trace and an apparently benign output. Existing output guardrails cannot reliably identify where such a trace first becomes unsupported. We present TraceGuard, a compact, locally deployable reasoning firewall that treats model-generated reasoning as untrusted input. Its design combines grounded generation of verifiable audit traces, Step-Aware Supervised Fine-Tuning (SSFT) for process-level supervision, and Verifier-Guided Reinforcement Learning (VGRL) for hardening against difficult reasoning traces. TraceGuard audits intermediate steps, localizes the initial Point of Fracture, and grounds its final decision in the complete audit evidence. We evaluate TraceGuard across heterogeneous open-weight architectures, reasoning domains, and reasoning-integrity attack families. A compact Qwen3-4B-Guard substantially outperforms an unaligned 20B model under strict end-to-end detection. Its auditing behavior transfers to attack families excluded from training, resists in-scope black-box probing, and remains robust in an additional white-box stress test. Overall, 210,456 step-level audit decisions support compact, process-aligned verification as an effective, deployable defense boundary for reasoning systems.

cs.CR↗

arXiv2026

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

A benchmark should deliver more than a scalar score: what makes an evaluation trustworthy is the reasoning that justifies the score. This is especially critical for world models, where judging a rollout requires understanding whether physics, causality, and world state evolve correctly. Humans spot such violations naturally, yet no existing benchmark automates this capability: metrics are computed brute-force, leaving no reasoning chain that can be examined or verified. We introduce HarnessEval-W, an agentified evaluation pipeline that brings the harness paradigm from the LLM ecosystem to world model benchmarking. Rather than applying a fixed rubric, HarnessEval-W interprets the context of each evaluation case, decomposes the evaluation question into measurable subproblems, and spawns specialized sub-agents, each equipped with tailored context and diagnostic tools to reason over its own subproblem. The parent agent then validates the gathered evidence and summarizes it into the final verdict. This hierarchical workflow turns every evaluation into a transparent evidence tree whose complete reasoning chain justifies the result. We apply HarnessEval-W to 18 representative world models over 330 evaluation cases. Its judgments closely align with human preferences while providing verifiable, fine-grained diagnoses of every generated rollout. We open-source the full pipeline as a live benchmark and invite the broad community to contribute to grow new skills and evaluation cases as world models evolve.

cs.CV↗

arXiv2026

ACE-Ego-Hand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery

Egocentric video offers scalable manipulation data for embodied AI, yet recovering metric 3D hand trajectories remains challenging due to severe object occlusion and frequent out-of-sight gaps. Existing single-frame and windowed temporal regressors fail when a hand shortly leaves the frame, while recent video diffusion models (VDMs) rely on heavy, stochastic multi-step sampling as pixel-space renderers. We instead repurpose VDM into a deterministic geometry encoder. A single forward pass over the clean latent exposes scene content beyond current observations, including occluded and out-of-sight hands. We introduce ACE-Ego-Hand, an offline clip-level framework that extracts features via a Deterministic Clean-Latent Encoder and decodes them with a Bidirectional Spatiotemporal Decoder. ACE-Ego-Hand recovers continuous bimanual trajectories with metric placement and no external detector, while a Ray-Based Camera Solver supports a second configuration that requires no test-time camera intrinsics. Across five egocentric benchmarks, ACE-Ego-Hand sets a new state of the art, cutting MPJPE-p by 30% on occlusion-heavy ARCTIC and 40% on HOT3D. These gains reach 46%-61% once out-of-sight hands are included in the evaluation, offering a scalable path from everyday human video to robot manipulation data.

cs.CV↗

arXiv2026

Converse and Collision-Based Achievability for Node Localization with Hybrid Distance-Spectral Graph Positional Encodings

Graph positional encodings are widely used in graph neural networks and graph Transformers, yet it remains unclear when the code itself can identify nodes. We study a hybrid distance-spectral encoding that combines anchor-distance profiles with quantized low-frequency Laplacian-energy coordinates. Treating the encoding as an observation map yields a simplex-refined converse, an exact collision factorization $κ_H=κ_Dκ_{S|D}$, and the collision information $I_H=-\logκ_D-\logκ_{S|D}$. On random regular graphs, the criterion is made explicit through a bounded-correlation Gaussian-wave surrogate; for actual Laplacian-energy coordinates, we give the distance-conditioned spectral collision condition sufficient for conditional actual-coordinate achievability. Experiments show that $I_H/\log n$ calibrates localization success, and PE-only structural task probes on Universal Dependencies trees show that hybrid encodings better recover syntactic-tree geometry than distance-only or spectral-only baselines.

cs.LG↗

arXiv2026

Quantum-interference metrology of dissipative Kerr solitons

Dissipative Kerr solitons in optical microresonators underpin chip-scale frequency combs with applications ranging from coherent telecommunications to precision spectroscopy. Yet the characterization of their intrinsic femtosecond temporal structure remains challenging, as the low pulse energy and broad spectral bandwidth necessitate optical amplification and careful dispersion compensation in conventional ultrafast diagnostics, both of which can significantly distort the waveform. Here we demonstrate a quantum-interference metrology of microcomb solitons based on Hong-Ou-Mandel interference. By attenuating the soliton stream to the single-photon level and measuring fourth-order interference, we directly retrieve near transform-limited pulse durations without amplification or dispersion management, remaining accurate even after propagation through 25 km of standard fiber. The same interferogram also provides direct access to the temporal separations in multi-soliton states by converting inter-soliton separations into additional interference dips at corresponding delays, enabling sub-picosecond characterization of their intracavity temporal structure. This quantum-inspired paradigm introduces a fundamentally new metrological approach that is immune to amplification and dispersion distortions, offering a powerful tool for the characterization of complex soliton physics.

quant-ph↗