JackZebra performs long-horizon route hijacking of vision-based AVs by converting adversarial patches into online-selected steering primitives via closed-loop control from an attacker vehicle.
super hub Mixed citations
librosa/librosa: 0.6.3
Mixed citation behavior. Most common role is background (55%).
178
Pith papers citing it
Background
55% of classified citations
hub tools
citation-role summary
background 15
method 9
other 3
baseline 1
extension 1
citation-polarity summary
co-cited works
representative citing papers
Fetal-Gauge benchmark shows state-of-the-art vision-language models reach only 55% accuracy on fetal ultrasound tasks, well below clinical needs and highlighting the requirement for domain-adapted models.
Derives non-asymptotic 2-norm and infinity-norm error bounds for deterministic and stochastic variants of OPTQ and Qronos PTQ algorithms.
A new 321-patient multi-center breast FNAC WSI dataset with 7398 patch-level C1-C5 annotations is released for AI-assisted classification research.
The cubic sum rule of S(q,ω) is tested as a kinetic energy estimator using PIMC data and dielectric models for the uniform electron gas, confirming consistency with thermodynamics but exposing flaws in semi-classical approximations.
STEMGym benchmark demonstrates that perception pipelines dominate dose efficiency in autonomous STEM over navigation methods across 33 agent setups.
A parton-shower-inspired local subtraction scheme for double-real corrections in color singlet decays is introduced, with finiteness verified for the e+e- to qqbar remainder and phase-space integrals computed analytically and via sector decomposition.
ColumnKeeper provides the first mitigations for ColumnDisturb using per-subarray counters or probabilistic refresh, with low overheads at 1M and 128K thresholds.
Proves sharp threshold on mutation parameter χ for (1+1)-EA on Dynamic Binary Value and Uniform weight dynamic linear problems, yielding O(n log n) runtime below threshold and 2^Ω(n) above, plus a second stagnation-distance threshold for the former.
POPSICLE introduces benchmark datasets for cryoET segmentation and localization built from the CryoET Data Portal.
First unified benchmark finds GLR family has only 3x median slowdown over LR(1) on deterministic grammars and is the fastest among generalized parsers.
Introduces ESAS benchmark dataset using LLM-assisted event injection into acoustic scenes, showing significant performance drops in existing ASC models.
Optimal SSB frame origin for LGWA cuts sampling time by 10x and tightens chirp mass and sky position constraints for stellar-mass binaries beyond LVK performance.
Randomized experiment finds AI draft assistance raises feedback provision by teaching assistants 10.8 percentage points without harming quality.
A matched-pair protocol and Accurate Differentiation Rate metric reveal that conventional LLM accuracy on SAT problems is often inflated by over-predicting satisfiability, while cross-representation agreement exceeds 80 percent for most models.
A new greedy rebalancing algorithm for multi-constraint hypergraphs, integrated into Mt-KaHyPar, reduces geometric mean connectivity by 11.5% versus Metis while improving partition balance reliability.
Bayesian optimization identifies cement-salt hydrate composites achieving up to five times higher specific energy than prior cement-based TCES materials, with LiCl-based formulations reaching 458 kJ/kg.
FLDD learns non-Markovian marginal and posterior distributions for the forward process so a factorized reverse process can match the target better and produce higher-quality samples in fewer steps.
Human face perception aligns with neural networks trained on inverse-generative and naturalistic discriminative tasks, as these best predict human dissimilarity judgments on controversial and random face pairs.
An SMT-based active learning algorithm learns minimal nondeterministic weighted automata over arbitrary semirings, with partial correctness proofs, a sufficient termination condition, and experiments showing smaller models and fewer queries than baselines.
Rabi coupling allows a third component to join a self-bound binary quantum droplet in Bose gases, stabilized by finite detuning despite added repulsive forces.
FDA-QC combines functional data analysis of curves with quasi-conformal mappings to register and analyze both boundaries and interiors of planar biological shapes for morphing and variation studies.
Text-guided class-agnostic counting models exhibit significant weaknesses in grounding textual prompts to visual objects, as demonstrated by new negative-label and distractor tests on a multi-category dataset.
A new Java bytecode optimizer fuses map and filter into mapMulti to reduce stream overhead, sidestepping Streamliner's restrictions and delivering superior results in two of nine benchmarks while passing all 31,799 Kafka tests.
citing papers explorer
-
Harnessing Toroidal Neutral Flows to Enhance Divertor Particle Exhaust
Toroidally oriented pump inlets reduce back-flow by up to 20% (deuterium) and 33% (helium) and enhance partial pressures by factors of 1.78 and 2.00 in DSMC simulations of plasma-imprinted neutral winds.
-
A Comparison of Fusion Techniques for Multi-Modal Human Activity Recognition on the HARMES Dataset
Gated Multi-modal Fusion reaches 0.82 macro F1 on HARMES, beating the concatenation baseline of 0.76 by 6 points under leave-one-participant-out evaluation.
-
Automated Galerkin time stepping in Irksome
Automation of DG and CPG Galerkin-in-time schemes in Irksome with support for auxiliary variables, flexible quadrature, and monolithic solvers.
-
Interfacial Roughness Spectra and Finite-Depth Salt-Finger Mixing at a Two-Layer Thermohaline Interface
The horizontal spectrum of interfacial roughness controls the route to vertical exchange in finite-depth salt-finger mixing simulations.
-
AdsMind: A Physics-Grounded Multi-Agent System for Self-Correcting Discovery of Adsorption Configurations on Heterogeneous Catalyst Surfaces
AdsMind is a multi-agent LLM framework with MLFF relaxation feedback that achieves 100% and 98.8% success on AA20 and OCD-GMAE62 benchmarks using roughly 4 relaxations per case and avoids sign errors seen in open-loop baselines on DFT checks.
-
PracRepair: LLM-Empowered Automated Program Repair Inspired by Human-Like Debugging Practices
PracRepair uses LLMs for on-demand static-dynamic context construction, question-driven failure diagnosis, and iterative patch refinement via validation diagnostics and trace changes, fixing more bugs than baselines on Defects4J V1.2/V2.0 and RWB.
-
UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction
UR-BERT scales multilingual TTS encoders to 495 languages via Romanization unification and speech token prediction, outperforming baselines with better generalization.
-
A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners
Supervised fine-tuning lets LLMs linearly encode action validity and state predicates, with broader state-space coverage during training improving world-model recovery.
-
Eccentric and unbound compact binaries in the LIGO-Virgo-KAGRA catalog: parameter estimation and waveform systematics with SEOBNRv6EHM
SEOBNRv6EHM reduces parameter biases for eccentric binaries versus prior models and shows mild support for eccentricity in five catalog events plus comparable unbound fits for three high-mass events.
-
Anisotropic magnetism and Kondo-lattice behavior in the frustrated antiferromagnet Ce3MgBi5
Ce3MgBi5 is a new antiferromagnet in the Ce3MPn5 family exhibiting Kondo-lattice behavior, magnetic anisotropy, and field-induced phase transitions.
-
Whose Name Comes Up? III: Persona Prompting Effects in LLM-Based Scholar Recommendation
Audits of 43 LLMs show that varying persona prompts (language, location, role-and-task) and context affects technical quality and social representativeness of scholar recommendations, with location impacting diversity and factuality.
-
Leveraging LLMs for Grammar Adaptation: A Study on Metamodel-Grammar Co-Evolution
LLM prompting achieves 100% grammar adaptation consistency on small test DSLs and reuses adaptations across QVTo evolution steps, outperforming rule-based methods, but drops below 90% on large grammars like EAST-ADL.
-
Multi-scale flow analysis for scale-aware urban-canopy models
Identifies morphology-dependent urban heterogeneity scales (~256 m original layout, ~64 m infilled) where resolved and sub-grid flow variability become comparable and tests drag and stress parameterizations for scale-aware urban canopy models.
-
Contract Based Verification of Non-functional Requirements for Embedded Automotive C Code
The authors define general non-functional rules for C modules, propose an interface contract language, implement a Frama-C checker plugin, and demonstrate verification on two Scania truck codebases alongside ACSL functional contracts.
-
Bowtie VarQTE: A Resource-Efficient Quantum State Preparation Primitive
Bowtie VarQTE is a hybrid classical-quantum variational time evolution method that exploits causal light-cones to reduce quantum resource use for state preparation while achieving fidelities comparable to approximate quantum compilation.
-
KoRe: Compact Knowledge Representations for Large Language Models
KoRe encodes 1-hop knowledge graph subgraphs as compact discrete tokens for injection into LLMs, achieving competitive benchmark performance with up to 10x token reduction.
-
Scalable Decision-Focused Learning through Cost-Sensitive Regression
Reframing decision-focused learning as cost-sensitive multi-output regression with cost-insensitive normalization, decision-aware asymmetric penalization, and instance-based costs enables scalable training with comparable task quality but far fewer optimization solves.
-
Neuroscience-inspired Staged Representation Learning with Disentangled Coarse- and Fine-Grained Semantics for EEG Visual Decoding
A neuroscience-inspired staged framework with dual-level semantic disentanglement and semantic latent channels improves EEG visual decoding performance on the THINGS-EEG benchmark under zero-shot settings.
-
Precise Verification of Transformers through ReLU-Catalyzed Abstraction Refinement
A ReLU-catalyzed abstraction method yields tighter bounds for transformer verification by converting dot-product constraints into ReLU forms that leverage standard convex relaxations.
-
Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training
Transcoda achieves state-of-the-art zero-shot OMR with an 18.46% OMR-NED error rate on synthetic scores and 63.97% on historical Polish scans using a 59M model trained in 6 hours via synthetic data, kern normalization, and grammar decoding.
-
Real-time Surface-Code Error Correction Using an FPGA-based Neural-Network Decoder
An FPGA-based neural-network decoder achieves 550 ns deterministic closed-loop latency for real-time distance-3 surface code error correction on a superconducting processor, matching offline decoding performance.
-
AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development
More capable LLMs and agents generate code with greater volume and architectural decay, following a Volume-Quality Inverse Law that neither functional correctness nor prompting mitigates.
-
Accelerating unrest at Campi Flegrei signals a critical transition within the next decade
Accelerating unrest at Campi Flegrei fits a regularised finite-time singularity better than exponential growth, converging on a critical time of 2030-2034.
-
A Complex-Valued Continuous-Variable Quantum Approximation Optimization Algorithm (CCV-QAOA)
CCV-QAOA is a new complex-valued continuous-variable variant of QAOA that solves real and complex multivariate optimization problems via a variational framework.
-
Visualising CTL Witnesses and Counterexamples -- Extended Version
A formal model of minimal evidence for each CTL operator is defined and paired with an implemented visualization scheme for witnesses and counterexamples.
-
From Natural Language to Executable Narsese: A Neuro-Symbolic Benchmark and Pipeline for Reasoning with NARS
A new benchmark and deterministic pipeline translate natural language reasoning into executable Narsese for NARS, with execution-based validation and initial LLM adaptation for three-label classification.
-
From Admission to Invariants: Measuring Deviation in Delegated Agent Systems
The Non-Identifiability Theorem shows admissible behavior space A0 is not identifiable from local enforcement signals g under the Local Observability Assumption, so the paper introduces an Invariant Measurement Layer to detect admission-time drift.
-
A Fast and Physically Grounded Ocean Model for GCMs: The Dynamical Slab Ocean Model of the Generic-PCM (rev. 3423)
A new dynamical slab ocean model incorporates Ekman transport via Sverdrup balance and Gent-McWilliams eddies to produce first-order matching ocean heat transport and improved Earth climate metrics at nearly zero extra cost.
-
Simple Types for Polymorphic Functions
A simple type system for combinatory logic gives combinators one type each, with polymorphism revealed by application, supporting more polymorphism than Hindley-Milner without quantified types and including type inference.
-
From Exact Space-Time Symmetry Conservation to Automatic Mesh Refinement in Discrete Initial Boundary Value Problems
Treating coordinate maps as dynamical variables in action-based IBVP discretizations yields exact Noether charge conservation and automatic mesh refinement even at high order when SBP operators are used.
-
CIR: Lightweight Container Image for Cross-Platform Deployment
CIR is a cross-platform container image format for Python/R-style apps that defers dependency assembly to deployment, cutting image size by 95% and deployment time by 40-60% versus traditional bundled images.
-
Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures
Watt Counts supplies over 5,000 energy measurements across 50 LLMs and 10 GPUs and shows that hardware-aware selection can reduce server-scenario energy use by up to 70 percent with little effect on user experience.
-
Spatiotemporally Resolved Multi-Scalar Measurements of Methane Tulip Flames in a Square Channel
Multi-plane dual-color PLIF yields spatiotemporally resolved 3D temperature and OH fields in methane tulip flames, revealing super-equilibrium OH in thermal boundary layers and near-constant pressure from wall heat loss.
-
Robust Nonlinear System Identification in Reproducing Kernel Hilbert Spaces via Scenario Optimization
Finite-dimensional RKHS approximation via n-widths enables scenario optimization to deliver violation guarantees on nonlinear one-step predictors without a priori bounds on the true RKHS norm or Lipschitz constant.
-
A Faceted Classification of Authenticator-Centric Authentication Techniques
The authors developed new faceted classification schemes for authentication techniques and authenticators and applied them to create a catalog from reviewed literature.
-
Structural Sensitivity in Compressed Transformers: Relative Error Propagation and Layer Removal
Per-layer error amplification factor rho predicts representation drift in compressed transformers and guides superior pruning and layer-removal decisions compared to prior heuristics.
-
Configuring Agentic AI Coding Tools: An Exploratory Study
Developers overwhelmingly rely on simple static context files such as AGENTS.md to configure agentic AI coding tools, while advanced mechanisms like skills and subagents see very low adoption.
-
RAG-GNN: Integrating Retrieved Knowledge with Graph Neural Networks for Precision Medicine
RAG-GNN augments GNNs with retrieved literature knowledge via gated fusion to improve functional clustering of 379 proteins in cancer signaling networks, raising silhouette score by 0.093.
-
Compact Hypercube Embeddings for Fast Text-based Wildlife Observation Retrieval
Compact binary hypercube embeddings enable efficient text-to-image and text-to-audio retrieval in wildlife databases with performance competitive to continuous embeddings but far lower memory and search costs.
-
Challenges in Android Data Disclosure: An Empirical Study
Survey and forum analysis of 683 Android developers finds they manually classify app data for Google's Data Safety Section or skip it, feel confident spotting collected data but not in translating it to the form, and worry about rejection.
-
Generating Verifiable Chain of Thoughts from Exection-Traces
A pipeline produces 54,000 execution-trace-verified bi-directional Chain-of-Thought rationales for code, and fine-tuning on them yields gains up to 26.6 points on LiveCodeBench-Exec and similar benchmarks.
-
Mapping Microstructure: Manifold Construction for Accelerated Materials Exploration
Distribution-based microstructure descriptors recover a two-dimensional latent manifold aligned with processing parameters in spinodal decomposition simulations, enabling invertible mappings.
-
The Fast and the Frame-Dragging: Efficient waveforms for asymmetric-mass eccentric equatorial inspirals into rapidly-spinning black holes
Extends FEW to produce adiabatic waveforms for eccentric equatorial inspirals into spinning black holes (|a|≤0.999) in ~100 ms with ~10^{-5} mismatches to reference waveforms.
-
VerteNet -- A Multi-Context Hybrid CNN Transformer for Accurate Vertebral Landmark Localization in Lateral Spine DXA Images
A dual-resolution self- and cross-attention hybrid model localizes T12-L5 vertebral landmarks in multi-scanner DXA images with normalized mean error 4.92 pixels and median 2.35 pixels, outperforming baselines.
-
CodeT5+: Open Code Large Language Models for Code Understanding and Generation
CodeT5+ is a flexible encoder-decoder LLM family for code pretrained with diverse objectives on multilingual corpora and initialized from existing LLMs, achieving state-of-the-art results on code generation, completion, math programming, and retrieval tasks including new SoTA on HumanEval with the 1
-
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
BLOOM is a 176B-parameter open-access multilingual language model trained on the ROOTS corpus that achieves competitive performance on benchmarks, with improved results after multitask prompted finetuning.
-
Evolving finite elements for advection diffusion with an evolving interface
Develops an evolving finite element method for parabolic PDEs with evolving interfaces, derives a suitable weak formulation, proves optimal error bounds for isoparametric elements of arbitrary order, and verifies convergence numerically.
-
The population of merging compact binaries inferred using gravitational waves through GWTC-3
GWTC-3 yields BNS merger rates of 10-1700 Gpc^{-3} yr^{-1}, NS-BH rates of 7.8-140, BBH rates of 17.9-44 at z=0.2 with (1+z)^{2.9} evolution, plus mass distributions showing peaks at chirp masses 8.3 and 27.9 solar masses and a sharp drop after the neutron-star maximum mass.
-
A closed-loop all-electronic pixel-wise adaptive imaging system for high dynamic range video
A closed-loop pixel-wise adaptive exposure CMOS system for HDR video implemented with all-electronic control.
-
Self Multi-Head Attention for Speaker Recognition
Self multi-head attention applied after CNN encoding of spectrograms outperforms temporal and statistical pooling for speaker verification on VoxCeleb1 with 18% relative EER reduction.