archive
Every paper Pith has read. Search by title, abstract, or pith.
85880 papers indexed · page 112
-
Markov Chain Decoders Fix Heavy-Tail Limits in VAEs
Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models
-
Almost every forbidden-blowup graph splits into r restricted parts
The typical structure of oriented graphs and digraphs with forbidden blow-up of transitive tournaments
-
Closed-form policy optimizes allocation in censored survival trials
Adaptive Experimentation for Censored Survival Outcomes
-
Edge perception fuses sensing and AI for 6G networks
Sense Smarter, Think Better: Edge Perception for Next-Generation Networks
-
Spacers tune singlet fission rates in aza-BODIPY dimers over orders of magnitude
Design Principles for Singlet Fission in Aza-BODIPY Dimers: Spacer-Controlled Electronic Structure and Energy Ordering
-
Sensors discover home activities using 90 percent less video
OrganicHAR: Towards Activity Discovery in Organic Settings for Privacy Preserving Sensors Using Efficient Video Analysis
-
Readable programs match deep RL on job scheduling benchmarks
Scheduling That Speaks: An Interpretable Programmatic Reinforcement Learning Framework
-
Localized singlets generate frustration that collapses Néel order in cuprates
Frustration from Localized Zhang-Rice States: A Unified Theory of Doping-Driven Magnetic Transitions in Cuprates
-
Phase squeezing gives 4.28 dB SNR boost to ion electric-field detection
Enhanced detection of electric field signals via squeezing-induced stochastic resonance
-
Agent turns top-down room images into executable Blender code
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis
-
Closed languages model unifies Kleene algebras with hypotheses
Continuous Algebras with Hypotheses
-
RL trajectories match real customer paths better than TSP or PNN
Modelling Customer Trajectories with Reinforcement Learning for Practical Retail Insights
-
Overestimating factors by a fixed amount keeps PCA consistent
Fixed-order PCA: Theory for Overestimated Factor Models
-
Per-image tweaks let NeRF reconstruct spacecraft despite lighting shifts and pose errors
NeRF-based Spacecraft Reconstruction from Monocular Imagery Under Illumination Variability and Pose Uncertainty
-
NeRF extensions fix illumination and pose issues for spacecraft models
NeRF-based Spacecraft Reconstruction from Monocular Imagery Under Illumination Variability and Pose Uncertainty
-
Representations of conformal nets are balanced by rotation action
The balanced structure on the category of representations of a conformal net
-
Accuracy unchanged when latent visual tokens replaced by dummies
What's Holding Back Latent Visual Reasoning?
-
Input flips extend multiplier life under NBTI aging
Building Reliable Arithmetic Multipliers Under NBTI Aging and Process Variations
-
Hybrid model forecasts single EV charging profiles
Electric Vehicle Charging Profile Forecasting Using Hybrid Models
-
Geometry conditioning adapts speaker extraction to any mic array
Flexible Multi-Channel Target Speaker Extraction Using Geometry-Conditioned Spatially Selective Non-linear Filters
-
REACT lets robot groups adapt formations while moving through clutter
REACT: Environment-Adaptive Architecture for Continuous Formation Navigation of Wheeled Mobile Robots
-
Spherical trigonometry gives Wigner's angle for any photon Lorentz boost
Geometrical derivation of Wigner's angle for arbitrary Lorentz transformations of massless particles
-
Diagnostic maps local turning axis in 3D recirculating flows
Mapping the Turn: An Eulerian Binormal-Axis Diagnostic for Recirculating 3D Flows
-
Orion BN/KL outflow matches 30-40 km/s dissociative shock models
Velocity-resolved [O I] 63,145 um, [C II] 158 um, and OH mapping along the Orion BN/KL explosive outflow and irradiated shocks
-
Clean experiences poison reflective LLM agents
OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences
-
Federated meta-RL speeds vehicular task offloading
Heterogeneous Tasks Offloading in Vehicular Edge Computing: A Federated Meta Deep Reinforcement Learning Approach
-
1,309-page dataset targets handwritten music recognition
A Dataset for the Recognition of Historical and Handwritten Music Scores in Western Notation
-
Alternative lattice reaches 10^35 luminosity for STCF collider
Alternative Lattice Design for the STCF Collider Rings
-
Text guidance focuses full images for cropped-query e-commerce search
TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval
-
Strong ergodicity transfers across coamenable relation inclusions
Coamenability and strong ergodicity
-
Set-membership rule trims cost of augmented affine projection
Augmented Set-membership Affine Projection Algorithm and Its Performance Analysis
-
Multi-robot MLLM lifts spatial reasoning accuracy by 7 percent
Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models
-
Benchmark shows LLMs falter on complex CAD topologies
Text2CAD-Bench: A Benchmark for LLM-based Text-to-Parametric CAD Generation
-
Altermagnetic splitting selects triplet pairing for locked Majorana edges
Direction-selective triplet pairing and spin-edge locking in altermagnetic metals
-
Third-gen detectors measure sub-solar spins to 0.001 precision
Probing (sub-)solar-mass black holes and superspinars with current and next-generation gravitational-wave observatories
-
Absorption modeling sets X1908+075 inclination at 46 degrees
Iron line diagnostics of the stellar wind in X1908+075
-
Galois conditions make Hilbert modular characters classical
Classicality for Hilbert modular forms
-
Infinite-dimensional GAN learns invariant distribution from single deterministic orbit
Generative Adversarial Learning from Deterministic Processes
-
Dual self-distillation balances privacy and utility in LLMs
It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
-
TDiff scalar fields yield cosmological perturbation equations
Cosmological perturbations of TDiff fields
-
Benchmark scores autonomous systems on ethical readiness
REBAR: Reference Ethical Benchmark for Autonomy Readiness
-
Riesz basis yields closed-form ANOVA for dependent inputs
Generalized Functional ANOVA in Closed-Form: A Unified View of Additive Explanations
-
No memory method works consistently for LLM agents
EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
-
Encapsulation graphs unify nestedness in higher-order networks
The nestedness of higher-order networks
-
Geometry-aware coresets lift VLM accuracy in pathology without training
Geometry-Aware Uncertainty Coresets for Robust Visual In-Context Learning in Histopathology
-
Epitaxial EuPdSi3 films show magnetic transitions at 19 K and 15 K
Epitaxial growth and magnetic phase transitions in non-centrosymmetric EuPdSi$_3$ thin films
-
The paper proposes the RTGA-IDROC algorithm
A Fast Robust Adaptive filter using Improved Data-Reuse Method
-
10-qubit quantum graph network matches classical boosted-jet tagging
Quantum enhanced identification of boosted jets with quantum graph neural networks
-
RNS comparison works over full range with one mixed-radix step
Residue Number System Comparison revisited, a software perspective
-
Architectural proxy stops unauthorized LLM tool use
Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control