archive
Every paper Pith has read. Search by title, abstract, or pith.
85880 papers indexed · page 118
-
Partner selection shifts opponents to favor cooperation under policy gradients
The Dynamics of Policy Gradient in Social Dilemmas with Partner Selection
-
External cameras boost robot scene recall by up to 79%
Fixed External Cameras as Common Prior Maps for Active 3D Scene Graph Generation
-
Fire-damaged batteries fragment into metal-rich fines
Characterisation of fire-damaged batteries,implications for recycling
-
Lensing time delays get no extra Lambda terms beyond standard distances
Gravitational lensing time delay beyond the Shapiro/geometry split
-
Varying environment rules builds agents that generalize
Scalable Environments Drive Generalizable Agents
-
Ridge regularization distorts feature-learning networks at vanishing strength
Canonical Regularisation of Wide Feature-Learning Neural Networks
4 Piths -
Semisimple algebras have one or uncountably many uniform norms
On Multiplicity of Uniform Norms and Maximal Spectral Substructures in Commutative Banach Algebras
-
Optical neural networks must prove value in real conditions
The thin line for optical neural networks towards broad practical relevance
-
TokenMask predicts masks directly from token affinities
Token-Space Mask Prediction for Efficient Vision Transformer Segmentation
-
Agentic selector ranks second on four-day multimodal challenge
MARS: Technical Report for the CASTLE Challenge at EgoVis 2026
-
Model spots sonata form boundaries automatically in Mozart
Sonalyzer-Moz: A Framework for Analyzing the Structure of Mozart's Sonata Form
-
Ringmaster LMO recovers optimal async time complexity for LMO
Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method
1 Piths -
Soft attention masks enable text spotting without rectification
Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting
-
Proxy images from EEG let AI models interpret brain signals
Visualizing the Invisible: Generative Visual Grounding Empowers Universal EEG Understanding in MLLMs
-
Counting algorithm stabilizes in O(f+1) rounds after actual faults
Early-Stabilizing Counting
-
Buffer parameters let ML predict signal integrity across IC technologies
Buffer-Parameterized Machine Learning Surrogate Models for Cross-Technology Signal Integrity Analysis and Optimization
-
4-input relative-phase Toffoli cuts T-depth for large gates
Adaptive Clifford+T Decomposition of Large Toffoli Gates with One Clean Ancilla
-
Benign audio clips jailbreak large audio language models universally
Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
-
Copula models improve diagnostic test meta-analysis
1-truncated C-vine copula mixed models for network meta-analysis of multiple diagnostic tests
-
Repository supplies hypergraph datasets for group interaction studies
Hypergraphx-data: a repository for higher-order network data
-
MASK token compression accelerates diffusion LLMs
Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs
-
Pattern counts bound entropy of symmetric subshifts
Explicit entropy bounds for symmetric nearest-neighbor subshifts
-
One universal fix reduces hallucinations in 15 models
TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction
-
Consistency reward lifts VLM spatial reasoning
Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
-
Red quasars trace a phase of suppressed black hole growth
SDSS-V: Revealing a weak accretion state in X-ray selected red quasars
-
New module keeps multimodal models true to images during long answers
Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models
-
Adaptive measurements cut overhead for multi-controlled Toffoli gates
Measurement-Driven Adaptive Low-Overhead Implementation of Multi-Controlled Toffoli Gates
-
Resolvent duality holds for any set-valued map
Resolvent Moreau identities without monotonicity: theory and applications to Gabay duality, Douglas--Rachford and ADMM
-
Directed network games yield closed-form Shapley values
A Tractable Class of Cooperative Games Defined by Directed Networks: Unanimity Decomposition and Shapley Value
-
Semi-supervised method removes nighttime flares from unlabeled images
Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares
-
Hybrid system generates natural sentences from nested logic
FOL2NS: Generating Natural Sentences from First-Order Logic
-
Neutrino texture predicts normal hierarchy and theta23 octant
The Triadic Texture: Neutrino Predictions, Viable Vacuum, and Phenomenological Constraints
-
Debating LLMs catch more code vulnerabilities
Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection
-
Polymerization alone unifies all amoeboid migration modes
Amoeboid cell migration and shape dynamics driven by actin polymerization
-
Zeeman method recovers M dwarf fields when analysis choices align
Testing the reliability of magnetic field strength measurements for M dwarfs
-
Black-box agents revive erased concepts in image generators
Whispers in the Noise: Surrogate-Guided Concept Awakening via a Multi-Agent Framework
-
HMI reduces manual interventions 80% in platooning
In-Vehicle Human-Machine Interface to Support Drivers in Conditionally Automated Platooning
-
Nonlocal action locates Wilson-Fisher fixed point at two independent dimensions
Taming the 3D Wilson-Fisher Fixed Point via Nonlocal Effective Action
-
Nonlocal ansatz locates 3D Wilson-Fisher fixed point at three loops
Taming the 3D Wilson-Fisher Fixed Point via Nonlocal Effective Action
-
Foundation models top credit risk benchmarks as data shrinks
Foundation Models for Credit Risk Prediction: A Game Changer?
-
zkSNARK proofs enable anonymous reputation at scale for crowdsourcing
DARTIC: Decentralized Anonymous Reputation at Scale for Trustworthy Crowdsourcing
-
-
pArticleMap recovers 10.8% of future papers from literature gaps
Evidence-Grounded Frontier Mapping and Agentic Hypothesis Generation in Nanomedicine
-
GenAI lifts average performance but splits gains by interaction skill
Generative AI and the Productivity Divide: Human-AI Complementarities in Education
-
Re-optimized functionals hit 13 MeV error on nuclear densities
Systematic study of one-point kinetic energy density functionals for atomic nuclei
-
One model distills its own reasoning by playing teacher and student
A Brief Overview: On-Policy Self-Distillation In Large Language Models
-
One LLM teaches itself to reason with 40-60% less memory
A Brief Overview: On-Policy Self-Distillation In Large Language Models
-
Faculty orientations predict AI adoption in research and teaching
Faculty Orientations Shape Adoption of AI in Research and Teaching
-
Dipolar BEC pattern spacing scales linearly with axial confinement
Confinement-controlled pattern selection in a finite population-imbalanced dipolar Bose-Einstein condensate
-
Pattern spacing scales linearly with axial confinement in dipolar condensate
Confinement-controlled pattern selection in a finite population-imbalanced dipolar Bose-Einstein condensate