archive
Every paper Pith has read. Search by title, abstract, or pith.
85798 papers indexed · page 95
-
English pivots cut causal grounding of explanations by up to 5.7x
Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations
-
Two-level atom dynamics run classical logic as finite-state machines
Implementation of Finite state logic machines via the dynamics of atomic systems
-
Quantum metric equivalence holds in non-Hermitian open-boundary systems
Non-Bloch Quantum Geometry of Non-Hermitian Systems
-
Probabilistic model equips rankings with confidence intervals
Ranking with Confidence: A Probabilistic Framework for Deterministic Ranking Methods
-
DECOR scores LLM responses on four manipulation dimensions for deception
DECOR: Auditing LLM Deception via Information Manipulation Theory
-
Transformers rewritten as GEMM epilogue programs
CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs
-
Transformers rewrite non-attention ops as GEMM epilogues
CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs
-
Decimated m-sequences yield exactly 13 correlation values
Sequences with thirteen-valued cross correlations
-
Collateral trigger makes hybrid AMM the Nash choice in duopoly
Bounding LVR in AMMs via Secant-Tangent Divergence and Collateralized Liquidity Scaling
-
End-to-end models output formal text straight from Chinese speech
FormalASR: End-to-End Spoken Chinese to Formal Text
-
Small abstract spaces enable RL generalization to larger tasks
Smaller Abstract State Spaces Enable Cross-Scale Generalization in Reinforcement Learning
-
Multi-agent system hardens test updates with mutations
MuMuTestUp: Mutation-based Multi-Agent Test Case Update
-
Stake-weighted votes approximate power to ownership in expectation
Swimming with Whales: Analysis of Power Imbalances in Stake-Weighted Governance
-
GMM curriculum cuts PINN errors on PDEs by up to 98%
From Simple to Complex: Curriculum-Guided Physics-Informed Neural Networks via Gaussian Mixture Models
-
Backdoor attack hits near-100% success on masked diffusion LMs
Backdooring Masked Diffusion Language Models
-
Self-healing web apps detect faults at 90.7% and recover 56% faster
When Web Apps Heal Themselves: A MAPE-K Based Approach to Fault Tolerance and Adaptive Recovery
-
Quadtrees cut GUI agent visual tokens by 30 percent
AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees
-
Python framework unifies XAI methods for ECG models
ExECG: An Explainable AI Framework for ECG models
-
LLMs tune rewards in 5.2 iterations from 500x off weights
ERFSL: An Efficient Reward Function Searcher via Language Models for Custom-Environment Multi-Objective Optimization (Student Abstract)
-
Monocular SLAM outputs metric trajectories without scale correction
PRISM-SLAM: Probabilistic Ray-Grounded Inference for Scale-aware Metric SLAM
-
Flow-map endpoint velocity replaces fake-score network
Distribution Matching Distillation without Fake Score Network
-
Low-cost compliant sensor enables stable bilateral teleoperation at 120 ms delay
Bilateral Teleoperation with Compliant 6-DOF Pose-and-Force Sensing
-
Smith normal form computation scales with matrix multiplication
A C implementation of the Smith massager algorithm
-
Trust scores detect backdoors in over-the-air federated learning
Detecting and Mitigating Backdoor Attacks in OTA-FL Systems: A Two-Stage Robust Aggregation Scheme
-
Microbial chemistry clusters in distinct elemental space
Elemental Stoichiometry as an Ecological Biosignature with Applications to Life Detection
-
New database assembles all known alpha and proton decay data
The Online Berkeley Evaluated Alpha and Proton Radioactivity database (BE$\alpha p$R) -- from Li to Og!
-
Imbalanced attention heads bias MLLMs toward text errors over visuals
Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination
-
Proxy of post-target continuations boosts time series forecasts
Beyond Extrapolation: Knowledge Utilization Paradigm with Bidirectional Inspiration for Time Series Forecasting
-
Entanglement halves bandwidth for oblivious updates in storage
Quantum Entanglement Halves the Oblivious Update Bandwidth
-
LLM templates expand NAS to discover better architectures
Structuring Open-Ended NAS: Semi-Automated Design Knowledge Structuring with LLMs for Efficient Neural Architecture Search
-
Example bundles auto-generate package queries with aggregate rules
Example-Driven Intent Synthesis for Constrained Data Bundle Retrieval: Focused Text Snippet Extraction and Beyond
-
Neutral atom gates gain 40% better fidelity bound near Förster resonances
Entangling gate performance and fidelity limits with neutral atom F\"orster resonances
-
Tessellation wavelets decompose particle dynamics by scale
Multiresolution analysis on tessellation graphs for inertial particle dynamics
-
Local distance graphs recover global Euclidean embeddings
Euclidean Embedding of Data Using Local Distances
-
Post-training lifts video models' physical consistency
PhyWorld: Physics-Faithful World Model for Video Generation
-
AGN dust tori may birth tens of millions of planets
Active Galactic Nucleus Tori: Potential Birthplace to Millions of Planets
-
CASPIAN detects cascade attacks via causal monitoring in LLM agents
CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring
-
Weyl laws compute noncommutative integrals for operator-valued operators
Weyl's laws and Connes' Trace Theorem for operator-valued pseudo-differential operators
-
Hidden quantum metric detected via separated photocurrents in 2D magnet
Harnessing hidden quantum metric response in a 2D magnet via nonlocal photovoltaic effect
-
GCAS enables first linear-space universal constructions for infinite arrivals
Generalized Compare-and-Swap and Space-Efficient Universal Constructions for the Infinite-Arrival Model
-
Peculiar velocities small enough for Laniakea ZoA reconstruction
Peculiar velocities at low Galactic latitude
-
Centralized critic removes action-sampling variance in self-play RL
GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning
-
Language access managers accept AI but require human oversight
AI Technologies in Language Access: Attitudes Towards AI and the Human Value of Language Access Managers
-
Quantum hybrid raises F1 when UAV detectors drop contextual proxies
Quantum Machine Learning for Cyber-Physical Anomaly Detection in Unmanned Aerial Vehicles: A Leakage-Free Evaluation with Proxy-Audited Feature Sets
-
Devilray model finds gaps in all seven FBS detectors tested
Devilray: A Systematic Adversarial Model Revealing Blind Spots in Fake Base Station Detection
-
Regime gate improves time series forecast accuracy under shifts
DeRegiME: Deep Regime Mixtures for Probabilistic Forecasting under Distribution Shift
-
Method reduces age bias in medical image classification by decorrelating difficulty
Robust Mitigation of Age-Dependent Confounding Effects via Sample-Difficulty Decorrelation
-
Theory-anchored LLM cuts bias in disaster survey gaps
Can Large Language Models Revolutionize Survey Research? Experiments with Disaster Preparedness Responses
-
Step-level scores flag reasoning errors in closed LLMs
Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution
-
Single trigger corrupts both text and image outputs in unified models
Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models