All Articles
17770 articles total
Free the Icons
A discussion regarding the liberation or open-sourcing of icons.
Is It Out Yet?
A thread discussing the anticipation and release status of an unspecified product or feature.
Hybrid Fact-Checking that Integrates Knowledge Graphs, Large Language Models, and Search-Based Retrieval Agents Improves Interpretable Claim Verification
Introduces a hybrid fact-checking pipeline integrating Knowledge Graphs, LLMs, and search agents to improve claim verification interpretability and accuracy.
Hybrid coupling with operator inference and the overlapping Schwarz alternating method
Proposes a hybrid coupling method using operator inference and the overlapping Schwarz alternating method to speed up 3D solid dynamics simulations by up to 106x.
Trust Region Masking for Long-Horizon LLM Reinforcement Learning
Presents Trust Region Masking (TRM) to provide non-vacuous monotonic improvement guarantees for long-horizon LLM Reinforcement Learning.
Pixelwise Uncertainty Quantification of Accelerated MRI Reconstruction
A framework for pixel-wise uncertainty quantification in accelerated MRI reconstruction using conformal quantile regression to identify unreliable image regions.
Psychometric Comparability of LLM-Based Digital Twins
Evaluates the psychometric comparability of LLM-based digital twins against human standards, finding they are most effective within specific validated boundaries.
DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing
Introduces DDSA, a resource-efficient adversarial robustness testing framework that optimizes testing through temporal selectivity and spatial precision.
Reasoning-Enhanced Rare-Event Prediction with Balanced Outcome Correction
Proposes LPCORP, a two-stage framework combining reasoning-enhanced prediction and confidence-based correction to improve rare-event prediction in imbalanced datasets.
Robustness of Constraint Automata for Description Logics with Concrete Domains
An automata-based approach to prove the EXPTIME upper bound for the consistency problem of description logics with concrete domains.
Ornith-1.0: Self-scaffolding LLMs for agentic coding
Ornith-1.0 is a new approach to self-scaffolding LLMs designed to enhance agentic coding capabilities.
Is sunscreen the new margarine? (2021)
An older article discussing the potential parallels between the current perception of sunscreen and the historical perception of margarine.
South Korea to spend $1T on more memory chip production and humanoid robots
South Korea announces a $1 trillion investment in memory chip production and the development of commercial humanoid robots by 2028.
Freshness and the Limits of Heuristic Trend Detection in Temporal RAG
Researchers propose a lightweight temporal layer for RAG to improve freshness and trend detection in cybersecurity data.
Unbiased Binning for Fairness-aware Attribute Representation
Introduces unbiased binning and an epsilon-biased binning algorithm to reduce bias and ensure fairness in attribute representation for datasets.
Ranking Before Serving: Low-Latency LLM Serving via Pairwise Learning-to-Rank
Introduces PARS, a prompt-aware scheduler for LLM serving that reduces latency by up to 15.7x by approximating shortest-job-first scheduling.
Deep Neural Networks Inspired by Differential Equations
A comprehensive review of deep neural network architectures inspired by differential equations, focusing on ODEs and SDEs for better interpretability.
MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
MetaBreak explores how special token manipulation can be used to jailbreak online LLM services and bypass content moderation.
A Primer on SO(3) Action Representations in Deep Reinforcement Learning
A guide and evaluation of SO(3) action representations in deep reinforcement learning for better robotic control.
LieSolver: PDE-Constrained Learning for IBVPs via Lie Symmetries
Introduces LieSolver, a method using Lie symmetries to solve partial differential equations exactly by construction, outperforming PINNs.