All Articles
17859 articles total
Efficient foundation decoders for fault-tolerant quantum computing
Introduces Neural Transfer Unification (NTU) and NTU-Transformer to efficiently train foundation decoders for fault-tolerant quantum computing across different code distances.
Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
Introduces iterative self-improving codebooks to enhance the safety of autoregressive image generation by identifying and removing harmful mappings without human annotation.
Gossamer: a Rust-flavoured language with real goroutines and pause-free memory
Introduction of Gossamer, a new programming language inspired by Rust that features real goroutines and pause-free memory management.
The "Bizarre Headgear" Exhibit at the Sam Noble Museum Is Incredible
An exhibit of bizarre headgear at the Sam Noble Museum is highlighted as incredible.
Novak Djokovic has a new job — advisor to private equity firm General Atlantic
Tennis star Novak Djokovic has become a global strategic advisor to the private equity firm General Atlantic.
FCC accused of hiding Chairman Carr's messages with DOGE and Musk
The FCC is accused of withholding messages between Chairman Carr and Elon Musk's DOGE initiative.
Netflix now requires every user profile to be tied to unique email address
Netflix implements a requirement for each user profile to be tied to a unique email address to prevent login sharing.
On-board Remote-Sensing Foundation Models for Unsupervised Change Detection of Disaster Events
A new unsupervised change detection method for disaster events is proposed using Remote-Sensing Foundation Models (RSFMs) for onboard satellite processing.
ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP
ShareLock is introduced as a stealthy multi-tool threshold poisoning attack framework targeting the Model Context Protocol (MCP) for LLM agents.
State Representation Matters in Deep Reinforcement Learning: Application to Energy Trading
Research demonstrates that state representation is critical for the success of Deep Reinforcement Learning agents in energy trading environments.
The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced Architecture for AI-Assisted Software Development
The Spec Growth Engine is a framework for AI-assisted software development that uses a machine-readable spec graph to prevent context explosion and spec-code drift.
NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models
NuclearQAv2 is a new structured benchmark designed to evaluate the quantitative reasoning and domain-science competence of LLMs in nuclear engineering.
What Is a Nomogram and Why Would It Interest Me?
A discussion on Hacker News exploring the concept of nomograms and their utility in calculation and data visualization.
Scaling Multi-Reference Image Generation with Dynamic Reward Optimization
Introduces OmniRef-Bench for evaluating multi-reference image generation and DyRef, a training framework to improve model performance in complex scenarios.
XMSE-Aware Adaptive Empirical Bayes Estimation
Proposes an XMSE-aware mixed estimator that interpolates between maximum likelihood and Empirical Bayes shrinkage to improve estimation under kernel misspecification.
In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics
Presents In-Context Model Predictive Generation (ICMPG), a framework integrating LLM planning with physics simulation for realistic human motion synthesis.
Auditing Framing-Sensitive Behavioral Instability in Large Language Models for Mental Health Interactions
Analyzes how different contextual framings impact the behavioral stability and internal representations of LLMs in mental health interaction scenarios.
ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models
Introduces ReaORE, a reasoning-guided progressive framework that uses coarse-to-fine reasoning to improve Open Relation Extraction.
Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs
Investigates emotion vectors in open-weight LLMs like Apertus and Gemma, discovering how valence representations emerge differently across model depth.
Decision-Aligned Evaluation of Uncertainty Quantification
Proposes a decision-aligned evaluation framework and prior-weighted utility metrics to better assess uncertainty quantification in machine learning.