All Articles
17859 articles total
Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders
Research proposing new sparsity regularizers for Top-k Sparse Autoencoders to improve the interpretability of vision foundation models.
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning
The PEEU method enhances GUI agents' planning abilities in small MLLMs through autonomous exploration and hindsight experience utilization.
Hightouch (YC S19) Is Hiring
Hightouch, a Y Combinator startup, is currently hiring for various positions.
Pre-Modern Armies for Worldbuilders, Part III: Paying for It
A detailed guide on the economic aspects of paying for pre-modern armies for worldbuilders.
Long Wave radio era set to end with Droitwich switch-off
The era of long wave radio is coming to an end with the shutdown of the Droitwich transmitter.
Russian citizens told "switch to Android" after Apple blocks key Russian apps
The Russian government has urged citizens to switch to Android after Apple blocked key Russian apps on the App Store.
NYT slams Microsoft for building copyright-infringing supercomputer for OpenAI
The New York Times is pursuing copyright claims against Microsoft and OpenAI regarding the use of a supercomputer for training AI models.
Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)
A prize-winning solution for bimanual garment folding using a vision-language-action (VLA) policy improved with reinforcement learning.
Automating Potential-based Reward Shaping with Vision Language Model Guidance
Introduces VLM-PBRS, a framework that uses Vision Language Models to automate potential-based reward shaping in reinforcement learning.
CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention
Introduces CARVE, a new recurrent architecture that improves efficiency and performance over GDN-2 by erasing only on the key axis.
Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contexts
A conceptual framework for analyzing dialogue dynamics in human-AI and multi-agent collaborative problem-solving.
From Celebrities to Anyone: Characterizing AI Nudification Content, Technology, and Community Dynamics on 4chan
A study on the proliferation of AI-generated non-consensual sexually explicit imagery, highlighting a shift toward targeting non-celebrities.
The Art of Kite Flying (1430–1929)
An exploration of the history and art of kite flying from 1430 to 1929.
Slisp: Simple Lisp compiler (Linux/amd64)
Slisp is a simple Lisp compiler targeting Linux/amd64.
Parametric Open Source Games
Introduces parametric open-source games as a continuous analogue of program equilibria in game theory, showing how open-source coupling can steer optimization toward cooperation.
Beyond Global Divergences: A Local-Mass Perspective on Bayesian Inference
Proposes a local-mass perspective on Bayesian inference using Mass Index and regularised extended KL (RE-KL) to better characterize local distributional discrepancy.
Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation
Reveals that security fine-tuning in LLMs can create evasion vulnerabilities by specializing inherited circuits into brittle indicator rules.
Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning
Presents CIRCLE, a class-incremental classifier using fixed reservoir features that eliminates the need for backbone backpropagation in cold-start continual learning.
Application of LLMs to Threat Assessment of Foreign Peacekeeping Missions
Describes a workflow using LLMs and OSINT to extract threats for foreign peacekeeping missions, showing high agreement with human analysts.
Heavy-Ball Q-Learning with Residual Weighting Correction
Proposes a heavy-ball Q-learning method with residual weighting correction to accelerate convergence in reinforcement learning.