All Articles
16870 articles total
SceneBind: Binding What and Where Across Vision, Audio and Language
SceneBind is introduced as an omni-modal representation for joint semantic and 3D spatial understanding across vision, audio, and language.
Learning a few things about running SQLite
A community discussion on the nuances and practicalities of running SQLite in production environments.
Homomorphically encrypted CIFAR-10 inference in 200ms
A technical demonstration of achieving high-speed inference on the CIFAR-10 dataset using homomorphic encryption.
Parameter-efficient Prompt Tuning of Vision Foundation Model With Adaptive Focal Loss for Interpretable MCI Screening
Proposes a parameter-efficient framework for MCI screening using frozen DINOv2-Small and adaptive focal loss to improve interpretability and accuracy.
ANet Patu-1: The Value of Connection in the Agent Network
Introduces ANet Patu-1, a self-organizing consensus protocol for AI agents that optimizes collaboration and scales effectively regardless of model strength.
Towards Hierarchical Structure Understanding of Newspaper Images
Explores hierarchical structure understanding of newspaper images using both a modular pipeline and a new end-to-end transformer architecture called Tiramisu.
Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents
Presents a multi-agent framework using SFT, DPO, and RAG to simulate and audit political coalition formation with LLM agents.
NIFA: Nonlinear IMC enhanced FPGA for efficient ML inference
Introduces NIFA, an FPGA architecture using ADC-free IMC blocks to significantly improve energy and area efficiency for ML inference, particularly for Transformers.
Scaling Behavior Foundation Model for Humanoid Robots
Develops a Behavior Foundation Model for humanoid robots using a 'Humanoid Transformer' architecture to improve whole-body coordination and task generalization.
T^2MLR: Transformer with Temporal Middle-Layer Recurrence
Introduces T2MLR, a transformer architecture that uses temporal middle-layer recurrence to allow intermediate reasoning states to persist across decoding steps.
Subjective Risk Decomposition: A New View for Uncertainty Quantification
A theoretical approach to uncertainty quantification by deriving epistemic and aleatoric uncertainty from the decomposition of subjective risk.
I replaced my space heater and ceiling fan with one Dyson appliance
Dyson has released the Hot+Cool HF1, a combined space heater and ceiling fan appliance for year-round home comfort.
How Apple’s big lawsuit could disrupt OpenAI’s IPO plans
Apple has filed a trade secrets lawsuit against OpenAI, alleging misconduct and the poaching of hundreds of former Apple employees, potentially impacting OpenAI's IPO plans.
Apple Music is getting a price hike
Apple Music is increasing its monthly subscription prices for individual, family, and student plans across several regions.
Apple’s plot to crush OpenAI
The Vergecast discusses Apple's lawsuit against OpenAI, exploring whether the move is a competitive strategic strike or a reaction to OpenAI's growth.
Troubling new details emerge on diabetes ouster controversy
The American Diabetes Association blocked the publication of op-ed articles, leading authors to release them as preprints.
Will Russia's answer to the Falcon 9 rocket ever take flight?
Russia is developing a reusable rocket similar to the Falcon 9, with Grasshopper-like tests potentially starting in 2028.
Brex built its AI agent policy by watching what agents actually do, not by writing rules first
Brex has open-sourced CrabTrap, an HTTP/HTTPS proxy that uses an LLM-as-a-judge to enforce security policies for AI agents based on observed network traffic.
OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios
OmniaBench is a new benchmark for evaluating general AI agents across 354 diverse domains and 1,431 tasks, revealing limitations in planning and adaptive correction.
LQCDMaster: Agentic Scientific Computing for Lattice Quantum Chromodynamics Research
LQCDMaster is a domain-specialized AI agent that converts natural-language research tasks into executable PyQUDA workflows for Lattice Quantum Chromodynamics research.