All Articles
16920 articles total
Koopman-driven grip force prediction through EMG sensing
A study on using Koopman operator theory and EMG sensing to predict grip force in real-time for robotic rehabilitation.
PersGuard: Preventing Malicious Personalization in Text-to-Image Diffusion Models via Model Backdoors
Presents PersGuard, a framework that uses model backdoors to prevent unauthorized personalization of text-to-image diffusion models.
NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache
Introduces NSNQuant, a calibration-free vector quantization method for low-bit KV cache compression in LLMs, improving throughput by up to 3x.
Uniform Approximation of Functions with Asymmetric Growth and Decay by Deep Weighted Polynomials
Proposes deep weighted polynomial approximants for functions with asymmetric growth and decay, with applications in option-pricing.
Post-Disaster Affected Area Segmentation with a Vision Transformer (ViT)-based EVAP Model using Sentinel-2 and Formosat-5 Imagery
A ViT-based framework for segmenting disaster-affected areas using Sentinel-2 and Formosat-5 satellite imagery.
Inverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision Mapping
Introduces Inverse-LLaVA, a multimodal architecture that projects text embeddings into visual space, reducing the need for explicit alignment pre-training.
Google Kills Custom Search API on Jan 1, 2027
Google is shutting down its Custom Search API on January 1, 2027.
Lingbot-map: A 3D foundation model for reconstructing scenes from streaming data
Lingbot-map is a 3D foundation model designed to reconstruct scenes from streaming data.
Canada says bridge tolls won't be split with U.S. until $6.4B of debt is repaid
Canada has stated that bridge tolls will not be split with the U.S. until $6.4 billion in debt is repaid.
Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study
Researchers developed a multi-expert routing system for low-resource Manchu OCR that handles various writing styles with high accuracy.
A Survey on Hypergame Theory: Modelling Misaligned Perceptions and Nested Beliefs for Multi-Agent Systems
A survey on Hypergame Theory explores modeling misaligned perceptions and nested beliefs in multi-agent systems to improve strategic realism.
Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate
Research shows that interaction protocols (synchronous vs. round-robin) significantly influence moral judgment and value alignment in multi-agent LLM debates.
Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution
Policy of Thoughts (PoT) introduces a framework for LLM reasoning that uses online policy evolution via GRPO to significantly boost performance in smaller models.
When Agents Disagree With Themselves: Behavioral Consistency as an Uncertainty Signal for LLM Agents
Study finds that behavioral consistency in LLM agents serves as a reliable uncertainty signal, improving prediction accuracy when used for selective classification.
Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation
Introduction of M-JudgeBench and Judge-MCTS to improve the evaluation and training of multimodal large language models acting as judges.
How LLMs Might Think
A philosophical exploration into whether LLMs think, arguing they may engage in arational, associative forms of thinking.
M 3.9 Experimental Explosion – 147 Km ENE of Ponce Inlet, Florida
Report of a magnitude 3.9 earthquake occurring northeast of Ponce Inlet, Florida.
Count the Bytes, Not the FLOPs
A discussion or article arguing for focusing on memory bandwidth and byte movement rather than floating-point operations (FLOPs) in performance optimization.
Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Reliability, and Blind-Spot Ceilings
Provides a mathematical theory for partially correlated verifier cascades in LLM harnesses, demonstrating that reliability saturates and failure decays polynomially rather than exponentially.
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
Introduces 'generative compilation', a method for providing real-time compiler feedback to LLMs during code generation, specifically implemented for Rust.