AI/ML arXiv cs.AI

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.

AI/ML arXiv cs.AI

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.

AI/ML arXiv cs.AI

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.

AI/ML arXiv cs.AI

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.

AI/ML arXiv cs.AI

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.

AI/ML arXiv cs.AI

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.

Tech Business/VC Hacker News

Google Kills Custom Search API on Jan 1, 2027

Google is shutting down its Custom Search API on January 1, 2027.

AI/ML Hacker News

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.

Other Hacker News

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.

AI/ML arXiv cs.AI

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.

AI/ML arXiv cs.AI

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.

AI/ML arXiv cs.AI

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.

AI/ML arXiv cs.AI

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.

AI/ML arXiv cs.AI

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.

AI/ML arXiv cs.AI

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.

AI/ML arXiv cs.AI

How LLMs Might Think

A philosophical exploration into whether LLMs think, arguing they may engage in arational, associative forms of thinking.

Other Hacker News

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.

Software Engineering Hacker News

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.

AI/ML arXiv cs.AI

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.

AI/ML arXiv cs.AI

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.