AI/ML arXiv cs.AI

Learner-based Concept Drift Detection: Analysis and Evaluation

A theoretical analysis and evaluation of various learner-based concept drift detection algorithms for streaming data environments.

AI/ML arXiv cs.AI

ScholarQuest: A Taxonomy-Guided Benchmark for Agentic Academic Paper Search in Open Literature Environments

ScholarQuest, a new taxonomy-guided benchmark for evaluating LLM-based agents performing academic paper searches in open literature.

AI/ML arXiv cs.AI

SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs

SPOT-E is a test-time entropy shaping method that uses visual spotlights to improve the grounding and robustness of frozen Vision-Language Models.

AI/ML arXiv cs.AI

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

Research showing that Vision-Language-Action (VLA) models can be compressed by up to 50% in depth without losing performance through a training-free structural compression pipeline.

AI/ML arXiv cs.AI

The Register Gap: A Meaning Intelligence Framework for Nigerian Public Discourse

The Meaning Intelligence Framework (MIF) is proposed to better analyze Nigerian public discourse by separating surface sentiment from true communicative intent.

AI/ML arXiv cs.AI

Editorial Alignment: A Participatory Approach to Engaging Editorial Expertise in LLM-mediated Knowledge Dissemination

A study on 'editorial alignment' as a design practice to ensure LLM-mediated knowledge dissemination adheres to the standards of public knowledge institutions.

AI/ML arXiv cs.AI

ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval

ELVA, a rule-based RL framework designed to mitigate 'grain blindness' in universal multimodal retrieval using MLLMs.

AI/ML arXiv cs.AI

Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement

Boundary Embedding Shaping (BES) is introduced as an adaptive contrastive learning plug-in for GNNs to reduce structural noise at decision boundaries.

Other Hacker News

Giant Banana Pulled over in Montana Driver Says Cops Have Stopped Him 100s Times

A news story about a giant banana statue in Montana causing frequent police stops.

Tech Business/VC The Verge

NASA selects Eric Schmidt’s rocket company for a 2028 mission to Mars

NASA has selected Eric Schmidt's rocket company, Relativity Space, to launch a Mars payload in 2028 to study the Martian atmosphere.

AI/ML arXiv cs.AI

Sensorimotor World Models: Perception for Action via Inverse Dynamics

Introduction of Sensorimotor World Models (SMWM), a latent world model trained with inverse dynamics regularization to prevent representation collapse and align representations with actions.

AI/ML arXiv cs.AI

Dual-Agent Framework for Cross-Model Verified Translation of Natural-Language Protocols into Robotic Laboratory Platform

A dual-agent framework using a Parser Agent and LLM Validation Agent to translate natural-language biological protocols into executable robotic lab commands.

AI/ML arXiv cs.AI

Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation

Frequency-Aware Flow Matching (FAFM) is proposed for continuous and consistent robotic action generation using DCT and Sobolev-type constraints.

AI/ML arXiv cs.AI

Hybrid ANN-SNN Pipeline with Local Plasticity

A hybrid ANN-SNN pipeline combining EfficientNet with a CoLaNET spiking classifier using local plasticity learning rules.

AI/ML arXiv cs.AI

From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models

Research analyzing how LLMs encode essay quality representations linearly and identify specific 'essay scoring neurons'.

AI/ML arXiv cs.AI

MedRLM: Recursive Multimodal Health Intelligence for Long-Context Clinical Reasoning, Sensor-Guided Screening, Evidence-Grounded Decision Support, and Community-to-Tertiary Referral Optimization

MedRLM is introduced as a recursive multimodal framework for long-context clinical reasoning and health intelligence using specialized agents and Evidence Graph Memory.

AI/ML arXiv cs.AI

Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs

The RS-Neg benchmark evaluates negation comprehension in remote sensing MLLMs, and the NeFo test-time learning method is proposed to improve it.

AI/ML arXiv cs.AI

HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-trainin

HilDA is a self-supervised pretraining framework for LiDAR backbones using hierarchical distillation and temporal occupancy diffusion.

Hardware/Chips Hacker News

I used sound waves to make espresso. It could cut coffee‑brewing energy use by ¾

An experimental project using sound waves to brew espresso, potentially reducing energy consumption by 75%.

AI/ML arXiv cs.AI

A Neuromorphic Reinforcement Learning Framework for Efficient Pathfinding in Robotic Mobile Fulfillment Systems

Introduction of SDQN-RMFS, a framework that deploys RL-trained policies onto neuromorphic chips for ultra-low-power robotic pathfinding.