AI/ML arXiv cs.AI

Vision-Language-Policy Model for Dynamic Robot Task Planning

Introduces a Vision-Language-Policy (VLP) model for dynamic robot task planning, allowing robots to adapt behavior based on visual and semantic inputs.

AI/ML arXiv cs.AI

Backpropagation-Free Test-Time Adaptation for Lightweight EEG-Based Brain-Computer Interfaces

Presents Backpropagation-Free Transformations (BFT) for EEG-based brain-computer interfaces to enable lightweight, on-device adaptation without the overhead of backpropagation.

AI/ML arXiv cs.AI

Knowledge-Guided Time-Varying Causal Inference for Arctic Sea Ice Dynamics

Develops the KGCM-VAE framework to quantify causal relationships between sea surface height and Arctic sea ice thickness using knowledge-guided causal inference.

AI/ML arXiv cs.AI

NeuraLSP: A Neural Spectral Preconditioner for Accelerating PDE Solvers

Introduces NeuraLSP, a neural spectral preconditioner that accelerates PDE solvers by replacing graph aggregation with low-rank spectral representations.

AI/ML arXiv cs.AI

PILD: Physics-Informed Learning via Diffusion

Proposes Physics-Informed Learning via Diffusion (PILD), a framework that integrates physical constraints into diffusion models for better fidelity in scientific tasks.

AI/ML arXiv cs.AI

Variational Speculative Decoding: Rethinking Draft Training from Token Likelihood to Sequence Acceptance

Presents Variational Speculative Decoding (VSD) to optimize draft training for LLM inference, increasing acceptance length and overall decoding speed.

AI/ML arXiv cs.AI

Multimodal Learning for Arcing Detection in Pantograph-Catenary Systems

Introduces MultiDeepSAD, a multimodal framework combining image and force data to detect electrical arcing in rail pantograph-catenary systems.

AI/ML arXiv cs.AI

Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents

Details a self-evolving recommendation system using Gemini-powered LLM agents to autonomously optimize model architectures and hyperparameters at YouTube.

Software Engineering Hacker News

A concrete explanation of how a cache works

A detailed technical explanation of how computer caches work, discussed within the Hacker News community.

AI/ML arXiv cs.AI

MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs

Introduction of MELLA, a multimodal dataset designed to improve the cultural groundedness and linguistic fluency of MLLMs in low-resource languages.

AI/ML arXiv cs.AI

Drive As You Like: Multi-Head Diffusion with Reinforcement Learning for Personalized Driving

A multi-strategy framework utilizing diffusion-based planning and RL to enable personalized, user-intent-aligned autonomous driving trajectories.

Cybersecurity arXiv cs.AI

DynaMark: A Reinforcement Learning Framework for Dynamic Watermarking in Industrial Machine Tool Controllers

DynaMark is an RL framework for dynamic watermarking in industrial machine tool controllers to detect replay attacks and ensure system security.

AI/ML arXiv cs.AI

Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs

SCoRe is a student-centered distillation framework that narrows the gap between small and large LLMs by focusing on early error correction and short-horizon RL.

AI/ML arXiv cs.AI

Equivariant Conditional Diffusion Model for Head and Neck CT Image Synthesis from CBCT

EqDiff-CT is a conditional diffusion model that synthesizes high-quality CT images from CBCT scans using rotational equivariance to preserve structural details.

AI/ML arXiv cs.AI

Simple Policy Gradients for Reasoning with Diffusion Language Models

Introduction of AGRPO, a policy gradient algorithm that optimizes individual denoising steps in diffusion language models to improve reasoning tasks.

AI/ML arXiv cs.AI

On the Granularity of Causal Effect Identifiability

A theoretical study on state-based causal effect identifiability, demonstrating how specific state interventions can be identifiable even when variable-based effects are not.

AI/ML arXiv cs.AI

Generative Artificial Intelligence in Bioinformatics: A Systematic Review of Models, Applications, and Methodological Advances

A systematic review of Generative AI's impact on bioinformatics, covering genomics, proteomics, and drug discovery through specialized architectures.

AI/ML arXiv cs.AI

TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework

TeaRAG is a token-efficient agentic RAG framework that uses graph retrieval and iterative process-aware DPO to reduce token overhead while maintaining accuracy.

AI/ML arXiv cs.AI

StackingNet: Collective Inference Across Independent AI Foundation Models

The paper introduces StackingNet, a meta-ensemble framework that aggregates predictions from multiple independent, black-box foundation models to improve accuracy and reduce errors without requiring internal model parameters.

AI/ML arXiv cs.AI

Diagnosing Pathological Chain-of-Thought in Reasoning Models

Researchers identify and categorize three failure modes of Chain-of-Thought reasoning in LLMs—post-hoc rationalization, encoded reasoning, and internalized reasoning—providing a toolkit for assessing these pathologies.