AI/ML arXiv cs.AI

Fine-grained Computation-Communication Overlap via Tile-level Signaling and Scheduling for Mixture-of-Experts

Introduces a fine-grained computation-communication overlap technique for Mixture-of-Experts (MoE) models, achieving up to 2.64x end-to-end speedup on multi-GPU systems.

Other arXiv cs.AI

Juxtaposition of Shallow Reservoir-Triggered Seismicity and Deep Tectonic Locking in the Qiaojia-Dongchuan Seismic Gap

Analyzes seismic gaps using a decoupling model to distinguish between shallow reservoir-triggered seismicity and deep tectonic strain.

AI/ML arXiv cs.AI

Causal dictionary learning reveals and validates transcription-factor binding features in genomic language models

Develops a causal dictionary learning framework to extract and validate interpretable transcription-factor binding features in genomic language models.

Open Source arXiv cs.AI

SCPP: A Unified Python Library for Soft Clustering

Presents SCPP, an open-source Python library for soft clustering that provides a standardized scikit-learn-compatible interface for various algorithms.

Software Engineering arXiv cs.AI

Understanding Developer Pain Points in Federated Learning: Insights from Stack Overflow and GitHub

An empirical study of developer pain points in Federated Learning based on analysis of Stack Overflow and GitHub, highlighting gaps in tooling and documentation.

AI/ML arXiv cs.AI

Adaptive Capitulation: A Structural Failure Mode of LLM Responses in Vulnerability Contexts

Identifies 'adaptive capitulation' as a failure mode in LLMs where the model validates social injustice before facilitating discouraged behavior in sensitive contexts.

Open Source Hacker News

Protecting our FLOSS commons from LLMs

A discussion on protecting Free and Libre Open Source Software (FLOSS) from being exploited by LLMs.

AI/ML arXiv cs.AI

Building Trust in Autonomous Commerce: A Verifiable Global Event Timeline and AI-Ready Fraud Intelligence Layer

Proposes a verifiable global event timeline and fraud intelligence layer for autonomous agentic commerce to ensure auditability and temporal ordering.

AI/ML arXiv cs.AI

BaseRT: Advancing Best-in-Class LLM Inference with Apple M5 Neural Accelerators

Introduces BaseRT, a native Metal inference runtime for LLMs on Apple M5 chips that significantly outperforms llama.cpp and MLX in throughput.

AI/ML arXiv cs.AI

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification

A study on machine unlearning, proposing a base-anchored held-out screen to better audit the removal of specific knowledge from models.

AI/ML arXiv cs.AI

Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents

Audits tool-augmented LLM agents, finding that safety-oriented system prompts can paradoxically increase 'unfaithful safety refusals' when tools fail silently.

AI/ML arXiv cs.AI

REGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning

Introduces REGEN, a method using offline RL and replay-recycling from teacher models to distill generalist LLMs at a lower computational cost.

AI/ML arXiv cs.AI

Predictive Extrema, Unprofitable Policies: An AI-Assisted Audit of Candle-Based Binance Spot Timing Models

An audit of AI-assisted candle-based trading models on Binance Spot, concluding they are generally unprofitable after costs.

AI/ML arXiv cs.AI

MoA-Structured Decode Attention DNF Derivation, KV-Cache Accumulation, GQA/MQA, and OpenACC Kernel

Derives memory-optimal inference artifacts for transformer attention, including a C/OpenACC GPU kernel and KV-cache optimizations.

Hardware/Chips arXiv cs.AI

ModPack: An Extensible Teleoperation Interface for Bimanual Mobile Manipulation

Presents ModPack, an extensible teleoperation interface for bimanual mobile manipulation robots, with open-sourced hardware and software.

Cybersecurity arXiv cs.AI

Integrity of peer-to-peer distributed LLM inference under malicious nodes

Proposes a method to detect malicious nodes in P2P distributed LLM inference by using secret canary inputs to measure activation drift.

Cybersecurity Hacker News

ANSI escape injection in MCP servers: Hidden from humans, visible to AI

Discussion on how ANSI escape sequences can be used for prompt injection in Model Context Protocol (MCP) servers to hide malicious instructions from humans while remaining visible to AI.

AI/ML arXiv cs.AI

Recovering Clinical Utility Under Differential Privacy: Empirical Validation of Adaptive Federated Aggregation on Heterogeneous Cardiovascular Datasets

Introduction of the FedCVR framework for federated learning on real cardiovascular datasets, demonstrating that adaptive optimization can preserve clinical utility under differential privacy.

AI/ML arXiv cs.AI

Structured Latent Space Modeling over Multi-Scale Temporal Patches for Multivariate Time Series Forecasting

Presentation of M2Patch, a CNN-based architecture for multivariate time series forecasting that uses multi-scale patching and latent space constraints for better accuracy and linear complexity.

AI/ML arXiv cs.AI

Auditing Retrieval-Augmented LLM Hypotheses for Longitudinal Cell Painting Morphology

A retrieval-augmented interpretation framework for longitudinal Cell Painting morphology that uses LLMs to generate auditable biological hypotheses with quantitative validation tests.