Other Hacker News

The Rise of Grocery Tourism

An exploration of the trend where people travel specifically to visit unique or high-quality grocery stores.

Software Engineering Hacker News

GTFO VR Mod Postmortem

A technical postmortem detailing the development and challenges of creating a VR mod for the game GTFO.

AI/ML arXiv cs.AI

When to Plan: Learning to Select Between Reactive Control and Deliberative Planning

Research on meta-reasoning in AI agents to dynamically switch between fast reactive control and slower, more computationally expensive deliberative planning based on uncertainty.

AI/ML arXiv cs.AI

Berkeley and Heiserman as an Unexhausted Architecture for Embodied Machine Intelligence

A theoretical exploration of the works of Berkeley and Heiserman as a foundation for embodied machine intelligence and robotic cognition.

AI/ML arXiv cs.AI

SEER: Supervised Learning to Control Energetic Reasoning

Introduction of SEER, an ML-based oracle function used to optimize Constraint Programming by deciding when to execute complex propagators.

AI/ML arXiv cs.AI

Nonuniformity Principle in Human-AI Coworking

The proposal of the 'nonuniformity principle' to optimize the placement of human oversight stages in AI-driven multi-step workflows.

AI/ML arXiv cs.AI

From Modalities to Propositions: A Language-Centric Framework for Multimodal Intelligence

A language-centric framework that represents multimodal data (image, video, text) as a bag of atomic propositions for better interpretability and reasoning.

AI/ML arXiv cs.AI

Exact Network Surgery: Functional Invariance and Gradient Plasticity in Reactive Computational Graphs

Formalization of Exact Network Surgery for bit-exact insertion of residual blocks into live computational graphs without destroying learned functions.

AI/ML arXiv cs.AI

FST.ai 2.5: Explainable and Uncertainty-Aware AI for Olympic and Para-Taekwondo Decision Support, Athlete Digital Twins, and Federation-Scale Analytics

Presentation of FST.ai 2.5, an explainable AI framework for digital twins and decision support in Olympic and Para-Taekwondo.

Other Hacker News

Do we just want slaves?

A Hacker News discussion thread regarding the ethical and societal implications of AI and the concept of digital servitude.

Open Source Hacker News

Show HN: Ex Situ – open-source spatial index of displaced cultural artifacts

Introduction of Ex Situ, an open-source spatial index designed to track and document displaced cultural artifacts.

Other Hacker News

Flight Planning with Little Navmap

A guide or discussion on utilizing Little Navmap for flight planning in aviation simulations.

AI/ML arXiv cs.AI

Accurate and Efficient Long-Term Memory for LLM Agents

Presents MOSAIC, a structured, conflict-aware long-term memory framework for LLM agents that improves accuracy and efficiency using entity-typed graph storage and LSH.

AI/ML arXiv cs.AI

Symbolic Augmentation Closes a Canonical-Equivalence Blind Spot in Neural Fact-Checkers

Introduces Symbolic Augmentation to fix a 'blind spot' in neural fact-checkers regarding canonical-equivalent quantities (e.g., Celsius vs Kelvin).

AI/ML arXiv cs.AI

SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation

Proposes SelKV, a training-free KV cache compression framework using a soft cosine gate and attention-ratio compensation to speed up LLM decoding.

AI/ML arXiv cs.AI

RAIL Guard: Closing the Evaluation-to-Remediation Gap in Responsible AI for LLM Agents

Introduces RAIL Guard, an open-source SDK and closed-loop pipeline for evaluating and iteratively remediating unsafe LLM agent outputs.

AI/ML arXiv cs.AI

Generalist AI Control: Towards Multi-purpose Adaptive Algorithms

Develops a Generalist Controller using attention mechanisms and MoE to handle diverse dynamical systems (SISO) without system-specific tuning.

AI/ML arXiv cs.AI

LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Models

Introduces LaCache, a training-free acceleration framework for Diffusion LLMs using lossless state memoization and FP8 quantization.

AI/ML arXiv cs.AI

Interactive Task Alignment as a POMDP

Analyzes task alignment in LLMs as a POMDP, finding that models struggle to resolve user ambiguity compared to humans.

Software Engineering Hacker News

Jane Street: Incremental

Jane Street presents 'Incremental', a tool or approach for incremental computation, though the snippet provides no detailed technical content.