AI/ML arXiv cs.AI

Revisiting the Platonic Representation Hypothesis: An Aristotelian View

This research challenges the Platonic Representation Hypothesis and proposes the Aristotelian Representation Hypothesis, suggesting NN representations converge to shared local neighborhood relationships.

AI/ML arXiv cs.AI

ReportLogic: Evaluating Logical Quality in Deep Research Reports

ReportLogic is a benchmark and open-source LogicJudge designed to evaluate the logical quality and auditability of deep research reports generated by LLMs.

AI/ML arXiv cs.AI

Learning to Select Maximum Clique Algorithms: From Traditional Machine Learning to a Dual-Channel Hybrid Neural Architecture

Researchers developed GAT-MLP, a dual-channel hybrid neural architecture that combines Graph Attention Networks and MLPs to select the most effective algorithm for solving the NP-hard Maximum Clique Problem.

AI/ML arXiv cs.AI

Through the Looking Glass: A Dual Perspective on Weakly-Supervised Few-Shot Segmentation

The TLG model introduces a homologous but heterogeneous network design to improve weakly-supervised few-shot semantic segmentation, significantly outperforming fully supervised models with fewer parameters.

AI/ML arXiv cs.AI

Reconstruction Alignment Improves Unified Multimodal Models

Reconstruction Alignment (RECA) is a resource-efficient post-training method that improves image generation and editing fidelity in unified multimodal models by leveraging visual understanding embeddings.

AI/ML arXiv cs.AI

Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimes

ReFine is a two-component framework for generating synthetic tabular data in low-data regimes by extracting symbolic rules from interpretable models and applying dual-granularity filtering.

AI/ML arXiv cs.AI

Rotary Position Encodings for Graphs

The WIRE approach applies rotary position encodings (RoPE) to graph-structured data by rotating tokens based on the graph Laplacian spectrum to inject structural information.

Other arXiv cs.AI

The Journal of Prompt-Engineered (Moral) Philosophy Or: Why AI-Assisted Ethics Research Requires Process Transparency

This paper argues for process transparency in AI-assisted ethics research, proposing a documentation-adequacy framework to ensure agent-integrity and meaningful human control.

AI/ML arXiv cs.AI

Patent Representation Learning via Self-supervision

Researchers propose a self-supervised patent representation learning strategy using mixed dropout-section positives to better align different sections of patent documents.

AI/ML arXiv cs.AI

Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training

Pianist Transformer uses large-scale self-supervised pre-training on MIDI data and an efficient asymmetric Transformer to generate expressive, human-like piano performances.

AI/ML arXiv cs.AI

The Best of the Two Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation

H2Rec is a framework that harmonizes semantic IDs and hash IDs in sequential recommender systems to balance performance between head and tail items.

AI/ML arXiv cs.AI

Improved Bounds for Private and Robust Alignment

This research establishes theoretical upper bounds on the suboptimality gap for private and robust alignment of language models, covering both offline and online settings.

Tech Business/VC Hacker News

US allows Anthropic to release Mythos to 'trusted partners'

The US government has allowed Anthropic to release its Mythos model to a select group of trusted partners.

Other Hacker News

Why does kinetic energy increase quadratically, not linearly, with speed? (2011)

An exploration into the physics of kinetic energy and why it increases quadratically with speed.

Software Engineering Hacker News

A Tiny Compiler for Data-Parallel Kernels

A presentation of a tiny compiler designed specifically for data-parallel kernels.

AI/ML Hacker News

AI in Mathematics Is Forcing Big Questions

A discussion on how advancements in AI are forcing fundamental questions and changes in the field of mathematics.

AI/ML arXiv cs.AI

Wearable Device-Based Real-Time Monitoring of Physiological Signals: Evaluating Cognitive Load Across Different Tasks

A study on using wearable devices to monitor EEG and HRV signals for real-time cognitive load assessment in students.

AI/ML arXiv cs.AI

Byzantine-Robust Aggregation for Securing Decentralized Federated Learning

Introduction of WFAgg, a Byzantine-robust aggregation algorithm designed to secure decentralized federated learning environments.

AI/ML arXiv cs.AI

Tuning Language Models by Mixture-of-Depths Ensemble

Introduction of the Mixture-of-Depths Ensemble (MoDE) framework to improve LLM reasoning by treating late layers as an ensemble.

AI/ML arXiv cs.AI

Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models

Proposed DCLA, a training-free decoding mechanism to mitigate hallucinations in Large Vision-Language Models through inter-layer consistency.