AI/ML arXiv cs.AI

InvestPhilBench: A Multi-Layer Benchmark for Evaluating Large Language Model Procedural Reasoning in Expert Investment Philosophy

Introduction of InvestPhilBench, a multi-layer benchmark to evaluate LLMs on their ability to apply expert investment philosophy procedural reasoning.

Tech Business/VC TechCrunch

Phia accused of ‘cookie stuffing,’ taking affiliate credit on purchases it didn’t earn

Shopping startup Phia, founded by Phoebe Gates, is accused of 'cookie stuffing' to fraudulently gain affiliate commissions on sales it did not earn.

AI/ML arXiv cs.AI

OpenCoF: Learning to Reason Through Video Generation

Researchers introduce OpenCoF, a framework and dataset for enhancing reasoning capabilities in video generation models through 'Chain-of-Frame' reasoning.

AI/ML arXiv cs.AI

IFAR: Multi-Perspective and Multi-Level Causal Discovery with LLMs

The IFAR framework is proposed to improve multi-perspective and multi-level abductive reasoning in LLMs, showing significant F1 score improvements over existing methods.

AI/ML arXiv cs.AI

Goal-Driven Reasoning in DatalogMTL with Magic Sets

A new reasoning method for DatalogMTL using magic sets technique is introduced to reduce computational complexity in temporal reasoning tasks.

AI/ML arXiv cs.AI

Dual-Difficulty Curriculum Learning for Direct Preference Optimization

GSP-Curri-DPO introduces a group-wise self-paced learning framework for LLM alignment, optimizing the learning trajectory based on prompt complexity and pairwise distinguishability.

AI/ML arXiv cs.AI

A Vision Toward Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents

A vision paper proposing a shift from massive general-purpose LLMs to energy-efficient, domain-specific multimodal agents for critical application domains.

AI/ML arXiv cs.AI

MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge Graphs

DualHNIE is a dual-channel hypergraph learning framework designed for better node importance estimation in heterogeneous knowledge graphs.

AI/ML arXiv cs.AI

SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection

SimRPD is a three-stage framework that uses a high-fidelity user simulator to optimize training data for recruitment-focused proactive dialogue agents.

AI/ML arXiv cs.AI

Conversational AI for Rapid Scientific Prototyping: A Case Study on ESA's ELOPE Competition

A case study on using ChatGPT for rapid scientific prototyping in a lunar trajectory estimation competition, highlighting both efficiency gains and reliability issues.

AI/ML arXiv cs.AI

RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments

RetailBench is introduced as a simulation benchmark to evaluate the long-horizon autonomous decision-making and strategy stability of LLM agents in retail environments.

Software Engineering Hacker News

Preemption is GC for memory reordering (2019)

A discussion on how preemption in operating systems can be viewed as a form of garbage collection for memory reordering.

Tech Business/VC TechCrunch

Meta removes controversial AI feature on Instagram after backlash

Meta has removed a controversial AI feature on Instagram following significant user backlash.

Other The Verge

No, Flock isn’t threatening people for debating surveillance

Flock Safety is facing criticism for allegedly attempting to silence discussions about its surveillance technology via cease and desist letters.

AI/ML The Verge

Meta turns off the Instagram feature that let users make AI deepfakes of public accounts

Meta disables an Instagram AI feature that allowed users to create deepfakes of public accounts without permission.

AI/ML arXiv cs.AI

A Practical Investigation of Training-free Relaxed Speculative Decoding

An investigation into training-free relaxed speculative decoding for accelerating LLM sampling, highlighting capability-speed trade-offs.

AI/ML arXiv cs.AI

ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation

Introduction of ProjAgent, a system for repository-level code generation using procedural similarity retrieval to better handle complex dependencies.

AI/ML arXiv cs.AI

Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction

BioModule is proposed as a lightweight plug-in for 3D pose estimators to predict biomechanical attributes for motion analysis.

AI/ML arXiv cs.AI

Validity of LLMs as data annotators: AMALIA on authority

A study on the AMALIA-9B model's validity as a data annotator for European Portuguese, questioning its reliance on surface correlates.

AI/ML arXiv cs.AI

Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph

Research demonstrating how applying graph algorithms to UMAP's internal kNN graph can enhance high-dimensional data sensemaking.