AI/ML arXiv cs.AI

Enhancing Fatigue Detection through Heterogeneous Multi-Source Data Integration and Cross-Domain Modality Imputation

A framework for fatigue detection in human operators using heterogeneous multi-source data and cross-domain modality imputation to handle real-world noise.

AI/ML arXiv cs.AI

When Cars Have Stereotypes: Auditing Demographic Bias in Objects from Text-to-Image Models

SODA framework introduced to audit demographic biases in objects generated by text-to-image models, revealing strong implicit stereotypes.

AI/ML arXiv cs.AI

"Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms

Researchers introduce 'Did-You-Lie' (DYL), a new method and testbed to evaluate the effectiveness of lie detectors in language models across various scales.

AI/ML arXiv cs.AI

Simple Domain Generalization Methods are Strong Baselines for Open Domain Generalization

A study demonstrates that simple domain generalization methods like CORAL and MMD serve as strong and computationally efficient baselines for open domain generalization.

AI/ML arXiv cs.AI

A DeepLearning Framework for Dynamic Estimation of Origin-Destination Sequence

A new deep learning framework is proposed to dynamically estimate origin-destination sequences in transportation, improving on traditional numerical optimization.

AI/ML arXiv cs.AI

Quality Perceptions and Intended Engagement in Response to AI-Generated and AI-Assisted News

A survey in Switzerland found that readers perceive AI-generated and human-written news similarly in quality, though disclosure of AI can increase initial curiosity.

AI/ML arXiv cs.AI

Scalable Batch Bayesian Optimization Via Subspace Acquisition Functions

Researchers propose a scalable batch Bayesian optimization approach using subspace acquisition functions to improve convergence speed in parallel computing.

AI/ML arXiv cs.AI

VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation

VidCRAFT3 is introduced as a unified framework for image-to-video generation with precise, coupled control over camera motion, object motion, and lighting.

AI/ML arXiv cs.AI

Efficient Zeroth-Order Federated Finetuning of Language Models on Resource-Constrained Devices

A new zeroth-order optimization method is proposed for efficient federated finetuning of LLMs on resource-constrained edge devices, reducing computation by up to 3x.

AI/ML arXiv cs.AI

Depth-Width tradeoffs in Algorithmic Reasoning of Graph Tasks with Transformers

Research reveals a depth-width tradeoff in Transformers for graph tasks, showing that increasing width can allow for shallower, faster models.

AI/ML arXiv cs.AI

Generalized Kullback-Leibler Divergence Loss

The Generalized Kullback-Leibler (GKL) Divergence loss is introduced to improve adversarial robustness and knowledge distillation in vision-language models.

Cybersecurity arXiv cs.AI

Revealing Hidden Vulnerabilities in Autoencoders through Gradient Signal Restoration

The GRILL framework is introduced to expose hidden vulnerabilities in autoencoders by restoring gradient signals in ill-conditioned layers during adversarial attacks.

AI/ML Hacker News

GLM-5.2: The Most Powerful Open Model yet and the Brutal Reality of Running It

Discussion on GLM-5.2, a powerful open-source model, and the high hardware requirements for running it locally.

Software Engineering Hacker News

To study how chips work, MIT researchers built their own operating system

MIT researchers created a custom operating system specifically designed to study the internal workings of computer chips.

Open Source Hacker News

Show HN: Talos – Open-source WASM interpreter for Lean

Talos is an open-source WebAssembly (WASM) interpreter specifically developed for the Lean theorem prover.

Homelab/Self-Hosting Hacker News

Building a robotics research setup that lives next to my desk

A developer shares their experience building a personalized robotics research setup for home use.

AI/ML arXiv cs.AI

Notation Matters: A Benchmark Study of Token-Optimized Formats in Agentic AI Systems

A benchmark study comparing token-optimized formats like TOON and TRON against JSON for structured data exchange in agentic AI systems.

Tech Business/VC arXiv cs.AI

AI Sovereignty as National Learning Capacity: A Human-Centered Learning Mechanics Viewpoint on France, the United States, and China

A viewpoint paper framing national AI sovereignty through the lens of Human-Centered Learning Mechanics (HCLM), specifically analyzing France.

AI/ML arXiv cs.AI

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

SkillRevise is an execution-grounded framework that iteratively refines LLM-authored agent skills to improve task success rates.

AI/ML arXiv cs.AI

DN-Hypo-Pipeline: An AI-Driven Workflow for Hypothesis Generation via Large Language Models and Scientific Explanations

DN-Hypo-Pipeline is an AI-driven workflow that uses LLMs and scientific explanations to generate novel research hypotheses.