arXiv:2609.38672v1 Announce Type: cross Abstract: Beam-search-based test-time methods provide an effective way to improve large language model (LLM)…
AI News Brief Hourly Summary 2026-10-02 03h : 18 posts
18 posts published in the last hour 00:31TERRA: Terrain-Aware Reconstruction, Retargeting and Control for Musculoskeletal Locomotion 00:31Differentiable Structure Learning for Cyclic Linear Gaussian Models with Latent Confounders 00:31Meta expands Muse to small businesses 00:31Interpretable but Fragile? Robustness of Concept Bottlenecks…
TERRA: Terrain-Aware Reconstruction, Retargeting and Control for Musculoskeletal Locomotion
arXiv:2609.38653v1 Announce Type: cross Abstract: Recent advances in musculoskeletal modeling and reinforcement learning have enabled muscle-actuated…
Differentiable Structure Learning for Cyclic Linear Gaussian Models with Latent Confounders
arXiv:2609.38618v1 Announce Type: cross Abstract: We study causal structure learning from observational data in linear Gaussian structural causal models…
Meta expands Muse to small businesses
The move comes as agentic AI plays an increasingly big part in business operations, sparking oversight concerns.
Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations
arXiv:2609.38625v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) are designed to provide interpretable intermediate representations, yet…
Meta disputes claim that Muse read a user’s private messages without permission
Meta says its Muse AI agent cannot access a user’s Messages without explicit permission, disputing a journalist’s account that the agent read his private…
Alignment via Training Against Probes Without Losing Monitorability
arXiv:2609.38645v1 Announce Type: cross Abstract: Models are usually aligned based on their observed outputs, using demonstrations, preference data, or…
Academia is for Ambition — Alex Zhang, MIT
We catch up with RLM first author Alex Zhang, MIT PhD, on Jev, PhD masxing, and the future of harnesses.
Template-Search Domain Adaptation via Multi-Stage Feature Alignment for Cross-Modal Object Tracking
arXiv:2609.38637v1 Announce Type: cross Abstract: Visual object tracking typically assumes that the initial template and subsequent search frames share…
FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing
arXiv:2609.38585v1 Announce Type: cross Abstract: Existing Large Language Model (LLM) routing methods score LLMs independently to select top-$k$ models.…
DoorDash launches an AI agent you can text to order food
By launching an AI agent for food ordering, DoorDash is looking to gain an edge over rivals Uber Eats and Grubhub.
Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions
arXiv:2609.38593v1 Announce Type: cross Abstract: Skills are external artifacts that Large Language Models (LLMs) consume at inference time to improve…
Forecasting space weather risks on power grids
Extreme space-weather events can damage power systems on Earth and degrade GPS accuracy and satellite operations. A new machine learning system can…
Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent
arXiv:2609.38604v1 Announce Type: cross Abstract: Modern LLM agents increasingly tackle complex tasks through interactive, long-horizon exchanges with…
Helping small businesses put AI to work
OpenAI is partnering with America’s SBDC to expand hands-on AI training and local support for small businesses, alongside a new report on how small teams…
Exo2EgoHOI: Hand-Object-Interaction Aware Exocentric-to-Egocentric Video Generation
arXiv:2609.38615v1 Announce Type: cross Abstract: Egocentric videos of human manipulation provide valuable visual experience for embodied intelligence,…
Query claims in natural language with Amazon Bedrock Knowledge Bases
This technical how-to builds a conversational claims assistant on Amazon Bedrock Knowledge Bases that answers natural-language questions with citations.…