arXiv:2610.14659v1 Announce Type: new Abstract: Streaming speech assistants can launch tools before users finish speaking, overlapping execution with…
ABB Robotics Adds AI Robot Trainer to Fashion Inductor Module
ABB Robotics on October 15, 2026, launched what it describes as its first end-to-end vision-based industrial-grade physical AI solution, integrating AI…
Shaping Latent Mixture-of-Experts: From Expert Geometry to Layerwise Capacity Allocation
arXiv:2610.14644v1 Announce Type: new Abstract: Fine-grained mixture-of-experts (MoE) models commonly increase expert count by narrowing each expert,…
120ft Raises €576,000 to Build Humanoid Robot Microfactories for Local Manufacturing
A factory small enough to fit inside three shipping containers sounds like a logistics idea. For Stockholm startup 120ft, the harder problem is teaching…
From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement
arXiv:2610.14625v1 Announce Type: new Abstract: Recursive self-improvement (RSI) offers a route to AI systems that participate in their own continued…
Iterate on an LLM, Serve on an SLM
arXiv:2610.14576v1 Announce Type: new Abstract: As frontier LLMs gain more capabilities, the cost to run them also goes up. At the same time, small…
Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning
arXiv:2610.14605v1 Announce Type: new Abstract: Current evaluations of multimodal unlearning typically focus on whether a model stops outputting target…
PsyMemBehav: Psychology-Informed and Memory-Grounded Two-Level Identity-to-Action Reasoning for Social-Media Behavior Simulation
arXiv:2610.14570v1 Announce Type: new Abstract: Large language models (LLMs) support social simulation, but faithfully reproducing real users requires…
CB-Agent: Concept-Based In-Context Learning for Sequential Action Selection
arXiv:2610.14574v1 Announce Type: new Abstract: In-context learning (ICL) allows large language models to use demonstrations without updating their…
Learning after Execution with Action-Specific Credit
arXiv:2610.14573v1 Announce Type: new Abstract: Execution is often used as terminal feedback: it scores a generated program, but the resulting state is…
AI News Brief Hourly Summary 2026-10-15 09h : 13 posts
13 posts published in the last hour 06:32FDE-Bench: Evaluating End-to-End Delivery from Underspecified Real-World Business Requests 06:32Energy Ring: Stabilizing Feature Energy for Reliable Test-Time Discovery 06:32MontageFlow: Physically Valid High Fidelity EEG Generation 06:32ScienceBuddy-PV: A Verifier-Governed Recursive Improvement Protocol for Panvascular…
FDE-Bench: Evaluating End-to-End Delivery from Underspecified Real-World Business Requests
arXiv:2610.14539v1 Announce Type: new Abstract: Real-world business requests often leave key requirements unstated because frontline practitioners…
Energy Ring: Stabilizing Feature Energy for Reliable Test-Time Discovery
arXiv:2610.14525v1 Announce Type: new Abstract: Test-Time Discovery (TTD) aims to recognize known classes and detect novel ones while the model is already…
MontageFlow: Physically Valid High Fidelity EEG Generation
arXiv:2610.14507v1 Announce Type: new Abstract: Generative modeling offers a promising solution to the scarcity of labeled clinical electroencephalography…
ScienceBuddy-PV: A Verifier-Governed Recursive Improvement Protocol for Panvascular Intervention Research
arXiv:2610.14523v1 Announce Type: new Abstract: ScienceBuddy-PV adapts the ScienceBuddy recursive-in-recursive design to panvascular intervention research…
Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration
arXiv:2610.14542v1 Announce Type: new Abstract: Multimodal benchmarks are central to evaluating whether models can reason over information from multiple…
Reels-RSI: Program-Level Self-Improvement for Code-Rendered Explainer Videos
arXiv:2610.14495v1 Announce Type: new Abstract: Explainer videos — a worked geometry problem, why the sky is blue, how a dynasty fell — are usually one…
Frustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer Support
arXiv:2610.14428v1 Announce Type: new Abstract: Enterprise workflow automation typically requires retrieving a complete and accurate set of relevant…