arXiv:2609.27165v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to measure public value orientations from long social…
Author: script
When Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defense
arXiv:2609.27124v1 Announce Type: cross Abstract: Federated Learning enables decentralized model training by exchanging model updates–rather than raw…
The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems
arXiv:2609.27155v1 Announce Type: cross Abstract: With recent advancements in large language models (LLMs) and LLM-based agents, these agents are becoming…
The Linear Representation Hypothesis Needs a Group Action
arXiv:2609.27158v1 Announce Type: cross Abstract: To make claims about representations that generalize beyond a particular trained model, we need to…
Australia to investigate if OpenAI hack of government health website broke the law
The incident is the first known breach to affect a government agency, and Australia’s prime minister has vowed to hold OpenAI accountable.
A Hierarchy-Aware Video-Language Model Evaluation and Hyperbolic Baseline for Surgery
arXiv:2609.27139v1 Announce Type: cross Abstract: Surgical procedures follow a phase-to-step hierarchy, yet the video-language models used to recognize…
AI News Brief Hourly Summary 2026-09-24 15h : 12 posts
12 posts published in the last hour 12:35Intelligence Across Embodiments 12:35Crossflow: Prefill-Decode Elasticity for Agentic LLM Serving 12:34The Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models 12:34EMA: Elastic and Performance Transparent Memory Across GPUs 12:34Local…
Intelligence Across Embodiments
arXiv:2609.27095v1 Announce Type: cross Abstract: Robotic embodiment encompasses the sensing, kinematics, dynamics, geometry, actuation, and control…
Crossflow: Prefill-Decode Elasticity for Agentic LLM Serving
arXiv:2609.27085v1 Announce Type: cross Abstract: As serving capacity demand surpasses that of training, serving efficiency becomes increasingly…
The Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models
arXiv:2609.27070v1 Announce Type: cross Abstract: Modern robot imitation learning increasingly relies on generative policies based on diffusion or…