arXiv:2609.16215v1 Announce Type: new Abstract: GPU high bandwidth memory is scarce and expensive, and KV caches consume much of it as chats, agent loops,…
Safe Error Correction for Language Models: Frozen-Base Adjustment with Capability Preservation
arXiv:2609.16145v1 Announce Type: new Abstract: We study a practical question: can a small correction module fix errors in a frozen language model’s…
GPEvac: GNN-Based PPO for Adaptive Evacuation Routing During Shooting Events
arXiv:2609.16163v1 Announce Type: new Abstract: The sharp increase in mass shootings underscores an urgent need for systems that guide victims to safety…
Calibrate, Then Route: A Measured Study of Learned Request Routing for Disaggregated LLM Serving
arXiv:2609.16206v1 Announce Type: new Abstract: Disaggregated LLM serving places compute heavy prefill and memory heavy decode on separate GPU pools.…
Optimal Pruning for Neural Architectures using Fisher Information Distances
arXiv:2609.16129v1 Announce Type: new Abstract: A new scheme for parameter pruning is introduced, derived from the differential-geometric distance in…
Position: AI Is Not Ready for Strategic Conflicts
arXiv:2609.16189v1 Announce Type: new Abstract: Open-ended strategic wargames are high-stakes LM-based social simulations: they model adversaries,…
AI News Brief Hourly Summary 2026-09-16 06h : 11 posts
11 posts published in the last hour 03:32RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes 03:32A Voxel-Spacing-Aware Extension of PyRadiomics for Anisotropic Texture Analysis 03:32LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models 03:32Real-Time Synthesis of Robust…
RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes
arXiv:2609.14100v1 Announce Type: cross Abstract: Fashion Image Captioning (FIC) plays a vital role in enhancing user experience and product search in…
A Voxel-Spacing-Aware Extension of PyRadiomics for Anisotropic Texture Analysis
arXiv:2609.14103v1 Announce Type: cross Abstract: Radiomic texture features are commonly extracted from anisotropic CT and MRI acquisitions, where…
LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models
arXiv:2609.14073v1 Announce Type: cross Abstract: Counterfactual world models (CWM) extract motion from pretrained video predictors by comparing factual…
Real-Time Synthesis of Robust Controlled Invariant Sets for Monotone Systems
arXiv:2609.14115v1 Announce Type: cross Abstract: Safety-critical control of autonomous systems requires formal safety certificates, such as controlled…
GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning
arXiv:2609.14066v1 Announce Type: cross Abstract: Although existing multi-agent Retrieval-Augmented Generation (RAG) systems have demonstrated promise on…
Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot Collaboration
arXiv:2609.13982v1 Announce Type: cross Abstract: In Human-Robot Interaction, the standard approach to learn a reward model that represents human…
Mizan: A National Benchmark for Evaluating Large Language Models on Iraqi Arabic and the Iraqi Civic Context
arXiv:2609.13980v1 Announce Type: cross Abstract: Arabic large-language-model (LLM) evaluation has matured around Modern Standard Arabic (MSA): aggregated…
SGWIB:Sliced Gromov-Wasserstein Information Bottleneck for Video Highlight Detection
arXiv:2609.13966v1 Announce Type: cross Abstract: Video highlight detection aims to identify temporally important segments that capture the most…
AGENTQ: Quantization-Conditioned Backdoor Attacks on LLM Agents
arXiv:2609.14060v1 Announce Type: cross Abstract: Quantization is one of the default deployment paths for open-weight LLM agents, but it is not…
Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control
arXiv:2609.14003v1 Announce Type: cross Abstract: Personal AI agents built on large language models (LLMs) are increasingly given access to a user’s…
AI News Brief Hourly Summary 2026-09-16 05h : 11 posts
11 posts published in the last hour 02:32Thought without systematicity? Evaluating reasoning models on rule induction tasks 02:32DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech Synthesis 02:32Finite-Time Node Separation in Recurrent Graph Neural Networks with Persistent Gaussian Perturbations 02:32CRITICS –…