arXiv:2608.28980v1 Announce Type: cross Abstract: Can the specialized architectures that machine learning has traditionally built for structured data be…
A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability
arXiv:2608.29034v1 Announce Type: cross Abstract: A wide range of methods have been proposed for interpreting language models, delivering important…
DocIntent: Answerability-Guided Agentic Restoration for Real-World Document Visual Question Answering
arXiv:2608.29037v1 Announce Type: cross Abstract: Real-world degradations such as blur, shadow, distortion, and moire patterns severely impair the…
AI News Brief Hourly Summary 2026-09-02 05h : 11 posts
11 posts published in the last hour 02:32The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice 02:32Free Speech and Artificial Intelligence 02:32The information geometry of product-reference discrete diffusion: Interaction growth complexity and optimal scheduling 02:32From the Loss Landscape…
The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice
arXiv:2608.28930v1 Announce Type: cross Abstract: Hidden-state probes effectively detect LLM hallucinations, but the geometry of the signal remains poorly…
Free Speech and Artificial Intelligence
arXiv:2608.28973v1 Announce Type: cross Abstract: Philosophers and legal scholars are engaged in debates about the implications of artificial intelligence…
The information geometry of product-reference discrete diffusion: Interaction growth complexity and optimal scheduling
arXiv:2608.28949v1 Announce Type: cross Abstract: We study a class of product-reference diffusion algorithms for sampling from a discrete distribution. We…
From the Loss Landscape to Diverse Feature Learning in Neural Networks
arXiv:2608.28948v1 Announce Type: cross Abstract: Over the course of the last decade, neural networks have grown from an academic curiosity to moving the…
Diagnose, Then Refine: A Closed-Loop TTS System with AudioLLM-Guided Correction
arXiv:2608.28970v1 Announce Type: cross Abstract: Current TTS systems typically rely on open-loop, single-pass generation and can produce sporadic local…
Structured State Reconciliation for Human-AI Task Handover
arXiv:2608.28907v1 Announce Type: cross Abstract: Task handover requires communicating enough current state for a successor to resume work, yet the…
Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management
arXiv:2608.28878v1 Announce Type: cross Abstract: This paper develops a hybrid offline-online multi-agent reinforcement learning framework based on…
Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions and Weight Consolidation Buy in Open-Ended Generation
arXiv:2608.28886v1 Announce Type: cross Abstract: What does a generation loop gain from learning on its own verified successes? In cycles of generate,…
No Detectable Change in Side-Level WER from Prompt-Level Context: A Preregistered Ablation on a Production Oral-History Corpus
arXiv:2608.28875v1 Announce Type: cross Abstract: Supplying context at inference time to a large multimodal model is an inexpensive lever for adapting…
ActiveAugment: Online Active Learning for Augmentation Selection in Deep Learning
arXiv:2608.28923v1 Announce Type: cross Abstract: Data augmentation is a cornerstone of deep learning pipelines, yet existing strategies treat it as a…
AI News Brief Hourly Summary 2026-09-02 04h : 12 posts
12 posts published in the last hour 01:32The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning 01:32Toward Postural State Classification in Immersive VR with Multimodal Data and Explainability Analysis 01:32Curvature Cryptanalysis of Smooth Transformer Feed-Forward Networks 01:32A rigor-matched…
The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning
arXiv:2608.28859v1 Announce Type: cross Abstract: Reasoning models do not stop when they know the answer. On DeepSeek-R1-Distill-Qwen-7B the chain of…
Toward Postural State Classification in Immersive VR with Multimodal Data and Explainability Analysis
arXiv:2608.28844v1 Announce Type: cross Abstract: Ensuring a safe virtual reality (VR) experience requires systems that can predict and respond when users…
Curvature Cryptanalysis of Smooth Transformer Feed-Forward Networks
arXiv:2608.28843v1 Announce Type: cross Abstract: We show that smooth two-layer feed-forward networks (FFNs) expose an additional structural model…