arXiv:2511.04707v2 Announce Type: replace-cross Abstract: Recent advances in long-context language models (LMs) have enabled million-token inputs,…
Sleeping Kelly
arXiv:2510.15911v4 Announce Type: replace-cross Abstract: The Sleeping Beauty problem is a problem of imperfect recall that has received considerable…
D$^2$ACCI: A Dual-Loop Diagnostic Protocol for Evidence-Preserving Agent Memory
arXiv:2608.17756v2 Announce Type: replace Abstract: Memory is a key capability of LLM agents. Persistent memory extends this across sessions—enabling…
`From Prompt to Perturbation’: An Adaptive Framework for Voice-Based Jailbreaks on Audio LLMs
arXiv:2502.00735v4 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly integrated into audio-based applications,…
Accuracy and Robustness of Model Cascades Under Data Perturbations
arXiv:2608.17711v2 Announce Type: replace Abstract: Prediction cascades significantly reduce energy consumption of Artificial Intelligence (AI) models…
The Curious Case of Exploding DecPOMDPs: Containing the Fire through Policy Counting
arXiv:2608.17749v2 Announce Type: replace Abstract: Decentralised partially observable Markov decision processes (DecPOMDPs) provide a general framework…
Automated Computational Energy Minimization of ML Algorithms using Constrained Bayesian Optimization
arXiv:2407.05788v2 Announce Type: replace-cross Abstract: Bayesian optimization (BO) is an efficient framework for optimization of black-box objectives…
AI News Brief Hourly Summary 2026-08-21 03h : 13 posts
13 posts published in the last hour 00:32VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End? 00:32Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence 00:32S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices 00:32Reconstruction: A…
VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?
arXiv:2608.15265v2 Announce Type: replace Abstract: Constructing an interactive 3D open world from a user query is important. However, existing methods…
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
arXiv:2608.12036v2 Announce Type: replace Abstract: AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their…
S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices
arXiv:2608.15018v2 Announce Type: replace Abstract: Deploying large language models (LLMs) for inference on edge devices is challenging due to severe…
Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies
arXiv:2608.16645v2 Announce Type: replace Abstract: Can a language model recover the true research idea of a published paper when given only that paper’s…
AI data startup Micro1 reaches $500M gross run rate amid AI training boom
Surging demand for AI training data is driving rapid growth for the startup and its rivals.
GRIP: Grounded Reasoning via Information-Restricted Premises
arXiv:2608.16776v2 Announce Type: replace Abstract: High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent…
Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks
arXiv:2608.03502v2 Announce Type: replace Abstract: Large Language Models (LLMs) have recently shown strong capabilities in reasoning, planning, and…
Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations
arXiv:2607.20379v2 Announce Type: replace Abstract: Natural-language autoencoders score explanations of hidden activations by reconstruction. An…
Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting
arXiv:2607.26643v2 Announce Type: replace Abstract: Enabling large language model (LLM) agents to accumulate and reuse experience from past interactions…
BrainBench: Benchmarking Large Language Models for Comprehensive EEG Understanding
arXiv:2608.04156v2 Announce Type: replace Abstract: Electroencephalography (EEG) analysis extends beyond assigning predefined labels to recordings; it…