arXiv:2609.03654v1 Announce Type: cross Abstract: The comparative analysis of banks’ financial statements poses significant challenges for automated…
Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning
arXiv:2609.03667v1 Announce Type: cross Abstract: Generalising to unseen tasks remains a fundamental challenge in offline multi-agent reinforcement…
Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners
arXiv:2609.03660v1 Announce Type: cross Abstract: The dominance of Neural Networks (NNs) in RL is partially due to their incremental learning capability,…
Doesn’t Stop Reasoning: Analysis of Spurious CoT Termination
arXiv:2609.03633v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning improves large reasoning models (LRMs) on complex tasks but often…
AI News Brief Hourly Summary 2026-09-04 18h : 12 posts
12 posts published in the last hour 15:33Test-time adaptation for speech enhancement with an autoregressive speech prior 15:33EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders 15:33Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation…
Test-time adaptation for speech enhancement with an autoregressive speech prior
arXiv:2609.03622v1 Announce Type: cross Abstract: Test-time adaptation (TTA) offers a promising direction for improving speech enhancement models under…
EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders
arXiv:2609.03629v1 Announce Type: cross Abstract: Recent advances in text-to-video (T2V) diffusion models have demonstrated remarkable generative…
Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation
arXiv:2609.03619v1 Announce Type: cross Abstract: Multi-agent debate (MAD) improves the reasoning capabilities of large language models by having multiple…
FailBench: How Reliable are VLMs at Judging Robot Task Success?
arXiv:2609.03611v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly used to evaluate robot manipulation outcomes, but…
ToolDF: Tool-Integrated Reasoning for Mixed-Authenticity Audio Deepfake Detection
arXiv:2609.03620v1 Announce Type: cross Abstract: Audio deepfake detection is commonly formulated as clip-level binary classification of single-domain…
LevelSyn: Physical-Aware Logic Synthesis via Level-Asynchronous Graph Neural Networks
arXiv:2609.03594v1 Announce Type: cross Abstract: As integrated circuit technology scales into the nanometer regime, the traditional disconnect between…
Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning
arXiv:2609.03565v1 Announce Type: cross Abstract: Action-conditioned JEPA world models enable planning toward visually specified goals without…
How Far Can Synthetic Data Take Thai OCR?
arXiv:2609.03595v1 Announce Type: cross Abstract: We investigate what makes synthetic OCR supervision transfer to real Thai documents and use the…
On the Interaction Between Model Compression and Test-Time Adaptation
arXiv:2609.03604v1 Announce Type: cross Abstract: Deep neural networks deployed in the wild must be both efficient and adaptable, requiring model…
Google’s Gemini Spark can now manage your Google Photos library
Gemini Spark can edit and curate photo albums, create shared collections, turn photos into calendar events, and handle other Google Photos tasks for AI…
From Prior-Guided Heuristics to Deployable Agents: Accelerating Demonstration-Driven Reinforcement Learning for Deadline-Constrained Network Control
arXiv:2609.03590v1 Announce Type: cross Abstract: Timely delivery of delay-sensitive information over dynamic, heterogeneous networks is essential for…
AI News Brief Hourly Summary 2026-09-04 17h : 15 posts
15 posts published in the last hour 14:33LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL 14:33TruncGradGS: Improved 3D Gaussian Splatting via Truncated Gradient Updates 14:33WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval 14:33Deepseek plans the largest known Huawei chip…
LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL
arXiv:2609.03528v1 Announce Type: cross Abstract: Diffusion reinforcement learning (RL) has recently achieved significant success in post-training image…