arXiv:2610.07016v1 Announce Type: cross Abstract: In few-shot industrial anomaly detection, the few normal target images provide no direct defect…
CrystalJev: thinking fast and slow with atomistic foundation models for materials discovery
arXiv:2610.06985v1 Announce Type: cross Abstract: Atomistic foundation models triage millions of hypothetical materials but are used as slow simulators,…
Visual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs
arXiv:2610.06977v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples,…
TARE: Weigh a Never-Poisoned Twin Before Reading Backdoor-Defense Costs
arXiv:2610.06994v1 Announce Type: cross Abstract: Backdoor-defense leaderboards print a clean-accuracy drop and read it as removal cost. Measured on the…
Mask-Guided KV Cache Eviction in Block Diffusion Language Models
arXiv:2610.06996v1 Announce Type: cross Abstract: Block diffusion language models keep a large key-value (KV) cache throughout generation and attend to it…
Nvidia, Samsung back $90M round for AI agent startup Nous Research
Nous Research Inc., the developer of the popular Hermes artificial intelligence agent, today announced that it has raised $90 million in funding.…
DART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution Strategies
arXiv:2610.06993v1 Announce Type: cross Abstract: Evolution Strategies (ES) enable memory efficient full parameter fine-tuning of large language models…
AI News Brief Hourly Summary 2026-10-09 04h : 16 posts
16 posts published in the last hour 01:32AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD 01:32Verdicts Without Annotated Evidence: Rejection Sampling or Label-Only Post-Training for Evidence Recovery? 01:31Component and Dimension Sparsity in Transformer Refusal Mechanisms 01:31AudioShake Launches The Refinery to…
AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD
arXiv:2610.06927v1 Announce Type: cross Abstract: The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates…
Verdicts Without Annotated Evidence: Rejection Sampling or Label-Only Post-Training for Evidence Recovery?
arXiv:2610.06962v1 Announce Type: cross Abstract: In many review workflows the verdict is the only thing retained. The passages behind it are not marked,…
Component and Dimension Sparsity in Transformer Refusal Mechanisms
arXiv:2610.06903v1 Announce Type: cross Abstract: Activation steering manipulates large language model behavior by intervening on internal activations,…
AudioShake Launches The Refinery to Turn Overlapping Conversations Into AI Training Data
People interrupt. They laugh over someone else’s last sentence, offer a quick agreement before a speaker has finished, and keep talking while music or…
APEX: Active Protection at Execution Boundaries for LLM Agents
arXiv:2610.06966v2 Announce Type: cross Abstract: Indirect prompt injection (IPI) hides adversarial instructions in content that large language model…
Microsoft event debuts new AI-friendly hardware and Windows changes
Get ready for more AI in your Windows and more AI on the desktop.
Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering
arXiv:2610.06950v1 Announce Type: cross Abstract: Injecting skills into a frozen language model currently costs a million parameters and a…
Learning When to Refine: Long-Horizon Reinforcement Learning for Budgeted Neural-Operator PDE Solvers
arXiv:2610.06883v1 Announce Type: cross Abstract: Neural operators provide fast surrogates for time-dependent PDEs, but autoregressive deployment creates…
Comparative review of hybrid forecasting models for short-term prediction of building thermal load
arXiv:2610.06881v2 Announce Type: cross Abstract: In this paper, a comparative review of different hybrid models for short-term forecasting of building…
Lava Finds Thousands of Exposed GPU Servers and a High-Severity NVIDIA Monitoring Flaw
The infrastructure behind an AI model can reveal a surprising amount before anyone breaks into it. A public monitoring endpoint may disclose the GPUs in a…