arXiv:2610.07032v1 Announce Type: cross Abstract: Large-scale pretrained transformer models have achieved state-of-the-art performance across diverse…
TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning
arXiv:2610.07043v1 Announce Type: cross Abstract: Low-precision execution can substantially accelerate reinforcement learning (RL) for large language…
An Empirical Fault Vulnerability Exploration of ReRAM-based Process-in-Memory CNN Accelerators
arXiv:2610.07029v1 Announce Type: cross Abstract: Resistive random-access memory (ReRAM)-based Processing-in-Memory (PIM) accelerator is a promising…
Learning to Simulate Individuals from Macro Social Signals
arXiv:2610.07062v1 Announce Type: cross Abstract: Large language models are increasingly used to simulate how individuals respond to new situations, yet…
AI News Brief Hourly Summary 2026-10-08 01h : 14 posts
14 posts published in the last hour 22:32TARE: Weigh a Never-Poisoned Twin Before Reading Backdoor-Defense Costs 22:32DART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution Strategies 22:32Mask-Guided KV Cache Eviction in Block Diffusion Language Models 22:32Where Does the…
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…
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…
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…
Where Does the Audio Jailbreak Live? A Controlled Frequency-Depth Audit of AdvWave-P on Qwen2-Audio
arXiv:2610.07005v1 Announce Type: cross Abstract: We audit frequency and decoder-depth claims for AdvWave-P, an additive audio jailbreak, on Qwen2-Audio.…
Anthropic releases Claude Haiku 5.5 small model and halves Sonnet 5.5 cache read prices
Anthropic PBC today released Claude Haiku 5.5, pricing its newest small model at roughly a quarter of what Haiku 4.5 costs to run. Claude Sonnet 5.5 is…
Which Image Property Carries the Jailbreak? A Controlled Dissection of Image-to-Text Jailbreaks
arXiv:2610.07009v1 Announce Type: cross Abstract: Image-to-text jailbreaks place harmful intent in text, image content, or the relationship between them.…
APEX: Active Protection at Execution Boundaries for LLM Agents
arXiv:2610.06966v1 Announce Type: cross Abstract: Indirect prompt injection (IPI) hides adversarial instructions in content that large language model…
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,…
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…
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,…
“Software is over”: Bold AI developer takes aim at Adobe with open source clones
Opus-built Creative Cloud alternatives are ambitious, free, and nowhere near finished.
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,…
AI News Brief Hourly Summary 2026-10-08 00h : 17 posts
17 posts published in the last hour 21:59AI News Brief Daily Summary 2026-10-07 21:31Dynamical low-rank equilibrium computation for stochastic games between advanced persistent threats and moving target defense 21:31Zero-Shot Visualization: Exploring Text Corpora with User-Prompted Axes 21:31Axiom Satisfiability of Linear…