Qwen3-8B

Named by 2 kept items in this workspace.

1 items name it under affected products and 1 under tools.

The items that name it 2

Protection Is Not One Event: A Survey of RAG Protection Research by Measured Endpoint
paperas affected products2026-10-21It is written here as Qwen3-8B: model used in the authors' controlled RAG testbed, where a three-query adaptive attacker recovered 48.3% of hidden facts.
DistillGuard: Malicious NPM Package Detection and API Attack Chain Analysis via Static Graph and LLM Distillation
paperas tools2026-09-24
open-source LLM fine-tuned via LoRA for offline malicious NPM package detection

In every workspace you can read 15

AI

Turing LLM Post-Training: Calibrated Distillation and Efficient Dynamic-MoE Execution
paper2026-10-29
EnvSched: Environment-Aware Scheduling for Rollout-Efficient Agent Reinforcement Learning
paper2026-10-27
Folding Attention Biases into Keys Makes Compacted KV Caches Run on Standard Kernels
paper2026-10-27
TriageRAG: Failure-Aware Self-Training for Adapting Retrieval-Augmented Language Models to Specialized Domains
paper2026-10-24
Training Small Language Models for Transferable Tool Selection
paper2026-10-22
Protection Is Not One Event: A Survey of RAG Protection Research by Measured Endpoint
paper2026-10-21
TorchNeuron: running HF models on AWS Trainium is easier than ever
article2026-10-19
Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models
paper2026-10-05
[AINews] not much happened today
article2026-10-03
NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents
paper2026-10-02
Open-sourcing AstaBrief, the fast report-generation model in Asta
article2026-10-02
[AINews] Opus 5.5 is good at explainer videos
article2026-09-29
whitecircle/halo
repo2026-08-26

Security

Protection Is Not One Event: A Survey of RAG Protection Research by Measured Endpoint
paper2026-10-21It is written here as Qwen3-8B: model used in the authors' controlled RAG testbed, where a three-query adaptive attacker recovered 48.3% of hidden facts.
DistillGuard: Malicious NPM Package Detection and API Attack Chain Analysis via Static Graph and LLM Distillation
paper2026-09-24

All technologies in this workspace.