Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG Paper • 2604.14572 • Published 3 days ago • 5
ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack Paper • 2509.25843 • Published 5 days ago • 18
IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures Paper • 2604.07709 • Published 5 days ago • 1
GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts Paper • 2604.12978 • Published 5 days ago • 5
Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness Paper • 2604.12373 • Published 5 days ago • 8
BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation Paper • 2604.09497 • Published 9 days ago • 28
TradingAgents: Multi-Agents LLM Financial Trading Framework Paper • 2412.20138 • Published Dec 28, 2024 • 47
Kronos: A Foundation Model for the Language of Financial Markets Paper • 2508.02739 • Published Aug 2, 2025 • 23
The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning Paper • 2604.06427 • Published 12 days ago • 11
view article Article How I contributed a new model to the Transformers library using Codex 20 days ago • 46
Reasoning Shift: How Context Silently Shortens LLM Reasoning Paper • 2604.01161 • Published 18 days ago • 31
view article Article Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand Dec 4, 2025 • 68
gpt-oss-safeguard Collection gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are safety reasoning models built-upon gpt-oss • 2 items • Updated Oct 29, 2025 • 67