arXiv ·
ToMStories: Interpreting Theory-of-Mind in Synthetic Narratives
Public paper from arXiv. Open the source to read the full record.
Home / Browse
Models & research
Examine models, papers and evaluations with their methods and limitations.
802 public stories
arXiv ·
Measuring Mechanistic Uncertainty in Large Language Models via Causal Robustness
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Inductive Learning of Concept Embeddings from Cross-Linguistic Colexification Patterns with Textual Attributes
Public paper from arXiv. Open the source to read the full record.
arXiv ·
SAFETYEDIT: Sparse Internal Targets with Prompt-Wide Control for LLM Jailbreak Backdoors
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Evidence-Gated Bilingual RAG for Reliable Consumer Banking Search
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Secondhand Stress: How Stressful Disclosures Affect Psychosocial Wellbeing in Online Graduate Admissions Communities
Public paper from arXiv. Open the source to read the full record.
arXiv ·
ProPerAgent: Toward Memory-Driven Proactive Assistance
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Multimodal Filesystem Memory For Long-Horizon Embodied Agents
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Explore Separately, Adopt Selectively: Execution-Guided Tool Use over Large Tool Libraries
Public paper from arXiv. Open the source to read the full record.
arXiv ·
First Passage Attention
Public paper from arXiv. Open the source to read the full record.
V2EX ·
[程序员] DeepSeek-V4.1-Flash-1017 发布了，今晚我让它通宵写代码（Day 4）
Public article from V2EX. Open the source to read the full record.
Hacker News ·
Assessing AI agents at autonomous theoretical physics problem solving
Hacker News recorded 1 points and 0 comments as of Oct 18, 2026 (UTC).
量子位 ·
端侧跑通超千亿大模型！联想YOGA Pro 15 RTX Spark超级AIPC今日正式发售
Public article from 量子位. Open the source to read the full record.
TechCrunch ·
Even Benchmark thinks AI is eroding the venture pact against backing rivals
Public article from TechCrunch. Open the source to read the full record.
Hugging Face ·
Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline
Public article from Hugging Face. Open the source to read the full record.
Hacker News ·
A Better Benchmark Harness for SRE Agents
Hacker News recorded 1 points and 0 comments as of Oct 16, 2026 (UTC).
Hacker News ·
Into the Unknown: Benchmarking AI agents on open scientific research problems
Hacker News recorded 1 points and 0 comments as of Oct 16, 2026 (UTC).
TechCrunch ·
Meta launches an open-weight AI model that runs on Macs
Public article from TechCrunch. Open the source to read the full record.
Hacker News ·
TheoPhysEval: Assessing AI agents at autonomous theoretical physics solving
Hacker News recorded 1 points and 0 comments as of Oct 15, 2026 (UTC).
量子位 ·
库克：苹果智能接入阿里千问大模型，10月底在中国发布测试版本
Public article from 量子位. Open the source to read the full record.
Hugging Face ·
Apertus 1.5 Release Notes
Public article from Hugging Face. Open the source to read the full record.
Hacker News ·
Forensic Analysis of RL/RLHF-Induced Privilege Escalation in AI Agents
Hacker News recorded 1 points and 0 comments as of Oct 15, 2026 (UTC).
量子位 ·
前华为小艺大模型负责人创业，押注“主动式物理AI”
Public article from 量子位. Open the source to read the full record.
arXiv ·
Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Evaluating Large Language Models for Multilingual Abstractive Summarization: A Comprehensive Study of English and Bengali
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Can LLMs Access their World Knowledge for Event Prediction?
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Joint Subspace Sparse Attention for Efficient Long-Context Decoding
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Crossing the Gender Binary: Modelling Gendered Reference in Science Fiction and General Fiction
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Pre-Trained Language Models as Zero-Shot Tools for Social Science Research
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena
Public paper from arXiv. Open the source to read the full record.