Skip to content
Papers.

Training Object Permanence in World Models research paper by Carnegie Mellon University, 2026

Carnegie Mellon University · Sep 23, 2026 · Training and scaling · 209 upvotes · unverified 5 days ago

Read on arXiv

What it shows

Object permanence and solidity are hallmarks of human cognitive priors.

UnverifiedHugging Face's summary; not yet checked by hand.

More from Carnegie Mellon University

All 5
PaperCitations
JEV-as-a-Judge: Accept When Confident, Escalate When UnsureLLM-as-a-judge enables evaluation across diverse tasks, but inference cost and confidence reliability become critical at scale.Agents and evaluation · Sep 2026 · Unverified6 days ago2
Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and EvaluationBenchmark Radar is a searchable living database and discovery engine for AI evaluation benchmarks that aggregates sources, score histories, and evidence to support benchmark selection and comparison.Agents and evaluation · Sep 2026 · Unverified2 weeks ago0
K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean ContextsKorean web-browsing agent benchmark K-BrowseComp evaluates frontier LLMs' capabilities with 400 problems, showing significant performance gaps compared to English benchmarks and highlighting the need for more robust Korean AI development.Agents and evaluation · Jun 2026 · Unverified3 months ago2
Mamba: Linear-Time Sequence Modeling with Selective State SpacesA selective state space model that scales linearly with sequence length and matches Transformers on language.Architectures · Dec 20232 years ago9,252

Other training and scaling papers

Topic
PaperCitations
LoRA: Low-Rank Adaptation of Large Language ModelsLoRA fine-tunes a large model by training small low-rank matrices, cutting trainable parameters by 10,000 times.Microsoft · Jun 20215 years ago23.3k
Scaling Laws for Neural Language ModelsLanguage model loss falls as a smooth power law as model size, data and compute grow.OpenAI · Jan 20206 years ago9,085
Training Compute-Optimal Large Language ModelsChinchilla: for a fixed compute budget, train a smaller model on more data; parameters and tokens should grow together.Google DeepMind · Mar 20224 years ago3,756
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model ParallelismMegatron-LM splits each Transformer layer across GPUs to train models with billions of parameters.NVIDIA · Sep 20197 years ago3,187
DeepSeek LLM: Scaling Open-Source Language Models with LongtermismDeepSeek LLM, an open-source language model project, develops a large dataset and employs SFT and DPO to achieve performance surpassing LLaMA-2 70B and GPT-3.5 in various benchmarks and open-ended evaluations.DeepSeek · Jan 2024 · Unverified2 years ago855
LoRA Learns Less and Forgets LessLoRA learns less than full fine-tuning on code and math, but forgets less of what the model already knew.Databricks · May 20242 years ago409
About this paper
Authors
Haotian Zhang, Fengyuan Yu, Dezhi Luo and 28 more
arXiv
2609.28654 · PDF
Citations
Not counted yet · Semantic Scholar
Upvotes
209 · Hugging Face
Code
github.com/hokindeng/object-permanence
Lab
Carnegie Mellon University

Changes

What changed
Upvotes208 to 209 (+1)Sep 28, 2026today
New paperFound by the weekly scan, unverifiedSep 28, 2026today

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.