SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.11499 · ICLR · 2024

DreamLLM: Synergistic Multimodal Comprehension and Creation

Liang Zhao, Xiangyu Zhang, Li, Jinrong Yang, Runpei Dong, Kaisheng Ma, Zekun Qi, Jianjian Sun, Zheng Ge, Xiangwen Kong, Chunrui Han, Yuang Peng, and 2 more

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
RunpeiDong/DreamLLM canonical 1 of 1
copy not recorded — 2 of 2
FunctionStatusWhere it lives
repeat_kv Ran this paper's copy was not recorded; identical code first harvested from fe1ixxu/ALMA
pointer only · get_code("30d7eec482ebf6b1")
apply_rotary_pos_emb Ran RunpeiDong/DreamLLM/omni/models/dreamllm/modeling_dreamllm.py
code served (permissive licence) · get_code("d61c483a3c2b3156")
rotate_half Ran this paper's copy was not recorded; identical code first harvested from fe1ixxu/ALMA
pointer only · get_code("b99eea6376d1e212")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper presents DREAMLLM, a learning framework that first achieves versatile Multimodal Large Language Models (MLLMs) empowered with frequently overlooked synergy between multimodal comprehension and creation. DREAMLLM operates on two fundamental principles. The first focuses on the generative modeling of both language and image posteriors by direct sampling in the raw multimodal space. This approach circumvents the limitations and information loss inherent to external feature extractors like CLIP, and a more thorough multimodal understanding is obtained. Second, DREAMLLM fosters the generation of raw, interleaved documents, modeling both text and image contents, along with unstructured layouts. This allows DREAMLLM to learn all conditional, marginal, and joint multimodal distributions effectively. As a result, DREAMLLM is the first MLLM capable of generating free-form interleaved content. Comprehensive experiments highlight DREAMLLM's superior performance as a zero-shot multimodal generalist, reaping from the enhanced learning synergy. Project page: dreamllm.github.io. "What I cannot create, I do not understand." Richard P. Feynman, on his blackboard at the time of his death, 1988

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2309.11499")
get_code_for_paper("2309.11499")
have("2309.11499")

Connect an agent — have() is free.