SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.17043 · 2023

LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 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
dvlab-research/llama-vid canonical 3 of 4
FunctionStatusWhere it lives
get_chunk Ran dvlab-research/llama-vid/llamavid/eval/model_activitynet_qa.py
code served (permissive licence) · get_code("42a46570620cd9fa")
is_none Ran dvlab-research/llama-vid/llamavid/eval/model_vqa_mmbench.py
code served (permissive licence) · get_code("bae18947b56f2be1")
split_list Ran dvlab-research/llama-vid/llamavid/eval/model_activitynet_qa.py
code served (permissive licence) · get_code("076c252c52cbb161")
apply_rotary_pos_emb_inference Not yet run dvlab-research/llama-vid/llamavid/train/llama_flash_attn_monkey_patch.py
code served (permissive licence) · get_code("d367874245639411")

Repositories linked to this paper

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

Abstract

In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. Current VLMs, while proficient in tasks like image captioning and visual question answering, face computational burdens when processing long videos due to the excessive visual tokens. LLaMA-VID addresses this issue by representing each frame with two distinct tokens, namely context token and content token. The context token encodes the overall image context based on user input, whereas the content token encapsulates visual cues in each frame. This dual-token strategy significantly reduces the overload of long videos while preserving critical information. Generally, LLaMA-VID empowers existing frameworks to support hour-long videos and pushes their upper limit with an extra context token. It is proved to surpass previous methods on most of video- or image-based benchmarks. Code is available https://github.com/dvlab-research/LLaMA-VID}{https://github.com/dvlab-research/LLaMA-VID

For agents

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

get_harvested_code_for_paper("2311.17043")
get_code_for_paper("2311.17043")
have("2311.17043")

Connect an agent — have() is free.