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.
| Repository | Role | Ran |
|---|---|---|
| dvlab-research/llama-vid | canonical | 3 of 4 |
| Function | Status | Where 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") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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
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.