[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.] #  @LiJunnan0409 Li Junnan Li Junnan posts on X about vision token, open ai, comet, knight the most. They currently have XXXXX followers and XX posts still getting attention that total XXXXX engagements in the last XX hours. ### Engagements: XXXXX [#](/creator/twitter::4716962310/interactions)  - X Week XXXXX +1,003% - X Month XXXXX -XX% - X Months XXXXXXX +1,140% - X Year XXXXXXX +223% ### Mentions: X [#](/creator/twitter::4716962310/posts_active)  - X Month X -XX% - X Months XX +900% - X Year XX +267% ### Followers: XXXXX [#](/creator/twitter::4716962310/followers)  - X Week XXXXX +1% - X Month XXXXX +4.40% - X Months XXXXX +20% - X Year XXXXX +28% ### CreatorRank: XXXXXXX [#](/creator/twitter::4716962310/influencer_rank)  ### Social Influence [#](/creator/twitter::4716962310/influence) --- **Social category influence** [cryptocurrencies](/list/cryptocurrencies) [technology brands](/list/technology-brands) **Social topic influence** [vision token](/topic/vision-token), [open ai](/topic/open-ai), [comet](/topic/comet), [knight](/topic/knight), [compact](/topic/compact) **Top assets mentioned** [Vision Token (VISION)](/topic/vision-token) ### Top Social Posts [#](/creator/twitter::4716962310/posts) --- Top posts by engagements in the last XX hours "1 vision token = XX text tokens is not something that can be concluded based on their experiments. XXX% text reconstruction does not imply that the vision tokens encode all textual information since the language decoder plays a big role. Need to remove the language prior to get a more accurate compression ratio. E.g. what if the image contains text in non-readable order" [X Link](https://x.com/LiJunnan0409/status/1980446374144667774) [@LiJunnan0409](/creator/x/LiJunnan0409) 2025-10-21T01:29Z 2777 followers, XXX engagements "Maybe ChatGPT Atlas should consider using our GTA1 grounder 😉" [X Link](https://x.com/LiJunnan0409/status/1980785983382765740) [@LiJunnan0409](/creator/x/LiJunnan0409) 2025-10-21T23:59Z 2777 followers, XXX engagements "There lacks evidence that pixel-based representations are more compact than representing language directly as text tokens. The saying An image is worth a thousand words actually implies that an image can be interpreted in countless ways most of which are irrelevant to language understanding. Even though a vision encoder can abstract away much of this irrelevant information it raises a question: why go through that detour when we can represent meaning directly with text tokens" [X Link](https://x.com/LiJunnan0409/status/1980788548375835071) [@LiJunnan0409](/creator/x/LiJunnan0409) 2025-10-22T00:09Z 2777 followers, 2299 engagements
[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
Li Junnan posts on X about vision token, open ai, comet, knight the most. They currently have XXXXX followers and XX posts still getting attention that total XXXXX engagements in the last XX hours.
Social category influence cryptocurrencies technology brands
Social topic influence vision token, open ai, comet, knight, compact
Top assets mentioned Vision Token (VISION)
Top posts by engagements in the last XX hours
"1 vision token = XX text tokens is not something that can be concluded based on their experiments. XXX% text reconstruction does not imply that the vision tokens encode all textual information since the language decoder plays a big role. Need to remove the language prior to get a more accurate compression ratio. E.g. what if the image contains text in non-readable order"
X Link @LiJunnan0409 2025-10-21T01:29Z 2777 followers, XXX engagements
"Maybe ChatGPT Atlas should consider using our GTA1 grounder 😉"
X Link @LiJunnan0409 2025-10-21T23:59Z 2777 followers, XXX engagements
"There lacks evidence that pixel-based representations are more compact than representing language directly as text tokens. The saying An image is worth a thousand words actually implies that an image can be interpreted in countless ways most of which are irrelevant to language understanding. Even though a vision encoder can abstract away much of this irrelevant information it raises a question: why go through that detour when we can represent meaning directly with text tokens"
X Link @LiJunnan0409 2025-10-22T00:09Z 2777 followers, 2299 engagements
/creator/x::LiJunnan0409