ddvd233 Profile Banner
dvd@dvd.chat Profile
Followers
19K
Following
104K
Media
7K
Statuses
51K

Student @MIT Media Lab | Multimodal LLMs | MS in Computer Science @Stanford, RA at @StanfordSVL supervised by @drfeifei | 艾默里归宅部荣誉部员|日本語本当下手

Palo Alto, CA
Joined October 2015
Don't wanna be here? Send us removal request.
#NewProfilePic 感觉差不多是时候把圣诞节头像换下来了(然后换上了春节图)
Tweet media one
19
2
118
突然意识到 thunderbolt (雷电)和 lightning (闪电)不是一个东西(
Tweet media one
20
2
133
DnD!.
@_akhaliq
AK
12 days
Drag-and-Drop LLMs. Zero-Shot Prompt-to-Weights
4
1
14
可以写 community notes 了(大概
Tweet media one
1
0
33
Google and Tsinghua have the most papers lol.
@papercopilot
Paper Copilot @ ICML 2025
15 days
Affiliations of the ICML 2025 papers. #ICML2025 @icmlconf
Tweet media one
4
3
31
删掉 pool 重建之后,ZFS 终于可以识别到正确的容量了)
Tweet media one
18
0
72
we have fully tested them to be completely incompatible
Tweet media one
4
1
26
4 天小长假!
Tweet media one
9
0
52
RT @pliang279: I am very excited about David's @ddvd233 line of work in developing generalist multimodal clinical foundation models. CLIMB….
0
3
0
RT @SonglinYang4: Flash Linear Attention ( will no longer maintain support for the RWKV series (existing code will….
0
75
0
最耗键盘的游戏).
@takeda_iori
竹田伊織
25 days
吸血鬼幸存者的开发者开发了一个你不需要精确按键而是需要猛!烈!砸!击!键!盘!就能出招的roguelite游戏.简单试了半个小时我啊啊啊啊啊啊啊啊啊啊哈哈哈哈啊啊啊啊啊啊啊啊哈哈哈啊啊啊啊啊啊啊啊啊
Tweet media one
1
0
20
🚀 QoQ-Med is now live on @huggingface!.Load it in seconds with ddvd233/QoQ-Med-VL-7B in your favorite 🤗 Transformers pipeline. No code? No problem: fire up LM Studio (or any llama.cpp GUI), search “QoQ”, and start chatting. Weights + docs →
Tweet media one
Thanks @iScienceLuvr for posting about our recent work! . We're excited to introduce QoQ-Med, a multimodal medical foundation model that jointly reasons across medical images, videos, time series (ECG), and clinical texts. Beyond the model itself, we developed a novel training
Tweet media one
4
8
43
Thanks @iScienceLuvr for posting about our recent work! . We're excited to introduce QoQ-Med, a multimodal medical foundation model that jointly reasons across medical images, videos, time series (ECG), and clinical texts. Beyond the model itself, we developed a novel training
Tweet media one
@iScienceLuvr
Tanishq Mathew Abraham, Ph.D.
1 month
QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training. "we introduce QoQ-Med-7B/32B, the first open generalist clinical foundation model that jointly reasons across medical images, time-series signals, and text reports. QoQ-Med is trained with
Tweet media one
6
15
67
RT @iScienceLuvr: QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training. "we introduce QoQ-Med-7B/32B, th….
0
27
0
RT @jas_x_flowers: Well. a new chapter is starting! I'm over the moon to be joining @MITEECS / @MIT_CSAIL as an Assistant Professor, star….
0
28
0
一直以为是苏南硕放机场,原来应该叫做无锡硕放机场吗
Tweet media one
17
1
74
NeurIPS 现在都不能选 review 数量的吗. 这一上来给我 assign 五篇
Tweet media one
7
0
31
但其实阵亡将士节的时候也会有人说不该说 Happy Memorial Day.(当然大部分人也不会在意)
Tweet media one
@python_xxt
Robinson · 鲁棒逊
1 month
大家 会说 端午安康 吗?. TK 认为 这是一种 刻奇 🤔
Tweet media one
3
0
20
RT @yuyinzhou_cs: Can MLLMs truly understand the full context from multiple medical images to answer complex clinical questions? 🤔. ✨ Intro….
0
22
0