Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Paper
•
2503.09573
•
Published
•
62
CompVis Community
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
compvis-community's activity
Skylion007
authored
a
paper
12 days ago
yyupenn
authored
3
papers
about 1 month ago
Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation
Paper
•
2502.14846
•
Published
•
13
Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model
Paper
•
2410.13882
•
Published
MiRAGeNews: Multimodal Realistic AI-Generated News Detection
Paper
•
2410.09045
•
Published
•
4
omerbartal
authored
a
paper
about 2 months ago
nupurkmr9
authored
a
paper
about 2 months ago
zwrq
authored
a
paper
2 months ago
Skylion007
authored
a
paper
2 months ago
Post
14526
Google drops Gemini 2.0 Flash Thinking
a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more
now available in anychat, try it out: akhaliq/anychat
a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more
now available in anychat, try it out: akhaliq/anychat
- 3 replies
hjzheng
authored
a
paper
3 months ago
Post
14791
QwQ-32B-Preview is now available in anychat
A reasoning model that is competitive with OpenAI o1-mini and o1-preview
try it out: akhaliq/anychat
A reasoning model that is competitive with OpenAI o1-mini and o1-preview
try it out: akhaliq/anychat
- 1 reply
Post
4293
Post
3202
anychat
supports chatgpt, gemini, perplexity, claude, meta llama, grok all in one app
try it out there: akhaliq/anychat
supports chatgpt, gemini, perplexity, claude, meta llama, grok all in one app
try it out there: akhaliq/anychat
patrickvonplaten
authored
a
paper
6 months ago
yyupenn
authored
a
paper
6 months ago
Skylion007
authored
a
paper
7 months ago
rishistyping
authored
a
paper
8 months ago
Post
1304
Llama 3.1 405B Instruct beats GPT-4o on MixEval-Hard
Just ran MixEval for 405B, Sonnet-3.5 and 4o, with 405B landing right between the other two at 66.19
The GPT-4o result of 64.7 replicated locally but Sonnet-3.5 actually scored 70.25/69.45 in my replications 🤔 Still well ahead of the other 2 though.
Sammple of 1 of the eval calls here: https://wandb.ai/morgan/MixEval/weave/calls/07b05ae2-2ef5-4525-98a6-c59963b76fe1
Quick auto-logging tracing for openai-compatible clients and many more here: https://wandb.github.io/weave/quickstart/
Just ran MixEval for 405B, Sonnet-3.5 and 4o, with 405B landing right between the other two at 66.19
The GPT-4o result of 64.7 replicated locally but Sonnet-3.5 actually scored 70.25/69.45 in my replications 🤔 Still well ahead of the other 2 though.
Sammple of 1 of the eval calls here: https://wandb.ai/morgan/MixEval/weave/calls/07b05ae2-2ef5-4525-98a6-c59963b76fe1
Quick auto-logging tracing for openai-compatible clients and many more here: https://wandb.github.io/weave/quickstart/
mannykayy
authored
2
papers
8 months ago