GradyanAkincilari/68k-combined-tr-gemini-2.0-flash-v6-lenfiltered
Viewer
•
Updated
•
68.8k
alkinun
AtAndDev
AI & ML interests
LLMs, Alignment, Merging, Unsloth, DPO, SFT, ORPO, SPIN..
Recent Activity
updated
a dataset
about 8 hours ago
GradyanAkincilari/68k-combined-tr-gemini-2.0-flash-v6-lenfiltered
published
a dataset
about 8 hours ago
GradyanAkincilari/68k-combined-tr-gemini-2.0-flash-v6-lenfiltered
upvoted
an
article
1 day ago
SmolLM3: smol, multilingual, long-context reasoner
Organizations
updated
a
dataset
about 8 hours ago
published
a
dataset
about 8 hours ago
upvoted
an
article
1 day ago
Article
SmolLM3: smol, multilingual, long-context reasoner
By
and 22 others
•
•
409
liked
2
models
2 days ago
updated
a
dataset
3 days ago
published
a
dataset
3 days ago
updated
a
dataset
3 days ago
published
a
dataset
3 days ago
reacted to
nroggendorff's
post with 🚀
4 days ago
Post
2642
I'm not really doing much on HuggingFace right now due to their new Docker space policies, so if you want to keep up with most of what I'm up to, follow my [instagram](https://sly.sh/ig)
- 11 replies
updated
a
dataset
4 days ago
published
a
dataset
4 days ago
reacted to
andito's
post with 🔥
5 days ago
Post
3823
🧠👁️ Can AI visualize solutions?
Humans often solve visual problems by sketching ideas in our minds. What if Vision-Language Models (VLMs) could do something similar, not by generating full images, but by using internal “mental sketches”?
That’s the idea behind Mirage, a new framework that empowers VLMs to reason using latent visual tokens. Instead of just thinking in words, Mirage mixes in abstract visual representations that help the model solve complex tasks.
These aren't photorealistic images. They're compact, internal representations optimized purely to support reasoning.
🔧 Mirage is trained in two phases:
1) Grounding: It learns to produce latent tokens anchored in real images.
2) Refinement: The model drops the images and learns to generate visual tokens on its own.
📈 And yes, it works!
On challenging benchmarks like Visual Spatial Planning, Jigsaw puzzles, and Spatial Attention Tasks, Mirage clearly outperforms GPT-4o and other strong baselines.
Smart sketches > empty words.
By mimicking the way humans visualize solutions, Mirage gives AI a new kind of imagination, one that’s faster, more efficient, and more human-like.
Kudos to the teams at UMass Amherst and MIT behind this exciting work.
Check the paper: Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (2506.17218)
Humans often solve visual problems by sketching ideas in our minds. What if Vision-Language Models (VLMs) could do something similar, not by generating full images, but by using internal “mental sketches”?
That’s the idea behind Mirage, a new framework that empowers VLMs to reason using latent visual tokens. Instead of just thinking in words, Mirage mixes in abstract visual representations that help the model solve complex tasks.
These aren't photorealistic images. They're compact, internal representations optimized purely to support reasoning.
🔧 Mirage is trained in two phases:
1) Grounding: It learns to produce latent tokens anchored in real images.
2) Refinement: The model drops the images and learns to generate visual tokens on its own.
📈 And yes, it works!
On challenging benchmarks like Visual Spatial Planning, Jigsaw puzzles, and Spatial Attention Tasks, Mirage clearly outperforms GPT-4o and other strong baselines.
Smart sketches > empty words.
By mimicking the way humans visualize solutions, Mirage gives AI a new kind of imagination, one that’s faster, more efficient, and more human-like.
Kudos to the teams at UMass Amherst and MIT behind this exciting work.
Check the paper: Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (2506.17218)
- 4 replies
upvoted
a
paper
5 days ago
reacted to
YerbaPage's
post with 🔥👀😎
5 days ago
Post
4710
Is 100% Pass Rate on HumanEval possible? Yes! ✅
Meet MGDebugger if you are tired of LLMs failing on complex bugs 🤔 Our MGDebugger, just hit 100% accuracy on HumanEval using the DeepSeek-R1 model. 🚀
✨ Demo: learnmlf/MGDebugger
📝 Paper: From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging (2410.01215)
💻 Code: https://github.com/YerbaPage/MGDebugger
HumanEval may be retired, we're ready for the next challenge In more complex scenarios! You may also take look at this repo for a collection of awesome repo-level coding tasks!
🖥️ https://github.com/YerbaPage/Awesome-Repo-Level-Code-Generation
Meet MGDebugger if you are tired of LLMs failing on complex bugs 🤔 Our MGDebugger, just hit 100% accuracy on HumanEval using the DeepSeek-R1 model. 🚀
✨ Demo: learnmlf/MGDebugger
📝 Paper: From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging (2410.01215)
💻 Code: https://github.com/YerbaPage/MGDebugger
HumanEval may be retired, we're ready for the next challenge In more complex scenarios! You may also take look at this repo for a collection of awesome repo-level coding tasks!
🖥️ https://github.com/YerbaPage/Awesome-Repo-Level-Code-Generation
liked
a
model
5 days ago
upvoted
a
collection
6 days ago
liked
a
model
6 days ago
