TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models
Paper • 2602.15449 • Published • 7
AI & ML interests
None defined yet.
chansung
authored a
paper 3 months ago
chansung
submitted a
paper to Daily Papers 3 months ago
Post
4584
Now with extra functionality at the same LTX-2 HF Space, you can now add also your last frame along side your first frame to guide the generated videos by choosing our frame interpolation mode...
Try it out: alexnasa/ltx-2-TURBO
Try it out: alexnasa/ltx-2-TURBO
Post
4385
Now also with LTX-2 Detailer (Lightricks/LTX-2-19b-IC-LoRA-Detailer)
Try it out: alexnasa/ltx-2-TURBO
Try it out: alexnasa/ltx-2-TURBO
Post
2273
Now with additional Dolly camera support, on the same HF page, with no overhead on generation time!
HF Space: alexnasa/ltx-2-TURBO
HF Space: alexnasa/ltx-2-TURBO
dawood
authored a
paper 7 months ago
abidlabs
authored 3
papers 7 months ago
Post
11262
Why I think local, open-source models will eventually win.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
- 8 replies
luodian
authored 4
papers 8 months ago
MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs
Paper • 2411.15296 • Published • 21
Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
Paper • 2501.13826 • Published • 24
LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
Paper • 2509.23661 • Published • 50
Visual Jigsaw Post-Training Improves MLLMs
Paper • 2509.25190 • Published • 37
Post
1610
What other features would you like to see on the Trackio Dashboard? ( gradio-templates/trackio-dashboard)
Post
3645
Say hello to
We are glad to announce a long-awaited quality-of-life improvement: the Hugging Face CLI has been officially renamed from huggingface-cli to hf!
So... why this change?
Typing huggingface-cli constantly gets old fast. More importantly, the CLI’s command structure became messy as new features were added over time (upload, download, cache management, repo management, etc.). Renaming the CLI is a chance to reorganize commands into a clearer, more consistent format.
We decided not to reinvent the wheel and instead follow a well-known CLI pattern: hf <resource> <action>. Isn't
The full rationale, implementation details, and migration notes are in the blog post: https://huggingface.co/blog/hf-cli
hf: a faster, friendlier Hugging Face CLI ✨We are glad to announce a long-awaited quality-of-life improvement: the Hugging Face CLI has been officially renamed from huggingface-cli to hf!
So... why this change?
Typing huggingface-cli constantly gets old fast. More importantly, the CLI’s command structure became messy as new features were added over time (upload, download, cache management, repo management, etc.). Renaming the CLI is a chance to reorganize commands into a clearer, more consistent format.
We decided not to reinvent the wheel and instead follow a well-known CLI pattern: hf <resource> <action>. Isn't
hf auth login easier to type and remember?The full rationale, implementation details, and migration notes are in the blog post: https://huggingface.co/blog/hf-cli
- 7 replies
Post
4832
YAML engineering becomes more and more important than ever from infra provisioning to model training (recipes).
Here, I built a simple editor first for @dstackai , and I will share the live endpoint this week. Let me know what you think about this approach.
Based on this approach, if people think this is useful, I am going to do the same thing for the LLM training recipes for popular frameworks such as Hugging Face open-r1, Axolotl, and so on. Let me hear.
Here, I built a simple editor first for @dstackai , and I will share the live endpoint this week. Let me know what you think about this approach.
Based on this approach, if people think this is useful, I am going to do the same thing for the LLM training recipes for popular frameworks such as Hugging Face open-r1, Axolotl, and so on. Let me hear.
luodian
authored 2
papers 11 months ago
Post
4506
The Gradio x Agents x MCP hackathon keeps growing! We now have more $1,000,000 in credit for participants and and >$16,000 in cash prizes for winners.
We've kept registration open until the end of this week, so join and let's build cool stuff together as a community: https://huggingface.co/spaces/ysharma/gradio-hackathon-registration-2025
We've kept registration open until the end of this week, so join and let's build cool stuff together as a community: https://huggingface.co/spaces/ysharma/gradio-hackathon-registration-2025