Spaces-explorers

Activity Feed Request to join this org

AI & ML interests

Contributors who are invited to beta-test our next big feature! Contact us if you want to join this team :-)

Recent Activity

varuny authored a paper 13 days ago

Training Continuous Chain of Thought Models: A Tale of Two Regimes

varuny authored a paper 13 days ago

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

vesteinn authored a paper about 1 month ago

Transducing Language Models

View all activity

jeffboudier

posted an update about 1 month ago

Post

287

@alvarobartt published a step-by-step guide to deploy zai-org/GLM-5.2 on AMD GPUs, using newly released features in Microsoft Foundry. The FP8 model fits on a single node of MI300X GPUs, which cuts the bill in half vs. H100.

https://alvarobartt.com/goal-glm-5.2-on-foundry/

abidlabs

posted an update about 1 month ago

Post

686

Uhh did Opus 4.8 cheat on PostTrainBench??

it found an API key in the PostTrainBench environment that allowed it to generate synthetic training data without using GPU hours, boosting the base model by 0.4913

Source: https://posttrainbench.com/traces/run.html?id=claude_non_api_max_claude-opus-4-8_10h_run1__healthbench_Qwen_Qwen3-4B-Base_17315102#tab=trace

1 reply

mryab

submitted a paper to Daily Papers 5 months ago

Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking

Paper • 2602.21196 • Published Feb 24 • 7

AlekseyKorshuk

authored a paper 6 months ago

Evaluation of a Robust Control System in Real-World Cable-Driven Parallel Robots

Paper • 2510.08270 • Published Oct 9, 2025 • 2

AlekseyKorshuk

authored a paper 7 months ago

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

Paper • 2512.03318 • Published Dec 3, 2025 • 4

abidlabs

authored 3 papers 9 months ago

posted an update 9 months ago

Post

11553

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.

8 replies

abidlabs

posted an update 11 months ago

Post

1619

What other features would you like to see on the Trackio Dashboard? ( gradio-templates/trackio-dashboard)

marksaroufim

authored a paper 11 months ago

TorchAO: PyTorch-Native Training-to-Serving Model Optimization

Paper • 2507.16099 • Published Jul 21, 2025 • 7

jeffboudier

posted an update 11 months ago

Post

3454

Quick 30s demo of the new Hub > Azure AI integration to deploy HF models in your own Azure account. Now with Py and CLI!

GG @alvarobartt @kramp @pagezyhf

andreaschandra

authored 2 papers about 1 year ago

A Survey on non-English Question Answering Dataset

Paper • 2112.13634 • Published Dec 27, 2021