←
AfterQuery106 posts
AfterQuery avatar✓

AfterQuery ✓

@AfterQuery

Applied research lab curating data solutions to accelerate foundation model development.

◷ Joined February 2025▧ 23 Photos and videos
AfterQuery avatar
AfterQuery@AfterQuery·Jun 12

Congratulations to @nvidia on the release of Nemotron 3 Ultra! Ultra now leads GDPval-AA by a good margin among US open source models. @AfterQuery is proud to have provided the GDPval training data used to hill climb the benchmark.

Post attachment
AfterQuery avatar
AfterQuery@AfterQuery·Nov 16

Training data is increasingly produced by systems where humans and models work together. That means data labs must be able to show exactly what produced their data and why it should be trusted. Today we're publishing our closed-model policy, how we enforce it, and a call for responsible training data production. afterquery.com/blog/a-call-f…

AfterQuery avatar
AfterQuery@AfterQuery·Nov 12

Today we're releasing CrossSearch, a new benchmark testing whether AI agents can do something people do at work every day: look through their files, search the internet, and reason through ambiguity. Unlike benchmarks that test web search or file understanding separately, CrossSearch tests whether agents can do both together to solve real-world problems. Across 100 tasks and 14 models, Gemini 4 Argon leads at just 64% pass³. Full blog, leaderboard, and dataset in the replies.

0:08
AfterQuery avatar
AfterQuery@AfterQuery·Nov 11

Can AI agents run a business as conditions change? Introducing StoreBench, a high-fidelity RL environment where agents manage a simulated online apparel store, with safeguards against reward hacking. StoreBench includes 12 evaluation tasks spanning 30–365 simulated days. Across the 11 tasks lasting 30–45 days, all seven models score lower on average than human participants and smart-triage, a rule-based program that prioritizes urgent work. Late restocking, unresolved refunds, and decisions based on outdated information show that sustained operations remain challenging for AI agents. Check out the comments to read more.

0:12
Spencer Mateega avatar
⟳ AfterQuery retweeted
Spencer Mateega@spencermateega·Nov 5

Congrats to @cognition on SWE-2 Flash! Exciting to see an increasing number of companies train models around the work they know best. Strong open foundations like @thinkymachines' Inkling-Small enable teams to shape intelligence around their own needs.

Post attachment
AfterQuery avatar
AfterQuery@AfterQuery·Nov 4

Excited to have one of our post-training runs showcased by @thinkymachines. Using Tinker, we post-trained gpt-oss-20b with SFT, then RL on our terminal agent data. Its Terminal-Bench 2.0 pass rate went from 3.1% to 17.0%. @AfterQuery datasets are validated with Tinker against held-out benchmarks before they ship. If you're building frontier models and want data with measured impact, reach out at research@afterquery.com.

Post attachment
Amish Sethi avatar
⟳ AfterQuery retweeted
Amish Sethi@amish_sethi04·Oct 30

Can collecting robot data be as easy as 𝗽𝗿𝗲𝘀𝘀𝗶𝗻𝗴 𝗿𝗲𝗰𝗼𝗿𝗱? Introducing UMI-Live, a 𝗰𝗼𝗺𝗽𝗹𝗲𝘁𝗲𝗹𝘆 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 bimanual UMI we made that takes you from handheld demonstrations all the way to a trained robot policy. It's built to be easy to use. Each gripper has its own camera, LiDAR, compute, and battery, so there are no base stations to mount and nothing to calibrate in the scene. You press one button and both hands start recording. While you keep collecting, our pipeline processes finished episodes in parallel and turns them into LeRobot datasets, automatically uploaded on Huggingface. VLAs fine-tuned mostly on this data succeed in 𝟭𝟬/𝟭𝟬 (π0.5) and 𝟴/𝟭𝟬 (MolmoAct2) trials on a real bimanual task. We're open-sourcing everything, from the hardware designs and build guides to the code and ~40 hours of data 🧵

0:36
AfterQuery avatar
AfterQuery@AfterQuery·Oct 29

We improved models on professional work tasks using NVIDIA AI’s xToken, NeMo Gym, and NeMo RL for cross tokenizer distillation. Read the full blog below.

AfterQuery avatar
AfterQuery@AfterQuery·Oct 29

We used @NVIDIAAI's xToken recipe along with NeMo Gym and NeMo RL open post-training libraries to improve models on professional work tasks through cross tokenizer distillation. Held-out GDP.pdf strict pass@1 (avg 5) in NeMo Gym: - Nemotron 3.5 Super VL: 6.67% to 11.83% - Qwen3.5-9B: 4.40% to 8.20% Read the full blog below.

0:12
AfterQuery avatar
AfterQuery@AfterQuery·Oct 26

Frontier models nearly run through the public internet for pre-training alone. The knowledge they need next is locked inside businesses. Today we're launching @AfterQuery Data Partnerships. If you're a business owner who is curious, or hesitant, about licensing your data, we would love to hear from you. Learn more in the replies.

0:12