BADAS 2.0: new collision prediction system from Nexar.
It's based on V-JEPA 2!!
JEPA is going to save lives.
RESEARCH
-
Nexar BADAS 2.0: V-JEPA collision prediction system
By
–
-
AI and HPC Accelerate Scientific Discovery from Hypothesis to Results
By
–
Scientific discovery shouldn't take years when it could take days. On May 7, Domino is hosting a session on how AI, ML, and HPC are compressing the path from hypothesis to validated results. See what top research organizations are doing right now: https://
hubs.ly/Q04cgxCl0 -
Agent Engineering Evolution: Environment Over Model Power 2022-2026
By
–
from weights → context → harness engineering (evolution of agent landscape from 2022-26) the biggest shift in AI agents had nothing to do with making models smarter. it was about making the environment around them smarter. here's how agent engineering evolved in just 4
-
From Data Hoarding to Explainable AI Insights for Executives
By
–
Why this matters to execs: → From collection → comprehension: you stop hoarding and start explaining. → Accuracy scales because answers come from your ground truth. → You finally get explainability you can take to a board meeting.
-
Context Engineering: Why Quality Data Beats Volume for LLMs
By
–
Most teams think “more data = smarter AI.” I make the opposite case: context beats volume. When LLMs are grounded in your company’s own signals—not just the internet—they deliver accurate, explainable decisions at scale. A thread on Context Engineering and why it changes
-
Analysis of 50000 AI Chatbot Health Interactions Study
By
–
Analysis of >50,000 public—AI chatbot health interactions @Copilot @Dominic1King @mooniean https://
nature.com/articles/s4436
0-026-00117-x
… -
Theoretical Beauty vs Practical Scalability in Machine Learning
By
–
SVM and kNN are intellectually beautiful and practically capped. That's a real tension the field doesn't talk about enough. Theoretical cleanliness and empirical scalability pulled in opposite directions for basically the entire deep learning era, and scalability won every
-
Guggenheim Fellows Awarded in Computer Science and AI Research
By
–
Congrats to all the winners of the @GuggFellows
! In computer science, this includes my friend and collaborator Ilias Diakonikolas (UWisc, Madison) and Vinod Vaikuntanathan (
@Vinod_MIT
, MIT) -
Anthropic Mythos Shelved Reveals Company’s Current Technical Ceiling
By
–
Mythos getting shelved is the more interesting signal here. Whatever they pulled back from tells you more about where Anthropic's ceiling currently sits than whatever ships today.
-
Unsloth Enables GRPO Training for Gemma 4 on Consumer GPUs
By
–
Train Gemma 4 with reinforcement learning! Unsloth just added GRPO support for Gemma 4. You can now RL fine-tune Google's latest model on a consumer GPU. The example notebook teaches Gemma 4 to solve Sudoku puzzles autonomously. The model learns through trial and error with