Interesting paper. What I like about this is that it is a relatively low-commitment attention modification. I.e., one can use it during most of training, switch back to vanilla attention near the end, and recover roughly the same modeling performance as if full attention had
AI
-
EgoMemReason: A Memory-Driven Benchmark for Egocentric Video Understanding
By
–
EgoMemReason A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Understanding
-
SenseNova-U1: Unifying Multimodal Understanding and Generation
By
–
SenseNova-U1 Unifying Multimodal Understanding and Generation with NEO-unify Architecture
-
Enterprise AI Governance and the Challenge of Agentic Workflows
By
–
Most companies do not have an AI problem. They have an AI governance problem. As agents move across systems, data, and workflows, the real challenge becomes: Visibility Control Accountability Microsoft’s Agent 365 updates point to the next enterprise bottleneck:
-
G²RPO-A: A New Training Method for Enhancing LLM Reasoning
By
–
Why can't smaller language models match larger ones on reasoning? Researchers from CUHK Shenzhen, Alibaba Group, and Westlake University introduce G²RPO-A. It adaptively feeds correct reasoning steps into training, dynamically adjusting guidance as the model improves. On math
-
Discussing the practice of AI-assisted vibecoding
By
–
Me every time I do vibecoding with Claude 😅
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 13 mai 2026
Be honest. How much code do you actually read when you’re vibecoding? 🤷♂️ pic.twitter.com/0arWpwgVETMe every time I do vibecoding with Claude Be honest. How much code do you actually read when you’re vibecoding?
-
The Future of AI Agents: The War Room
By
–
The future of AI agents isn't text. It's a war room.
— AlphaSignal AI (@AlphaSignalAI) 13 mai 2026
Hermes already lets you run a fleet of specialized agents that hand work to each other.
The problem was visibility.
You had to SSH into your machine and grep logs to see what each one was doing.
Orchestration War Room is… pic.twitter.com/lYFiHWyrVWThe future of AI agents isn't text. It's a war room. Hermes already allows you to run a fleet of specialized agents that hand off work to each other. The issue was visibility. You had to SSH into your machine and grep logs to see what each one was doing. Orchestration War Room is…
-
Exécuter plusieurs agents en parallèle pour optimiser les résultats
By
–
5/5 Ensemble: Run multiple distinct agent configs in parallel → select the best trajectory. Leverages success of the portfolio vs single variants (see also: @/karpathy’s LLM Council). Can outperform best-of-N on accuracy but at lower cost & latency. Here’s how each method did
-
Best-of-N : optimisation parallèle d’agents IA
By
–
4/5 Best-of-N: Run one agent config N times in parallel → select the best trajectory. Leverages LLMs’ non-determinism – but hinges on a good eval mechanism (we use an LLM-as-a-Judge). Can increase accuracy without linearly increasing latency – but parallel runs can add up $$.
-
Agent Scaffolding: Building the Infrastructure
By
–
3/5 Agent scaffolding: Adjust prompts, integrate tools/skills, set execution policies, retries, memory, etc. → create the operational framework. Useful for long-horizon or multi-step tasks.