NIDHAL ZITOUNI
@zitouni-nidhal.bsky.social
LLM benchmark snapshot 📊
Across long contexts, MiniMax-M2.1 (4-bit) leads in throughput, efficiency, and memory usage, while GLM-4.7 scales with higher cost.
Quantization still matters.
#LLM #AIResearch #MachineLearning #DeepLearning #GenerativeAI #Inference #ModelEfficiency #LongContext #Benchmarks
Across long contexts, MiniMax-M2.1 (4-bit) leads in throughput, efficiency, and memory usage, while GLM-4.7 scales with higher cost.
Quantization still matters.
#LLM #AIResearch #MachineLearning #DeepLearning #GenerativeAI #Inference #ModelEfficiency #LongContext #Benchmarks
December 27, 2025 at 6:39 PM
LLM benchmark snapshot 📊
Across long contexts, MiniMax-M2.1 (4-bit) leads in throughput, efficiency, and memory usage, while GLM-4.7 scales with higher cost.
Quantization still matters.
#LLM #AIResearch #MachineLearning #DeepLearning #GenerativeAI #Inference #ModelEfficiency #LongContext #Benchmarks
Across long contexts, MiniMax-M2.1 (4-bit) leads in throughput, efficiency, and memory usage, while GLM-4.7 scales with higher cost.
Quantization still matters.
#LLM #AIResearch #MachineLearning #DeepLearning #GenerativeAI #Inference #ModelEfficiency #LongContext #Benchmarks
New paper introduces Gnosis, a lightweight self-awareness mechanism that lets frozen LLMs predict correctness by inspecting internal circuits (hidden states & attention).
📄 arXiv: 2512.20578
#AI #LLMs #MachineLearning #SelfAwareness #Interpretability #AIAlignment #NeurIPS #ICLR #DeepLearning
📄 arXiv: 2512.20578
#AI #LLMs #MachineLearning #SelfAwareness #Interpretability #AIAlignment #NeurIPS #ICLR #DeepLearning
December 26, 2025 at 8:35 PM
New paper introduces Gnosis, a lightweight self-awareness mechanism that lets frozen LLMs predict correctness by inspecting internal circuits (hidden states & attention).
📄 arXiv: 2512.20578
#AI #LLMs #MachineLearning #SelfAwareness #Interpretability #AIAlignment #NeurIPS #ICLR #DeepLearning
📄 arXiv: 2512.20578
#AI #LLMs #MachineLearning #SelfAwareness #Interpretability #AIAlignment #NeurIPS #ICLR #DeepLearning
[AI] Propose, Solve, Verify: Self-Play Through Formal Verification
A Wilf, P Aggarwal, B Parno, D Fried... [CMU] (2025)
arxiv.org/abs/2512.18160
#AI
#MachineLearning
#DeepLearning
#ArtificialIntelligence
#DataScience
#NeuralNetworks
#MLResearch
#AIResearch
A Wilf, P Aggarwal, B Parno, D Fried... [CMU] (2025)
arxiv.org/abs/2512.18160
#AI
#MachineLearning
#DeepLearning
#ArtificialIntelligence
#DataScience
#NeuralNetworks
#MLResearch
#AIResearch
December 25, 2025 at 1:24 PM
[AI] Propose, Solve, Verify: Self-Play Through Formal Verification
A Wilf, P Aggarwal, B Parno, D Fried... [CMU] (2025)
arxiv.org/abs/2512.18160
#AI
#MachineLearning
#DeepLearning
#ArtificialIntelligence
#DataScience
#NeuralNetworks
#MLResearch
#AIResearch
A Wilf, P Aggarwal, B Parno, D Fried... [CMU] (2025)
arxiv.org/abs/2512.18160
#AI
#MachineLearning
#DeepLearning
#ArtificialIntelligence
#DataScience
#NeuralNetworks
#MLResearch
#AIResearch
🚀 Retrieval-Augmented Navigation (RANa) — a new approach that integrates retrieval-augmented context into embodied AI agents.
📖 Learn more: arxiv.org/abs/2410.10429
📖 Learn more: arxiv.org/abs/2410.10429
October 26, 2025 at 10:22 PM
🚀 Retrieval-Augmented Navigation (RANa) — a new approach that integrates retrieval-augmented context into embodied AI agents.
📖 Learn more: arxiv.org/abs/2410.10429
📖 Learn more: arxiv.org/abs/2410.10429
Reposted by NIDHAL ZITOUNI
Build a fully-local voice assistant via LangGraph + MCP servers with no subscriptions, no cloud, just fast, on-device smarts that actually work. The future of personal AI is private and modular.
#AI #VoiceAssistant #LangGraph #MCP #Privacy #ModularAI #LocalAI
#AI #VoiceAssistant #LangGraph #MCP #Privacy #ModularAI #LocalAI
Using LangGraph and MCP Servers to Create My Own Voice Assistant | Towards Data Science
Built over 14 days, all locally run, no API keys, cloud services, or subscription fees.
towardsdatascience.com
September 5, 2025 at 12:01 PM
Build a fully-local voice assistant via LangGraph + MCP servers with no subscriptions, no cloud, just fast, on-device smarts that actually work. The future of personal AI is private and modular.
#AI #VoiceAssistant #LangGraph #MCP #Privacy #ModularAI #LocalAI
#AI #VoiceAssistant #LangGraph #MCP #Privacy #ModularAI #LocalAI
Instead of just trying to be “more accurate”, a probabilistic approach becomes more robust against errors and uncertainties, more flexible and therefore more adaptable to new situations, and more comprehensible and interpretable. #ML #AI #probabilisticthinking
Beyond Glorified Curve Fitting: Exploring the Probabilistic Foundations of Machine Learning | Towards Data Science
An introduction to probabilistic thinking — and why it’s the foundation for robust and explainable AI systems.
towardsdatascience.com
May 29, 2025 at 3:46 PM
🚚💨 Check out this truck with a built-in blender! Perfect for making smoothies on the go or blending up a snack while on the road. A game-changer for truckers and travelers alike! #TruckLife #Innovation #SmoothieOnTheGo
#Blender
#3Danimation
#3DModel
#Blender
#3Danimation
#3DModel
January 7, 2025 at 3:59 PM
🚚💨 Check out this truck with a built-in blender! Perfect for making smoothies on the go or blending up a snack while on the road. A game-changer for truckers and travelers alike! #TruckLife #Innovation #SmoothieOnTheGo
#Blender
#3Danimation
#3DModel
#Blender
#3Danimation
#3DModel
November 25, 2024 at 11:05 PM