Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Models
Paper: https://
arxiv.org/pdf/2504.13351
v1
…
Page:
@jiqizhixin
-
Chain-of-Modality: Learning Robot Manipulation from Multimodal Videos
By
–
-
Chain-of-Modality: New Prompting Strategy for Vision-Language Models
By
–
DeepMind and Stanford just dropped a new paper!
— 机器之心 JIQIZHIXIN (@jiqizhixin) 22 avril 2025
They propose Chain-of-Modality, a prompting strategy that enables Vision-Language Models to reason over multimodal human demonstrations — bridging modalities step by step.
A smart way to unlock richer, more grounded reasoning. 🧠📷 pic.twitter.com/fhbZNpd48vDeepMind and Stanford just dropped a new paper!
They propose Chain-of-Modality, a prompting strategy that enables Vision-Language Models to reason over multimodal human demonstrations — bridging modalities step by step.
A smart way to unlock richer, more grounded reasoning. -
Parameter-Efficient Unlearning Methods for Large Language Models
By
–
Unified Parameter-Efficient Unlearning for LLMs
Paper: https://
arxiv.org/pdf/2412.00383
Code: https://
github.com/oceanoceanna/L
LMEraser
… -
LLMEraser: Machine Unlearning for Privacy and Security
By
–
Sometimes, we don’t need LLMs to learn more — we need them to forget.
This paper explores unlearning as a way to address privacy and security risks.
Their method, LLMEraser, tackles a wide range of unlearning tasks while preserving overall model performance. -
Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, Applications
By
–
A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications https://
arxiv.org/pdf/2503.07137 -
Antidistillation Sampling Protects Models Against Knowledge Theft
By
–
Antidistillation Sampling — a novel method to curb the effectiveness of distillation without sacrificing model performance.
A technique big AI labs might be very interested in.
Paper: https://
arxiv.org/pdf/2504.13146
Page: https://
antidistillation.com -
Reinforcement Learning State for LLM Reasoning Optimization
By
–
The State of Reinforcement Learning for LLM Reasoning
A must-read deep dive by Sebastian Raschka @rasbt
. Essential if you're into aligning, optimizing, or understanding how RL shapes reasoning in LLMs. -
OpenAI o3, Gemini 2.5 Pro, Claude 3.7 top AI IQ rankings
By
–
OpenAI o3, Gemini 2.5 Pro, and Claude 3.7 Sonnet Extended top the IQ charts among AI models, per Tracking AI. For reference, average human IQ = 100.
-
Ollama Works Great for AI Development
By
–
Working great! We love Ollama.❤️ https://t.co/EDSs3oNDYy pic.twitter.com/LkfHnwdADF
— 机器之心 JIQIZHIXIN (@jiqizhixin) 19 avril 2025Working great! We love Ollama.
-
Test-Time Scaling in Large Language Models: Survey
By
–
What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models
Paper: https://
arxiv.org/pdf/2503.24235
Repo: https://
github.com/testtimescalin
g/testtimescaling.github.io/
…