mem-agent: Equipping LLM Agents with Memory Using RL
driaforall
โข โข 33NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Ring-flash-linear-2.0: A Highly Efficient Hybrid Architecture for Test-Time Scaling
RichardBian
โข โข 11Ethics + Sustainability = Responsible AI
sasha
โข โข 16๐ ML-Agents Tips & Lessons Learned (AutoMind + MLE-Bench)
JohnsonZheng03
โข โข 6๐๏ธ CNN (Convolutional Neural Networks) โ Quand l'IA apprend ร voir comme toi ! ๐ธ๐ง
RDTvlokip
โข โข 2๐๏ธ CNN (Convolutional Neural Networks) โ When AI learns to see like you! ๐ธ๐ง
RDTvlokip
โข โข 1Moondream3 and Salesforce GTA-1 for UI grounding in computer-use agents
dhruv3006
โข How Financial News Can Be Used to Train Good Financial Models
SelmaNajih001
โข โข 10IndicPhi-Mini: Adapting Phi-mini-MoE to Indic Langauge with Curated Data
SandLogicTechnologies
โข โข 1Reactive Transformer (RxT): Fixing the Memory Problem in Conversational AI
AdamF92
โข โข 6Connect all your systems from a single chat โ with governance
mrmanna
โข ๐ ๐ข๐ฝ๐ฒ๐ป ๐ฆ๐ผ๐๐ฟ๐ฐ๐ฒ ๐๐ด๐ฒ๐ป๐๐ถ๐ฐ ๐๐ผ๐ป๐๐ฟ๐ฎ๐ฐ๐ ๐ ๐ผ๐ฑ๐ฒ๐น ๐๐ฌ.๐ฑ.๐ฌ โ โ๐๐ต๐ฎ๐ ๐ฎ๐ ๐๐ผ๐๐ฟ ๐๐ป๐๐ฒ๐ฟ๐ฝ๐ฟ๐ถ๐๐ฒ ๐๐ผ๐ป๐๐ฟ๐ผ๐น ๐ฆ๐๐ฟ๐ณ๐ฎ๐ฐ๐ฒโ
mrmanna
โข A New Fine-Tuning Approach for LLMs Using Evolution Strategies
danyoung
โข โข 1Top AI/ML competitions for developers in 2025
avi81
โข Visualizing How VLMs Work
not-lain
โข โข 57๐ RNN (Recurrent Neural Networks) โ When AI has the memory of a goldfish! ๐๐ง
RDTvlokip
โข โข 2๐ RNN (Recurrent Neural Networks) โ Quand l'IA a la mรฉmoire d'un poisson rouge ! ๐๐ง
RDTvlokip
โข โข 1CHARIOT
MarcusLammers
โข Combining GRPO and RAG for Explainable Financial Predictions
SelmaNajih001
โข โข 3Why Your Marketing RAG System Needs Domain-Specific Embeddings ๐ฏ
Sri-Vigneshwar-DJ
โข โข 1