-
2024-11-07
AI Agents Create a New World - MBTI Personalities
-
2024-11-07
Fourier-Enhanced Fine-Tuning Vision Language Models (PEFT-VFPT)
-
2024-11-06
NextGen AI Agents: SAIA
-
2024-11-05
NEW: Post-Training Optimization Multimodal Retriever (Stanford Univ, MIT)
-
2024-11-04
NEW Knowledge-Graph Adaptive Reasoning: Plan-on-Graph LLM
-
2024-11-03
NEW AI Models Solve Hamiltonian Mechanics
-
2024-11-01
New VLM Post-Training Layer Scaling: No more Forgetting #ai
-
2024-11-01
Inside the VLM: NEW "Task Vectors" emerge (UC Berkeley)
-
2024-10-31
NEW: LoRA Models override Pre-trained Knowledge (MIT)
-
2024-10-30
AI Prompt Programming: Beyond DSPy & TextGrad: PDL
-
2024-10-29
SOLVED: Perfect Reasoning for every AI AGENT (ReasonAgain)
-
2024-10-28
Decoding on Graphs: Empower LLMs with KGs (MIT)
-
2024-10-26
AI Agents for Smarter Data Input: DocETL (Berkeley)
-
2024-10-25
NEW 3.5 SONNET V2 Has a LOGIC BUG: Reasoning ERROR
-
2024-10-24
MCTS Enhanced AI AGENTS: SELA (Stanford, UC Berkeley)
-
2024-10-23
CRM AI AGENTS: Microsoft, Salesforce, or Anthropic?
-
2024-10-22
RL Loses Against Multi-Agent Intelligence: CoMAL
-
2024-10-21
How Far Can AI Reason? The limits of AI exposed
-
2024-10-20
The Perfect Communication Protocol for Multi-Agents AI
-
2024-10-19
NEW Multi-Agent CODE explained (by OpenAI)
-
2024-10-18
Seven AI Agents and a Knowledge-Graph: AGENTiGraph
-
2024-10-17
Automate Agentic Workflow of LLMs: AFLOW (NEW)
-
2024-10-16
GPT-4o goes CRAZY & Creates SCIENCE ABSTRACTIONS (that work)
-
2024-10-15
ADD LLM TO Knowledge-Graph: NEW GIVE Method (Berkeley)
-
2024-10-14
Google's NEW Dual-Agent AI
-
2024-10-13
Stanford & OpenAI Code an Intelligent Shield
-
2024-10-12
Gödel's Theorem to Gödel AI: The Blueprint for Self-Learning Machines
-
2024-10-10
Harvard Presents NEW Knowledge-Graph AGENT (MedAI)
-
2024-10-09
Neuro-Symbolic GRAPH REASONING #ai
-
2024-10-08
Smart LLM Routing & Novel Multi-Agent Framework
-
2024-10-07
Inside Strawberry's LOGIC Engine & Gemini's LOGIC Bug
-
2024-10-06
Multi-Agent Sys: NEW SUPER AGENT & MIT FutureYou
-
2024-10-05
Overparametrized LLM: COMPLEX Reasoning (Yale Univ)
-
2024-10-04
GPT-4o w/ CANVAS - LIVE TEST
-
2024-10-03
NEW 3D LLMs for Spatial Intelligence (Robin3D)
-
2024-10-03
Embodied RAG and non-parametric Memory
-
2024-10-01
LIQUID AI 40B (MIT): REAL Performance on Reasoning (My 5 Tests)
-
2024-09-30
Anthropic's new improved RAG: Explained (for all LLM)
-
2024-09-29
Multi-Scale Insight Agents for Advanced AI Reasoning (Stanford)
-
2024-09-27
NEW Llama 3.2 11B vs 90B VISION (Pixtral 12B, GPT4o)
-
2024-09-26
NEW Llama 3.2 90B - TEST for Image Reasoning (careful!)
-
2024-09-25
NEW by Google: Michelangelo (1 Mio Token Reasoning)
-
2024-09-25
AI NEWS: MultiModal AI - Research Sept 25, 2024
-
2024-09-24
Today's AI NEWS: 13 NEW AI Papers - Sept 24, 2024
-
2024-09-23
Why Chain-of-Thought Isn't Enough & Google's SCoRe Method Explained
-
2024-09-23
Today's AI NEWS: 12 Reports - September 23, 2024
-
2024-09-21
2025 AI Revolution: Multi-Agent Systems, Apple's Next Move, Unlocking Profit Strategies
-
2024-09-20
New Qwen2.5-72B MATH & Vision (BEST Open-Source?)
-
2024-09-19
NEW AI Forecasting (UC Berkeley)
-
2024-09-18
GPT-4omni achieves o1 Causal Reasoning (Strawberry)
-
2024-09-17
NEW EXTREME LOGIC test for OpenAI o1 (Strawberry)
-
2024-09-16
Game Theory: Omni superior to Strawberry in Strategy?
-
2024-09-15
OpenAI o1 - Explore the LIMITS of o1
-
2024-09-14
AI Swarm Intelligence: Multi-Agent Ecosystem
-
2024-09-13
OpenAI o1 when it FAILS
-
2024-09-13
OpenAI o1 w/ 3 Logic Tests & QCD Feynman Integral
-
2024-09-13
NEW DataGemma-27B LLM Uncover the Truth: RIG + RAG
odevtube: YouTube for Developers
