langchain-ai/agents-from-scratch
github.com·13h
👨‍💻AI Coding
TAI #160: More Leaps in AI for Health; Drug Discovery and Diagnosis With Chai-2, AlphaGenome and…
pub.towardsai.net·1h
🆕New AI
LLaMeSIMD – LLM SIMD Intrinsic and Function Translation Benchmarking Suite
github.com·13h·
Discuss: Hacker News
🏆LLM Benchmarking
Spatio-Temporal LLM: Reasoning about Environments and Actions
arxiv.org·10h
🏆LLM Benchmarking
Instruction Aware Embeddings – Why Your Retriever Is Failing
dipkumar.dev·3h·
Discuss: Hacker News
📌Embedding Retrieval
AI Agents Under the Hood
blog.surkar.in·3h·
Discuss: Hacker News
🆕New AI
Latent Thermodynamic Flows: Unified Representation Learning and Generative Modeling of Temperature-Dependent Behaviors from Limited Data
arxiv.org·10h
🕯️Candle
Disentangling Doubt in Deep Causal AI
arxiv.org·10h
🔍AI Interpretability
Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?
arxiv.org·10h
🏆LLM Benchmarking
Introducing Answered with Evidence -- a framework for evaluating whether LLM responses to biomedical questions are founded in evidence
arxiv.org·10h
🔍Information Retrieval
From Answers to Rationales: Self-Aligning Multimodal Reasoning with Answer-Oriented Chain-of-Thought
arxiv.org·10h
🔍AI Interpretability
On the functional self of LLMs
lesswrong.com·23h
🪄Prompt Engineering
Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
arxiv.org·10h
🛡️AI Safety
Counterfactual Tuning for Temporal Sensitivity Enhancement in Large Language Model-based Recommendation
arxiv.org·10h
📊Feed Optimization
Learning unitaries with quantum statistical queries
arxiv.org·10h
🎯Qdrant
ReliableMath: Benchmark of Reliable Mathematical Reasoning on Large Language Models
arxiv.org·10h
🧮SMT Solvers
Verified Language Processing with Hybrid Explainability: A Technical Report
arxiv.org·10h
📝Text Parsing
Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning
arxiv.org·10h
📊Embeddings
Identify, Isolate, and Purge: Mitigating Hallucinations in LVLMs via Self-Evolving Distillation
arxiv.org·10h
🎯Qdrant
Read Quietly, Think Aloud: Decoupling Comprehension and Reasoning in LLMs
arxiv.org·10h
🪄Prompt Engineering