🧠 LLM Research - inarcissuss

Discussed on Hacker News

🧠Claude arXiv·

Sub-Billion, Super-Frontier: Small Language Models Rival Zero-Shot Frontier LLMs on General and Literary Relation Extraction

💬LLM Prompting GitHub·

chatstore – persistent chat history service for LLM apps, zero infrastructure

Discussed on DEV

🧠LLM Training arXiv·

The Table Says Otherwise: Testing LLMs with Counterfactual Relational Data

🔎AI Interpretability arXiv·

Emergent Capabilities Arise Randomly from Learning Sparse Attention Patterns

🧠LLM Training arXiv·

Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?

🤖AI Development arXiv·

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

🗣️Large Language Models arXiv·

Project Auto-World: Towards Automated Benchmarking of Neural Relational Reasoners

🧠LLM Training arXiv·

Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning

🧠LLM Training arXiv·

Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty

🗣️Large Language Models arXiv·

The Topology of Ill-Posed Questions: Persistent Homology for Detection and Steering in LLMs

🤖人工智能 arXiv·

Narrative Feature or Structured Feature? A Study of Large Language Models to Identify Cancer Patients at Risk of Heart Failure

🧠LLM Training arXiv·

Empirical evidence of Large Language Model’s influence on human spoken communication

Covered by Stat Significant

🔬Deep Learning arXiv·

Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention

🗣️Large Language Models arXiv·

Evaluating LLM Usage for Efficient and Explainable Numerical and Classified Implicit Sentiment Analysis of Product Desirability

🧠LLM arXiv·

Privacy Vulnerabilities of Attention Layers in Tabular Foundation Models and Protection of High-Risk Queries

🧠LLM Training arXiv·

moBERTo: A Modern Encoder for Portuguese via Continued Pretraining of ModernBERT

🔬ML Research arXiv·

ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments

🤖AI arXiv·

Mind the Heads: Topological Representation Alignment for Multimodal LLMs

Covered by 何夕2077的个人站

DREAM: Dense Retrieval Embeddings via Autoregressive Modeling

PsychAdapter: Personality in LLM output via trait-language patterns, not prompts

Sub-Billion, Super-Frontier: Small Language Models Rival Zero-Shot Frontier LLMs on General and Literary Relation Extraction

chatstore – persistent chat history service for LLM apps, zero infrastructure

The Table Says Otherwise: Testing LLMs with Counterfactual Relational Data

Emergent Capabilities Arise Randomly from Learning Sparse Attention Patterns

Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

Project Auto-World: Towards Automated Benchmarking of Neural Relational Reasoners

Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning

Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty

The Topology of Ill-Posed Questions: Persistent Homology for Detection and Steering in LLMs

Narrative Feature or Structured Feature? A Study of Large Language Models to Identify Cancer Patients at Risk of Heart Failure

Empirical evidence of Large Language Model’s influence on human spoken communication

Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention

Evaluating LLM Usage for Efficient and Explainable Numerical and Classified Implicit Sentiment Analysis of Product Desirability

Privacy Vulnerabilities of Attention Layers in Tabular Foundation Models and Protection of High-Risk Queries

moBERTo: A Modern Encoder for Portuguese via Continued Pretraining of ModernBERT

ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments

Mind the Heads: Topological Representation Alignment for Multimodal LLMs