DataSci Ocean
Posts Tags Categories
English
DataSci Ocean

All Posts

2026

VideoDR: Bridging the Gap Between Video Understanding and Agentic Search on the Open Web 01-25
Stop Using Giant LLMs for Everything: Why NVIDIA Research Says Small Language Models (SLMs) Are the Future of AI Agents 01-19
Google's "Free Lunch" for LLMs: How Prompt Repetition Fixes Attention Bottlenecks with Zero Latency 01-19
Is RLHF Killing Creativity? How Verbalized Sampling Mitigates Mode Collapse and Unlocks LLM Diversity 01-03
Beyond Self-Consistency: How CER Boosts LLM Reasoning by Leveraging "Process Confidence" (ACL 2025) 01-03

2025

Stop AI Hallucinations Early: How Meta's DeepConf Uses Token Confidence to Cut Inference Costs by 80% 12-28
rStar Deep Dive: How MCTS & Mutual Reasoning Boost LLaMA2-7B Accuracy from 12% to 64% Without Fine-tuning 12-10
Your Base Model Is Smarter Than You Think: How MCMC Sampling Can Outperform RL 12-02
Beyond Prompt Engineering: Inside Agentic Context Engineering, The Future of Self-Evolving AI 10-27
Dynamic Cheatsheet: The Secret to Self-Improving LLMs that Learn During Inference 10-15
Let AI Write Flawless SQL: A Deep Dive into the SQL-of-Thought Multi-Agent Framework 10-12
Beyond Top-k: How Adaptive-k Dynamically Selects the Best Context for RAG Without Latency 09-22
SENSE Explained: How Strong and Weak LLMs Achieve State-of-the-Art Text-to-SQL (ACL 2024) 09-15
The Concurrency Trap in FastAPI: From Race Conditions to Deadlocks with Global Variables 08-31
MIRIX: Multi-Agent Memory System for LLM-Based Agents 07-17
Decoupled Planning and Execution: A Hierarchical Reasoning Framework for Deep Search 07-06
AutoMind: Adaptive Knowledgeable Agent for Automated Data Science 06-28
Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA 06-28
OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning 06-02
Steering Large Language Models Between Code Execution and Textual Reasoning 05-25