Sercan O Arik

CoDA: Agentic Systems for Collaborative Data Visualization

ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality

Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies

MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement

Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

LLM Alignment as Retriever Optimization: An Information Retrieval Perspective

Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG

Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in Realistic Environments

Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL

Retrieval Augmented Time Series Forecasting

From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation

Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL

Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies

SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging

Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models

Embedding-Converter: A Unified Framework for Cross-Model Embedding Transformation

Retrieval Augmented Time Series Forecasting

LLM-Guided Self-Supervised Tabular Learning With Task-Specific Pre-text Tasks