AIConfPaper
← Search

Sercan O Arik

31 accepted papers

2026

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

Shayne Longpre, Sneha Kudugunta, Niklas Muennighoff, I-Hung Hsu, Isaac Rayburn Caswell, Alex Pentland +3
ICLR 2026poster

Scaling laws research has focused overwhelmingly on English—yet the most prominent AI models explicitly serve billions of international users. In this work, we undertake the largest multilingual scaling laws study to date, totaling 774 multilingual training experiments, spanning 10M-8B model paramet…

Cited by 0Source ↗Scholar ↗
2026

CoDA: Agentic Systems for Collaborative Data Visualization

Zichen Chen, Jiefeng Chen, Sercan O Arik, Misha Sra, Tomas Pfister, Jinsung Yoon
ICLR 2026poster

Automating data visualization from natural language is crucial for data science, yet current systems struggle with complex datasets containing multiple files and iterative refinement. Existing approaches, including simple single- or multi-agent systems, often oversimplify the task, focusing on initi…

Cited by 0Source ↗code ↗Scholar ↗
2026

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

Han Zhou, Xingchen Wan, Ruoxi Sun, Hamid Palangi, Shariq Iqbal, Ivan Vulić +2
ICLR 2026poster

Large language models, employed as multiple agents that interact and collaborate with each other, have excelled at solving complex tasks. The agents are programmed with prompts that declare their functionality, along with the topologies that orchestrate interactions across agents. Designing prompts…

Cited by 0Source ↗Scholar ↗
2025

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

Fei Wang, Xingchen Wan, Ruoxi Sun, Jiefeng Chen, Sercan O Arik
ACL 2025long

Retrieval augmented generation (RAG), while effectively integrating external knowledge to address the inherent limitations of large language models (LLMs), can be hindered by imperfect retrieval that contain irrelevant, misleading, or even malicious information. Previous studies have rarely connecte…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

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

Hongjin SU, Howard Yen, Mengzhou Xia, Weijia Shi, Niklas Muennighoff, Han-yu Wang +9
ICLR 2025spotlight

Existing retrieval benchmarks primarily consist of information-seeking queries (e.g., aggregated questions from search engines) where keyword or semantic-based retrieval is usually sufficient. However, many complex real-world queries require in-depth reasoning to identify relevant documents that go…

Cited by 24Source ↗PDF ↗Scholar ↗
2025

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

Mohammadreza Pourreza, Hailong Li, Ruoxi Sun, Yeounoh Chung, Shayan Talaei, Gaurav Tarlok Kakkar +4
ICLR 2025poster

We present CHASE-SQL, a novel framework addressing large language model (LLM) performance challenges for Text-to-SQL tasks by leveraging multi-agent modeling and test-time compute for improved candidate generation and selection. CHASE-SQL uses LLMs to generate diverse SQL candidates with: (1) a divi…

Cited by 36Source ↗PDF ↗Scholar ↗
2025

Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modeling

Maximillian Chen, Ruoxi Sun, Sercan O Arik
ACL 2025finding

Conversational assistants are increasingly popular across diverse real-world applications, highlighting the need for advanced multimodal speech modeling. Speech, as a natural mode of communication, encodes rich user-specific characteristics such as speaking rate and pitch, making it critical for eff…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

FLAIRR-TS - Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series

Gunjan Jalori, Preetika Verma, Sercan O Arik
EMNLP 2025

Time series Forecasting with large language models (LLMs) requires bridging numerical patterns and natural language. Effective forecasting on LLM often relies on extensive pre-processing and fine-tuning. Recent studies show that a frozen LLM can rival specialized forecasters when supplied with a car

Cited by 0Source ↗PDF ↗Scholar ↗
2025

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

Xingchen Wan, Han Zhou, Ruoxi Sun, Sercan O Arik
ICLR 2025poster

Recent advances in long-context large language models (LLMs) have led to the emerging paradigm of many-shot in-context learning (ICL), where it is observed that scaling many more demonstrating examples beyond the conventional few-shot setup in the context can lead to performance benefits. However, d…

Cited by 2Source ↗PDF ↗Scholar ↗
2025

LLM Alignment as Retriever Optimization: An Information Retrieval Perspective

Bowen Jin, Jinsung Yoon, Zhen Qin, Ziqi Wang, Wei Xiong, Yu Meng +2
ICML 2025poster

Large Language Models (LLMs) have revolutionized artificial intelligence with capabilities in reasoning, coding, and communication, driving innovation across industries. Their true potential depends on effective alignment to ensure correct, trustworthy and ethical behavior, addressing challenges lik…

Cited by 1Source ↗PDF ↗Scholar ↗
2025

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

Hongjin SU, Ruoxi Sun, Jinsung Yoon, Pengcheng Yin, Tao Yu, Sercan O Arik
ICLR 2025poster

Autonomous agents powered by large language models (LLMs) have the potential to enhance human capabilities, assisting with digital tasks from sending emails to performing data analysis. The abilities of existing LLMs at such tasks are often hindered by the lack of high-quality agent data from the…

Cited by 8Source ↗PDF ↗Scholar ↗
2025

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

Maximillian Chen, Ruoxi Sun, Tomas Pfister, Sercan O Arik
ICLR 2025poster

Large language models (LLMs), optimized through human feedback, have rapidly emerged as a leading paradigm for developing intelligent conversational assistants. However, despite their strong performance across many benchmarks, LLM-based agents might still lack conversational skills such as disambigu…

Cited by 8Source ↗PDF ↗Scholar ↗
2025

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

Bowen Jin, Jinsung Yoon, Jiawei Han, Sercan O Arik
ICLR 2025poster

Retrieval-augmented generation (RAG) empowers large language models (LLMs) to utilize external knowledge sources. The increasing capacity of LLMs to process longer input sequences opens up avenues for providing more retrieved information, to potentially enhance the quality of generated outputs. Fro…

Cited by 19Source ↗PDF ↗Scholar ↗
2025

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

Jaehyun Nam, Jinsung Yoon, Jiefeng Chen, Jinwoo Shin, Sercan O Arik, Tomas Pfister
NeurIPS 2025poster

Agents based on large language models (LLMs) for machine learning engineering (MLE) can automatically implement ML models via code generation. However, existing approaches to build such agents often rely heavily on inherent LLM knowledge and employ coarse exploration strategies that modify the entir…

Cited by 0Source ↗Scholar ↗
2025

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

Pritam Sarkar, Sayna Ebrahimi, Ali Etemad, Ahmad Beirami, Sercan O Arik, Tomas Pfister
ICLR 2025poster

Despite their significant advancements, Multimodal Large Language Models (MLLMs) often generate factually inaccurate information, referred to as hallucination. In this work, we address object hallucinations in MLLMs, where information is generated about an object not present in the input image. We i…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Chain of Agents: Large Language Models Collaborating on Long-Context Tasks

Yusen Zhang, Ruoxi Sun, Yanfei Chen, Tomas Pfister, Rui Zhang, Sercan O Arik
NeurIPS 2024poster

Addressing the challenge of effectively processing long contexts has become a critical issue for Large Language Models (LLMs). Two common strategies have emerged: 1) reducing the input length, such as retrieving relevant chunks by Retrieval-Augmented Generation (RAG), and 2) expanding the context wi…

Cited by 31Source ↗PDF ↗Scholar ↗
2024

Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning

Sungwon Han, Jinsung Yoon, Sercan O Arik, Tomas Pfister
ICML 2024poster

Large Language Models (LLMs), with their remarkable ability to tackle challenging and unseen reasoning problems, hold immense potential for tabular learning, that is vital for many real-world applications. In this paper, we propose a novel in-context learning framework, FeatLLM, which employs LLMs a…

Cited by 24Source ↗PDF ↗code ↗Scholar ↗
2024

Matryoshka-Adaptor: Unsupervised and Supervised Tuning for Smaller Embedding Dimensions

Jinsung Yoon, Rajarishi Sinha, Sercan O Arik, Tomas Pfister
EMNLP 2024main

Embeddings from Large Language Models (LLMs) have emerged as critical components in various applications, particularly for information retrieval. While high-dimensional embeddings generally demonstrate superior performance as they contain more salient information, their practical application is freq…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting

Defu Cao, Furong Jia, Sercan O Arik, Tomas Pfister, Yixiang Zheng, Wen Ye +1
ICLR 2024poster

The past decade has witnessed significant advances in time series modeling with deep learning. While achieving state-of-the-art results, the best-performing architectures vary highly across applications and domains. Meanwhile, for natural language processing, the Generative Pre-trained Transformer (…

Cited by 202Source ↗PDF ↗code ↗Scholar ↗
2024

Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization

Xingchen Wan, Ruoxi Sun, Hootan Nakhost, Sercan O Arik
NeurIPS 2024poster

Large language models have demonstrated remarkable capabilities but their performance is heavily reliant on effective prompt engineering. Automatic prompt optimization (APO) methods are designed to automate this and can be broadly categorized into those targeting instructions (instruction optimizati…

Cited by 13Source ↗PDF ↗Scholar ↗
2023

Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs

Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan O Arik, Tomas Pfister, Somesh Jha
EMNLP 2023long findings

Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes decision-making scenarios is still limited due to the potential for errors. *Selective prediction* is a technique that can…

Cited by 0Source ↗Scholar ↗
2023

Koopman Neural Operator Forecaster for Time-series with Temporal Distributional Shifts

Rui Wang, Yihe Dong, Sercan O Arik, Rose Yu
ICLR 2023poster

Temporal distributional shifts, with underlying dynamics changing over time, frequently occur in real-world time series and pose a fundamental challenge for deep neural networks (DNNs). In this paper, we propose a novel deep sequence model based on the Koopman theory for time series forecasting: Koo…

Cited by 17Source ↗PDF ↗Scholar ↗
2023

Universal Self-Adaptive Prompting

Xingchen Wan, Ruoxi Sun, Hootan Nakhost, Hanjun Dai, Julian Martin Eisenschlos, Sercan O Arik +1
EMNLP 2023long main

A hallmark of modern large language models (LLMs) is their impressive general zero-shot and few-shot abilities, often elicited through in-context learning (ICL) via prompting. However, while highly coveted and being the most general, zero-shot performances in LLMs are still typically weaker due to t…

Cited by 0Source ↗Scholar ↗
2022

Decoupling Local and Global Representations of Time Series

Sana Tonekaboni, Chun-Liang Li, Sercan O. Arik, Anna Goldenberg, Tomas Pfister
AISTATS 2022poster

Real-world time series data are often generated from several sources of variation. Learning representations that capture the factors contributing to this variability enables better understanding of the data via its underlying generative process and can lead to improvements in performance on downstre…

Cited by 29Source ↗PDF ↗code ↗Scholar ↗
2022

Self-Supervised Learning with an Information Maximization Criterion

Serdar Ozsoy, Shadi Hamdan, Sercan O Arik, Deniz Yuret, Alper Tunga Erdogan
NeurIPS 2022accept

Self-supervised learning allows AI systems to learn effective representations from large amounts of data using tasks that do not require costly labeling. Mode collapse, i.e., the model producing identical representations for all inputs, is a central problem to many self-supervised learning approache…

Cited by 40Source ↗PDF ↗code ↗Scholar ↗
2021

Controlling Neural Networks with Rule Representations

Sungyong Seo, Sercan O Arik, Jinsung Yoon, Xiang Zhang, Kihyuk Sohn, Tomas Pfister
NeurIPS 2021poster

We propose a novel training method that integrates rules into deep learning, in a way the strengths of the rules are controllable at inference. Deep Neural Networks with Controllable Rule Representations (DeepCTRL) incorporates a rule encoder into the model coupled with a rule-based objective, enabl…

Cited by 50Source ↗PDF ↗Scholar ↗
2020

Distilling Effective Supervision From Severe Label Noise

Zizhao Zhang, Han Zhang, Sercan O. Arik, Honglak Lee, Tomas Pfister
CVPR 2020poster

Collecting large-scale data with clean labels for supervised training of neural networks is practically challenging. Although noisy labels are usually cheap to acquire, existing methods suffer a lot from label noise. This paper targets at the challenge of robust training at high label noise regimes.…

Cited by 174PDF ↗code ↗Scholar ↗
2018

Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning

Wei Ping, Kainan Peng, Andrew Gibiansky, Sercan O. Arik, Ajay Kannan, Sharan Narang +2
ICLR 2018poster

We present Deep Voice 3, a fully-convolutional attention-based neural text-to-speech (TTS) system. Deep Voice 3 matches state-of-the-art neural speech synthesis systems in naturalness while training an order of magnitude faster. We scale Deep Voice 3 to dataset sizes unprecedented for TTS, training…

Cited by 586Source ↗PDF ↗Scholar ↗