LL
Lajanugen Logeswaran
cs.CLcs.AIcs.LGcs.CVcs.HCcs.CYcs.IRcs.NEstat.ML
On Valency
published · living versionsW_gb4p66m9·v1 · currentpublished
The Culture Within: Towards Mechanistic Understanding of Cultural Reasoning in LLMs
with Samee Arif, Furkan Danisman, Angana Borah, Honglak Lee +4
1 version
W_t6vmu6zg·v1published
Preprints & journals
37 papers in the corpus · 2016–2026The Culture Within: Towards Mechanistic Understanding of Cultural Reasoning in LLMs2610.27202v1 · Samee Arif, Furkan Danisman, Angana Borah et al.2026 · 0 citationsarXivon Valency
Co-Evolving Actor-Conditioned Critics for Non-Verifiable Generation2608.30397v1 · Jinyoung Kim, Muhammad Khalifa, Lajanugen Logeswaran et al.2026 · 0 citationsarXiv
Scaling Web Agent Training through Automatic Data Generation and Fine-grained Evaluation2602.12544v1 · Lajanugen Logeswaran, Jaekyeom Kim, Sungryull Sohn et al.2026 · 0 citationsarXiv
Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation2601.14691v2 · Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim et al.2026 · 0 citationsarXiv
Selective LoRA for Visual Tokens and Attention Heads2512.19219v2 · Tiange Luo, Lajanugen Logeswaran, Jaekyeom Kim et al.2025 · 0 citationsarXiv
Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languages2512.02841v1 · Lechen Zhang, Yusheng Zhou, Tolga Ergen et al.2025 · 1 citationarXiv
Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?2507.13490v1 · Siqi Shen, Mehar Singh, Lajanugen Logeswaran et al.2025 · 0 citationsarXiv
Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents2505.12632v1 · Yunseok Jang, Yeda Song, Sungryull Sohn et al.2025 · 2 citationsarXiv
Visual Test-time Scaling for GUI Agent Grounding2505.00684v2 · Tiange Luo, Lajanugen Logeswaran, Justin Johnson et al.2025 · 3 citationsarXiv
Process Reward Models That Think2504.16828v5 · Muhammad Khalifa, Rishabh Agarwal, Lajanugen Logeswaran et al.2025 · 2 citationsarXiv
MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?2504.09702v3 · Yunxiang Zhang, Muhammad Khalifa, Shitanshu Bhushan et al.2025 · 2 citationsarXiv
Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents2410.22552v1 · Jaekyeom Kim, Dong-Ki Kim, Lajanugen Logeswaran et al.2024 · 4 citationsarXiv
SPRIG: Improving Large Language Model Performance by System Prompt Optimization2410.14826v3 · Lechen Zhang, Tolga Ergen, Lajanugen Logeswaran et al.2024 · 3 citationsarXiv
Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense2405.04655v1 · Siqi Shen, Lajanugen Logeswaran, Moontae Lee et al.2024 · 23 citationsarXiv
Small Language Models Need Strong Verifiers to Self-Correct Reasoning2404.17140v2 · Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran et al.2024 · 6 citationsarXiv
AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents2403.08978v2 · Yao Fu, Dong-Ki Kim, Jaekyeom Kim et al.2024 · 4 citationsarXiv
TOD-Flow: Modeling the Structure of Task-Oriented Dialogues2312.04668v1 · Sungryull Sohn, Yiwei Lyu, Anthony Liu et al.2023 · 3 citationsarXiv
Code Models are Zero-shot Precondition Reasoners2311.09601v1 · Lajanugen Logeswaran, Sungryull Sohn, Yiwei Lyu et al.2023 · 1 citationarXiv
You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments2311.09718v2 · Bangzhao Shu, Lechen Zhang, Minje Choi et al.2023 · 12 citationsarXiv
When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models2311.10054v3 · Mingqian Zheng, Jiaxin Pei, Lajanugen Logeswaran et al.2023 · 81 citationsarXiv
MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning2310.16730v1 · Dong-Ki Kim, Sungryull Sohn, Lajanugen Logeswaran et al.2023 · 0 citationsarXiv
Merging Generated and Retrieved Knowledge for Open-Domain QA2310.14393v1 · Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran et al.2023 · 14 citationsarXiv
Exploring Demonstration Ensembling for In-context Learning2308.08780v2 · Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee et al.2023 · 0 citationsarXiv
GRACE: Discriminator-Guided Chain-of-Thought Reasoning2305.14934v3 · Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee et al.2023 · 7 citationsarXiv
A Picture is Worth a Thousand Words: Language Models Plan from Pixels2303.09031v1 · Anthony Z. Liu, Lajanugen Logeswaran, Sungryull Sohn et al.2023 · 4 citationsarXiv
Multimodal Subtask Graph Generation from Instructional Videos2302.08672v1 · Yunseok Jang, Sungryull Sohn, Lajanugen Logeswaran et al.2023 · 5 citationsarXiv
Unsupervised Task Graph Generation from Instructional Video Transcripts2302.09173v2 · Lajanugen Logeswaran, Sungryull Sohn, Yunseok Jang et al.2023 · 8 citationsarXiv
Exploring the Benefits of Training Expert Language Models over Instruction Tuning2302.03202v2 · Joel Jang, Seungone Kim, Seonghyeon Ye et al.2023 · 23 citationsarXiv
Knowledge Unlearning for Mitigating Privacy Risks in Language Models2210.01504v2 · Joel Jang, Dongkeun Yoon, Sohee Yang et al.2022 · 88 citationsarXiv
Few-shot Subgoal Planning with Language Models2205.14288v1 · Lajanugen Logeswaran, Yao Fu, Moontae Lee et al.2022 · 8 citationsarXiv
Few-shot Reranking for Multi-hop QA via Language Model Prompting2205.12650v3 · Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee et al.2022 · 8 citationsarXiv
Few-shot Sequence Learning with Transformers2012.09543v1 · Lajanugen Logeswaran, Ann Lee, Myle Ott et al.2020 · 7 citationsarXiv
Zero-Shot Entity Linking by Reading Entity Descriptions1906.07348v1 · Lajanugen Logeswaran, Ming-Wei Chang, Kenton Lee et al.2019 · 247 citationsarXiv
Content preserving text generation with attribute controls1811.01135v1 · Lajanugen Logeswaran, Honglak Lee, Samy Bengio2018 · 97 citationsarXiv
An efficient framework for learning sentence representations1803.02893v1 · Lajanugen Logeswaran, Honglak Lee2018 · 428 citationsarXiv
Sentence Ordering and Coherence Modeling using Recurrent Neural Networks1611.02654v2 · Lajanugen Logeswaran, Honglak Lee, Dragomir Radev2016 · 114 citationsarXiv
Generative Adversarial Text to Image Synthesis1605.05396v2 · Scott Reed, Zeynep Akata, Xinchen Yan et al.2016 · 2,497 citationsarXiv
Career total: 60 works. 37 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.