Posts by Collection

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

Learning the Generative Principles of a Symbol System from Limited Examples

Published in Cognition, 2020, 1900

Recommended citation: L. Yuan, Violet Xiang, D. Crandall, L. Smith.
Download Paper

Defending Against Microphone-Based Attacks with Personalized Noise

Published in Proceedings on Privacy Enhancing Technologies, 2021, 1900

Recommended citation: Y. Liu, Violet Xiang, E. J. Seong, A. Kapadia, D. S. Williamson.
Download Paper

How Well Do Unsupervised Learning Algorithms Model Human Real-Time and Lifelong Learning?

Published in NeurIPS 2022 Datasets & Benchmarks Track, 1900

Recommended citation: C. Zhuang*, Violet Xiang*, Y. Bai, X. Jia, N. Turk-Browne, K. Norman, J. J. DiCarlo, D. L. K. Yamins.
Download Paper

From Centralized to Self-Supervised: Pursuing Realistic Multi-Agent Reinforcement Learning

Published in NeurIPS 2023 ALOE Workshop · Poster, 1900

Recommended citation: Violet Xiang, L. Cross, J.-P. Fränken, N. Haber.
Download Paper

Animate Agent World Modeling Benchmark

Published in Proceedings of the Annual Meeting of the Cognitive Science Society, 2024, 1900

Recommended citation: Logan Cross, Violet Xiang, Nick Haber, Daniel Yamins.
Download Paper

The BabyView Dataset: High-Resolution Egocentric Videos of Infants’ and Young Children’s Everyday Experiences

Published in Computational Cognitive Neuroscience 2025 Proceedings, 1900

Recommended citation: B. Long*, R. Sparks*, Violet Xiang*, S. Stojanov*, et al.
Download Paper

The BabyView Camera: Designing a New Head-Mounted Camera to Capture Children’s Early Social and Visual Environments

Published in Behavior Research Methods, Volume 56, 2024, 1900

Recommended citation: B. Long, S. Goodin, G. Kachergis, V. A. Marchman, S. F. Radwan, R. Z. Sparks, Violet Xiang, et al.
Download Paper

Rethinking Social Cognition Benchmarks: Why Context Matters for Reliable Evaluation

Published in Manuscript, 2024, 1900

Recommended citation: Violet Xiang, Logan Cross, Diyi Yang, Nick Haber.
Download Paper

Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models

Published in ICLR 2025 · Poster, 1900

Recommended citation: L. Cross, Violet Xiang, A. Bhatia, D. L. K. Yamins, N. Haber.
Download Paper

Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning

Published in NeurIPS 2025 Efficient Reasoning Workshop · Spotlight, 1900

Recommended citation: Violet Xiang, C. Blagden, R. Rafailov, N. Lile, S. Truong, C. Finn, N. Haber.
Download Paper

Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought

Published in Preprint, 2025, 1900

Recommended citation: Violet Xiang, C. Snell, K. Gandhi, A. Albalak, A. Singh, C. Blagden, D. Phung, R. Rafailov, N. Lile, D. Mahan, L. Castricato, J.-P. Fränken, N. Haber, C. Finn.
Download Paper

ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code

Published in NeurIPS 2025 Datasets & Benchmarks Track · Spotlight, 1900

Recommended citation: T. Hua, H. Hua, Violet Xiang, B. Klieger, S. Truong, W. Liang, F.-Y. Sun, N. Haber.
Download Paper

ExpRL: Exploratory RL for LLM Mid-Training

Published in COLM 2026, 1900

Recommended citation: Violet Xiang, A. Setlur, C. Blagden, N. Haber, A. Kumar.
Download Paper

LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing

Published in EACL 2026 · Long Paper, 1900

Recommended citation: D. Fein*, S. Russo*, Violet Xiang*, K. Jolly, R. Rafailov, N. Haber.
Download Paper

One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models

Published in ICML 2026, 1900

Recommended citation: D. Fein*, M. Lamparth*, Violet Xiang, M. J. Kochenderfer, N. Haber.
Download Paper

Test-Time Self Improvement by Scaling Unsupervised World Internalization

Published in Under review at ICLR 2027, 1900

Experiments used Qwen 9B and 27B models across Harvey, StudyBench, and Equational Theories. U-WIN increased the share of agentic trajectories that recall environment knowledge from 20.6% to 99.8%. Self-written notes also outperformed token-matched raw documents or observations for knowledge retention.

Recommended citation: Violet Xiang, M. Khalifa, I. Wu, Y. Shen, J. Leskovec, N. Haber, A. Kumar.
Download Paper

Talk 1 on Relevant Topic in Your Field

Published: March 01, 2012

This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!

Tutorial 1 on Relevant Topic in Your Field

Published: March 01, 2013

More information here

Talk 2 on Relevant Topic in Your Field

Published: February 01, 2014

More information here

Conference Proceeding talk 3 on Relevant Topic in Your Field

Published: March 01, 2014

This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.