YT
Yulia Tsvetkov
cs.CLcs.LGcs.AIcs.CVcs.CYcs.SIstat.MLcs.CRcs.HCBlackLivesMatter
On Valency
published · living versionsW_3sasu23e·v1 · currentpublished
s: Simple Scaling of Swarms via Cooperative Multi-agent RL
with Kunal Jha, Gonçalo Faria, Shuyue Stella Li, Scott Geng +4
1 version
Preprints & journals
153 papers in the corpus · 2015–2026Pushback in a Haystack: Language Models Respond to Factual Errors Ambiguously and Ineffectively2610.17703v1 · Li Lucy, Myra Cheng, Svenja Guhr et al.2026 · 0 citationsarXiv
IsoVRBench: Video Reward Modeling Without Human Feedback2610.17234v1 · Shuyue Stella Li, Jacqueline He, Jiahui Chen et al.2026 · 0 citationsarXiv
Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning2610.17456v1 · Shangbin Feng, Yulia Tsvetkov, Jan Kautz et al.2026 · 0 citationsarXiv
Reading, Not Manipulating: Leveraging Router Logits for Multimodal Safety in MoE Vision-Language Models2610.07774v1 · Ziyuan Yang, Wenxuan Ding, Shangbin Feng et al.2026 · 0 citationsarXiv
ExploreNet: Learning Where to Explore in Diffusion GRPO2609.38329v1 · Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov et al.2026 · 0 citationsarXiv
Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts2609.35641v1 · Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov et al.2026 · 0 citationsarXiv
Save Your Saturated Data: Learning Beyond Reward Saturation in Group-Based RL2609.33126v1 · Ziyuan Yang, Yike Wang, Shangbin Feng et al.2026 · 0 citationsarXiv
Before the Rollout Ends: Early Terminal Reward Prediction for Long-horizon Coding Agents2609.31995v1 · Jihan Yao, Sihan Zeng, Shangbin Feng et al.2026 · 0 citationsarXiv
One Form to Transfer Them All: Pretraining Multilingual Language Models Beyond Native Orthography2608.25904v3 · Muge Zhang, Aaron Jencks, Krishna Badikela et al.2026 · 0 citationsarXiv
Evaluating Large Language Models for Antisemitic Incident Classification2607.04890v1 · Karina Halevy, Julia Mendelsohn, Chan Young Park et al.2026 · 0 citationsarXiv
Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues2606.31644v3 · Mohammadamin Shafiei, Shuyue Stella Li, Yulia Tsvetkov2026 · 0 citationsarXiv
Multilingual Reasoning Cascades Need More Context2606.27306v2 · Arnav Mazumder, Dengjia Zhang, Shuyue Stella Li et al.2026 · 0 citationsarXiv
Scaling Participation in Modular AI Systems2606.07812v2 · Shangbin Feng, Yike Wang, Weijia Shi et al.2026 · 0 citationsarXiv
Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest2604.08525v3 · Addison J. Wu, Ryan Liu, Shuyue Stella Li et al.2026 · 2 citationsarXiv
InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioning2603.05909v1 · Maksym Taranukhin, Shuyue Stella Li, Evangelos Milios et al.2026 · 0 citationsarXiv
Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems2602.05176v1 · Ziyuan Yang, Wenxuan Ding, Shangbin Feng et al.2026 · 0 citationsarXiv
RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments2511.07317v2 · Zhiyuan Zeng, Hamish Ivison, Yiping Wang et al.2025 · 0 citationsarXiv
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)2510.22954v2 · Liwei Jiang, Yuanjun Chai, Margaret Li et al.2025 · 7 citationsarXiv
PrefPalette: Personalized Preference Modeling with Latent Attributes2507.13541v1 · Shuyue Stella Li, Melanie Sclar, Hunter Lang et al.2025 · 0 citationsarXiv
Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?2506.18322v1 · Yiwei Yang, Chung Peng Lee, Shangbin Feng et al.2025 · 0 citationsarXiv
Spurious Rewards: Rethinking Training Signals in RLVR2506.10947v2 · Rulin Shao, Shuyue Stella Li, Rui Xin et al.2025 · 1 citationarXiv
MADFormer: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation2506.07999v1 · Junhao Chen, Yulia Tsvetkov, Xiaochuang Han2025 · 0 citationsarXiv
Precise Information Control in Long-Form Text Generation2506.06589v2 · Jacqueline He, Howard Yen, Margaret Li et al.2025 · 0 citationsarXiv
SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat2506.04721v3 · Yuru Jiang, Wenxuan Ding, Shangbin Feng et al.2025 · 0 citationsarXiv
GuessBench: Sensemaking Multimodal Creativity in the Wild2506.00814v2 · Zifeng Zhu, Shangbin Feng, Herun Wan et al.2025 · 0 citationsarXiv
Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment2506.00845v3 · Yizhuo Zhang, Heng Wang, Shangbin Feng et al.2025 · 0 citationsarXiv
Data Swarms: Optimizable Generation of Synthetic Evaluation Data2506.00741v2 · Shangbin Feng, Yike Wang, Weijia Shi et al.2025 · 0 citationsarXiv
ScienceMeter: Tracking Scientific Knowledge Updates in Language Models2505.24302v3 · Yike Wang, Shangbin Feng, Yulia Tsvetkov et al.2025 · 0 citationsarXiv
A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage2504.21035v4 · Rui Xin, Niloofar Mireshghallah, Shuyue Stella Li et al.2025 · 2 citationsarXiv
Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection2504.11900v3 · Kabir Ahuja, Melanie Sclar, Yulia Tsvetkov2025 · 1 citationarXiv
FACTS&EVIDENCE: An Interactive Tool for Transparent Fine-Grained Factual Verification of Machine-Generated Text2503.14797v1 · Varich Boonsanong, Vidhisha Balachandran, Xiaochuang Han et al.2025 · 1 citationarXiv
Medical Hallucination in Foundation Models and Their Impact on Healthcare10.1101/2025.02.28.25323115v2 · Kim, Y., Jeong, H., Chen, S. et al.2025 · 137 citationsmedRxiv
When One LLM Drools, Multi-LLM Collaboration Rules2502.04506v1 · Shangbin Feng, Wenxuan Ding, Alisa Liu et al.2025 · 1 citationarXiv
Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems2502.04510v2 · Shangbin Feng, Zifeng Wang, Palash Goyal et al.2025 · 0 citationsarXiv
Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning2412.12175v1 · Melanie Sclar, Jane Yu, Maryam Fazel-Zarandi et al.2024 · 0 citationsarXiv
ComPO: Community Preferences for Language Model Personalization2410.16027v1 · Sachin Kumar, Chan Young Park, Yulia Tsvetkov et al.2024 · 0 citationsarXiv
Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence2410.11163v2 · Shangbin Feng, Zifeng Wang, Yike Wang et al.2024 · 2 citationsarXiv
Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only2410.11055v1 · Jihan Yao, Wenxuan Ding, Shangbin Feng et al.2024 · 0 citationsarXiv
Biased AI can Influence Political Decision-Making2410.06415v4 · Jillian Fisher, Shangbin Feng, Robert Aron et al.2024 · 4 citationsarXiv
Locating Information Gaps and Narrative Inconsistencies Across Languages: A Case Study of LGBT People Portrayals on Wikipedia2410.04282v1 · Farhan Samir, Chan Young Park, Anjalie Field et al.2024 · 3 citationsarXiv
CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming2410.02677v2 · Yu Ying Chiu, Liwei Jiang, Bill Yuchen Lin et al.2024 · 1 citationarXiv
JPEG-LM: LLMs as Image Generators with Canonical Codec Representations2408.08459v2 · Xiaochuang Han, Marjan Ghazvininejad, Pang Wei Koh et al.2024 · 1 citationarXiv
Know Your Limits: A Survey of Abstention in Large Language Models2407.18418v3 · Bingbing Wen, Jihan Yao, Shangbin Feng et al.2024 · 42 citationsarXiv
MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization2407.08818v2 · Orevaoghene Ahia, Sachin Kumar, Hila Gonen et al.2024 · 5 citationsarXiv
ValueScope: Unveiling Implicit Norms and Values via Return Potential Model of Social Interactions2407.02472v2 · Chan Young Park, Shuyue Stella Li, Hayoung Jung et al.2024 · 0 citationsarXiv
Voices Unheard: NLP Resources and Models for Yorùbá Regional Dialects2406.19564v1 · Orevaoghene Ahia, Anuoluwapo Aremu, Diana Abagyan et al.2024 · 0 citationsarXiv
Can LLM Graph Reasoning Generalize beyond Pattern Memorization?2406.15992v2 · Yizhuo Zhang, Heng Wang, Shangbin Feng et al.2024 · 13 citationsarXiv
Teaching LLMs to Abstain across Languages via Multilingual Feedback2406.15948v3 · Shangbin Feng, Weijia Shi, Yike Wang et al.2024 · 4 citationsarXiv
Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration2406.15951v2 · Shangbin Feng, Taylor Sorensen, Yuhan Liu et al.2024 · 18 citationsarXiv
MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning2406.00922v3 · Shuyue Stella Li, Vidhisha Balachandran, Shangbin Feng et al.2024 · 19 citationsarXiv
Career total: 215 works. 153 are in this corpus.Showing the 50 most recent.
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.