NP
Nanyun Peng
cs.CLcs.AIcs.LGcs.CVcs.HCcs.SIcs.CYcs.IRcs.MMcs.SD
On Valency
published · living versionsW_eure52qd·v1 · currentpublished
OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory
with Yu Zhou, Cheng-Fu Yang, Rui Sun, Di Wu +6
1 version
W_2kxyrrcm·v1published
Preprints & journals
230 papers in the corpus · 2016–2026Diffusion Language Models Change Speed Across Tasks and Languages2610.25835v1 · Mohsen Fayyaz, Ali Modarressi, Daniel Israel et al.2026 · 0 citationsarXiv
KEEP-Bench: Evaluating Evidence Preservation in Context Compression2610.26827v1 · Ziqing Man, Di Wu, Jia-Chen Gu et al.2026 · 0 citationsarXivon Valency
OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory2610.26860v1 · Yu Zhou, Cheng-Fu Yang, Rui Sun et al.2026 · 0 citationsarXivon Valency
STRIDE: Evaluating Spatiotemporal Reasoning in Driving Edge Cases2610.22795v1 · Lieqi Liu, Rui gao, Jia-Chen Gu et al.2026 · 0 citationsarXiv
Lean Graph Search for Formal Theorem Proving2610.22339v1 · Yihan Xu, Jia-Chen Gu, Junyi Zhang et al.2026 · 0 citationsarXiv
DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck2610.17184v1 · Shubham Agarwal, Akshat Gupta, Mike Heddes et al.2026 · 0 citationsarXiv
VIS-Ground: Video Interactive Storytelling with Contextual Grounding2610.09326v2 · Bingxuan Li, Yiwen Song, Xueqing Wu et al.2026 · 0 citationsarXiv
Continual Graph Memory for Mathematical Research Agents2610.02945v1 · Junyi Zhang, Jinxi Yu, Eric Hanchen Jiang et al.2026 · 0 citationsarXiv
SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting2610.04109v1 · Mingtian Tan, Palash Goyal, Mihir Parmar et al.2026 · 0 citationsarXiv
Multilinguality in Hybrid Attention LLMs2609.35378v1 · Lucas Bandarkar, Junlin Hu, Chenyuan Yang et al.2026 · 0 citationsarXiv
Overwhelmed by Choice: Studying LLM Decision Making at Scale2609.32809v1 · Yu-Chi Lin, Aryan Seth, Anshul Aravind et al.2026 · 0 citationsarXiv
LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks2606.03303v2 · Po-Nien Kung, Linfeng Song, Dawsen Hwang et al.2026 · 0 citationsarXiv
Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts2605.28042v2 · Liu O. Martin, Lucas Bandarkar, Nanyun Peng2026 · 0 citationsarXiv
Nexus : An Agentic Framework for Context-Aware Time Series Forecasting2605.14389v2 · Sarkar Snigdha Sarathi Das, Palash Goyal, Mihir Parmar et al.2026 · 0 citationsarXiv
LEAF: A Living Benchmark for Event-Augmented Forecasting2605.16358v2 · Mingtian Tan, Mihir Parmar, Palash Goyal et al.2026 · 0 citationsarXiv
The Network Structure of Mathlib2604.24797v2 · Xinze Li, Nanyun Peng, Simone Severini et al.2026 · 0 citationsarXiv
TaoBench: Do Automated Theorem Prover LLMs Generalize Beyond MathLib?2603.12744v1 · Alexander K Taylor, Junyi Zhang, Ethan Ji et al.2026 · 0 citationsarXiv
CoLyricist: Enhancing Lyric Writing with AI through Workflow-Aligned Support2602.22606v1 · Masahiro Yoshida, Bingxuan Li, Songyan Zhao et al.2026 · 1 citationarXiv
Translation as a Scalable Proxy for Multilingual Evaluation2601.11778v1 · Sheriff Issaka, Erick Rosas Gonzalez, Lieqi Liu et al.2026 · 0 citationsarXiv
MMGR: Multi-Modal Generative Reasoning Benchmark and Evaluation2512.14691v3 · Zefan Cai, Haoyi Qiu, Tianyi Ma et al.2025 · 0 citationsarXiv
ScalePRM: Training Process Reward Models by Scaling Verification Compute Without Ground Truth2512.03244v2 · Salman Rahman, Sruthi Gorantla, Arpit Gupta et al.2025 · 1 citationarXiv
TOD-ProcBench: Benchmarking Complex Instruction-Following in Task-Oriented Dialogues2511.15976v1 · Sarik Ghazarian, Abhinav Gullapalli, Swair Shah et al.2025 · 0 citationsarXiv
From Preferences to Prejudice: The Role of Alignment Tuning in Shaping Social Bias in Video Diffusion Models2510.17247v2 · Zefan Cai, Haoyi Qiu, Haozhe Zhao et al.2025 · 0 citationsarXiv
ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping2510.08457v1 · Shuang Chen, Yue Guo, Yimeng Ye et al.2025 · 0 citationsarXiv
Multilingual Routing in Mixture-of-Experts2510.04694v2 · Lucas Bandarkar, Chenyuan Yang, Mohsen Fayyaz et al.2025 · 0 citationsThe Fourteenth International Conference on Learning Representations (2026)
Decoupling Task-Solving and Output Formatting in LLM Generation2510.03595v2 · Haikang Deng, Po-Nien Kung, Nanyun Peng2025 · 0 citationsProceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics, 2026, pp. 16764-16781
VaPR -- Vision-language Preference alignment for Reasoning2510.01700v1 · Rohan Wadhawan, Fabrice Y Harel-Canada, Zi-Yi Dou et al.2025 · 0 citationsCOLM 2025
TemMed-Bench: Evaluating Temporal Medical Image Reasoning in Vision-Language Models2509.25143v2 · Junyi Zhang, Jia-Chen Gu, Wenbo Hu et al.2025 · 0 citationsarXiv
How to Make Large Language Models Generate 100% Valid Molecules?2509.23099v1 · Wen Tao, Jing Tang, Alvin Chan et al.2025 · 2 citationsarXiv
FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline2508.16514v1 · Parker Seegmiller, Kartik Mehta, Soumya Saha et al.2025 · 0 citationsarXiv
Rethinking Creativity Evaluation: A Critical Analysis of Existing Creativity Evaluations2508.05470v4 · Li-Chun Lu, Miri Liu, Pin-Chun Lu et al.2025 · 1 citationarXiv
Scaling Probabilistic Circuits via Monarch Matrices2506.12383v1 · Honghua Zhang, Meihua Dang, Benjie Wang et al.2025 · 0 citationsarXiv
DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning2506.05128v2 · Tanmay Parekh, Kartik Mehta, Ninareh Mehrabi et al.2025 · 2 citationsarXiv
AI Debate Aids Assessment of Controversial Claims2506.02175v2 · Salman Rahman, Sheriff Issaka, Ashima Suvarna et al.2025 · 1 citationarXiv
SkillVerse : Assessing and Enhancing LLMs with Tree Evaluation2506.00319v1 · Yufei Tian, Jiao Sun, Nanyun Peng et al.2025 · 0 citationsarXiv
3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model2505.22657v2 · Wenbo Hu, Yining Hong, Yanjun Wang et al.2025 · 3 citationsarXiv
PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding2505.20759v3 · Ansel Blume, Jeonghwan Kim, Hyeonjeong Ha et al.2025 · 0 citationsarXiv
The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs2505.18356v2 · Lucas Bandarkar, Nanyun Peng2025 · 0 citationsarXiv
Multimodal Cultural Safety: Evaluation Framework and Alignment Strategies2505.14972v2 · Haoyi Qiu, Kung-Hsiang Huang, Ruichen Zheng et al.2025 · 0 citationsarXiv
Enhancing Substance Use Detection in Clinical Notes with Large Language Models.40470194 · Harel-Canada, Fabrice, Salimian, Anabel, Moghanian, Brandon et al.2025 · 3 citationsResearch square. 2025
Sandcastles in the Storm: Revisiting the (Im)possibility of Strong Watermarking2505.06827v1 · Fabrice Y Harel-Canada, Boran Erol, Connor Choi et al.2025 · 0 citationsarXiv
Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 20252504.09737v1 · Nitya Thakkar, Mert Yuksekgonul, Jake Silberg et al.2025 · 4 citationsarXiv
Do "New Snow Tablets" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs2504.03786v3 · Sifan Li, Yujun Cai, Bryan Hooi et al.2025 · 0 citationsarXiv
Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization2504.01018v3 · Di Wu, Jia-Chen Gu, Kai-Wei Chang et al.2025 · 0 citationsarXiv
CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization2503.17136v1 · Brihi Joshi, Sriram Venkatapathy, Mohit Bansal et al.2025 · 0 citationsarXiv
OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles2503.17352v3 · Yihe Deng, Hritik Bansal, Fan Yin et al.2025 · 18 citationsarXiv
CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners2503.16356v3 · Yunzhi Yao, Jizhan Fang, Jia-Chen Gu et al.2025 · 2 citationsarXiv
Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence2503.05037v2 · Mohsen Fayyaz, Ali Modarressi, Hinrich Schuetze et al.2025 · 8 citationsarXiv
Structured Outputs Enable General-Purpose LLMs to be Medical Experts2503.03194v1 · Guangfu Guo, Kai Zhang, Bryan Hoo et al.2025 · 1 citationarXiv
SYNTHIA: Novel Concept Design with Affordance Composition2502.17793v4 · Hyeonjeong Ha, Xiaomeng Jin, Jeonghwan Kim et al.2025 · 0 citationsarXiv
Career total: 307 works. 230 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.