SY
Semih Yavuz
cs.CLcs.AIcs.LGcs.SEcs.IRcs.MAcs.CVcs.PLstat.MLcs.DC
On Valency
published · living versionsW_hy7hbh5s·v1 · currentpublished
TEX: Test-Time Scaling Testing Agents via Execution-based Cross-Validation
with Akash Gokul, Srijan Bansal, Yingbo Zhou
1 version
Preprints & journals
61 papers in the corpus · 2013–2026TEX: Test-Time Scaling Testing Agents via Execution-based Cross-Validation2610.27290v1 · Akash Gokul, Srijan Bansal, Yingbo Zhou et al.2026 · 0 citationsarXivon Valency
Understanding the Synergy between SFT, RLVR, and OPD in LLM Post-Training2609.31900v1 · Emre Can Acikgoz, Yang Li, Zeyu Leo Liu et al.2026 · 0 citationsarXiv
Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents2609.27334v1 · Yefan Zhou, Yang Li, Zeyu Leo Liu et al.2026 · 0 citationsarXiv
RISE: Recursive Improvement via Self-Extrapolating Policy Distillation2609.05295v1 · Yang Li, Semih Yavuz, Shafiq Joty2026 · 0 citationsarXiv
EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?2609.04280v3 · Zixuan Ke, Vaidehi Patil, Haizhou Shi et al.2026 · 0 citationsarXiv
Learning Generalizable Behaviors for Terminal Agents2608.22631v3 · Yihang Yao, Bo Pang, Xuan Phi Nguyen et al.2026 · 0 citationsarXiv
Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models2607.01844v1 · Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao et al.2026 · 0 citationsarXiv
Procedural Memory Distillation: Online Reflection for Self-Improving Language Models2607.01480v1 · Ye Liu, Srijan Bansal, Bo Pang et al.2026 · 0 citationsarXiv
Reward Modeling for Multi-Agent Orchestration2606.13598v1 · King Yeung Tsang, Zihao Zhao, Vishal Venkataramani et al.2026 · 0 citationsarXiv
Learning from Language Feedback via Variational Policy Distillation2605.15113v2 · Yang Li, Erik Nijkamp, Semih Yavuz et al.2026 · 0 citationsarXiv
VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?2603.15921v1 · Srijan Bansal, Jiao Fangkai, Yilun Zhou et al.2026 · 0 citationsarXiv
MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems2602.03053v2 · Vishal Venkataramani, Haizhou Shi, Zixuan Ke et al.2026 · 0 citationsarXiv
MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks2601.14652v5 · Zixuan Ke, Yifei Ming, Austin Xu et al.2026 · 0 citationsarXiv
SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization2512.20482v1 · Revanth Gangi Reddy, Ye Liu, Wenting Zhao et al.2025 · 0 citationsarXiv
SSR: Socratic Self-Refine for Large Language Model Reasoning2511.10621v1 · Haizhou Shi, Ye Liu, Bo Pang et al.2025 · 0 citationsarXiv
Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement2511.05931v1 · Hiroaki Hayashi, Bo Pang, Wenting Zhao et al.2025 · 0 citationsarXiv
Retrofitting Small Multilingual Models for Retrieval: Matching 7B Performance with 300M Parameters2510.14274v2 · Lifu Tu, Yingbo Zhou, Semih Yavuz2025 · 0 citationsarXiv
VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents2507.04590v1 · Rui Meng, Ziyan Jiang, Ye Liu et al.2025 · 0 citationsarXiv
Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining2505.11293v2 · Raghuveer Thirukovalluru, Rui Meng, Ye Liu et al.2025 · 1 citationarXiv
SweRank: Software Issue Localization with Code Ranking2505.07849v2 · Revanth Gangi Reddy, Tarun Suresh, JaeHyeok Doo et al.2025 · 2 citationsarXiv
Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings2503.15620v1 · Austin Xu, Srijan Bansal, Yifei Ming et al.2025 · 7 citationsarXiv
Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown2411.15993v2 · Lifu Tu, Rui Meng, Shafiq Joty et al.2024 · 0 citationsarXiv
CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval2411.12644v3 · Ye Liu, Rui Meng, Shafiq Joty et al.2024 · 2 citationsarXiv
JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking2411.00142v1 · Tong Niu, Shafiq Joty, Ye Liu et al.2024 · 2 citationsarXiv
P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains2410.09207v1 · Simeng Han, Aaron Yu, Rui Shen et al.2024 · 3 citationsarXiv
VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks2410.05160v3 · Ziyan Jiang, Rui Meng, Xinyi Yang et al.2024 · 1 citationarXiv
Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification2410.05318v1 · Zhenwen Liang, Ye Liu, Tong Niu et al.2024 · 1 citationarXiv
Traffic Light or Light Traffic? Investigating Phrasal Semantics in Large Language Models2410.02308v1 · Rui Meng, Ye Liu, Lifu Tu et al.2024 · 0 citationsarXiv
Parameter-Efficient Detoxification with Contrastive Decoding2401.06947v1 · Tong Niu, Caiming Xiong, Semih Yavuz et al.2024 · 2 citationsarXiv
Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding2312.06149v4 · Lifu Tu, Semih Yavuz, Jin Qu et al.2023 · 3 citationsarXiv
DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text2310.20170v1 · Wenting Zhao, Ye Liu, Tong Niu et al.2023 · 6 citationsarXiv
L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models2309.17446v2 · Ansong Ni, Pengcheng Yin, Yilun Zhao et al.2023 · 22 citationsarXiv
Investigating Answerability of LLMs for Long-Form Question Answering2309.08210v1 · Meghana Moorthy Bhat, Rui Meng, Ye Liu et al.2023 · 2 citationsarXiv
XGen-7B Technical Report2309.03450v1 · Erik Nijkamp, Tian Xie, Hiroaki Hayashi et al.2023 · 4 citationsarXiv
Modeling Uncertainty and Using Post-fusion as Fallback Improves Retrieval Augmented Generation with LLMs2308.12574v2 · Ye Liu, Semih Yavuz, Rui Meng et al.2023 · 1 citationarXiv
Few-shot Unified Question Answering: Tuning Models or Prompts?2305.14569v1 · Srijan Bansal, Semih Yavuz, Bo Pang et al.2023 · 0 citationsarXiv
HPE:Answering Complex Questions over Text by Hybrid Question Parsing and Execution2305.07789v2 · Ye Liu, Semih Yavuz, Rui Meng et al.2023 · 4 citationsarXiv
Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning2304.01295v4 · Lifu Tu, Jin Qu, Semih Yavuz et al.2023 · 5 citationsarXiv
AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentation2212.08841v4 · Rui Meng, Ye Liu, Semih Yavuz et al.2022 · 3 citationsarXiv
Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database2211.05165v1 · Ye Liu, Semih Yavuz, Rui Meng et al.2022 · 23 citationsarXiv
FOLIO: Natural Language Reasoning with First-Order Logic2209.00840v3 · Simeng Han, Hailey Schoelkopf, Yilun Zhao et al.2022 · 65 citationsarXiv
Improving the Faithfulness of Abstractive Summarization via Entity Coverage Control2207.02263v1 · Haopeng Zhang, Semih Yavuz, Wojciech Kryscinski et al.2022 · 25 citationsarXiv
Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors2205.12854v2 · Liyan Tang, Tanya Goyal, Alexander R. Fabbri et al.2022 · 54 citationsarXiv
Modeling Multi-hop Question Answering as Single Sequence Prediction2205.09226v1 · Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou et al.2022 · 23 citationsarXiv
Converse: A Tree-Based Modular Task-Oriented Dialogue System2203.12187v3 · Tian Xie, Xinyi Yang, Angela S. Lin et al.2022 · 4 citationsarXiv
Choose Your QA Model Wisely: A Systematic Study of Generative and Extractive Readers for Question Answering2203.07522v1 · Man Luo, Kazuma Hashimoto, Semih Yavuz et al.2022 · 19 citationsarXiv
Dense Hierarchical Retrieval for Open-Domain Question Answering2110.15439v1 · Ye Liu, Kazuma Hashimoto, Yingbo Zhou et al.2021 · 23 citationsarXiv
RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering2109.08678v2 · Xi Ye, Semih Yavuz, Kazuma Hashimoto et al.2021 · 121 citationsarXiv
Task-adaptive Pre-training and Self-training are Complementary for Natural Language Understanding2109.06466v2 · Shiyang Li, Semih Yavuz, Wenhu Chen et al.2021 · 9 citationsarXiv
Stage-wise Fine-tuning for Graph-to-Text Generation2105.08021v2 · Qingyun Wang, Semih Yavuz, Victoria Lin et al.2021 · 13 citationsarXiv
Career total: 85 works. 61 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.