KS
Karthik Abinav Sankararaman
cs.LGcs.AIcs.DSstat.MLcs.CLcs.GTcs.CYcs.DMcs.MAmath.CO
On Valency
published · living versionsW_5yrdmwj8·v1 · currentpublished
Self-Credit: Credit Assignment for Long-Horizon Agentic RL via Intra-group Rescaling
with Fangcong Yin, Ming Yin, Tanvi Bhandarkar, Aashu Singh +5
1 version
Preprints & journals
32 papers in the corpus · 2016–2026Self-Credit: Credit Assignment for Long-Horizon Agentic RL via Intra-group Rescaling2610.28388v1 · Fangcong Yin, Ming Yin, Tanvi Bhandarkar et al.2026 · 0 citationsarXivon Valency
Bradley-Terry Policy Optimization for Generative Preference Modeling2510.15242v3 · Shengyu Feng, Yun He, Shuang Ma et al.2025 · 0 citationsarXiv
Generalized Parallel Scaling with Interdependent Generations2510.01143v3 · Harry Dong, David Brandfonbrener, Eryk Helenowski et al.2025 · 0 citationsarXiv
Reinforcement Learning from User Feedback2505.14946v1 · Eric Han, Jun Chen, Karthik Abinav Sankararaman et al.2025 · 0 citationsarXiv
Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation2505.12265v1 · Chengwei Qin, Wenxuan Zhou, Karthik Abinav Sankararaman et al.2025 · 0 citationsarXiv
Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization2501.17974v2 · Zishun Yu, Tengyu Xu, Di Jin et al.2025 · 0 citationsarXiv
Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following2410.15553v2 · Yun He, Di Jin, Chaoqi Wang et al.2024 · 5 citationsarXiv
Preference Optimization with Multi-Sample Comparisons2410.12138v2 · Chaoqi Wang, Zhuokai Zhao, Chen Zhu et al.2024 · 0 citationsarXiv
The Perfect Blend: Redefining RLHF with Mixture of Judges2409.20370v1 · Tengyu Xu, Eryk Helenowski, Karthik Abinav Sankararaman et al.2024 · 2 citationsarXiv
On the Equivalence of Graph Convolution and Mixup2310.00183v2 · Xiaotian Han, Hanqing Zeng, Yu Chen et al.2023 · 0 citationsarXiv
Effective Long-Context Scaling of Foundation Models2309.16039v3 · Wenhan Xiong, Jingyu Liu, Igor Molybog et al.2023 · 41 citationsarXiv
Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial?2306.07893v2 · Fan Yao, Chuanhao Li, Karthik Abinav Sankararaman et al.2023 · 6 citationsarXiv
Improved Adaptive Algorithm for Scalable Active Learning with Weak Labeler2211.02233v1 · Yifang Chen, Karthik Sankararaman, Alessandro Lazaric et al.2022 · 1 citationarXiv
BayesFormer: Transformer with Uncertainty Estimation2206.00826v1 · Karthik Abinav Sankararaman, Sinong Wang, Han Fang2022 · 6 citationsarXiv
Online minimum matching with uniform metric and random arrivals2112.05247v1 · Sharmila Duppala, Karthik A. Sankararaman, Pan Xu2021 · 5 citationsarXiv
Matching Algorithms for Blood Donation2108.04862v2 · Duncan C McElfresh, Christian Kroer, Sergey Pupyrev et al.2021 · 12 citationsarXiv
Stochastic Bandits for Multi-platform Budget Optimization in Online Advertising2103.10246v2 · Vashist Avadhanula, Riccardo Colini-Baldeschi, Stefano Leonardi et al.2021 · 30 citationsarXiv
Beyond Regret for Decentralized Bandits in Matching Markets2103.07501v1 · Soumya Basu, Karthik Abinav Sankararaman, Abishek Sankararaman2021 · 7 citationsarXiv
Improved Approximation Algorithms for Stochastic-Matching Problems2010.08142v1 · Marek Adamczyk, Brian Brubach, Fabrizio Grandoni et al.2020 · 0 citationsarXiv
Robust Identifiability in Linear Structural Equation Models of Causal Inference2007.06869v1 · Karthik Abinav Sankararaman, Anand Louis, Navin Goyal2020 · 0 citationsarXiv
Dominate or Delete: Decentralized Competing Bandits in Serial Dictatorship2006.15166v2 · Abishek Sankararaman, Soumya Basu, Karthik Abinav Sankararaman2020 · 13 citationsarXiv
Bandits with Knapsacks beyond the Worst-Case2002.00253v7 · Karthik Abinav Sankararaman, Aleksandrs Slivkins2020 · 3 citationsarXiv
Balancing the Tradeoff between Profit and Fairness in Rideshare Platforms During High-Demand Hours1912.08388v2 · Vedant Nanda, Pan Xu, Karthik Abinav Sankararaman et al.2019 · 44 citationsarXiv
Mix and Match: Markov Chains & Mixing Times for Matching in Rideshare1912.00225v1 · Michael J. Curry, John P. Dickerson, Karthik Abinav Sankararaman et al.2019 · 0 citationsarXiv
Stability of Linear Structural Equation Models of Causal Inference1905.06836v3 · Karthik Abinav Sankararaman, Anand Louis, Navin Goyal2019 · 2 citationsarXiv
The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent1904.06963v5 · Karthik A. Sankararaman, Soham De, Zheng Xu et al.2019 · 70 citationsarXiv
Balancing Relevance and Diversity in Online Bipartite Matching via Submodularity1811.05100v1 · John P. Dickerson, Karthik Abinav Sankararaman, Aravind Srinivasan et al.2018 · 26 citationsarXiv
Attenuate Locally, Win Globally: An Attenuation-based Framework for Online Stochastic Matching with Timeouts1804.08062v2 · Brian Brubach, Karthik Abinav Sankararaman, Aravind Srinivasan et al.2018 · 3 citationsarXiv
Allocation Problems in Ride-Sharing Platforms: Online Matching with Offline Reusable Resources1711.08345v2 · John P Dickerson, Karthik A Sankararaman, Aravind Srinivasan et al.2017 · 91 citationsarXiv
Algorithms to Approximate Column-Sparse Packing Problems1711.02724v6 · Brian Brubach, Karthik Abinav Sankararaman, Aravind Srinivasan et al.2017 · 7 citationsarXiv
Combinatorial Semi-Bandits with Knapsacks1705.08110v3 · Karthik Abinav Sankararaman, Aleksandrs Slivkins2017 · 24 citationsarXiv
Online Stochastic Matching: New Algorithms and Bounds1606.06395v4 · Brian Brubach, Karthik Abinav Sankararaman, Aravind Srinivasan et al.2016 · 19 citationsarXiv
Career total: 58 works. 32 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.