SK
Sanjiv Kumar
cs.LGstat.MLcs.CLcs.AIcs.CVcs.CRcs.IRmath.OCBalancecs.DS
On Valency
published · living versionsW_nkj8q39j·v1 · currentpublished
Preprints & journals
105 papers in the corpus · 1999–2025Effect of proprioceptive neuromuscular facilitation on balance, strength, cognition and ADL'S IN elderly - A randomized control study.41316556 · George, Christina Mary, Kumar, Sanjiv2025 · 1 citationJournal of bodywork and movement therapies. 2025;45:1053-1057
Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe2509.16411v1 · Chong You, Rajesh Jayaram, Ananda Theertha Suresh et al.2025 · 0 citationsarXiv
Spark Transformer: Reactivating Sparsity in FFN and Attention2506.06644v2 · Chong You, Kan Wu, Zhipeng Jia et al.2025 · 0 citationsarXiv
Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation2504.11284v2 · Michal Lukasik, Lin Chen, Harikrishna Narasimhan et al.2025 · 0 citationsarXiv
Structured Preconditioners in Adaptive Optimization: A Unified Analysis2503.10537v2 · Shuo Xie, Tianhao Wang, Sashank Reddi et al.2025 · 0 citationsarXiv
Reasoning with Latent Thoughts: On the Power of Looped Transformers2502.17416v1 · Nikunj Saunshi, Nishanth Dikkala, Zhiyuan Li et al.2025 · 2 citationsarXiv
Analyzing Similarity Metrics for Data Selection for Language Model Pretraining2502.02494v3 · Dylan Sam, Ayan Chakrabarti, Afshin Rostamizadeh et al.2025 · 0 citationsarXiv
LatentCRF: Continuous CRF for Efficient Latent Diffusion2412.18596v1 · Kanchana Ranasinghe, Sadeep Jayasumana, Andreas Veit et al.2024 · 0 citationsarXiv
On the Role of Depth and Looping for In-Context Learning with Task Diversity2410.21698v1 · Khashayar Gatmiry, Nikunj Saunshi, Sashank J. Reddi et al.2024 · 0 citationsarXiv
LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization2410.20625v2 · Jui-Nan Yen, Si Si, Zhao Meng et al.2024 · 0 citationsarXiv
A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs2410.18779v1 · Ankit Singh Rawat, Veeranjaneyulu Sadhanala, Afshin Rostamizadeh et al.2024 · 1 citationarXiv
SoftSRV: Learn to Generate Targeted Synthetic Data2410.16534v3 · Giulia DeSalvo, Jean-Fracois Kagy, Lazaros Karydas et al.2024 · 0 citationsarXiv
Mimetic Initialization Helps State Space Models Learn to Recall2410.11135v1 · Asher Trockman, Hrayr Harutyunyan, J. Zico Kolter et al.2024 · 0 citationsarXiv
Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?2410.08292v1 · Khashayar Gatmiry, Nikunj Saunshi, Sashank J. Reddi et al.2024 · 0 citationsarXiv
On the Inductive Bias of Stacking Towards Improving Reasoning2409.19044v1 · Nikunj Saunshi, Stefani Karp, Shankar Krishnan et al.2024 · 1 citationarXiv
Validity and reliability of a questionnaire assessing the knowledge, attitude, and awareness in the informal caregivers of comatose patients: An observational study.40231036 · Swaminathan, Aishwarya, Kumar, Sanjiv2026 · 0 citationsCurrent journal of neurology. 2024;23(3):144-151
Effectiveness of coma arousal therapy on patients with disorders of consciousness - A systematic review and meta-analysis.39036297 · Kumar, Sanjiv, Agarwal, Nupur, Sanal, Thankappan S2024 · 7 citationsBrain circulation. 2024;10(2):119-133
Efficient Document Ranking with Learnable Late Interactions2406.17968v1 · Ziwei Ji, Himanshu Jain, Andreas Veit et al.2024 · 3 citationsarXiv
Landscape-Aware Growing: The Power of a Little LAG2406.02469v1 · Stefani Karp, Nikunj Saunshi, Sobhan Miryoosefi et al.2024 · 0 citationsarXiv
Faster Cascades via Speculative Decoding2405.19261v2 · Harikrishna Narasimhan, Wittawat Jitkrittum, Ankit Singh Rawat et al.2024 · 0 citationsarXiv
Language Model Cascades: Token-level uncertainty and beyond2404.10136v1 · Neha Gupta, Harikrishna Narasimhan, Wittawat Jitkrittum et al.2024 · 3 citationsarXiv
Exploring and Improving Drafts in Blockwise Parallel Decoding2404.09221v2 · Taehyeon Kim, Ananda Theertha Suresh, Kishore Papineni et al.2024 · 0 citationsarXiv
Effects of Head and Neck pattern of PNF combined with conventional balance training in older adults with balance impairment - A Randomized control Trial.39593642 · Kumar, Sanjiv, George, Christina Mary2024 · 0 citationsJournal of bodywork and movement therapies. 2024;40:552-556
Tandem Transformers for Inference Efficient LLMs2402.08644v4 · Aishwarya P S, Pranav Ajit Nair, Yashas Samaga et al.2024 · 0 citationsarXiv
Efficient Stagewise Pretraining via Progressive Subnetworks2402.05913v2 · Abhishek Panigrahi, Nikunj Saunshi, Kaifeng Lyu et al.2024 · 0 citationsarXiv
SpacTor-T5: Pre-training T5 Models with Span Corruption and Replaced Token Detection2401.13160v1 · Ke Ye, Heinrich Jiang, Afshin Rostamizadeh et al.2024 · 0 citationsarXiv
A Weighted K-Center Algorithm for Data Subset Selection2312.10602v1 · Srikumar Ramalingam, Pranjal Awasthi, Sanjiv Kumar2023 · 0 citationsarXiv
ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent2312.10003v1 · Renat Aksitov, Sobhan Miryoosefi, Zonglin Li et al.2023 · 5 citationsarXiv
DistillSpec: Improving Speculative Decoding via Knowledge Distillation2310.08461v2 · Yongchao Zhou, Kaifeng Lyu, Ankit Singh Rawat et al.2023 · 9 citationsarXiv
What do larger image classifiers memorise?2310.05337v1 · Michal Lukasik, Vaishnavh Nagarajan, Ankit Singh Rawat et al.2023 · 1 citationarXiv
Functional Interpolation for Relative Positions Improves Long Context Transformers2310.04418v2 · Shanda Li, Chong You, Guru Guruganesh et al.2023 · 3 citationsarXiv
Think before you speak: Training Language Models With Pause Tokens2310.02226v3 · Sachin Goyal, Ziwei Ji, Ankit Singh Rawat et al.2023 · 2 citationsarXiv
Nonunion of an Isolated Medial Condyle of a Femur Hoffa Fracture in a 21-Year-Old Male: A Case Report.37809124 · Mohan, Ravindra, Agarwal, Rishabh, Abbas, Mohammad Baqar et al.2023 · 0 citationsCureus. 2023;15(9):e44722
Adolescent Health Academy Statement on the Care of Transgender Children, Adolescents, and Youth.37179471 · Pemde, Harish Kumar, Bansal, Utkarsh, Bhattacharya, Piyali et al.2026 · 2 citationsIndian pediatrics. 2023;60(10):843-854
Depth Dependence of P Learning Rates in ReLU MLPs2305.07810v1 · Samy Jelassi, Boris Hanin, Ziwei Ji et al.2023 · 0 citationsarXiv
Validation of Quantitative Ultrasonography for Osteoporosis Diagnosis in Postmenopausal Women Compared to Dual-Energy X-Ray Absorptiometry (DEXA).37284400 · Kushwaha, Narendra S, Singh, Arpit, Kumar, Sanjiv et al.2023 · 5 citationsCureus. 2023;15(5):e38562
Local Versus Systemic Tranexamic Acid in Total Hip Arthroplasty in Young Adults.37069867 · Kushwaha, Narendra S, Singh, Shubham, Kumar, Sanjiv et al.2023 · 5 citationsCureus. 2023;15(3):e36230
Need to Bring Family to the Heart of Healthcare as it is Home, not a Hospital, Where Healthcare Begins and Ends.37323734 · Kumar, Sanjiv, Bhardwaj, Pankaj, Kumar, Neeta2023 · 5 citationsIndian journal of community medicine : official publication of Indian Association of Preventive & Social Medicine. 2023;48(2):209-213
Plugin estimators for selective classification with out-of-distribution detection2301.12386v4 · Harikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum et al.2023 · 1 citationarXiv
Leveraging Importance Weights in Subset Selection2301.12052v1 · Gui Citovsky, Giulia DeSalvo, Sanjiv Kumar et al.2023 · 0 citationsarXiv
Supervision Complexity and its Role in Knowledge Distillation2301.12245v1 · Hrayr Harutyunyan, Ankit Singh Rawat, Aditya Krishna Menon et al.2023 · 1 citationarXiv
EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval2301.12005v2 · Seungyeon Kim, Ankit Singh Rawat, Manzil Zaheer et al.2023 · 4 citationsarXiv
Automating Nearest Neighbor Search Configuration with Constrained Optimization2301.01702v2 · Philip Sun, Ruiqi Guo, Sanjiv Kumar2023 · 1 citationarXiv
Large Language Models with Controllable Working Memory2211.05110v1 · Daliang Li, Ankit Singh Rawat, Manzil Zaheer et al.2022 · 46 citationsarXiv
Two-stage LLM Fine-tuning with Less Specialization and More Generalization2211.00635v3 · Yihan Wang, Si Si, Daliang Li et al.2022 · 8 citationsarXiv
When does mixup promote local linearity in learned representations?2210.16413v1 · Arslan Chaudhry, Aditya Krishna Menon, Andreas Veit et al.2022 · 0 citationsNeurIPS 2022 (First Workshop on Interpolation and Beyond)
The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers2210.06313v2 · Zonglin Li, Chong You, Srinadh Bhojanapalli et al.2022 · 18 citationsarXiv
Teacher Guided Training: An Efficient Framework for Knowledge Transfer2208.06825v1 · Manzil Zaheer, Ankit Singh Rawat, Seungyeon Kim et al.2022 · 1 citationarXiv
ELM: Embedding and Logit Margins for Long-Tail Learning2204.13208v1 · Wittawat Jitkrittum, Aditya Krishna Menon, Ankit Singh Rawat et al.2022 · 6 citationsarXiv
Predicting on the Edge: Identifying Where a Larger Model Does Better2202.07652v1 · Taman Narayan, Heinrich Jiang, Sen Zhao et al.2022 · 4 citationsarXiv
Career total: 255 works. 105 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.