Publications by Tags
Selected Papers Conditional Computation, Efficiency, Mixture of Experts, Reinforcement Learning, Societal Impact, Theory, VisionSelected Papers
Sahil Goyal, Debapriya Tula, Gagan Jain, Pradeep Shenoy, Prateek Jain, Sujoy Paul
Under ReviewTLDR: An efficient framework for progressive decoding with nested models for faster inference.
Selected Papers Conditional Computation, Efficiency, Vision
Arpan Dasgupta, Gagan Jain, Arun Suggala, Karthikeyan Shanmugam, Milind Tambe, Aparna Taneja
Under ReviewTLDR: An improved collaborative bandits approach with bayesian regret derivation for a special case!
Selected Papers Reinforcement Learning, Societal Impact, Theory
Gagan Jain, Nidhi Hegde, Aditya Kusupati, Arsha Nagrani, Shyamal Buch, Prateek Jain, Anurag Arnab, Sujoy Paul
NeurIPS 2024TLDR: Token-wise routing between nested experts for tackling redundancy in visual modalities.
Selected Papers Conditional Computation, Efficiency, Mixture of Experts, Vision
Rajat Koner, Gagan Jain, Prateek Jain, Volker Tresp, Sujoy Paul
ECCV 2024TLDR: An asyncronous version of attention with sub-quadratic scaling and superior performance.
Selected Papers Efficiency, VisionConditional Computation
Sahil Goyal, Debapriya Tula, Gagan Jain, Pradeep Shenoy, Prateek Jain, Sujoy Paul
Under ReviewTLDR: An efficient framework for progressive decoding with nested models for faster inference.
Selected Papers Conditional Computation, Efficiency, VisionGagan Jain, Nidhi Hegde, Aditya Kusupati, Arsha Nagrani, Shyamal Buch, Prateek Jain, Anurag Arnab, Sujoy Paul
NeurIPS 2024TLDR: Token-wise routing between nested experts for tackling redundancy in visual modalities.
Selected Papers Conditional Computation, Efficiency, Mixture of Experts, VisionEfficiency
Sahil Goyal, Debapriya Tula, Gagan Jain, Pradeep Shenoy, Prateek Jain, Sujoy Paul
Under ReviewTLDR: An efficient framework for progressive decoding with nested models for faster inference.
Selected Papers Conditional Computation, Efficiency, VisionGagan Jain, Nidhi Hegde, Aditya Kusupati, Arsha Nagrani, Shyamal Buch, Prateek Jain, Anurag Arnab, Sujoy Paul
NeurIPS 2024TLDR: Token-wise routing between nested experts for tackling redundancy in visual modalities.
Selected Papers Conditional Computation, Efficiency, Mixture of Experts, VisionRajat Koner, Gagan Jain, Prateek Jain, Volker Tresp, Sujoy Paul
ECCV 2024TLDR: An asyncronous version of attention with sub-quadratic scaling and superior performance.
Selected Papers Efficiency, VisionMixture of Experts
Gagan Jain, Nidhi Hegde, Aditya Kusupati, Arsha Nagrani, Shyamal Buch, Prateek Jain, Anurag Arnab, Sujoy Paul
NeurIPS 2024TLDR: Token-wise routing between nested experts for tackling redundancy in visual modalities.
Selected Papers Conditional Computation, Efficiency, Mixture of Experts, VisionReinforcement Learning
Arpan Dasgupta, Gagan Jain, Arun Suggala, Karthikeyan Shanmugam, Milind Tambe, Aparna Taneja
Under ReviewTLDR: An improved collaborative bandits approach with bayesian regret derivation for a special case!
Selected Papers Reinforcement Learning, Societal Impact, TheorySocietal Impact
Arpan Dasgupta, Gagan Jain, Arun Suggala, Karthikeyan Shanmugam, Milind Tambe, Aparna Taneja
Under ReviewTLDR: An improved collaborative bandits approach with bayesian regret derivation for a special case!
Selected Papers Reinforcement Learning, Societal Impact, TheoryTheory
Arpan Dasgupta, Gagan Jain, Arun Suggala, Karthikeyan Shanmugam, Milind Tambe, Aparna Taneja
Under ReviewTLDR: An improved collaborative bandits approach with bayesian regret derivation for a special case!
Selected Papers Reinforcement Learning, Societal Impact, TheoryVision
Sahil Goyal, Debapriya Tula, Gagan Jain, Pradeep Shenoy, Prateek Jain, Sujoy Paul
Under ReviewTLDR: An efficient framework for progressive decoding with nested models for faster inference.
Selected Papers Conditional Computation, Efficiency, VisionGagan Jain, Nidhi Hegde, Aditya Kusupati, Arsha Nagrani, Shyamal Buch, Prateek Jain, Anurag Arnab, Sujoy Paul
NeurIPS 2024TLDR: Token-wise routing between nested experts for tackling redundancy in visual modalities.
Selected Papers Conditional Computation, Efficiency, Mixture of Experts, VisionRajat Koner, Gagan Jain, Prateek Jain, Volker Tresp, Sujoy Paul
ECCV 2024TLDR: An asyncronous version of attention with sub-quadratic scaling and superior performance.
Selected Papers Efficiency, Vision