Ranajoy Sadhukhan

11 papers A* 3B 2Journal 5Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	STEM: Scaling Transformers with Embedding Modules. CoRR Ranajoy Sadhukhan, Sheng Cao, Harry Dong, Changsheng Zhao, Attiano Purpura-Pontoniere, Yuandong Tian, Zechun Liu, Beidi Chen
2025	J	`jnl`	Kinetics: Rethinking Test-Time Scaling Laws. CoRR Ranajoy Sadhukhan, Zhuoming Chen, Haizhong Zheng, Yang Zhou, Emma Strubell, Beidi Chen
2025	A*	`conf`	MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding. ICLR Ranajoy Sadhukhan, Jian Chen, Zhuoming Chen, Vashisth Tiwari, Ruihang Lai, Jinyuan Shi, Ian En-Hsu Yen, Avner May, Tianqi Chen, Beidi Chen
2025	A*	`conf`	MagicPIG: LSH Sampling for Efficient LLM Generation. ICLR Zhuoming Chen, Ranajoy Sadhukhan, Zihao Ye, Yang Zhou, Jianyu Zhang, Niklas Nolte, Yuandong Tian, Matthijs Douze, Léon Bottou, Zhihao Jia, Beidi Chen
2025	A*	`conf`	Memory Mosaics. ICLR Jianyu Zhang, Niklas Nolte, Ranajoy Sadhukhan, Beidi Chen, Léon Bottou
2024	J	`jnl`	MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding. CoRR Jian Chen, Vashisth Tiwari, Ranajoy Sadhukhan, Zhuoming Chen, Jinyuan Shi, Ian En-Hsu Yen, Beidi Chen
2024	J	`jnl`	MagicPIG: LSH Sampling for Efficient LLM Generation. CoRR Zhuoming Chen, Ranajoy Sadhukhan, Zihao Ye, Yang Zhou, Jianyu Zhang, Niklas Nolte, Yuandong Tian, Matthijs Douze, Léon Bottou, Zhihao Jia, Beidi Chen
2024	J	`jnl`	Memory Mosaics. CoRR Jianyu Zhang, Niklas Nolte, Ranajoy Sadhukhan, Beidi Chen, Léon Bottou
2023	—	`conf`	A Memory Efficient Run-time Re-configurable Convolution IP Core for Deep Neural Networks Inference on FPGA Devices. iSES Swati, Ranajoy Sadhukhan, Mitul Sudhirkumar Nagar, Pinalkumar Engineer
2022	B	`conf`	Taxonomy Driven Learning Of Semantic Hierarchy Of Classes. ICIP Ranajoy Sadhukhan, Ankita Chatterjee, Jayanta Mukhopadhyay, Amit Patra
2020	B	`conf`	Knowledge Distillation Inspired Fine-Tuning Of Tucker Decomposed CNNS and Adversarial Robustness Analysis. ICIP Ranajoy Sadhukhan, Avinab Saha, Jayanta Mukhopadhyay, Amit Patra

Nicolò Altamura, Enrico Bragastini, Marco Campion, Mila Dalla Preda

Chang Liu, Noah Fleischmann, Nicolò Altamura, Edward Raff, James Holt, Kristopher Micinski