Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Tushar Krishna

Tushar Krishna

8 indexed papers

Recent (6 mo)
6
With code
0
Influential cites
0
Benchmarked
0

Publications per year

8
26

Top categories

ML×5AI×4Distributed×4Architecture×3Multiagent×2Crypto×2Emerging Tech×1Networking×1

Frequent co-authors

Souvik Kundu4×
Sarbartha Banerjee3×
William Won3×
Hanjiang Wu3×
Hanchen Yang2×
Abhimanyu Rajeshkumar Bambhaniya2×

Research Timeline

2026
Privatar: Scalable Privacy-preserving Multi-user VR via Secure Offloading

Privatar introduces a scalable, privacy-preserving framework to offload computationally intensive multi-user avatar reconstruction from VR headsets to untrusted local devices, significantly improving user capacity while maintaining strong privacy guarantees.

Enabling AI ASICs for Zero Knowledge Proof

The paper introduces MORPH, a framework that reformulates Zero-Knowledge Proof (ZKP) computations to efficiently utilize AI ASICs like TPUs, achieving up to 10x higher throughput on NTT.

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving

The paper systematically analyzes the benefits and limits of Attention-FFN Disaggregation (AFD) for Mixture-of-Experts (MoE) LLM serving, demonstrating that AFD is crucial for achieving high throughput under strict latency constraints.

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving

The paper systematically analyzes the benefits and limits of Attention-FFN Disaggregation (AFD) for Mixture-of-Experts (MoE) LLM serving, demonstrating that AFD is crucial for achieving high throughput under strict latency constraints.

ASTRA-sim 3.0: Next-Level Distributed Machine Learning Simulations via High-Fidelity GPU and Infrastructure Modeling

This paper updates the ASTRA-sim simulator for distributed machine learning with new features and a standardized infrastructure representation.

A Workflow-Aware Serving Layer for Agentic Applications

The paper presents Dyserve, a workflow-aware serving layer for agentic AI applications that compiles per-node model and verifier choices into an integer linear program, allowing for efficient model selection and verification under serving-time conditions.

TRACE-ROUTER: Task-Consistent and Adaptive Online Routing for Agentic AI

The paper introduces TRACE-Router, a task-level routing framework for large language models that aligns routing with the unit of supervision using delayed task feedback.

LLMET: Enabling Cross-Layer Evaluation of Emerging M3D Memories for Energy-Efficient LLM Serving

This paper investigates the energy efficiency of Large Language Model (LLM) serving using emerging memory technologies, specifically monolithic 3D (M3D) integration, and presents simulation results showing significant energy savings.

Highlighted terms show continued research focus across papers

Papers

cs.ARcs.AIcs.ETEmpiricalRecentJul 29, 2026

LLMET: Enabling Cross-Layer Evaluation of Emerging M3D Memories for Energy-Efficient LLM Serving

Ming-Yen Lee, Hanchen Yang, Faaiq Waqar, Harsono Simka +3 more

This paper investigates the energy efficiency of Large Language Model (LLM) serving using emerging memory technologies, specifically monolithic 3D (M3D) integration, and presents simulation results sh…

View →
cs.AIcs.LGcs.MAEmpirical
Recent
Jul 24, 2026

TRACE-ROUTER: Task-Consistent and Adaptive Online Routing for Agentic AI

Ritik Raj, Souvik Kundu, Sarbartha Banerjee, Dheemanth Joshi +2 more

The paper introduces TRACE-Router, a task-level routing framework for large language models that aligns routing with the unit of supervision using delayed task feedback.

View →
cs.DCcs.MATheoreticalRecentJul 3, 2026

A Workflow-Aware Serving Layer for Agentic Applications

Jiayi Qian, Zishen Wan, Hanchen Yang, Chun Tao +2 more

The paper presents Dyserve, a workflow-aware serving layer for agentic AI applications that compiles per-node model and verifier choices into an integer linear program, allowing for efficient model se…

View →
cs.DCcs.LGcs.NIEmpiricalRecentJun 9, 2026

ASTRA-sim 3.0: Next-Level Distributed Machine Learning Simulations via High-Fidelity GPU and Infrastructure Modeling

William Won, Jinsun Yoo, Tuan Ta, Moumita Dey +15 more

This paper updates the ASTRA-sim simulator for distributed machine learning with new features and a standardized infrastructure representation.

View →
cs.LGcs.AIcs.DCRecentMay 27, 2026

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving

Hanjiang Wu, Abhimanyu Rajeshkumar Bambhaniya, Sarbartha Banerjee, Tuhin Khare +8 more

The paper systematically analyzes the benefits and limits of Attention-FFN Disaggregation (AFD) for Mixture-of-Experts (MoE) LLM serving, demonstrating that AFD is crucial for achieving high throughpu…

View →
cs.LGcs.AIcs.DCRecentMay 27, 2026

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving

Hanjiang Wu, Abhimanyu Rajeshkumar Bambhaniya, Sarbartha Banerjee, Tuhin Khare +8 more

The paper systematically analyzes the benefits and limits of Attention-FFN Disaggregation (AFD) for Mixture-of-Experts (MoE) LLM serving, demonstrating that AFD is crucial for achieving high throughpu…

View →
cs.ARcs.CLcs.CRApr 20, 2026

Enabling AI ASICs for Zero Knowledge Proof

Jianming Tong, Jingtian Dang, Simon Langowski, Tianhao Huang +5 more

The paper introduces MORPH, a framework that reformulates Zero-Knowledge Proof (ZKP) computations to efficiently utilize AI ASICs like TPUs, achieving up to 10x higher throughput on NTT.

View →
cs.CRcs.ARcs.CVApr 19, 2026

Privatar: Scalable Privacy-preserving Multi-user VR via Secure Offloading

Jianming Tong, Hanshen Xiao, Krishna Kumar Nair, Hao Kang +4 more

Privatar introduces a scalable, privacy-preserving framework to offload computationally intensive multi-user avatar reconstruction from VR headsets to untrusted local devices, significantly improving…

View →