Picture for Raghuraman Krishnamoorthi

Raghuraman Krishnamoorthi

EdgeTAM: On-Device Track Anything Model

Add code
Jan 13, 2025
Viaarxiv icon

Efficient Track Anything

Add code
Nov 28, 2024
Viaarxiv icon

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Add code
Nov 18, 2024
Viaarxiv icon

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Add code
Oct 22, 2024
Viaarxiv icon

Agent-as-a-Judge: Evaluate Agents with Agents

Add code
Oct 14, 2024
Figure 1 for Agent-as-a-Judge: Evaluate Agents with Agents
Figure 2 for Agent-as-a-Judge: Evaluate Agents with Agents
Figure 3 for Agent-as-a-Judge: Evaluate Agents with Agents
Figure 4 for Agent-as-a-Judge: Evaluate Agents with Agents
Viaarxiv icon

SpinQuant: LLM quantization with learned rotations

Add code
May 28, 2024
Figure 1 for SpinQuant: LLM quantization with learned rotations
Figure 2 for SpinQuant: LLM quantization with learned rotations
Figure 3 for SpinQuant: LLM quantization with learned rotations
Figure 4 for SpinQuant: LLM quantization with learned rotations
Viaarxiv icon

Communication Efficient Distributed Training with Distributed Lion

Add code
Mar 30, 2024
Viaarxiv icon

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

Add code
Feb 22, 2024
Viaarxiv icon

SqueezeSAM: User friendly mobile interactive segmentation

Add code
Dec 11, 2023
Viaarxiv icon

Gen2Det: Generate to Detect

Add code
Dec 07, 2023
Viaarxiv icon