Picture for Subhabrata Mukherjee

Subhabrata Mukherjee

Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing

Add code
Apr 22, 2024
Viaarxiv icon

Polaris: A Safety-focused LLM Constellation Architecture for Healthcare

Add code
Mar 20, 2024
Figure 1 for Polaris: A Safety-focused LLM Constellation Architecture for Healthcare
Figure 2 for Polaris: A Safety-focused LLM Constellation Architecture for Healthcare
Figure 3 for Polaris: A Safety-focused LLM Constellation Architecture for Healthcare
Figure 4 for Polaris: A Safety-focused LLM Constellation Architecture for Healthcare
Viaarxiv icon

Teaching Language Models to Hallucinate Less with Synthetic Tasks

Add code
Oct 10, 2023
Figure 1 for Teaching Language Models to Hallucinate Less with Synthetic Tasks
Figure 2 for Teaching Language Models to Hallucinate Less with Synthetic Tasks
Figure 3 for Teaching Language Models to Hallucinate Less with Synthetic Tasks
Figure 4 for Teaching Language Models to Hallucinate Less with Synthetic Tasks
Viaarxiv icon

Task-Based MoE for Multitask Multilingual Machine Translation

Add code
Sep 11, 2023
Figure 1 for Task-Based MoE for Multitask Multilingual Machine Translation
Figure 2 for Task-Based MoE for Multitask Multilingual Machine Translation
Figure 3 for Task-Based MoE for Multitask Multilingual Machine Translation
Figure 4 for Task-Based MoE for Multitask Multilingual Machine Translation
Viaarxiv icon

SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference

Add code
Jul 05, 2023
Figure 1 for SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference
Figure 2 for SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference
Figure 3 for SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference
Figure 4 for SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference
Viaarxiv icon

Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding

Add code
Jun 21, 2023
Figure 1 for Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding
Figure 2 for Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding
Figure 3 for Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding
Figure 4 for Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding
Viaarxiv icon

Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Add code
Jun 05, 2023
Figure 1 for Orca: Progressive Learning from Complex Explanation Traces of GPT-4
Figure 2 for Orca: Progressive Learning from Complex Explanation Traces of GPT-4
Figure 3 for Orca: Progressive Learning from Complex Explanation Traces of GPT-4
Figure 4 for Orca: Progressive Learning from Complex Explanation Traces of GPT-4
Viaarxiv icon

GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions

Add code
May 24, 2023
Figure 1 for GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions
Figure 2 for GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions
Figure 3 for GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions
Figure 4 for GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions
Viaarxiv icon

A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training

Add code
May 03, 2023
Figure 1 for A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training
Figure 2 for A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training
Figure 3 for A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training
Figure 4 for A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training
Viaarxiv icon

Accelerating Dataset Distillation via Model Augmentation

Add code
Dec 12, 2022
Figure 1 for Accelerating Dataset Distillation via Model Augmentation
Figure 2 for Accelerating Dataset Distillation via Model Augmentation
Figure 3 for Accelerating Dataset Distillation via Model Augmentation
Figure 4 for Accelerating Dataset Distillation via Model Augmentation
Viaarxiv icon