Oshin Dutta oshindutta
-
Indian Institute of Technology (IIT) Delhi
- India
- oshindutta.github.io
- @dutta_oshin
- in/oshindutta
Stars
Official Repo for ReVeal: Self-Evolving Code Agents via Reliable Self-Verification
KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
A high-throughput and memory-efficient inference and serving engine for LLMs
SGLang is a high-performance serving framework for large language models and multimodal models.
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor...
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
[ICML 2024 Es-FoMo] - Efficient LLM Pruning with Global Token-Dependency Awareness and Hardware-Adapted Inference
up-to-date curated list of state-of-the-art Large vision language models hallucinations research work, papers & resources
π A curated list of resources dedicated to hallucination of multimodal large language models (MLLM).
Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages
The official repo for paper, LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods.
Compressing Neural Networks using the Variational Information Bottleneck
π€ Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
ACL 2022: Structured Pruning Learns Compact and Accurate Models https://arxiv.org/abs/2204.00408
Less is More: Task-aware Layer-wise Distillation for Language Model Compression (ICML2023)
[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning
[ACL 2023]: Training Trajectories of Language Models Across Scales https://arxiv.org/pdf/2212.09803.pdf
[ACL 2022] Structured Pruning Learns Compact and Accurate Models https://arxiv.org/abs/2204.00408
A framework for few-shot evaluation of language models.
Official code for LREC-COLING2024 paper "Pruning before Fine-tuning: A Retraining-free Compression Framework for Pre-trained Language Models"
β° AI conference deadline countdowns
Text recognition (optical character recognition) with deep learning methods, ICCV 2019
Python audio and music signal processing library
Random Erasing Data Augmentation. Experiments on CIFAR10, CIFAR100 and Fashion-MNIST