Jinghong Chen

Sign in Subscribe

Latest

Generative AI should amplify human creativity, not replace it - my positions in 2025

I’ve been thinking about starting a company based on Generative AI technology , drawing on what I've learned and done so far in my PhD in Cambridge and my work at To0Space as a R&D leader. The natural questions are: what should be the business of

The Six Elements of NLP Experiments. Part 1: Datasets

Telling AI from Human: DeepFake Texts in the era of Large Language Models. Tutorial Notes @NAACL 2024

Telling AI from Human: DeepFake Texts in the era of Large Language Models. Tutorial Notes @NAACL 2024

Control-DAG: Constraining Non-Autoregressive Text Generation with Weighted Finite State Automata (WFSA)

Control-DAG: Constraining Non-Autoregressive Text Generation with Weighted Finite State Automata (WFSA)

PreFLMR: SoTA Open-sourced Multi-modal Knowledge Retriever from Scaling Up FLMR

Deriving Speculative Sampling Intuitively

Retrieval-Augmented Image Synthesis: A Researcher's Guide

Articles

Deriving Speculative Sampling Intuitively

[538 words, 2-minute read] A family of lossless LLM inference acceleration techniques has been developed based on speculative sampling (review here). Proposed by Google and Deepmind, speculative sampling is the following three-step procedure: 1. Draft: a small model (draft model, \(p(\cdot|\text{context})\)) quickly generates a K-token draft. 2.

Retrieval-Augmented Image Synthesis: A Researcher's Guide

Catch up on Speculative Decoding in 5 minutes: a survey for researchers as of December 2023

Estimate LLM inference speed and VRAM usage quickly: with a Llama-7B case study

Papers with Practical Values for Vision-Language Research @NeurIPS 2023 Day 5.

(Vision-Language Researcher) Selected Papers @NeurIPS 2023

Efficient Learning Orals @NeurIPS 2023

my work

Control-DAG: Constraining Non-Autoregressive Text Generation with Weighted Finite State Automata (WFSA)

Control-DAG: Constraining Non-Autoregressive Text Generation with Weighted Finite State Automata (WFSA)

[4-minute read] TL;DR. Non-autoregressive (NAR) models generate texts much faster than auto-regresssive (AR) models. However, we find previous NAR approaches, largely developed for Machine Translation, fail harshly when faced with Task-Oriented Dialogue and Data-to-Text. Our NAACL 2024 paper introduces Control-DAG, a constrained decoding algorithm that uses Weighted Finite State

PreFLMR: SoTA Open-sourced Multi-modal Knowledge Retriever from Scaling Up FLMR

3-minute Pitch: Retrieval Guided Contrastive Learning for Hateful Memes Detection

3-minute Pitch: Late-Interaction Knowledge Retriever (FLMR) for Visual Question Answering @NeurIPS 2023

3-minute Pitch: Learning from MBR decoding using Direct Preference Optimization

paper read

[Paper Express] Data Selection for Language Models via Importance Resampling (DSIR)

[Paper Express] Data Selection for Language Models via Importance Resampling (DSIR)

README. Data Selection (DS) aims to select a given number of samples from a large, unlabeled dataset for training a capable model in a target domain. In the case of training langauge models, practical DS methods need to efficiently select from raw text corpus containing trillions of tokens. This paper,

MultiLoRA explained in 3 minutes: Democratizing LoRA for Better Multi-Task Learning

Papers with Practical Values for Vision-Language Research @NeurIPS 2023 Day 5.