2 citations · 4 across the 10 of their papers we have counts for
11 papers
SGPO: Self-Generated Preference Optimization based on Self-Improver
Hyeonji Lee, Daejin Jo, Seohwan Yun +1
Large language models (LLMs), despite their extensive pretraining on diverse datasets, require effective alignment to human preferences for practical and reliable deployment. Conve…
LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization
Daejin Jo, Jeeyoung Yun, Byungseok Roh +1
With the rapid progress of speech language models (SLMs), discrete speech tokens have emerged as a core interface between speech and text, enabling unified modeling across modaliti…
Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM
Donghwan Chi, Hyomin Kim, Yoonjin Oh +7
Recently, multimodal large language models (MLLMs) have emerged as a key approach in achieving artificial general intelligence. In particular, vision-language MLLMs have been devel…
TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback
Eunseop Yoon, Hee Suk Yoon, SooHwan Eom +7
Reinforcement Learning from Human Feedback (RLHF) leverages human preference data to train language models to align more closely with human essence. These human preference data, ho…
Hexa: Self-Improving for Knowledge-Grounded Dialogue System
Daejin Jo, Daniel Wontae Nam, Gunsoo Han +4
A common practice in knowledge-grounded dialogue generation is to explicitly utilize intermediate steps (e.g., web-search, memory retrieval) with modular approaches. However, data…
Effortless Integration of Memory Management into Open-Domain Conversation Systems
Eunbi Choi, Kyoung-Woon On, Gunsoo Han +6
Open-domain conversation systems integrate multiple conversation skills into a single system through a modular approach. One of the limitations of the system, however, is the absen…
MAGVLT: Masked Generative Vision-and-Language Transformer
Sungwoong Kim, Daejin Jo, Donghoon Lee +1
While generative modeling on multimodal image-text data has been actively developed with large-scale paired datasets, there have been limited attempts to generate both image and te…
LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward
Daejin Jo, Sungwoong Kim, Daniel Wontae Nam +4
Episodic count has been widely used to design a simple yet effective intrinsic motivation for reinforcement learning with a sparse reward. However, the use of episodic count in a h…
Selective Token Generation for Few-shot Natural Language Generation
Daejin Jo, Taehwan Kwon, Eun-Sol Kim +1
Natural language modeling with limited training data is a challenging problem, and many algorithms make use of large-scale pretrained language models (PLMs) for this due to its gre…
Insights From the NeurIPS 2021 NetHack Challenge
Eric Hambro, Sharada Mohanty, Dmitrii Babaev +26
In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can win (i.e., 'ascend' i…
Token Manipulation Generative Adversarial Network for Text Generation
DaeJin Jo
MaskGAN opens the query for the conditional language model by filling in the blanks between the given tokens. In this paper, we focus on addressing the limitations caused by having…